mirror of
https://github.com/KnugiHK/WhatsApp-Chat-Exporter.git
synced 2026-07-07 22:55:09 +02:00
Compare commits
28 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 KnugiHK
|
49ad409293 | ||
|
KnugiHK
|
ea1f8b4068 | ||
|
KnugiHK
|
05184d4a27 | ||
|
KnugiHK
|
3264fa44ec | ||
|
KnugiHK
|
3950797b7b | ||
|
KnugiHK
|
0b34f45dde | ||
|
KnugiHK
|
01852b1d61 | ||
|
KnugiHK
|
df8a8197e9 | ||
|
KnugiHK
|
0aec1075a7 | ||
|
KnugiHK
|
d48096a0a5 | ||
|
KnugiHK
|
24bad20b4d | ||
|
KnugiHK
|
9be38fce53 | ||
|
KnugiHK
|
019edd5825 | ||
|
KnugiHK
|
5caf9df045 | ||
|
KnugiHK
|
de693f9df1 | ||
|
KnugiHK
|
46df657b9b | ||
|
KnugiHK
|
713d7ec43b | ||
 Knugi
|
8e6271ba8d | ||
|
KnugiHK
|
31a5f89a99 | ||
|
Knugi
|
7268845986 | ||
|
KnugiHK
|
ae9f3a99d3 | ||
|
KnugiHK
|
b0abda301a | ||
|
KnugiHK
|
26ae5cecdf | ||
|
KnugiHK
|
3be2c0f1fc | ||
|
KnugiHK
|
13b468d463 | ||
|
Knugi
|
cda80b86cc | ||
|
KnugiHK
|
7ed5ed80f6 | ||
|
KnugiHK
|
a5a511ca2c |
@@ -1,37 +0,0 @@
|
||||
---
|
||||
name: Bug report
|
||||
about: Create a report to help us improve
|
||||
title: "[BUG]"
|
||||
labels: ''
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
||||
# Must have
|
||||
- WhatsApp version: [WhatsApp version]
|
||||
- OS: [Android/iOS] - [version]
|
||||
- Platform: [Linux/Windows/MacOS]
|
||||
- Exporter's branch and version: [main/dev] - [exporter version]
|
||||
|
||||
**Describe the bug**
|
||||
A clear and concise description of what the bug is.
|
||||
|
||||
If it is an error yield by Python, please also provide the trackback
|
||||
```
|
||||
[trackback here]
|
||||
```
|
||||
|
||||
# Nice to have
|
||||
|
||||
**To Reproduce**
|
||||
Steps to reproduce the behavior:
|
||||
1. Go to '...'
|
||||
2. Click on '....'
|
||||
3. Scroll down to '....'
|
||||
4. See error
|
||||
|
||||
**Screenshots**
|
||||
If applicable, add screenshots to help explain your problem.
|
||||
|
||||
**Additional context**
|
||||
Add any other context about the problem here.
|
||||
@@ -1,17 +0,0 @@
|
||||
---
|
||||
name: Feature request
|
||||
about: Suggest an idea for this project
|
||||
title: "[FEATURE]"
|
||||
labels: ''
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
||||
**Is your feature request related to a problem? Please describe.**
|
||||
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
|
||||
|
||||
**Describe the solution you'd like**
|
||||
A clear and concise description of what you want to happen.
|
||||
|
||||
**Additional context**
|
||||
Add any other context or screenshots about the feature request here.
|
||||
@@ -1,8 +0,0 @@
|
||||
## Related Issue
|
||||
- Please reference the related issue here (e.g., `Fixes #123` or `Closes #456`), if there are any.
|
||||
|
||||
## Description of Changes
|
||||
- Briefly describe the changes made in this PR. Explain the purpose, the implementation details, and any important information that reviewers should be aware of.
|
||||
|
||||
## Important (Please remove this section before submitting the PR)
|
||||
- Before submitting this PR, please make sure to look at **[this issue](https://github.com/KnugiHK/WhatsApp-Chat-Exporter/issues/137)**. It contains crucial context and discussion that may affect the changes in this PR.
|
||||
@@ -1,84 +0,0 @@
|
||||
name: Compile standalone binary
|
||||
|
||||
on:
|
||||
release:
|
||||
types: [published]
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
linux:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.13'
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install pycryptodome vobject javaobj-py3 ordered-set zstandard nuitka==2.6.7
|
||||
pip install .
|
||||
- name: Build binary with Nuitka
|
||||
run: |
|
||||
python -m nuitka --no-deployment-flag=self-execution --onefile \
|
||||
--include-data-file=./Whatsapp_Chat_Exporter/whatsapp.html=./Whatsapp_Chat_Exporter/whatsapp.html \
|
||||
--assume-yes-for-downloads --follow-imports Whatsapp_Chat_Exporter/__main__.py --output-filename=wtsexporter_linux_x64
|
||||
sha256sum wtsexporter_linux_x64
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: binary-linux
|
||||
path: |
|
||||
./wtsexporter_linux_x64
|
||||
|
||||
windows:
|
||||
runs-on: windows-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.13'
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install pycryptodome vobject javaobj-py3 ordered-set zstandard nuitka==2.6.7
|
||||
pip install .
|
||||
- name: Build binary with Nuitka
|
||||
run: |
|
||||
python -m nuitka --no-deployment-flag=self-execution --onefile --include-data-file=./Whatsapp_Chat_Exporter/whatsapp.html=./Whatsapp_Chat_Exporter/whatsapp.html --assume-yes-for-downloads --follow-imports Whatsapp_Chat_Exporter\__main__.py --output-filename=wtsexporter
|
||||
copy wtsexporter.exe wtsexporter_x64.exe
|
||||
Get-FileHash wtsexporter_x64.exe
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: binary-windows
|
||||
path: |
|
||||
.\wtsexporter_x64.exe
|
||||
|
||||
macos:
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.13'
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install pycryptodome vobject javaobj-py3 ordered-set zstandard nuitka==2.6.7
|
||||
pip install .
|
||||
- name: Build binary with Nuitka
|
||||
run: |
|
||||
python -m nuitka --no-deployment-flag=self-execution --onefile \
|
||||
--include-data-file=./Whatsapp_Chat_Exporter/whatsapp.html=./Whatsapp_Chat_Exporter/whatsapp.html \
|
||||
--assume-yes-for-downloads --follow-imports Whatsapp_Chat_Exporter/__main__.py --output-filename=wtsexporter_macos_x64
|
||||
shasum -a 256 wtsexporter_macos_x64
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: binary-macos
|
||||
path: |
|
||||
./wtsexporter_macos_x64
|
||||
@@ -1,37 +0,0 @@
|
||||
# This workflow will upload a Python Package using Twine when a release is created
|
||||
# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
|
||||
|
||||
# This workflow uses actions that are not certified by GitHub.
|
||||
# They are provided by a third-party and are governed by
|
||||
# separate terms of service, privacy policy, and support
|
||||
# documentation.
|
||||
|
||||
name: Upload Python Package
|
||||
|
||||
on:
|
||||
release:
|
||||
types: [published]
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
id-token: write
|
||||
|
||||
jobs:
|
||||
deploy:
|
||||
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.x'
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install build
|
||||
- name: Build package
|
||||
run: python -m build
|
||||
- name: Publish package
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
-147
@@ -1,147 +0,0 @@
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
pip-wheel-metadata/
|
||||
share/python-wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
*.py,cover
|
||||
.hypothesis/
|
||||
.pytest_cache/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# IPython
|
||||
profile_default/
|
||||
ipython_config.py
|
||||
|
||||
# pyenv
|
||||
.python-version
|
||||
|
||||
# pipenv
|
||||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||||
# install all needed dependencies.
|
||||
#Pipfile.lock
|
||||
|
||||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
|
||||
__pypackages__/
|
||||
|
||||
# Celery stuff
|
||||
celerybeat-schedule
|
||||
celerybeat.pid
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
/site
|
||||
|
||||
# mypy
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# Pyre type checker
|
||||
.pyre/
|
||||
|
||||
# Nuitka
|
||||
*.build/
|
||||
*.dist/
|
||||
*.onefile-build/
|
||||
*.exe
|
||||
__main__
|
||||
|
||||
|
||||
# Dev time intermidiates & temp files
|
||||
result/
|
||||
WhatsApp/
|
||||
/*.db
|
||||
/*.db-*
|
||||
/myout
|
||||
/msgstore.db
|
||||
/myout-json
|
||||
.vscode/
|
||||
@@ -1,63 +0,0 @@
|
||||
# Contributing Guidelines
|
||||
|
||||
*Pull requests, bug reports, and all other forms of contribution are welcomed and highly encouraged!*
|
||||
|
||||
> **This guide serves to set clear expectations for everyone involved with the project so that we can improve it together while also creating a welcoming space for everyone to participate. Following these guidelines will help ensure a positive experience for contributors and maintainers.**
|
||||
|
||||
<sub> Maintainer's note: I aim to keep things simple and flexible, without imposing too many restrictions, while still ensuring it’s useful for the project. </sub>
|
||||
|
||||
## :book: Code of Conduct
|
||||
|
||||
There isn't an official code of conduct at the moment, and we hope it won't be necessary. The rule is simple: be reasonable and treat others with respect!
|
||||
|
||||
## :bulb: Asking Questions
|
||||
|
||||
While there is no formal support from the maintainer, they are happy to help if you provide enough information. However, please note:
|
||||
|
||||
If you feel the questions or difficulties you're encountering aren't related to the software itself, please [open a discussion thread](https://github.com/KnugiHK/WhatsApp-Chat-Exporter/discussions/new/choose). Do not open an issue just to ask a question. While asking questions in the project issues is not strictly prohibited, any issues that don't qualify as genuine problems will be converted into discussion threads.
|
||||
|
||||
Hopefully, the community will be able to offer assistance as well. You can check out the article [How do I ask a good question?](https://stackoverflow.com/help/how-to-ask) on StackOverflow to learn how to craft questions that encourage more people to respond.
|
||||
|
||||
## :inbox_tray: Opening an Issue
|
||||
|
||||
Before [creating an issue](https://help.github.com/en/github/managing-your-work-on-github/creating-an-issue), check if you are using the latest version of the project. If you are not up-to-date, see if updating fixes your issue first.
|
||||
|
||||
### :lock: Reporting Security Issues
|
||||
|
||||
Please report any vulnerability to [GitHub Security Advisory](https://github.com/KnugiHK/WhatsApp-Chat-Exporter/security/advisories/new). **Do not** file a public issue for security vulnerabilities.
|
||||
|
||||
### :beetle: Bug Reports and Feature Requests
|
||||
|
||||
- **Do not open a duplicate issue!** Search through existing issues to see if your issue or request has previously been reported. If your issue exists, comment with any additional information you have. You may simply note "I have this problem too/I want this feature too", which helps prioritize the most common problems and requests.
|
||||
|
||||
- **Fully complete the provided issue template.** The issue templates request all the information we need to quickly and efficiently address your issue. Be clear, concise, and descriptive. Provide as much information as you can, including steps to reproduce, stack traces, compiler errors, library versions, OS versions, and screenshots (if applicable). This will assist the maintainer in efficiently triaging your issues and isolating the problems.
|
||||
|
||||
- For feature requests, be specific about the proposed outcome and how it fits with the existing features. If possible, include implementation details.
|
||||
|
||||
Note that feature requests may be out of scope for the project, and if accepted, we cannot commit to a specific timeline for implementation.
|
||||
|
||||
## :repeat: Submitting Pull Requests
|
||||
|
||||
- **Smaller is better.** Submit **one** pull request per bug fix or feature. A pull request should contain isolated changes pertaining to a single bug fix or feature implementation. **Do not** refactor or reformat code that is unrelated to your change. It is better to **submit many small pull requests** rather than a single large one. Enormous pull requests will take enormous amounts of time to review, or may be rejected altogether.
|
||||
|
||||
- **Coordinate bigger changes.** For large and non-trivial changes, open an issue to discuss a strategy with the maintainers. Otherwise, you risk doing a lot of work for nothing!
|
||||
|
||||
- **Follow PEP8.** Python code should follow PEP8 formatting and styling guidelines. Consider using automated tools like [autopep8](https://github.com/hhatto/autopep8) or [flake8](https://github.com/PyCQA/flake8) to ensure your code adheres to these standards.
|
||||
|
||||
- **[Resolve any merge conflicts](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/resolving-a-merge-conflict-on-github)** that occur.
|
||||
|
||||
- Use spaces, not tabs.
|
||||
|
||||
- Make sure all commits work with the new template — the old one is being deprecated.
|
||||
|
||||
## :memo: Copyright
|
||||
|
||||
This repository is licensed under the MIT License. **Any contributions you submit will be licensed under the same terms.**
|
||||
|
||||
By contributing, you confirm that your contributions do not infringe on the rights of others.
|
||||
|
||||
If your contribution includes code from other open-source projects, ensure that their licenses are compatible with this one. For example, code licensed under the GPL cannot be included in this project.
|
||||
|
||||
## :pray: Credit
|
||||
|
||||
This contribution guidelines is remixed from [jessesquires/.github:CONTRIBUTING.md](https://github.com/jessesquires/.github/blob/main/CONTRIBUTING.md) which also incorporated other works. *We commend them for their efforts to facilitate collaboration in their projects.*
|
||||
@@ -1,21 +0,0 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2021-2023 Knugi
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
@@ -1,36 +0,0 @@
|
||||
The Whatsapp Chat Exporter is licensed under the MIT license. For more information,
|
||||
refer to the file LICENSE.
|
||||
|
||||
Whatsapp Chat Exporter incorporates code from Django, governed by the three-clause
|
||||
BSD license—a permissive open-source license. The copyright and license details are
|
||||
provided below to adhere to Django's terms.
|
||||
|
||||
------
|
||||
|
||||
Copyright (c) Django Software Foundation and individual contributors.
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without modification,
|
||||
are permitted provided that the following conditions are met:
|
||||
|
||||
1. Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
2. Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
3. Neither the name of Django nor the names of its contributors may be used
|
||||
to endorse or promote products derived from this software without
|
||||
specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
||||
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
||||
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
|
||||
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
||||
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
||||
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
|
||||
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
||||
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
@@ -1,260 +0,0 @@
|
||||
# Whatsapp-Chat-Exporter
|
||||
[](https://pypi.org/project/whatsapp-chat-exporter/)
|
||||
[](https://github.com/KnugiHK/WhatsApp-Chat-Exporter/blob/main/LICENSE)
|
||||
[](https://pypi.org/project/Whatsapp-Chat-Exporter/)
|
||||
[](https://matrix.to/#/#wtsexporter:matrix.org)
|
||||
|
||||
|
||||
A customizable Android and iPhone Whatsapp database parser that will give you the history of your Whatsapp conversations in HTML and JSON. Inspired by [Telegram Chat Export Tool](https://telegram.org/blog/export-and-more).
|
||||
> [!TIP]
|
||||
> If you plan to uninstall WhatsApp or delete your WhatsApp account, please make a backup of your WhatsApp database. You may want to use this exporter again on the same database in the future as the exporter develops.
|
||||
|
||||
If you would like to support this project, all you need to do is to contribute or share this project! If you think otherwise and want to make a donation, please refer to the [Donation Guide](https://blog.knugi.com/DONATE.html).
|
||||
|
||||
To contribute, see the [Contributing Guidelines](https://github.com/KnugiHK/WhatsApp-Chat-Exporter/blob/main/CONTRIBUTING.md).
|
||||
|
||||
# Usage
|
||||
|
||||
> [!NOTE]
|
||||
> Usage in README may be removed in the future. Check the usage in [Wiki](https://github.com/KnugiHK/Whatsapp-Chat-Exporter/wiki)
|
||||
|
||||
First, install the exporter by:
|
||||
```shell
|
||||
pip install whatsapp-chat-exporter
|
||||
pip install whatsapp-chat-exporter[android_backup] :; # Optional, if you want it to support decrypting Android WhatsApp backup.
|
||||
```
|
||||
Then, create a working directory in somewhere you want
|
||||
```shell
|
||||
mkdir working_wts
|
||||
cd working_wts
|
||||
```
|
||||
|
||||
> [!TIP]
|
||||
> macOS users should grant *Full Disk Access* to Terminal in the *Security & Privacy* settings before using the exporter.
|
||||
|
||||
## Working with Android
|
||||
### Unencrypted WhatsApp database
|
||||
Extract the WhatsApp database with whatever means, one possible means is to use the [WhatsApp-Key-DB-Extractor](https://github.com/KnugiHK/WhatsApp-Key-DB-Extractor). Note that the extractor only works on Android 4.0 to 13.
|
||||
|
||||
After you obtain your WhatsApp database, copy the WhatsApp database and media folder to the working directory. The database is called msgstore.db. If you also want the name of your contacts, get the contact database, which is called wa.db. And copy the WhatsApp (Media) directory from your phone directly.
|
||||
|
||||
And now, you should have something like this in the working directory.
|
||||
|
||||
|
||||
#### Extracting
|
||||
Simply invoke the following command from shell.
|
||||
```sh
|
||||
wtsexporter -a
|
||||
```
|
||||
#### Enriching Contact from vCard
|
||||
The default WhatsApp contact database typically contained contact names extracted from your phone, which the exporter used to map your chats. However, in some reported cases, the database may have never been populated. In such case, you can export your contacts to a vCard file from your phone or a cloud provider like Google Contacts. Then, install the necessary dependency and run the following command from the shell:
|
||||
```sh
|
||||
pip install whatsapp-chat-exporter["vcards"]
|
||||
wtsexporter -a --enrich-from-vcard contacts.vcf --default-country-code 852
|
||||
```
|
||||
|
||||
### Encrypted Android WhatsApp Backup
|
||||
In order to support the decryption, install pycryptodome if it is not installed
|
||||
```sh
|
||||
pip install pycryptodome # Or
|
||||
pip install whatsapp-chat-exporter["android_backup"] # install along with this software
|
||||
```
|
||||
|
||||
> [!TIP]
|
||||
> Crypt15 is now the easiest way to decrypt a backup. If you have the 32 bytes hex key generated when you enable End-to-End encrypted backup, you can use it to decrypt the backup. If you do not have the 32 bytes hex key, you can still use the key file extracted just like extacting key file for Crypt12 and Crypt14 to decrypt the backup.
|
||||
|
||||
#### Crypt12 or Crypt14
|
||||
You will need the decryption key file from your phone. If you have root access, you can find it as `/data/data/com.whatsapp/files/key`. Otherwise, if you used WhatsApp-Key-DB-Extractor before, it will appear in the WhatsApp backup directory as `WhatsApp/Databases/.nomedia`.
|
||||
|
||||
Place the decryption key file (key) and the encrypted WhatsApp Backup (msgstore.db.crypt14) in the working directory. If you also want the name of your contacts, get the contact database, which is called wa.db. And copy the WhatsApp (Media) directory from your phone directly.
|
||||
|
||||
And now, you should have something like this in the working directory.
|
||||
|
||||
|
||||
#### Extracting
|
||||
Simply invoke the following command from shell.
|
||||
```sh
|
||||
wtsexporter -a -k key -b msgstore.db.crypt14
|
||||
```
|
||||
|
||||
#### Crypt15 (End-to-End Encrypted Backup)
|
||||
To support Crypt15 backup, install javaobj-py3 if it is not installed
|
||||
```sh
|
||||
pip install javaobj-py3 # Or
|
||||
pip install whatsapp-chat-exporter["crypt15"] # install along with this software
|
||||
```
|
||||
Before proceeding with this method, you must first create an end-to-end encrypted backup. For detailed instructions, refer to [WhatsApp's help center](https://faq.whatsapp.com/490592613091019).
|
||||
|
||||
Once you have copied the backup files to your computer, place the encrypted WhatsApp backup file (msgstore.db.crypt15) into the working directory. If you also wish to include your contacts' names, obtain the contact database file, named wa.db. Additionally, copy the WhatsApp Media folder directly from your phone.
|
||||
|
||||
If you do not have the 32 bytes hex key (64 hexdigits), place the decryption key file (encrypted_backup.key) extracted from Android. If you gave the 32 bytes hex key, simply put the key in the shell.
|
||||
|
||||
Now, you should have something like this in the working directory (if you do not have 32 bytes hex key).
|
||||
|
||||
|
||||
##### Extracting
|
||||
If you do not have 32 bytes hex key but have the key file available, simply invoke the following command from shell.
|
||||
```sh
|
||||
wtsexporter -a -k encrypted_backup.key -b msgstore.db.crypt15
|
||||
```
|
||||
If you have the 32 bytes hex key, simply put the hex key in the -k option and invoke the command from shell like this:
|
||||
```sh
|
||||
wtsexporter -a -k 432435053b5204b08e5c3823423399aa30ff061435ab89bc4e6713969cdaa5a8 -b msgstore.db.crypt15
|
||||
```
|
||||
|
||||
## Working with iOS/iPadOS (iPhone or iPad)
|
||||
Do an iPhone/iPad Backup with iTunes/Finder first.
|
||||
* iPhone backup on Mac: https://support.apple.com/HT211229
|
||||
* iPhone backup on Windows: https://support.apple.com/HT212156
|
||||
* iPad backup: https://support.apple.com/guide/ipad/ipad9a74df05xx/ipados
|
||||
### Encrypted iOS/iPadOS Backup
|
||||
> [!NOTE]
|
||||
> If you are working on unencrypted iOS/iPadOS backup, skip this.
|
||||
|
||||
If you want to work on an encrypted iOS/iPadOS Backup, you should install iphone_backup_decrypt from [KnugiHK/iphone_backup_decrypt](https://github.com/KnugiHK/iphone_backup_decrypt) before you run the extract_iphone_media.py.
|
||||
```sh
|
||||
pip install git+https://github.com/KnugiHK/iphone_backup_decrypt
|
||||
```
|
||||
> [!NOTE]
|
||||
> You will need to disable the built-in end-to-end encryption for WhatsApp backups. See [WhatsApp's FAQ](https://faq.whatsapp.com/490592613091019#turn-off-end-to-end-encrypted-backup) for how to do it.
|
||||
### Extracting
|
||||
To extract messages from iOS/iPadOS backups, run the following command in the shell, making sure to replace the username and device ID with the correct values. Keep in mind that there are at least two possible paths for the backups on Windows.
|
||||
#### Windows
|
||||
```powershell
|
||||
# Possible path one
|
||||
wtsexporter -i -b "C:\Users\[Username]\AppData\Roaming\Apple Computer\MobileSync\Backup\[device id]"
|
||||
|
||||
# Possible path two
|
||||
wtsexporter -i -b "C:\Users\[Username]\Apple\MobileSync\Backup\[device id]"
|
||||
```
|
||||
|
||||
#### Mac
|
||||
```sh
|
||||
wtsexporter -i -b ~/Library/Application\ Support/MobileSync/Backup/[device id]
|
||||
```
|
||||
|
||||
## Results
|
||||
After extracting, you will get these:
|
||||
#### Private Message
|
||||
|
||||
|
||||
#### Group Message
|
||||
|
||||
|
||||
## More options
|
||||
Invoke the wtsexporter with --help option will show you all options available.
|
||||
```sh
|
||||
> wtsexporter --help
|
||||
usage: wtsexporter [-h] [-a] [-i] [-e EXPORTED] [-w WA] [-m MEDIA] [-b BACKUP] [-d DB] [-k [KEY]]
|
||||
[--call-db [CALL_DB_IOS]] [--wab WAB] [-o OUTPUT] [-j [JSON]] [--txt [TEXT_FORMAT]] [--no-html]
|
||||
[--size [SIZE]] [--avoid-encoding-json] [--pretty-print-json [PRETTY_PRINT_JSON]] [--per-chat]
|
||||
[--import] [-t TEMPLATE] [--offline OFFLINE] [--no-avatar] [--experimental-new-theme]
|
||||
[--headline HEADLINE] [-c] [--create-separated-media] [--time-offset {-12 to 14}] [--date DATE]
|
||||
[--date-format FORMAT] [--include [phone number ...]] [--exclude [phone number ...]]
|
||||
[--dont-filter-empty] [--enrich-from-vcards ENRICH_FROM_VCARDS]
|
||||
[--default-country-code DEFAULT_COUNTRY_CODE] [-s] [--check-update] [--assume-first-as-me]
|
||||
[--business] [--decrypt-chunk-size DECRYPT_CHUNK_SIZE]
|
||||
[--max-bruteforce-worker MAX_BRUTEFORCE_WORKER]
|
||||
|
||||
A customizable Android and iOS/iPadOS WhatsApp database parser that will give you the history of your WhatsApp
|
||||
conversations in HTML and JSON. Android Backup Crypt12, Crypt14 and Crypt15 supported.
|
||||
|
||||
options:
|
||||
-h, --help show this help message and exit
|
||||
|
||||
Device Type:
|
||||
-a, --android Define the target as Android
|
||||
-i, --ios Define the target as iPhone/iPad
|
||||
-e, --exported EXPORTED
|
||||
Define the target as exported chat file and specify the path to the file
|
||||
|
||||
Input Files:
|
||||
-w, --wa WA Path to contact database (default: wa.db/ContactsV2.sqlite)
|
||||
-m, --media MEDIA Path to WhatsApp media folder (default: WhatsApp)
|
||||
-b, --backup BACKUP Path to Android (must be used together with -k)/iOS WhatsApp backup
|
||||
-d, --db DB Path to database file (default: msgstore.db/7c7fba66680ef796b916b067077cc246adacf01d)
|
||||
-k, --key [KEY] Path to key file. If this option is set for crypt15 backup but nothing is specified, you will
|
||||
be prompted to enter the key.
|
||||
--call-db [CALL_DB_IOS]
|
||||
Path to call database (default: 1b432994e958845fffe8e2f190f26d1511534088) iOS only
|
||||
--wab, --wa-backup WAB
|
||||
Path to contact database in crypt15 format
|
||||
|
||||
Output Options:
|
||||
-o, --output OUTPUT Output to specific directory (default: result)
|
||||
-j, --json [JSON] Save the result to a single JSON file (default if present: result.json)
|
||||
--txt [TEXT_FORMAT] Export chats in text format similar to what WhatsApp officially provided (default if present:
|
||||
result/)
|
||||
--no-html Do not output html files
|
||||
--size, --output-size, --split [SIZE]
|
||||
Maximum (rough) size of a single output file in bytes, 0 for auto
|
||||
|
||||
JSON Options:
|
||||
--avoid-encoding-json
|
||||
Don't encode non-ascii characters in the output JSON files
|
||||
--pretty-print-json [PRETTY_PRINT_JSON]
|
||||
Pretty print the output JSON.
|
||||
--per-chat Output the JSON file per chat
|
||||
--import Import JSON file and convert to HTML output
|
||||
|
||||
HTML Options:
|
||||
-t, --template TEMPLATE
|
||||
Path to custom HTML template
|
||||
--offline OFFLINE Relative path to offline static files
|
||||
--no-avatar Do not render avatar in HTML output
|
||||
--experimental-new-theme
|
||||
Use the newly designed WhatsApp-alike theme
|
||||
--headline HEADLINE The custom headline for the HTML output. Use '??' as a placeholder for the chat name
|
||||
|
||||
Media Handling:
|
||||
-c, --move-media Move the media directory to output directory if the flag is set, otherwise copy it
|
||||
--create-separated-media
|
||||
Create a copy of the media seperated per chat in <MEDIA>/separated/ directory
|
||||
|
||||
Filtering Options:
|
||||
--time-offset {-12 to 14}
|
||||
Offset in hours (-12 to 14) for time displayed in the output
|
||||
--date DATE The date filter in specific format (inclusive)
|
||||
--date-format FORMAT The date format for the date filter
|
||||
--include [phone number ...]
|
||||
Include chats that match the supplied phone number
|
||||
--exclude [phone number ...]
|
||||
Exclude chats that match the supplied phone number
|
||||
--dont-filter-empty By default, the exporter will not render chats with no valid message. Setting this flag will
|
||||
cause the exporter to render those. This is useful if chat(s) are missing from the output
|
||||
|
||||
Contact Enrichment:
|
||||
--enrich-from-vcards ENRICH_FROM_VCARDS
|
||||
Path to an exported vcf file from Google contacts export. Add names missing from WhatsApp's
|
||||
default database
|
||||
--default-country-code DEFAULT_COUNTRY_CODE
|
||||
Use with --enrich-from-vcards. When numbers in the vcf file does not have a country code, this
|
||||
will be used. 1 is for US, 66 for Thailand etc. Most likely use the number of your own country
|
||||
|
||||
Miscellaneous:
|
||||
-s, --showkey Show the HEX key used to decrypt the database
|
||||
--check-update Check for updates (require Internet access)
|
||||
--assume-first-as-me Assume the first message in a chat as sent by me (must be used together with -e)
|
||||
--business Use Whatsapp Business default files (iOS only)
|
||||
--decrypt-chunk-size DECRYPT_CHUNK_SIZE
|
||||
Specify the chunk size for decrypting iOS backup, which may affect the decryption speed.
|
||||
--max-bruteforce-worker MAX_BRUTEFORCE_WORKER
|
||||
Specify the maximum number of worker for bruteforce decryption.
|
||||
|
||||
WhatsApp Chat Exporter: 0.12.0 Licensed with MIT. See https://wts.knugi.dev/docs?dest=osl for all open source
|
||||
licenses.
|
||||
```
|
||||
|
||||
# To do
|
||||
See [issues](https://github.com/KnugiHK/Whatsapp-Chat-Exporter/issues).
|
||||
|
||||
# Legal Stuff & Disclaimer
|
||||
This is a MIT licensed project.
|
||||
|
||||
The Telegram Desktop's export is the reference for whatsapp.html in this repo.
|
||||
|
||||
`bplist.py` was released by Vladimir "Farcaller" Pouzanov under MIT license.
|
||||
|
||||
Please also refer to any files prefixed with `LICENSE` to obtain copies of the various licenses.
|
||||
|
||||
WhatsApp Chat Exporter is not affiliated, associated, authorized, endorsed by, or in any way officially connected with the WhatsApp LLC, or any of its subsidiaries or its affiliates. The official WhatsApp LLC website can be found at https://www.whatsapp.com/.
|
||||
@@ -1,733 +0,0 @@
|
||||
#!/usr/bin/python3
|
||||
|
||||
import io
|
||||
import os
|
||||
import sqlite3
|
||||
import shutil
|
||||
import json
|
||||
import string
|
||||
import glob
|
||||
import importlib.metadata
|
||||
from Whatsapp_Chat_Exporter import android_crypt, exported_handler, android_handler
|
||||
from Whatsapp_Chat_Exporter import ios_handler, ios_media_handler
|
||||
from Whatsapp_Chat_Exporter.data_model import ChatCollection, ChatStore
|
||||
from Whatsapp_Chat_Exporter.utility import APPLE_TIME, Crypt, check_update, DbType
|
||||
from Whatsapp_Chat_Exporter.utility import readable_to_bytes, sanitize_filename
|
||||
from Whatsapp_Chat_Exporter.utility import import_from_json, bytes_to_readable
|
||||
from argparse import ArgumentParser, SUPPRESS
|
||||
from datetime import datetime
|
||||
from getpass import getpass
|
||||
from sys import exit
|
||||
from typing import Tuple, Optional, List, Dict, Any, Union
|
||||
|
||||
# Try to import vobject for contacts processing
|
||||
try:
|
||||
import vobject
|
||||
except ModuleNotFoundError:
|
||||
vcards_deps_installed = False
|
||||
else:
|
||||
from Whatsapp_Chat_Exporter.vcards_contacts import ContactsFromVCards
|
||||
vcards_deps_installed = True
|
||||
|
||||
|
||||
def setup_argument_parser() -> ArgumentParser:
|
||||
"""Set up and return the argument parser with all options."""
|
||||
parser = ArgumentParser(
|
||||
description='A customizable Android and iOS/iPadOS WhatsApp database parser that '
|
||||
'will give you the history of your WhatsApp conversations in HTML '
|
||||
'and JSON. Android Backup Crypt12, Crypt14 and Crypt15 supported.',
|
||||
epilog=f'WhatsApp Chat Exporter: {importlib.metadata.version("whatsapp_chat_exporter")} Licensed with MIT. See '
|
||||
'https://wts.knugi.dev/docs?dest=osl for all open source licenses.'
|
||||
)
|
||||
|
||||
# Device type arguments
|
||||
device_group = parser.add_argument_group('Device Type')
|
||||
device_group.add_argument(
|
||||
'-a', '--android', dest='android', default=False, action='store_true',
|
||||
help="Define the target as Android"
|
||||
)
|
||||
device_group.add_argument(
|
||||
'-i', '--ios', dest='ios', default=False, action='store_true',
|
||||
help="Define the target as iPhone/iPad"
|
||||
)
|
||||
device_group.add_argument(
|
||||
"-e", "--exported", dest="exported", default=None,
|
||||
help="Define the target as exported chat file and specify the path to the file"
|
||||
)
|
||||
|
||||
# Input file paths
|
||||
input_group = parser.add_argument_group('Input Files')
|
||||
input_group.add_argument(
|
||||
"-w", "--wa", dest="wa", default=None,
|
||||
help="Path to contact database (default: wa.db/ContactsV2.sqlite)"
|
||||
)
|
||||
input_group.add_argument(
|
||||
"-m", "--media", dest="media", default=None,
|
||||
help="Path to WhatsApp media folder (default: WhatsApp)"
|
||||
)
|
||||
input_group.add_argument(
|
||||
"-b", "--backup", dest="backup", default=None,
|
||||
help="Path to Android (must be used together with -k)/iOS WhatsApp backup"
|
||||
)
|
||||
input_group.add_argument(
|
||||
"-d", "--db", dest="db", default=None,
|
||||
help="Path to database file (default: msgstore.db/7c7fba66680ef796b916b067077cc246adacf01d)"
|
||||
)
|
||||
input_group.add_argument(
|
||||
"-k", "--key", dest="key", default=None, nargs='?',
|
||||
help="Path to key file. If this option is set for crypt15 backup but nothing is specified, you will be prompted to enter the key."
|
||||
)
|
||||
input_group.add_argument(
|
||||
"--call-db", dest="call_db_ios", nargs='?', default=None, type=str,
|
||||
const="1b432994e958845fffe8e2f190f26d1511534088",
|
||||
help="Path to call database (default: 1b432994e958845fffe8e2f190f26d1511534088) iOS only"
|
||||
)
|
||||
input_group.add_argument(
|
||||
"--wab", "--wa-backup", dest="wab", default=None,
|
||||
help="Path to contact database in crypt15 format"
|
||||
)
|
||||
|
||||
# Output options
|
||||
output_group = parser.add_argument_group('Output Options')
|
||||
output_group.add_argument(
|
||||
"-o", "--output", dest="output", default="result",
|
||||
help="Output to specific directory (default: result)"
|
||||
)
|
||||
output_group.add_argument(
|
||||
'-j', '--json', dest='json', nargs='?', default=None, type=str, const="result.json",
|
||||
help="Save the result to a single JSON file (default if present: result.json)"
|
||||
)
|
||||
output_group.add_argument(
|
||||
"--txt", dest="text_format", nargs='?', default=None, type=str, const="result",
|
||||
help="Export chats in text format similar to what WhatsApp officially provided (default if present: result/)"
|
||||
)
|
||||
output_group.add_argument(
|
||||
"--no-html", dest="no_html", default=False, action='store_true',
|
||||
help="Do not output html files"
|
||||
)
|
||||
output_group.add_argument(
|
||||
"--size", "--output-size", "--split", dest="size", nargs='?', const=0, default=None,
|
||||
help="Maximum (rough) size of a single output file in bytes, 0 for auto"
|
||||
)
|
||||
|
||||
# JSON formatting options
|
||||
json_group = parser.add_argument_group('JSON Options')
|
||||
json_group.add_argument(
|
||||
'--avoid-encoding-json', dest='avoid_encoding_json', default=False, action='store_true',
|
||||
help="Don't encode non-ascii characters in the output JSON files"
|
||||
)
|
||||
json_group.add_argument(
|
||||
'--pretty-print-json', dest='pretty_print_json', default=None, nargs='?', const=2, type=int,
|
||||
help="Pretty print the output JSON."
|
||||
)
|
||||
json_group.add_argument(
|
||||
"--per-chat", dest="json_per_chat", default=False, action='store_true',
|
||||
help="Output the JSON file per chat"
|
||||
)
|
||||
json_group.add_argument(
|
||||
"--import", dest="import_json", default=False, action='store_true',
|
||||
help="Import JSON file and convert to HTML output"
|
||||
)
|
||||
|
||||
# HTML options
|
||||
html_group = parser.add_argument_group('HTML Options')
|
||||
html_group.add_argument(
|
||||
"-t", "--template", dest="template", default=None,
|
||||
help="Path to custom HTML template"
|
||||
)
|
||||
html_group.add_argument(
|
||||
"--embedded", dest="embedded", default=False, action='store_true',
|
||||
help=SUPPRESS or "Embed media into HTML file (not yet implemented)"
|
||||
)
|
||||
html_group.add_argument(
|
||||
"--offline", dest="offline", default=None,
|
||||
help="Relative path to offline static files"
|
||||
)
|
||||
html_group.add_argument(
|
||||
"--no-avatar", dest="no_avatar", default=False, action='store_true',
|
||||
help="Do not render avatar in HTML output"
|
||||
)
|
||||
html_group.add_argument(
|
||||
"--experimental-new-theme", dest="whatsapp_theme", default=False, action='store_true',
|
||||
help="Use the newly designed WhatsApp-alike theme"
|
||||
)
|
||||
html_group.add_argument(
|
||||
"--headline", dest="headline", default="Chat history with ??",
|
||||
help="The custom headline for the HTML output. Use '??' as a placeholder for the chat name"
|
||||
)
|
||||
|
||||
# Media handling
|
||||
media_group = parser.add_argument_group('Media Handling')
|
||||
media_group.add_argument(
|
||||
"-c", "--move-media", dest="move_media", default=False, action='store_true',
|
||||
help="Move the media directory to output directory if the flag is set, otherwise copy it"
|
||||
)
|
||||
media_group.add_argument(
|
||||
"--create-separated-media", dest="separate_media", default=False, action='store_true',
|
||||
help="Create a copy of the media seperated per chat in <MEDIA>/separated/ directory"
|
||||
)
|
||||
|
||||
# Filtering options
|
||||
filter_group = parser.add_argument_group('Filtering Options')
|
||||
filter_group.add_argument(
|
||||
"--time-offset", dest="timezone_offset", default=0, type=int, choices=range(-12, 15),
|
||||
metavar="{-12 to 14}", help="Offset in hours (-12 to 14) for time displayed in the output"
|
||||
)
|
||||
filter_group.add_argument(
|
||||
"--date", dest="filter_date", default=None, metavar="DATE",
|
||||
help="The date filter in specific format (inclusive)"
|
||||
)
|
||||
filter_group.add_argument(
|
||||
"--date-format", dest="filter_date_format", default="%Y-%m-%d %H:%M", metavar="FORMAT",
|
||||
help="The date format for the date filter"
|
||||
)
|
||||
filter_group.add_argument(
|
||||
"--include", dest="filter_chat_include", nargs='*', metavar="phone number",
|
||||
help="Include chats that match the supplied phone number"
|
||||
)
|
||||
filter_group.add_argument(
|
||||
"--exclude", dest="filter_chat_exclude", nargs='*', metavar="phone number",
|
||||
help="Exclude chats that match the supplied phone number"
|
||||
)
|
||||
filter_group.add_argument(
|
||||
"--dont-filter-empty", dest="filter_empty", default=True, action='store_false',
|
||||
help=("By default, the exporter will not render chats with no valid message. "
|
||||
"Setting this flag will cause the exporter to render those. "
|
||||
"This is useful if chat(s) are missing from the output")
|
||||
)
|
||||
|
||||
# Contact enrichment
|
||||
contact_group = parser.add_argument_group('Contact Enrichment')
|
||||
contact_group.add_argument(
|
||||
"--enrich-from-vcards", dest="enrich_from_vcards", default=None,
|
||||
help="Path to an exported vcf file from Google contacts export. Add names missing from WhatsApp's default database"
|
||||
)
|
||||
contact_group.add_argument(
|
||||
"--default-country-code", dest="default_country_code", default=None,
|
||||
help="Use with --enrich-from-vcards. When numbers in the vcf file does not have a country code, this will be used. 1 is for US, 66 for Thailand etc. Most likely use the number of your own country"
|
||||
)
|
||||
|
||||
# Miscellaneous
|
||||
misc_group = parser.add_argument_group('Miscellaneous')
|
||||
misc_group.add_argument(
|
||||
"-s", "--showkey", dest="showkey", default=False, action='store_true',
|
||||
help="Show the HEX key used to decrypt the database"
|
||||
)
|
||||
misc_group.add_argument(
|
||||
"--check-update", dest="check_update", default=False, action='store_true',
|
||||
help="Check for updates (require Internet access)"
|
||||
)
|
||||
misc_group.add_argument(
|
||||
"--assume-first-as-me", dest="assume_first_as_me", default=False, action='store_true',
|
||||
help="Assume the first message in a chat as sent by me (must be used together with -e)"
|
||||
)
|
||||
misc_group.add_argument(
|
||||
"--business", dest="business", default=False, action='store_true',
|
||||
help="Use Whatsapp Business default files (iOS only)"
|
||||
)
|
||||
misc_group.add_argument(
|
||||
"--decrypt-chunk-size", dest="decrypt_chunk_size", default=1 * 1024 * 1024, type=int,
|
||||
help="Specify the chunk size for decrypting iOS backup, which may affect the decryption speed."
|
||||
)
|
||||
misc_group.add_argument(
|
||||
"--max-bruteforce-worker", dest="max_bruteforce_worker", default=10, type=int,
|
||||
help="Specify the maximum number of worker for bruteforce decryption."
|
||||
)
|
||||
|
||||
return parser
|
||||
|
||||
|
||||
def validate_args(parser: ArgumentParser, args) -> None:
|
||||
"""Validate command line arguments and modify them if needed."""
|
||||
# Basic validation checks
|
||||
if args.android and args.ios and args.exported and args.import_json:
|
||||
parser.error("You must define only one device type.")
|
||||
if not args.android and not args.ios and not args.exported and not args.import_json:
|
||||
parser.error("You must define the device type.")
|
||||
if args.no_html and not args.json and not args.text_format:
|
||||
parser.error("You must either specify a JSON output file, text file output directory or enable HTML output.")
|
||||
if args.import_json and (args.android or args.ios or args.exported or args.no_html):
|
||||
parser.error("You can only use --import with -j and without --no-html, -a, -i, -e.")
|
||||
elif args.import_json and not os.path.isfile(args.json):
|
||||
parser.error("JSON file not found.")
|
||||
if args.android and args.business:
|
||||
parser.error("WhatsApp Business is only available on iOS for now.")
|
||||
if "??" not in args.headline:
|
||||
parser.error("--headline must contain '??' for replacement.")
|
||||
|
||||
# JSON validation
|
||||
if args.json_per_chat and args.json and (
|
||||
(args.json.endswith(".json") and os.path.isfile(args.json)) or
|
||||
(not args.json.endswith(".json") and os.path.isfile(args.json))
|
||||
):
|
||||
parser.error("When --per-chat is enabled, the destination of --json must be a directory.")
|
||||
|
||||
# vCards validation
|
||||
if args.enrich_from_vcards is not None and args.default_country_code is None:
|
||||
parser.error("When --enrich-from-vcards is provided, you must also set --default-country-code")
|
||||
|
||||
# Size validation
|
||||
if args.size is not None and not isinstance(args.size, int) and not args.size.isnumeric():
|
||||
try:
|
||||
args.size = readable_to_bytes(args.size)
|
||||
except ValueError:
|
||||
parser.error("The value for --split must be ended in pure bytes or with a proper unit (e.g., 1048576 or 1MB)")
|
||||
|
||||
# Date filter validation and processing
|
||||
if args.filter_date is not None:
|
||||
process_date_filter(parser, args)
|
||||
|
||||
# Crypt15 key validation
|
||||
if args.key is None and args.backup is not None and args.backup.endswith("crypt15"):
|
||||
args.key = getpass("Enter your encryption key: ")
|
||||
|
||||
# Theme validation
|
||||
if args.whatsapp_theme:
|
||||
args.template = "whatsapp_new.html"
|
||||
|
||||
# Chat filter validation
|
||||
if args.filter_chat_include is not None and args.filter_chat_exclude is not None:
|
||||
parser.error("Chat inclusion and exclusion filters cannot be used together.")
|
||||
|
||||
validate_chat_filters(parser, args.filter_chat_include)
|
||||
validate_chat_filters(parser, args.filter_chat_exclude)
|
||||
|
||||
|
||||
def validate_chat_filters(parser: ArgumentParser, chat_filter: Optional[List[str]]) -> None:
|
||||
"""Validate chat filters to ensure they contain only phone numbers."""
|
||||
if chat_filter is not None:
|
||||
for chat in chat_filter:
|
||||
if not chat.isnumeric():
|
||||
parser.error("Enter a phone number in the chat filter. See https://wts.knugi.dev/docs?dest=chat")
|
||||
|
||||
|
||||
def process_date_filter(parser: ArgumentParser, args) -> None:
|
||||
"""Process and validate date filter arguments."""
|
||||
if " - " in args.filter_date:
|
||||
start, end = args.filter_date.split(" - ")
|
||||
start = int(datetime.strptime(start, args.filter_date_format).timestamp())
|
||||
end = int(datetime.strptime(end, args.filter_date_format).timestamp())
|
||||
|
||||
if start < 1009843200 or end < 1009843200:
|
||||
parser.error("WhatsApp was first released in 2009...")
|
||||
if start > end:
|
||||
parser.error("The start date cannot be a moment after the end date.")
|
||||
|
||||
if args.android:
|
||||
args.filter_date = f"BETWEEN {start}000 AND {end}000"
|
||||
elif args.ios:
|
||||
args.filter_date = f"BETWEEN {start - APPLE_TIME} AND {end - APPLE_TIME}"
|
||||
else:
|
||||
process_single_date_filter(parser, args)
|
||||
|
||||
|
||||
def process_single_date_filter(parser: ArgumentParser, args) -> None:
|
||||
"""Process single date comparison filters."""
|
||||
if len(args.filter_date) < 3:
|
||||
parser.error("Unsupported date format. See https://wts.knugi.dev/docs?dest=date")
|
||||
|
||||
_timestamp = int(datetime.strptime(args.filter_date[2:], args.filter_date_format).timestamp())
|
||||
|
||||
if _timestamp < 1009843200:
|
||||
parser.error("WhatsApp was first released in 2009...")
|
||||
|
||||
if args.filter_date[:2] == "> ":
|
||||
if args.android:
|
||||
args.filter_date = f">= {_timestamp}000"
|
||||
elif args.ios:
|
||||
args.filter_date = f">= {_timestamp - APPLE_TIME}"
|
||||
elif args.filter_date[:2] == "< ":
|
||||
if args.android:
|
||||
args.filter_date = f"<= {_timestamp}000"
|
||||
elif args.ios:
|
||||
args.filter_date = f"<= {_timestamp - APPLE_TIME}"
|
||||
else:
|
||||
parser.error("Unsupported date format. See https://wts.knugi.dev/docs?dest=date")
|
||||
|
||||
|
||||
def setup_contact_store(args) -> Optional['ContactsFromVCards']:
|
||||
"""Set up and return a contact store if needed."""
|
||||
if args.enrich_from_vcards is not None:
|
||||
if not vcards_deps_installed:
|
||||
print(
|
||||
"You don't have the dependency to enrich contacts with vCard.\n"
|
||||
"Read more on how to deal with enriching contacts:\n"
|
||||
"https://github.com/KnugiHK/Whatsapp-Chat-Exporter/blob/main/README.md#usage"
|
||||
)
|
||||
exit(1)
|
||||
contact_store = ContactsFromVCards()
|
||||
contact_store.load_vcf_file(args.enrich_from_vcards, args.default_country_code)
|
||||
return contact_store
|
||||
return None
|
||||
|
||||
|
||||
def decrypt_android_backup(args) -> int:
|
||||
"""Decrypt Android backup files and return error code."""
|
||||
if args.key is None or args.backup is None:
|
||||
print("You must specify the backup file with -b and a key with -k")
|
||||
return 1
|
||||
|
||||
print("Decryption key specified, decrypting WhatsApp backup...")
|
||||
|
||||
# Determine crypt type
|
||||
if "crypt12" in args.backup:
|
||||
crypt = Crypt.CRYPT12
|
||||
elif "crypt14" in args.backup:
|
||||
crypt = Crypt.CRYPT14
|
||||
elif "crypt15" in args.backup:
|
||||
crypt = Crypt.CRYPT15
|
||||
else:
|
||||
print("Unknown backup format. The backup file must be crypt12, crypt14 or crypt15.")
|
||||
return 1
|
||||
|
||||
# Get key
|
||||
keyfile_stream = False
|
||||
if not os.path.isfile(args.key) and all(char in string.hexdigits for char in args.key.replace(" ", "")):
|
||||
key = bytes.fromhex(args.key.replace(" ", ""))
|
||||
else:
|
||||
key = open(args.key, "rb")
|
||||
keyfile_stream = True
|
||||
|
||||
# Read backup
|
||||
db = open(args.backup, "rb").read()
|
||||
|
||||
# Process WAB if provided
|
||||
error_wa = 0
|
||||
if args.wab:
|
||||
wab = open(args.wab, "rb").read()
|
||||
error_wa = android_crypt.decrypt_backup(
|
||||
wab,
|
||||
key,
|
||||
args.wa,
|
||||
crypt,
|
||||
args.showkey,
|
||||
DbType.CONTACT,
|
||||
keyfile_stream=keyfile_stream,
|
||||
max_worker=args.max_bruteforce_worker
|
||||
)
|
||||
if isinstance(key, io.IOBase):
|
||||
key.seek(0)
|
||||
|
||||
# Decrypt message database
|
||||
error_message = android_crypt.decrypt_backup(
|
||||
db,
|
||||
key,
|
||||
args.db,
|
||||
crypt,
|
||||
args.showkey,
|
||||
DbType.MESSAGE,
|
||||
keyfile_stream=keyfile_stream,
|
||||
max_worker=args.max_bruteforce_worker
|
||||
)
|
||||
|
||||
# Handle errors
|
||||
if error_wa != 0:
|
||||
return error_wa
|
||||
return error_message
|
||||
|
||||
|
||||
def handle_decrypt_error(error: int) -> None:
|
||||
"""Handle decryption errors with appropriate messages."""
|
||||
if error == 1:
|
||||
print("Dependencies of decrypt_backup and/or extract_encrypted_key"
|
||||
" are not present. For details, see README.md.")
|
||||
exit(3)
|
||||
elif error == 2:
|
||||
print("Failed when decompressing the decrypted backup. "
|
||||
"Possibly incorrect offsets used in decryption.")
|
||||
exit(4)
|
||||
else:
|
||||
print("Unknown error occurred.", error)
|
||||
exit(5)
|
||||
|
||||
|
||||
def process_contacts(args, data: ChatCollection, contact_store=None) -> None:
|
||||
"""Process contacts from the database."""
|
||||
contact_db = args.wa if args.wa else "wa.db" if args.android else "ContactsV2.sqlite"
|
||||
|
||||
if os.path.isfile(contact_db):
|
||||
with sqlite3.connect(contact_db) as db:
|
||||
db.row_factory = sqlite3.Row
|
||||
if args.android:
|
||||
android_handler.contacts(db, data, args.enrich_from_vcards)
|
||||
else:
|
||||
ios_handler.contacts(db, data)
|
||||
|
||||
|
||||
def process_messages(args, data: ChatCollection) -> None:
|
||||
"""Process messages, media and vcards from the database."""
|
||||
msg_db = args.db if args.db else "msgstore.db" if args.android else args.identifiers.MESSAGE
|
||||
|
||||
if not os.path.isfile(msg_db):
|
||||
print(
|
||||
"The message database does not exist. You may specify the path "
|
||||
"to database file with option -d or check your provided path."
|
||||
)
|
||||
exit(6)
|
||||
|
||||
filter_chat = (args.filter_chat_include, args.filter_chat_exclude)
|
||||
|
||||
with sqlite3.connect(msg_db) as db:
|
||||
db.row_factory = sqlite3.Row
|
||||
|
||||
# Process messages
|
||||
if args.android:
|
||||
message_handler = android_handler
|
||||
else:
|
||||
message_handler = ios_handler
|
||||
|
||||
message_handler.messages(
|
||||
db, data, args.media, args.timezone_offset,
|
||||
args.filter_date, filter_chat, args.filter_empty
|
||||
)
|
||||
|
||||
# Process media
|
||||
message_handler.media(
|
||||
db, data, args.media, args.filter_date,
|
||||
filter_chat, args.filter_empty, args.separate_media
|
||||
)
|
||||
|
||||
# Process vcards
|
||||
message_handler.vcard(
|
||||
db, data, args.media, args.filter_date,
|
||||
filter_chat, args.filter_empty
|
||||
)
|
||||
|
||||
# Process calls
|
||||
process_calls(args, db, data, filter_chat)
|
||||
|
||||
|
||||
def process_calls(args, db, data: ChatCollection, filter_chat) -> None:
|
||||
"""Process call history if available."""
|
||||
if args.android:
|
||||
android_handler.calls(db, data, args.timezone_offset, filter_chat)
|
||||
elif args.ios and args.call_db_ios is not None:
|
||||
with sqlite3.connect(args.call_db_ios) as cdb:
|
||||
cdb.row_factory = sqlite3.Row
|
||||
ios_handler.calls(cdb, data, args.timezone_offset, filter_chat)
|
||||
|
||||
|
||||
def handle_media_directory(args) -> None:
|
||||
"""Handle media directory copying or moving."""
|
||||
if os.path.isdir(args.media):
|
||||
media_path = os.path.join(args.output, args.media)
|
||||
|
||||
if os.path.isdir(media_path):
|
||||
print("\nWhatsApp directory already exists in output directory. Skipping...", end="\n")
|
||||
else:
|
||||
if args.move_media:
|
||||
try:
|
||||
print("\nMoving media directory...", end="\n")
|
||||
shutil.move(args.media, f"{args.output}/")
|
||||
except PermissionError:
|
||||
print("\nCannot remove original WhatsApp directory. "
|
||||
"Perhaps the directory is opened?", end="\n")
|
||||
else:
|
||||
print("\nCopying media directory...", end="\n")
|
||||
shutil.copytree(args.media, media_path)
|
||||
|
||||
|
||||
def create_output_files(args, data: ChatCollection, contact_store=None) -> None:
|
||||
"""Create output files in the specified formats."""
|
||||
# Create HTML files if requested
|
||||
if not args.no_html:
|
||||
# Enrich from vcards if available
|
||||
if contact_store and not contact_store.is_empty():
|
||||
contact_store.enrich_from_vcards(data)
|
||||
|
||||
android_handler.create_html(
|
||||
data,
|
||||
args.output,
|
||||
args.template,
|
||||
args.embedded,
|
||||
args.offline,
|
||||
args.size,
|
||||
args.no_avatar,
|
||||
args.whatsapp_theme,
|
||||
args.headline
|
||||
)
|
||||
|
||||
# Create text files if requested
|
||||
if args.text_format:
|
||||
print("Writing text file...")
|
||||
android_handler.create_txt(data, args.text_format)
|
||||
|
||||
# Create JSON files if requested
|
||||
if args.json and not args.import_json:
|
||||
export_json(args, data, contact_store)
|
||||
|
||||
|
||||
def export_json(args, data: ChatCollection, contact_store=None) -> None:
|
||||
"""Export data to JSON format."""
|
||||
# Enrich from vcards if available
|
||||
if contact_store and not contact_store.is_empty():
|
||||
contact_store.enrich_from_vcards(data)
|
||||
|
||||
# Convert ChatStore objects to JSON
|
||||
if isinstance(data.get(next(iter(data), None)), ChatStore):
|
||||
data = {jik: chat.to_json() for jik, chat in data.items()}
|
||||
|
||||
# Export as a single file or per chat
|
||||
if not args.json_per_chat:
|
||||
export_single_json(args, data)
|
||||
else:
|
||||
export_multiple_json(args, data)
|
||||
|
||||
|
||||
def export_single_json(args, data: Dict) -> None:
|
||||
"""Export data to a single JSON file."""
|
||||
with open(args.json, "w") as f:
|
||||
json_data = json.dumps(
|
||||
data,
|
||||
ensure_ascii=not args.avoid_encoding_json,
|
||||
indent=args.pretty_print_json
|
||||
)
|
||||
print(f"\nWriting JSON file...({bytes_to_readable(len(json_data))})")
|
||||
f.write(json_data)
|
||||
|
||||
|
||||
def export_multiple_json(args, data: Dict) -> None:
|
||||
"""Export data to multiple JSON files, one per chat."""
|
||||
# Adjust output path if needed
|
||||
json_path = args.json[:-5] if args.json.endswith(".json") else args.json
|
||||
|
||||
# Create directory if it doesn't exist
|
||||
if not os.path.isdir(json_path):
|
||||
os.makedirs(json_path, exist_ok=True)
|
||||
|
||||
# Export each chat
|
||||
total = len(data.keys())
|
||||
for index, jik in enumerate(data.keys()):
|
||||
if data[jik]["name"] is not None:
|
||||
contact = data[jik]["name"].replace('/', '')
|
||||
else:
|
||||
contact = jik.replace('+', '')
|
||||
|
||||
with open(f"{json_path}/{sanitize_filename(contact)}.json", "w") as f:
|
||||
file_content = json.dumps(
|
||||
{jik: data[jik]},
|
||||
ensure_ascii=not args.avoid_encoding_json,
|
||||
indent=args.pretty_print_json
|
||||
)
|
||||
f.write(file_content)
|
||||
print(f"Writing JSON file...({index + 1}/{total})", end="\r")
|
||||
print()
|
||||
|
||||
|
||||
def process_exported_chat(args, data: ChatCollection) -> None:
|
||||
"""Process an exported chat file."""
|
||||
exported_handler.messages(args.exported, data, args.assume_first_as_me)
|
||||
|
||||
if not args.no_html:
|
||||
android_handler.create_html(
|
||||
data,
|
||||
args.output,
|
||||
args.template,
|
||||
args.embedded,
|
||||
args.offline,
|
||||
args.size,
|
||||
args.no_avatar,
|
||||
args.whatsapp_theme,
|
||||
args.headline
|
||||
)
|
||||
|
||||
# Copy files to output directory
|
||||
for file in glob.glob(r'*.*'):
|
||||
shutil.copy(file, args.output)
|
||||
|
||||
|
||||
def main():
|
||||
"""Main function to run the WhatsApp Chat Exporter."""
|
||||
# Set up and parse arguments
|
||||
parser = setup_argument_parser()
|
||||
args = parser.parse_args()
|
||||
|
||||
# Check for updates
|
||||
if args.check_update:
|
||||
exit(check_update())
|
||||
|
||||
# Validate arguments
|
||||
validate_args(parser, args)
|
||||
|
||||
# Create output directory if it doesn't exist
|
||||
os.makedirs(args.output, exist_ok=True)
|
||||
|
||||
# Initialize data collection
|
||||
data = ChatCollection()
|
||||
|
||||
# Set up contact store for vCard enrichment if needed
|
||||
contact_store = setup_contact_store(args)
|
||||
|
||||
if args.import_json:
|
||||
# Import from JSON
|
||||
import_from_json(args.json, data)
|
||||
android_handler.create_html(
|
||||
data,
|
||||
args.output,
|
||||
args.template,
|
||||
args.embedded,
|
||||
args.offline,
|
||||
args.size,
|
||||
args.no_avatar,
|
||||
args.whatsapp_theme,
|
||||
args.headline
|
||||
)
|
||||
elif args.exported:
|
||||
# Process exported chat
|
||||
process_exported_chat(args, data)
|
||||
else:
|
||||
# Process Android or iOS data
|
||||
if args.android:
|
||||
# Set default media path if not provided
|
||||
if args.media is None:
|
||||
args.media = "WhatsApp"
|
||||
|
||||
# Set default DB paths if not provided
|
||||
if args.db is None:
|
||||
args.db = "msgstore.db"
|
||||
if args.wa is None:
|
||||
args.wa = "wa.db"
|
||||
|
||||
# Decrypt backup if needed
|
||||
if args.key is not None:
|
||||
error = decrypt_android_backup(args)
|
||||
if error != 0:
|
||||
handle_decrypt_error(error)
|
||||
elif args.ios:
|
||||
# Set up identifiers based on business flag
|
||||
if args.business:
|
||||
from Whatsapp_Chat_Exporter.utility import WhatsAppBusinessIdentifier as identifiers
|
||||
else:
|
||||
from Whatsapp_Chat_Exporter.utility import WhatsAppIdentifier as identifiers
|
||||
args.identifiers = identifiers
|
||||
|
||||
# Set default media path if not provided
|
||||
if args.media is None:
|
||||
args.media = identifiers.DOMAIN
|
||||
|
||||
# Extract media from backup if needed
|
||||
if args.backup is not None:
|
||||
if not os.path.isdir(args.media):
|
||||
ios_media_handler.extract_media(args.backup, identifiers, args.decrypt_chunk_size)
|
||||
else:
|
||||
print("WhatsApp directory already exists, skipping WhatsApp file extraction.")
|
||||
|
||||
# Set default DB paths if not provided
|
||||
if args.db is None:
|
||||
args.db = identifiers.MESSAGE
|
||||
if args.wa is None:
|
||||
args.wa = "ContactsV2.sqlite"
|
||||
|
||||
# Process contacts
|
||||
process_contacts(args, data, contact_store)
|
||||
|
||||
# Process messages, media, and calls
|
||||
process_messages(args, data)
|
||||
|
||||
# Create output files
|
||||
create_output_files(args, data, contact_store)
|
||||
|
||||
# Handle media directory
|
||||
handle_media_directory(args)
|
||||
|
||||
print("Everything is done!")
|
||||
@@ -1,328 +0,0 @@
|
||||
import hmac
|
||||
import io
|
||||
import zlib
|
||||
import concurrent.futures
|
||||
from typing import Tuple, Union
|
||||
from hashlib import sha256
|
||||
from sys import exit
|
||||
from Whatsapp_Chat_Exporter.utility import CRYPT14_OFFSETS, Crypt, DbType
|
||||
|
||||
try:
|
||||
import zlib
|
||||
from Crypto.Cipher import AES
|
||||
except ModuleNotFoundError:
|
||||
support_backup = False
|
||||
else:
|
||||
support_backup = True
|
||||
|
||||
try:
|
||||
import javaobj
|
||||
except ModuleNotFoundError:
|
||||
support_crypt15 = False
|
||||
else:
|
||||
support_crypt15 = True
|
||||
|
||||
|
||||
class DecryptionError(Exception):
|
||||
"""Base class for decryption-related exceptions."""
|
||||
pass
|
||||
|
||||
|
||||
class InvalidKeyError(DecryptionError):
|
||||
"""Raised when the provided key is invalid."""
|
||||
pass
|
||||
|
||||
|
||||
class InvalidFileFormatError(DecryptionError):
|
||||
"""Raised when the input file format is invalid."""
|
||||
pass
|
||||
|
||||
|
||||
class OffsetNotFoundError(DecryptionError):
|
||||
"""Raised when the correct offsets for decryption cannot be found."""
|
||||
pass
|
||||
|
||||
|
||||
def _derive_main_enc_key(key_stream: bytes) -> Tuple[bytes, bytes]:
|
||||
"""
|
||||
Derive the main encryption key for the given key stream.
|
||||
|
||||
Args:
|
||||
key_stream (bytes): The key stream to generate HMAC of HMAC.
|
||||
|
||||
Returns:
|
||||
Tuple[bytes, bytes]: A tuple containing the main encryption key and the original key stream.
|
||||
"""
|
||||
intermediate_hmac = hmac.new(b'\x00' * 32, key_stream, sha256).digest()
|
||||
key = hmac.new(intermediate_hmac, b"backup encryption\x01", sha256).digest()
|
||||
return key, key_stream
|
||||
|
||||
|
||||
def _extract_enc_key(keyfile: bytes) -> Tuple[bytes, bytes]:
|
||||
"""
|
||||
Extract the encryption key from the keyfile.
|
||||
|
||||
Args:
|
||||
keyfile (bytes): The keyfile containing the encrypted key.
|
||||
|
||||
Returns:
|
||||
Tuple[bytes, bytes]: values from _derive_main_enc_key()
|
||||
"""
|
||||
key_stream = b''.join([byte.to_bytes(1, "big", signed=True) for byte in javaobj.loads(keyfile)])
|
||||
return _derive_main_enc_key(key_stream)
|
||||
|
||||
|
||||
def brute_force_offset(max_iv: int = 200, max_db: int = 200):
|
||||
"""
|
||||
Brute force the offsets for IV and database start position in WhatsApp backup files.
|
||||
|
||||
Args:
|
||||
max_iv (int, optional): Maximum value to try for IV offset. Defaults to 200.
|
||||
max_db (int, optional): Maximum value to try for database start offset. Defaults to 200.
|
||||
|
||||
Yields:
|
||||
tuple: A tuple containing:
|
||||
- int: Start position of IV
|
||||
- int: End position of IV (start + 16)
|
||||
- int: Start position of database
|
||||
"""
|
||||
for iv in range(0, max_iv):
|
||||
for db in range(0, max_db):
|
||||
yield iv, iv + 16, db
|
||||
|
||||
|
||||
def _decrypt_database(db_ciphertext: bytes, main_key: bytes, iv: bytes) -> bytes:
|
||||
"""Decrypt and decompress a database chunk.
|
||||
|
||||
Args:
|
||||
db_ciphertext (bytes): The encrypted chunk of the database.
|
||||
main_key (bytes): The main decryption key.
|
||||
iv (bytes): The initialization vector.
|
||||
|
||||
Returns:
|
||||
bytes: The decrypted and decompressed database.
|
||||
|
||||
Raises:
|
||||
zlib.error: If decompression fails.
|
||||
ValueError: if the plaintext is not a SQLite database.
|
||||
"""
|
||||
cipher = AES.new(main_key, AES.MODE_GCM, iv)
|
||||
db_compressed = cipher.decrypt(db_ciphertext)
|
||||
db = zlib.decompress(db_compressed)
|
||||
if db[0:6].upper() != b"SQLITE":
|
||||
raise ValueError(
|
||||
"The plaintext is not a SQLite database. Ensure you are using the correct key."
|
||||
)
|
||||
return db
|
||||
|
||||
def _decrypt_crypt14(database: bytes, main_key: bytes, max_worker: int = 10) -> bytes:
|
||||
"""Decrypt a crypt14 database using multithreading for brute-force offset detection.
|
||||
|
||||
Args:
|
||||
database (bytes): The encrypted database.
|
||||
main_key (bytes): The decryption key.
|
||||
max_worker (int, optional): The maximum number of threads to use for brute force. Defaults to 10.
|
||||
|
||||
Returns:
|
||||
bytes: The decrypted database.
|
||||
|
||||
Raises:
|
||||
InvalidFileFormatError: If the file is too small.
|
||||
OffsetNotFoundError: If no valid offsets are found.
|
||||
"""
|
||||
if len(database) < 191:
|
||||
raise InvalidFileFormatError("The crypt14 file must be at least 191 bytes")
|
||||
|
||||
# Attempt known offsets first
|
||||
for offsets in CRYPT14_OFFSETS:
|
||||
iv = database[offsets["iv"]:offsets["iv"] + 16]
|
||||
db_ciphertext = database[offsets["db"]:]
|
||||
try:
|
||||
return _decrypt_database(db_ciphertext, main_key, iv)
|
||||
except (zlib.error, ValueError):
|
||||
pass # Try next offset
|
||||
|
||||
print("Common offsets failed. Initiating brute-force with multithreading...")
|
||||
|
||||
# Convert brute force generator into a list for parallel processing
|
||||
offset_combinations = list(brute_force_offset())
|
||||
|
||||
def attempt_decrypt(offset_tuple):
|
||||
"""Attempt decryption with the given offsets."""
|
||||
start_iv, end_iv, start_db = offset_tuple
|
||||
iv = database[start_iv:end_iv]
|
||||
db_ciphertext = database[start_db:]
|
||||
|
||||
try:
|
||||
db = _decrypt_database(db_ciphertext, main_key, iv)
|
||||
print(
|
||||
f"The offsets of your IV and database are {start_iv} and "
|
||||
f"{start_db}, respectively. To include your offsets in the "
|
||||
"program, please report it by creating an issue on GitHub: "
|
||||
"https://github.com/KnugiHK/Whatsapp-Chat-Exporter/discussions/47"
|
||||
"\nShutting down other threads..."
|
||||
)
|
||||
return db
|
||||
except (zlib.error, ValueError):
|
||||
return None # Decryption failed, move to next
|
||||
|
||||
with concurrent.futures.ThreadPoolExecutor(max_worker) as executor:
|
||||
future_to_offset = {executor.submit(attempt_decrypt, offset): offset for offset in offset_combinations}
|
||||
|
||||
try:
|
||||
for future in concurrent.futures.as_completed(future_to_offset):
|
||||
result = future.result()
|
||||
if result is not None:
|
||||
# Shutdown remaining threads
|
||||
executor.shutdown(wait=False, cancel_futures=True)
|
||||
return result
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print("\nBrute force interrupted by user (Ctrl+C). Exiting gracefully...")
|
||||
executor.shutdown(wait=False, cancel_futures=True)
|
||||
exit(1)
|
||||
|
||||
raise OffsetNotFoundError("Could not find the correct offsets for decryption.")
|
||||
|
||||
|
||||
|
||||
def _decrypt_crypt12(database: bytes, main_key: bytes) -> bytes:
|
||||
"""Decrypt a crypt12 database.
|
||||
|
||||
Args:
|
||||
database (bytes): The encrypted database.
|
||||
main_key (bytes): The decryption key.
|
||||
|
||||
Returns:
|
||||
bytes: The decrypted database.
|
||||
|
||||
Raises:
|
||||
ValueError: If the file format is invalid or the signature mismatches.
|
||||
"""
|
||||
if len(database) < 67:
|
||||
raise InvalidFileFormatError("The crypt12 file must be at least 67 bytes")
|
||||
|
||||
t2 = database[3:35]
|
||||
iv = database[51:67]
|
||||
db_ciphertext = database[67:-20]
|
||||
return _decrypt_database(db_ciphertext, main_key, iv)
|
||||
|
||||
|
||||
def _decrypt_crypt15(database: bytes, main_key: bytes, db_type: DbType) -> bytes:
|
||||
"""Decrypt a crypt15 database.
|
||||
|
||||
Args:
|
||||
database (bytes): The encrypted database.
|
||||
main_key (bytes): The decryption key.
|
||||
db_type (DbType): The type of database.
|
||||
|
||||
Returns:
|
||||
bytes: The decrypted database.
|
||||
|
||||
Raises:
|
||||
ValueError: If the file format is invalid or the signature mismatches.
|
||||
"""
|
||||
if not support_crypt15:
|
||||
raise RuntimeError("Crypt15 is not supported")
|
||||
if len(database) < 131:
|
||||
raise InvalidFileFormatError("The crypt15 file must be at least 131 bytes")
|
||||
|
||||
if db_type == DbType.MESSAGE:
|
||||
iv = database[8:24]
|
||||
db_offset = database[0] + 2
|
||||
elif db_type == DbType.CONTACT:
|
||||
iv = database[7:23]
|
||||
db_offset = database[0] + 1
|
||||
else:
|
||||
raise ValueError(f"Invalid db_type: {db_type}")
|
||||
|
||||
db_ciphertext = database[db_offset:]
|
||||
return _decrypt_database(db_ciphertext, main_key, iv)
|
||||
|
||||
|
||||
def decrypt_backup(
|
||||
database: bytes,
|
||||
key: Union[str, io.IOBase],
|
||||
output: str = None,
|
||||
crypt: Crypt = Crypt.CRYPT14,
|
||||
show_crypt15: bool = False,
|
||||
db_type: DbType = DbType.MESSAGE,
|
||||
*,
|
||||
dry_run: bool = False,
|
||||
keyfile_stream: bool = False,
|
||||
max_worker: int = 10
|
||||
) -> int:
|
||||
"""
|
||||
Decrypt the WhatsApp backup database.
|
||||
|
||||
Args:
|
||||
database (bytes): The encrypted database file.
|
||||
key (str or io.IOBase): The key to decrypt the database.
|
||||
output (str, optional): The path to save the decrypted database. Defaults to None.
|
||||
crypt (Crypt, optional): The encryption version of the database. Defaults to Crypt.CRYPT14.
|
||||
show_crypt15 (bool, optional): Whether to show the HEX key of the crypt15 backup. Defaults to False.
|
||||
db_type (DbType, optional): The type of database (MESSAGE or CONTACT). Defaults to DbType.MESSAGE.
|
||||
dry_run (bool, optional): Whether to perform a dry run. Defaults to False.
|
||||
keyfile_stream (bool, optional): Whether the key is a key stream. Defaults to False.
|
||||
|
||||
Returns:
|
||||
int: The status code of the decryption process (0 for success).
|
||||
|
||||
Raises:
|
||||
ValueError: If the key is invalid or output file not provided when dry_run is False.
|
||||
DecryptionError: for errors during decryption
|
||||
RuntimeError: for dependency errors
|
||||
"""
|
||||
if not support_backup:
|
||||
raise RuntimeError("Dependencies for backup decryption are not available.")
|
||||
|
||||
if not dry_run and output is None:
|
||||
raise ValueError(
|
||||
"The path to the decrypted database must be specified unless dry_run is true."
|
||||
)
|
||||
|
||||
if isinstance(key, io.IOBase):
|
||||
key = key.read()
|
||||
|
||||
if crypt is not Crypt.CRYPT15 and len(key) != 158:
|
||||
raise InvalidKeyError("The key file must be 158 bytes")
|
||||
|
||||
#signature check, this is check is used in crypt 12 and 14
|
||||
if crypt != Crypt.CRYPT15:
|
||||
t1 = key[30:62]
|
||||
|
||||
if t1 != database[15:47] and crypt == Crypt.CRYPT14:
|
||||
raise ValueError("The signature of key file and backup file mismatch")
|
||||
|
||||
if t1 != database[3:35] and crypt == Crypt.CRYPT12:
|
||||
raise ValueError("The signature of key file and backup file mismatch")
|
||||
|
||||
|
||||
if crypt == Crypt.CRYPT15:
|
||||
if keyfile_stream:
|
||||
main_key, hex_key = _extract_enc_key(key)
|
||||
else:
|
||||
main_key, hex_key = _derive_main_enc_key(key)
|
||||
if show_crypt15:
|
||||
hex_key_str = ' '.join([hex_key.hex()[c:c+4] for c in range(0, len(hex_key.hex()), 4)])
|
||||
print(f"The HEX key of the crypt15 backup is: {hex_key_str}")
|
||||
else:
|
||||
main_key = key[126:]
|
||||
|
||||
try:
|
||||
if crypt == Crypt.CRYPT14:
|
||||
db = _decrypt_crypt14(database, main_key, max_worker)
|
||||
elif crypt == Crypt.CRYPT12:
|
||||
db = _decrypt_crypt12(database, main_key)
|
||||
elif crypt == Crypt.CRYPT15:
|
||||
db = _decrypt_crypt15(database, main_key, db_type)
|
||||
else:
|
||||
raise ValueError(f"Unsupported crypt type: {crypt}")
|
||||
except (InvalidFileFormatError, OffsetNotFoundError, ValueError) as e:
|
||||
raise DecryptionError(f"Decryption failed: {e}") from e
|
||||
|
||||
|
||||
if not dry_run:
|
||||
with open(output, "wb") as f:
|
||||
f.write(db)
|
||||
return 0
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,292 +0,0 @@
|
||||
#################################################################################
|
||||
# Copyright (C) 2009-2011 Vladimir "Farcaller" Pouzanov <farcaller@gmail.com> #
|
||||
# #
|
||||
# Permission is hereby granted, free of charge, to any person obtaining a copy #
|
||||
# of this software and associated documentation files (the "Software"), to deal #
|
||||
# in the Software without restriction, including without limitation the rights #
|
||||
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell #
|
||||
# copies of the Software, and to permit persons to whom the Software is #
|
||||
# furnished to do so, subject to the following conditions: #
|
||||
# #
|
||||
# The above copyright notice and this permission notice shall be included in #
|
||||
# all copies or substantial portions of the Software. #
|
||||
# #
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR #
|
||||
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, #
|
||||
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE #
|
||||
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER #
|
||||
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, #
|
||||
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN #
|
||||
# THE SOFTWARE. #
|
||||
#################################################################################
|
||||
|
||||
import struct
|
||||
import codecs
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
class BPListWriter(object):
|
||||
def __init__(self, objects):
|
||||
self.bplist = ""
|
||||
self.objects = objects
|
||||
|
||||
def binary(self):
|
||||
'''binary -> string
|
||||
|
||||
Generates bplist
|
||||
'''
|
||||
self.data = 'bplist00'
|
||||
|
||||
# TODO: flatten objects and count max length size
|
||||
|
||||
# TODO: write objects and save offsets
|
||||
|
||||
# TODO: write offsets
|
||||
|
||||
# TODO: write metadata
|
||||
|
||||
return self.data
|
||||
|
||||
def write(self, filename):
|
||||
'''
|
||||
|
||||
Writes bplist to file
|
||||
'''
|
||||
if self.bplist != "":
|
||||
pass
|
||||
# TODO: save self.bplist to file
|
||||
else:
|
||||
raise Exception('BPlist not yet generated')
|
||||
|
||||
class BPListReader(object):
|
||||
def __init__(self, s):
|
||||
self.data = s
|
||||
self.objects = []
|
||||
self.resolved = {}
|
||||
|
||||
def __unpackIntStruct(self, sz, s):
|
||||
'''__unpackIntStruct(size, string) -> int
|
||||
|
||||
Unpacks the integer of given size (1, 2 or 4 bytes) from string
|
||||
'''
|
||||
if sz == 1:
|
||||
ot = '!B'
|
||||
elif sz == 2:
|
||||
ot = '!H'
|
||||
elif sz == 4:
|
||||
ot = '!I'
|
||||
elif sz == 8:
|
||||
ot = '!Q'
|
||||
else:
|
||||
raise Exception('int unpack size '+str(sz)+' unsupported')
|
||||
return struct.unpack(ot, s)[0]
|
||||
|
||||
def __unpackInt(self, offset):
|
||||
'''__unpackInt(offset) -> int
|
||||
|
||||
Unpacks int field from plist at given offset
|
||||
'''
|
||||
return self.__unpackIntMeta(offset)[1]
|
||||
|
||||
def __unpackIntMeta(self, offset):
|
||||
'''__unpackIntMeta(offset) -> (size, int)
|
||||
|
||||
Unpacks int field from plist at given offset and returns its size and value
|
||||
'''
|
||||
obj_header = self.data[offset]
|
||||
obj_type, obj_info = (obj_header & 0xF0), (obj_header & 0x0F)
|
||||
int_sz = 2**obj_info
|
||||
return int_sz, self.__unpackIntStruct(int_sz, self.data[offset+1:offset+1+int_sz])
|
||||
|
||||
def __resolveIntSize(self, obj_info, offset):
|
||||
'''__resolveIntSize(obj_info, offset) -> (count, offset)
|
||||
|
||||
Calculates count of objref* array entries and returns count and offset to first element
|
||||
'''
|
||||
if obj_info == 0x0F:
|
||||
ofs, obj_count = self.__unpackIntMeta(offset+1)
|
||||
objref = offset+2+ofs
|
||||
else:
|
||||
obj_count = obj_info
|
||||
objref = offset+1
|
||||
return obj_count, objref
|
||||
|
||||
def __unpackFloatStruct(self, sz, s):
|
||||
'''__unpackFloatStruct(size, string) -> float
|
||||
|
||||
Unpacks the float of given size (4 or 8 bytes) from string
|
||||
'''
|
||||
if sz == 4:
|
||||
ot = '!f'
|
||||
elif sz == 8:
|
||||
ot = '!d'
|
||||
else:
|
||||
raise Exception('float unpack size '+str(sz)+' unsupported')
|
||||
return struct.unpack(ot, s)[0]
|
||||
|
||||
def __unpackFloat(self, offset):
|
||||
'''__unpackFloat(offset) -> float
|
||||
|
||||
Unpacks float field from plist at given offset
|
||||
'''
|
||||
obj_header = self.data[offset]
|
||||
obj_type, obj_info = (obj_header & 0xF0), (obj_header & 0x0F)
|
||||
int_sz = 2**obj_info
|
||||
return int_sz, self.__unpackFloatStruct(int_sz, self.data[offset+1:offset+1+int_sz])
|
||||
|
||||
def __unpackDate(self, offset):
|
||||
td = int(struct.unpack(">d", self.data[offset+1:offset+9])[0])
|
||||
return datetime(year=2001,month=1,day=1) + timedelta(seconds=td)
|
||||
|
||||
def __unpackItem(self, offset):
|
||||
'''__unpackItem(offset)
|
||||
|
||||
Unpacks and returns an item from plist
|
||||
'''
|
||||
obj_header = self.data[offset]
|
||||
obj_type, obj_info = (obj_header & 0xF0), (obj_header & 0x0F)
|
||||
if obj_type == 0x00:
|
||||
if obj_info == 0x00: # null 0000 0000
|
||||
return None
|
||||
elif obj_info == 0x08: # bool 0000 1000 // false
|
||||
return False
|
||||
elif obj_info == 0x09: # bool 0000 1001 // true
|
||||
return True
|
||||
elif obj_info == 0x0F: # fill 0000 1111 // fill byte
|
||||
raise Exception("0x0F Not Implemented") # this is really pad byte, FIXME
|
||||
else:
|
||||
raise Exception('unpack item type '+str(obj_header)+' at '+str(offset)+ 'failed')
|
||||
elif obj_type == 0x10: # int 0001 nnnn ... // # of bytes is 2^nnnn, big-endian bytes
|
||||
return self.__unpackInt(offset)
|
||||
elif obj_type == 0x20: # real 0010 nnnn ... // # of bytes is 2^nnnn, big-endian bytes
|
||||
return self.__unpackFloat(offset)
|
||||
elif obj_type == 0x30: # date 0011 0011 ... // 8 byte float follows, big-endian bytes
|
||||
return self.__unpackDate(offset)
|
||||
elif obj_type == 0x40: # data 0100 nnnn [int] ... // nnnn is number of bytes unless 1111 then int count follows, followed by bytes
|
||||
obj_count, objref = self.__resolveIntSize(obj_info, offset)
|
||||
return self.data[objref:objref+obj_count] # XXX: we return data as str
|
||||
elif obj_type == 0x50: # string 0101 nnnn [int] ... // ASCII string, nnnn is # of chars, else 1111 then int count, then bytes
|
||||
obj_count, objref = self.__resolveIntSize(obj_info, offset)
|
||||
return self.data[objref:objref+obj_count]
|
||||
elif obj_type == 0x60: # string 0110 nnnn [int] ... // Unicode string, nnnn is # of chars, else 1111 then int count, then big-endian 2-byte uint16_t
|
||||
obj_count, objref = self.__resolveIntSize(obj_info, offset)
|
||||
return self.data[objref:objref+obj_count*2].decode('utf-16be')
|
||||
elif obj_type == 0x80: # uid 1000 nnnn ... // nnnn+1 is # of bytes
|
||||
# FIXME: Accept as a string for now
|
||||
obj_count, objref = self.__resolveIntSize(obj_info, offset)
|
||||
return self.data[objref:objref+obj_count]
|
||||
elif obj_type == 0xA0: # array 1010 nnnn [int] objref* // nnnn is count, unless '1111', then int count follows
|
||||
obj_count, objref = self.__resolveIntSize(obj_info, offset)
|
||||
arr = []
|
||||
for i in range(obj_count):
|
||||
arr.append(self.__unpackIntStruct(self.object_ref_size, self.data[objref+i*self.object_ref_size:objref+i*self.object_ref_size+self.object_ref_size]))
|
||||
return arr
|
||||
elif obj_type == 0xC0: # set 1100 nnnn [int] objref* // nnnn is count, unless '1111', then int count follows
|
||||
# XXX: not serializable via apple implementation
|
||||
raise Exception("0xC0 Not Implemented") # FIXME: implement
|
||||
elif obj_type == 0xD0: # dict 1101 nnnn [int] keyref* objref* // nnnn is count, unless '1111', then int count follows
|
||||
obj_count, objref = self.__resolveIntSize(obj_info, offset)
|
||||
keys = []
|
||||
for i in range(obj_count):
|
||||
keys.append(self.__unpackIntStruct(self.object_ref_size, self.data[objref+i*self.object_ref_size:objref+i*self.object_ref_size+self.object_ref_size]))
|
||||
values = []
|
||||
objref += obj_count*self.object_ref_size
|
||||
for i in range(obj_count):
|
||||
values.append(self.__unpackIntStruct(self.object_ref_size, self.data[objref+i*self.object_ref_size:objref+i*self.object_ref_size+self.object_ref_size]))
|
||||
dic = {}
|
||||
for i in range(obj_count):
|
||||
dic[keys[i]] = values[i]
|
||||
return dic
|
||||
else:
|
||||
raise Exception('don\'t know how to unpack obj type '+hex(obj_type)+' at '+str(offset))
|
||||
|
||||
def __resolveObject(self, idx):
|
||||
try:
|
||||
return self.resolved[idx]
|
||||
except KeyError:
|
||||
obj = self.objects[idx]
|
||||
if type(obj) == list:
|
||||
newArr = []
|
||||
for i in obj:
|
||||
newArr.append(self.__resolveObject(i))
|
||||
self.resolved[idx] = newArr
|
||||
return newArr
|
||||
if type(obj) == dict:
|
||||
newDic = {}
|
||||
for k,v in obj.items():
|
||||
key_resolved = self.__resolveObject(k)
|
||||
if isinstance(key_resolved, str):
|
||||
rk = key_resolved
|
||||
else:
|
||||
rk = codecs.decode(key_resolved, "utf-8")
|
||||
rv = self.__resolveObject(v)
|
||||
newDic[rk] = rv
|
||||
self.resolved[idx] = newDic
|
||||
return newDic
|
||||
else:
|
||||
self.resolved[idx] = obj
|
||||
return obj
|
||||
|
||||
def parse(self):
|
||||
# read header
|
||||
if self.data[:8] != b'bplist00':
|
||||
raise Exception('Bad magic')
|
||||
|
||||
# read trailer
|
||||
self.offset_size, self.object_ref_size, self.number_of_objects, self.top_object, self.table_offset = struct.unpack('!6xBB4xI4xI4xI', self.data[-32:])
|
||||
#print "** plist offset_size:",self.offset_size,"objref_size:",self.object_ref_size,"num_objs:",self.number_of_objects,"top:",self.top_object,"table_ofs:",self.table_offset
|
||||
|
||||
# read offset table
|
||||
self.offset_table = self.data[self.table_offset:-32]
|
||||
self.offsets = []
|
||||
ot = self.offset_table
|
||||
for i in range(self.number_of_objects):
|
||||
offset_entry = ot[:self.offset_size]
|
||||
ot = ot[self.offset_size:]
|
||||
self.offsets.append(self.__unpackIntStruct(self.offset_size, offset_entry))
|
||||
#print "** plist offsets:",self.offsets
|
||||
|
||||
# read object table
|
||||
self.objects = []
|
||||
k = 0
|
||||
for i in self.offsets:
|
||||
obj = self.__unpackItem(i)
|
||||
#print "** plist unpacked",k,type(obj),obj,"at",i
|
||||
k += 1
|
||||
self.objects.append(obj)
|
||||
|
||||
# rebuild object tree
|
||||
#for i in range(len(self.objects)):
|
||||
# self.__resolveObject(i)
|
||||
|
||||
# return root object
|
||||
return self.__resolveObject(self.top_object)
|
||||
|
||||
@classmethod
|
||||
def plistWithString(cls, s):
|
||||
parser = cls(s)
|
||||
return parser.parse()
|
||||
|
||||
# helpers for testing
|
||||
def plist(obj):
|
||||
from Foundation import NSPropertyListSerialization, NSPropertyListBinaryFormat_v1_0
|
||||
b = NSPropertyListSerialization.dataWithPropertyList_format_options_error_(obj, NSPropertyListBinaryFormat_v1_0, 0, None)
|
||||
return str(b.bytes())
|
||||
|
||||
def unplist(s):
|
||||
from Foundation import NSData, NSPropertyListSerialization
|
||||
d = NSData.dataWithBytes_length_(s, len(s))
|
||||
return NSPropertyListSerialization.propertyListWithData_options_format_error_(d, 0, None, None)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import os
|
||||
import sys
|
||||
import json
|
||||
file_path = sys.argv[1]
|
||||
|
||||
with open(file_path, "rb") as fp:
|
||||
data = fp.read()
|
||||
|
||||
out = BPListReader(data).parse()
|
||||
|
||||
with open(file_path + ".json", "w") as fp:
|
||||
json.dump(out, indent=4)
|
||||
@@ -1,313 +0,0 @@
|
||||
import os
|
||||
from datetime import datetime, tzinfo, timedelta
|
||||
from typing import MutableMapping, Union, Optional, Dict, Any
|
||||
|
||||
|
||||
class Timing:
|
||||
"""
|
||||
Handles timestamp formatting with timezone support.
|
||||
"""
|
||||
def __init__(self, timezone_offset: Optional[int]) -> None:
|
||||
"""
|
||||
Initialize Timing object.
|
||||
|
||||
Args:
|
||||
timezone_offset (Optional[int]): Hours offset from UTC
|
||||
"""
|
||||
self.timezone_offset = timezone_offset
|
||||
|
||||
def format_timestamp(self, timestamp: Optional[Union[int, float]], format: str) -> Optional[str]:
|
||||
"""
|
||||
Format a timestamp with the specified format string.
|
||||
|
||||
Args:
|
||||
timestamp (Optional[Union[int, float]]): Unix timestamp to format
|
||||
format (str): strftime format string
|
||||
|
||||
Returns:
|
||||
Optional[str]: Formatted timestamp string, or None if timestamp is None
|
||||
"""
|
||||
if timestamp:
|
||||
timestamp = timestamp / 1000 if timestamp > 9999999999 else timestamp
|
||||
return datetime.fromtimestamp(timestamp, TimeZone(self.timezone_offset)).strftime(format)
|
||||
return None
|
||||
|
||||
|
||||
class TimeZone(tzinfo):
|
||||
"""
|
||||
Custom timezone class with fixed offset.
|
||||
"""
|
||||
def __init__(self, offset: int) -> None:
|
||||
"""
|
||||
Initialize TimeZone object.
|
||||
|
||||
Args:
|
||||
offset (int): Hours offset from UTC
|
||||
"""
|
||||
self.offset = offset
|
||||
|
||||
def utcoffset(self, dt: Optional[datetime]) -> timedelta:
|
||||
"""Get UTC offset."""
|
||||
return timedelta(hours=self.offset)
|
||||
|
||||
def dst(self, dt: Optional[datetime]) -> timedelta:
|
||||
"""Get DST offset (always 0)."""
|
||||
return timedelta(0)
|
||||
|
||||
|
||||
class ChatCollection(MutableMapping):
|
||||
"""
|
||||
A collection of chats that provides dictionary-like access with additional chat management methods.
|
||||
Inherits from MutableMapping to implement a custom dictionary-like behavior.
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
"""Initialize an empty chat collection."""
|
||||
self._chats: Dict[str, ChatStore] = {}
|
||||
|
||||
def __getitem__(self, key: str) -> 'ChatStore':
|
||||
"""Get a chat by its ID. Required for dict-like access."""
|
||||
return self._chats[key]
|
||||
|
||||
def __setitem__(self, key: str, value: 'ChatStore') -> None:
|
||||
"""Set a chat by its ID. Required for dict-like access."""
|
||||
if not isinstance(value, ChatStore):
|
||||
raise TypeError("Value must be a ChatStore object")
|
||||
self._chats[key] = value
|
||||
|
||||
def __delitem__(self, key: str) -> None:
|
||||
"""Delete a chat by its ID. Required for dict-like access."""
|
||||
del self._chats[key]
|
||||
|
||||
def __iter__(self):
|
||||
"""Iterate over chat IDs. Required for dict-like access."""
|
||||
return iter(self._chats)
|
||||
|
||||
def __len__(self) -> int:
|
||||
"""Get number of chats. Required for dict-like access."""
|
||||
return len(self._chats)
|
||||
|
||||
def get_chat(self, chat_id: str) -> Optional['ChatStore']:
|
||||
"""
|
||||
Get a chat by its ID.
|
||||
|
||||
Args:
|
||||
chat_id (str): The ID of the chat to retrieve
|
||||
|
||||
Returns:
|
||||
Optional['ChatStore']: The chat if found, None otherwise
|
||||
"""
|
||||
return self._chats.get(chat_id)
|
||||
|
||||
def add_chat(self, chat_id: str, chat: 'ChatStore') -> None:
|
||||
"""
|
||||
Add a new chat to the collection.
|
||||
|
||||
Args:
|
||||
chat_id (str): The ID for the chat
|
||||
chat (ChatStore): The chat to add
|
||||
|
||||
Raises:
|
||||
TypeError: If chat is not a ChatStore object
|
||||
"""
|
||||
if not isinstance(chat, ChatStore):
|
||||
raise TypeError("Chat must be a ChatStore object")
|
||||
self._chats[chat_id] = chat
|
||||
return self._chats[chat_id]
|
||||
|
||||
def remove_chat(self, chat_id: str) -> None:
|
||||
"""
|
||||
Remove a chat from the collection.
|
||||
|
||||
Args:
|
||||
chat_id (str): The ID of the chat to remove
|
||||
"""
|
||||
if chat_id in self._chats:
|
||||
del self._chats[chat_id]
|
||||
|
||||
def items(self):
|
||||
"""Get chat items (id, chat) pairs."""
|
||||
return self._chats.items()
|
||||
|
||||
def values(self):
|
||||
"""Get all chats."""
|
||||
return self._chats.values()
|
||||
|
||||
def keys(self):
|
||||
"""Get all chat IDs."""
|
||||
return self._chats.keys()
|
||||
|
||||
def to_dict(self) -> Dict[str, Any]:
|
||||
"""
|
||||
Convert the collection to a dictionary.
|
||||
|
||||
Returns:
|
||||
Dict[str, Any]: Dictionary representation of all chats
|
||||
"""
|
||||
return {chat_id: chat.to_json() for chat_id, chat in self._chats.items()}
|
||||
|
||||
|
||||
class ChatStore:
|
||||
"""
|
||||
Stores chat information and messages.
|
||||
"""
|
||||
def __init__(self, type: str, name: Optional[str] = None, media: Optional[str] = None) -> None:
|
||||
"""
|
||||
Initialize ChatStore object.
|
||||
|
||||
Args:
|
||||
type (str): Device type (IOS or ANDROID)
|
||||
name (Optional[str]): Chat name
|
||||
media (Optional[str]): Path to media folder
|
||||
|
||||
Raises:
|
||||
TypeError: If name is not a string or None
|
||||
"""
|
||||
if name is not None and not isinstance(name, str):
|
||||
raise TypeError("Name must be a string or None")
|
||||
self.name = name
|
||||
self._messages: Dict[str, 'Message'] = {}
|
||||
self.type = type
|
||||
if media is not None:
|
||||
from Whatsapp_Chat_Exporter.utility import Device
|
||||
if self.type == Device.IOS:
|
||||
self.my_avatar = os.path.join(media, "Media/Profile/Photo.jpg")
|
||||
elif self.type == Device.ANDROID:
|
||||
self.my_avatar = None # TODO: Add Android support
|
||||
else:
|
||||
self.my_avatar = None
|
||||
else:
|
||||
self.my_avatar = None
|
||||
self.their_avatar = None
|
||||
self.their_avatar_thumb = None
|
||||
self.status = None
|
||||
self.media_base = ""
|
||||
|
||||
def __len__(self) -> int:
|
||||
"""Get number of chats. Required for dict-like access."""
|
||||
return len(self._messages)
|
||||
|
||||
def add_message(self, id: str, message: 'Message') -> None:
|
||||
"""Add a message to the chat store."""
|
||||
if not isinstance(message, Message):
|
||||
raise TypeError("message must be a Message object")
|
||||
self._messages[id] = message
|
||||
|
||||
def get_message(self, id: str) -> 'Message':
|
||||
"""Get a message from the chat store."""
|
||||
return self._messages.get(id)
|
||||
|
||||
def delete_message(self, id: str) -> None:
|
||||
"""Delete a message from the chat store."""
|
||||
if id in self._messages:
|
||||
del self._messages[id]
|
||||
|
||||
def to_json(self) -> Dict[str, Any]:
|
||||
"""Convert chat store to JSON-serializable dict."""
|
||||
return {
|
||||
'name': self.name,
|
||||
'type': self.type,
|
||||
'my_avatar': self.my_avatar,
|
||||
'their_avatar': self.their_avatar,
|
||||
'their_avatar_thumb': self.their_avatar_thumb,
|
||||
'status': self.status,
|
||||
'messages': {id: msg.to_json() for id, msg in self._messages.items()}
|
||||
}
|
||||
|
||||
def get_last_message(self) -> 'Message':
|
||||
"""Get the most recent message in the chat."""
|
||||
return tuple(self._messages.values())[-1]
|
||||
|
||||
def items(self):
|
||||
"""Get message items pairs."""
|
||||
return self._messages.items()
|
||||
|
||||
def values(self):
|
||||
"""Get all messages in the chat."""
|
||||
return self._messages.values()
|
||||
|
||||
def keys(self):
|
||||
"""Get all message keys in the chat."""
|
||||
return self._messages.keys()
|
||||
|
||||
|
||||
class Message:
|
||||
"""
|
||||
Represents a single message in a chat.
|
||||
"""
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
from_me: Union[bool, int],
|
||||
timestamp: int,
|
||||
time: Union[int, float, str],
|
||||
key_id: int,
|
||||
received_timestamp: int,
|
||||
read_timestamp: int,
|
||||
timezone_offset: int = 0,
|
||||
message_type: Optional[int] = None
|
||||
) -> None:
|
||||
"""
|
||||
Initialize Message object.
|
||||
|
||||
Args:
|
||||
from_me (Union[bool, int]): Whether message was sent by the user
|
||||
timestamp (int): Message timestamp
|
||||
time (Union[int, float, str]): Message time
|
||||
key_id (int): Message unique identifier
|
||||
received_timestamp (int): When message was received
|
||||
read_timestamp (int): When message was read
|
||||
timezone_offset (int, optional): Hours offset from UTC. Defaults to 0
|
||||
message_type (Optional[int], optional): Type of message. Defaults to None
|
||||
|
||||
Raises:
|
||||
TypeError: If time is not a string or number
|
||||
"""
|
||||
self.from_me = bool(from_me)
|
||||
self.timestamp = timestamp / 1000 if timestamp > 9999999999 else timestamp
|
||||
timing = Timing(timezone_offset)
|
||||
|
||||
if isinstance(time, (int, float)):
|
||||
self.time = timing.format_timestamp(self.timestamp, "%H:%M")
|
||||
elif isinstance(time, str):
|
||||
self.time = time
|
||||
else:
|
||||
raise TypeError("Time must be a string or number")
|
||||
|
||||
self.media = False
|
||||
self.key_id = key_id
|
||||
self.meta = False
|
||||
self.data = None
|
||||
self.sender = None
|
||||
self.safe = False
|
||||
self.mime = None
|
||||
self.message_type = message_type,
|
||||
self.received_timestamp = timing.format_timestamp(received_timestamp, "%Y/%m/%d %H:%M")
|
||||
self.read_timestamp = timing.format_timestamp(read_timestamp, "%Y/%m/%d %H:%M")
|
||||
|
||||
# Extra attributes
|
||||
self.reply = None
|
||||
self.quoted_data = None
|
||||
self.caption = None
|
||||
self.thumb = None # Android specific
|
||||
self.sticker = False
|
||||
|
||||
def to_json(self) -> Dict[str, Any]:
|
||||
"""Convert message to JSON-serializable dict."""
|
||||
return {
|
||||
'from_me': self.from_me,
|
||||
'timestamp': self.timestamp,
|
||||
'time': self.time,
|
||||
'media': self.media,
|
||||
'key_id': self.key_id,
|
||||
'meta': self.meta,
|
||||
'data': self.data,
|
||||
'sender': self.sender,
|
||||
'safe': self.safe,
|
||||
'mime': self.mime,
|
||||
'reply': self.reply,
|
||||
'quoted_data': self.quoted_data,
|
||||
'caption': self.caption,
|
||||
'thumb': self.thumb,
|
||||
'sticker': self.sticker
|
||||
}
|
||||
@@ -1,181 +0,0 @@
|
||||
#!/usr/bin/python3
|
||||
|
||||
import os
|
||||
from datetime import datetime
|
||||
from mimetypes import MimeTypes
|
||||
from Whatsapp_Chat_Exporter.data_model import ChatStore, Message
|
||||
from Whatsapp_Chat_Exporter.utility import Device
|
||||
|
||||
|
||||
def messages(path, data, assume_first_as_me=False):
|
||||
"""
|
||||
Extracts messages from an exported WhatsApp chat file.
|
||||
|
||||
Args:
|
||||
path: Path to the exported chat file
|
||||
data: Data container object to store the parsed chat
|
||||
assume_first_as_me: If True, assumes the first message is sent from the user without asking
|
||||
|
||||
Returns:
|
||||
Updated data container with extracted messages
|
||||
"""
|
||||
# Create a new chat in the data container
|
||||
chat = data.add_chat("ExportedChat", ChatStore(Device.EXPORTED))
|
||||
you = "" # Will store the username of the current user
|
||||
user_identification_done = False # Flag to track if user identification has been done
|
||||
|
||||
# First pass: count total lines for progress reporting
|
||||
with open(path, "r", encoding="utf8") as file:
|
||||
total_row_number = sum(1 for _ in file)
|
||||
|
||||
# Second pass: process the messages
|
||||
with open(path, "r", encoding="utf8") as file:
|
||||
for index, line in enumerate(file):
|
||||
you, user_identification_done = process_line(
|
||||
line, index, chat, path, you,
|
||||
assume_first_as_me, user_identification_done
|
||||
)
|
||||
|
||||
# Show progress
|
||||
if index % 1000 == 0:
|
||||
print(f"Processing messages & media...({index}/{total_row_number})", end="\r")
|
||||
|
||||
print(f"Processing messages & media...({total_row_number}/{total_row_number})")
|
||||
return data
|
||||
|
||||
|
||||
def process_line(line, index, chat, file_path, you, assume_first_as_me, user_identification_done):
|
||||
"""
|
||||
Process a single line from the chat file
|
||||
|
||||
Returns:
|
||||
Tuple of (updated_you_value, updated_user_identification_done_flag)
|
||||
"""
|
||||
parts = line.split(" - ", 1)
|
||||
|
||||
# Check if this is a new message (has timestamp format)
|
||||
if len(parts) > 1:
|
||||
time = parts[0]
|
||||
you, user_identification_done = process_new_message(
|
||||
time, parts[1], index, chat, you, file_path,
|
||||
assume_first_as_me, user_identification_done
|
||||
)
|
||||
else:
|
||||
# This is a continuation of the previous message
|
||||
process_message_continuation(line, index, chat)
|
||||
|
||||
return you, user_identification_done
|
||||
|
||||
|
||||
def process_new_message(time, content, index, chat, you, file_path,
|
||||
assume_first_as_me, user_identification_done):
|
||||
"""
|
||||
Process a line that contains a new message
|
||||
|
||||
Returns:
|
||||
Tuple of (updated_you_value, updated_user_identification_done_flag)
|
||||
"""
|
||||
# Create a new message
|
||||
msg = Message(
|
||||
from_me=False, # Will be updated later if needed
|
||||
timestamp=datetime.strptime(time, "%d/%m/%Y, %H:%M").timestamp(),
|
||||
time=time.split(", ")[1].strip(),
|
||||
key_id=index,
|
||||
received_timestamp=None,
|
||||
read_timestamp=None
|
||||
)
|
||||
|
||||
# Check if this is a system message (no name:message format)
|
||||
if ":" not in content:
|
||||
msg.data = content
|
||||
msg.meta = True
|
||||
else:
|
||||
# Process user message
|
||||
name, message = content.strip().split(":", 1)
|
||||
|
||||
# Handle user identification
|
||||
if you == "":
|
||||
if chat.name is None:
|
||||
# First sender identification
|
||||
if not user_identification_done:
|
||||
if not assume_first_as_me:
|
||||
# Ask only once if this is the user
|
||||
you = prompt_for_user_identification(name)
|
||||
user_identification_done = True
|
||||
else:
|
||||
you = name
|
||||
user_identification_done = True
|
||||
else:
|
||||
# If we know the chat name, anyone else must be "you"
|
||||
if name != chat.name:
|
||||
you = name
|
||||
|
||||
# Set the chat name if needed
|
||||
if chat.name is None and name != you:
|
||||
chat.name = name
|
||||
|
||||
# Determine if this message is from the current user
|
||||
msg.from_me = (name == you)
|
||||
|
||||
# Process message content
|
||||
process_message_content(msg, message, file_path)
|
||||
|
||||
chat.add_message(index, msg)
|
||||
return you, user_identification_done
|
||||
|
||||
|
||||
def process_message_content(msg, message, file_path):
|
||||
"""Process and set the content of a message based on its type"""
|
||||
if "<Media omitted>" in message:
|
||||
msg.data = "The media is omitted in the chat"
|
||||
msg.mime = "media"
|
||||
msg.meta = True
|
||||
elif "(file attached)" in message:
|
||||
process_attached_file(msg, message, file_path)
|
||||
else:
|
||||
msg.data = message.replace("\r\n", "<br>").replace("\n", "<br>")
|
||||
|
||||
|
||||
def process_attached_file(msg, message, file_path):
|
||||
"""Process an attached file in a message"""
|
||||
mime = MimeTypes()
|
||||
msg.media = True
|
||||
|
||||
# Extract file path and check if it exists
|
||||
file_name = message.split("(file attached)")[0].strip()
|
||||
attached_file_path = os.path.join(os.path.dirname(file_path), file_name)
|
||||
|
||||
if os.path.isfile(attached_file_path):
|
||||
msg.data = attached_file_path
|
||||
guess = mime.guess_type(attached_file_path)[0]
|
||||
msg.mime = guess if guess is not None else "application/octet-stream"
|
||||
else:
|
||||
msg.data = "The media is missing"
|
||||
msg.mime = "media"
|
||||
msg.meta = True
|
||||
|
||||
|
||||
def process_message_continuation(line, index, chat):
|
||||
"""Process a line that continues a previous message"""
|
||||
# Find the previous message
|
||||
lookback = index - 1
|
||||
while lookback not in chat.keys():
|
||||
lookback -= 1
|
||||
|
||||
msg = chat.get_message(lookback)
|
||||
|
||||
# Add the continuation line to the message
|
||||
if msg.media:
|
||||
msg.caption = line.strip()
|
||||
else:
|
||||
msg.data += "<br>" + line.strip()
|
||||
|
||||
|
||||
def prompt_for_user_identification(name):
|
||||
"""Ask the user if the given name is their username"""
|
||||
while True:
|
||||
ans = input(f"Is '{name}' you? (Y/N)").lower()
|
||||
if ans == "y":
|
||||
return name
|
||||
elif ans == "n":
|
||||
return ""
|
||||
@@ -1,602 +0,0 @@
|
||||
#!/usr/bin/python3
|
||||
|
||||
import os
|
||||
import shutil
|
||||
from glob import glob
|
||||
from pathlib import Path
|
||||
from mimetypes import MimeTypes
|
||||
from markupsafe import escape as htmle
|
||||
from Whatsapp_Chat_Exporter.data_model import ChatStore, Message
|
||||
from Whatsapp_Chat_Exporter.utility import APPLE_TIME, CURRENT_TZ_OFFSET, get_chat_condition
|
||||
from Whatsapp_Chat_Exporter.utility import bytes_to_readable, convert_time_unit, slugify, Device
|
||||
|
||||
|
||||
def contacts(db, data):
|
||||
"""Process WhatsApp contacts with status information."""
|
||||
c = db.cursor()
|
||||
c.execute("""SELECT count() FROM ZWAADDRESSBOOKCONTACT WHERE ZABOUTTEXT IS NOT NULL""")
|
||||
total_row_number = c.fetchone()[0]
|
||||
print(f"Pre-processing contacts...({total_row_number})")
|
||||
|
||||
c.execute("""SELECT ZWHATSAPPID, ZABOUTTEXT FROM ZWAADDRESSBOOKCONTACT WHERE ZABOUTTEXT IS NOT NULL""")
|
||||
content = c.fetchone()
|
||||
while content is not None:
|
||||
zwhatsapp_id = content["ZWHATSAPPID"]
|
||||
if not zwhatsapp_id.endswith("@s.whatsapp.net"):
|
||||
zwhatsapp_id += "@s.whatsapp.net"
|
||||
|
||||
current_chat = ChatStore(Device.IOS)
|
||||
current_chat.status = content["ZABOUTTEXT"]
|
||||
data.add_chat(zwhatsapp_id, current_chat)
|
||||
content = c.fetchone()
|
||||
|
||||
|
||||
def process_contact_avatars(current_chat, media_folder, contact_id):
|
||||
"""Process and assign avatar images for a contact."""
|
||||
path = f'{media_folder}/Media/Profile/{contact_id.split("@")[0]}'
|
||||
avatars = glob(f"{path}*")
|
||||
|
||||
if 0 < len(avatars) <= 1:
|
||||
current_chat.their_avatar = avatars[0]
|
||||
else:
|
||||
for avatar in avatars:
|
||||
if avatar.endswith(".thumb") and current_chat.their_avatar_thumb is None:
|
||||
current_chat.their_avatar_thumb = avatar
|
||||
elif avatar.endswith(".jpg") and current_chat.their_avatar is None:
|
||||
current_chat.their_avatar = avatar
|
||||
|
||||
|
||||
def get_contact_name(content):
|
||||
"""Determine the appropriate contact name based on push name and partner name."""
|
||||
is_phone = content["ZPARTNERNAME"].replace("+", "").replace(" ", "").isdigit()
|
||||
if content["ZPUSHNAME"] is None or (content["ZPUSHNAME"] and not is_phone):
|
||||
return content["ZPARTNERNAME"]
|
||||
else:
|
||||
return content["ZPUSHNAME"]
|
||||
|
||||
|
||||
def messages(db, data, media_folder, timezone_offset, filter_date, filter_chat, filter_empty):
|
||||
"""Process WhatsApp messages and contacts from the database."""
|
||||
c = db.cursor()
|
||||
cursor2 = db.cursor()
|
||||
|
||||
# Build the chat filter conditions
|
||||
chat_filter_include = get_chat_condition(filter_chat[0], True, ["ZWACHATSESSION.ZCONTACTJID", "ZMEMBERJID"], "ZGROUPINFO", "ios")
|
||||
chat_filter_exclude = get_chat_condition(filter_chat[1], False, ["ZWACHATSESSION.ZCONTACTJID", "ZMEMBERJID"], "ZGROUPINFO", "ios")
|
||||
date_filter = f'AND ZMESSAGEDATE {filter_date}' if filter_date is not None else ''
|
||||
|
||||
# Process contacts first
|
||||
contact_query = f"""
|
||||
SELECT count()
|
||||
FROM (SELECT DISTINCT ZCONTACTJID,
|
||||
ZPARTNERNAME,
|
||||
ZWAPROFILEPUSHNAME.ZPUSHNAME
|
||||
FROM ZWACHATSESSION
|
||||
INNER JOIN ZWAMESSAGE
|
||||
ON ZWAMESSAGE.ZCHATSESSION = ZWACHATSESSION.Z_PK
|
||||
LEFT JOIN ZWAPROFILEPUSHNAME
|
||||
ON ZWACHATSESSION.ZCONTACTJID = ZWAPROFILEPUSHNAME.ZJID
|
||||
LEFT JOIN ZWAGROUPMEMBER
|
||||
ON ZWAMESSAGE.ZGROUPMEMBER = ZWAGROUPMEMBER.Z_PK
|
||||
WHERE 1=1
|
||||
{chat_filter_include}
|
||||
{chat_filter_exclude}
|
||||
GROUP BY ZCONTACTJID);
|
||||
"""
|
||||
c.execute(contact_query)
|
||||
total_row_number = c.fetchone()[0]
|
||||
print(f"Processing contacts...({total_row_number})")
|
||||
|
||||
# Get distinct contacts
|
||||
contacts_query = f"""
|
||||
SELECT DISTINCT ZCONTACTJID,
|
||||
ZPARTNERNAME,
|
||||
ZWAPROFILEPUSHNAME.ZPUSHNAME
|
||||
FROM ZWACHATSESSION
|
||||
INNER JOIN ZWAMESSAGE
|
||||
ON ZWAMESSAGE.ZCHATSESSION = ZWACHATSESSION.Z_PK
|
||||
LEFT JOIN ZWAPROFILEPUSHNAME
|
||||
ON ZWACHATSESSION.ZCONTACTJID = ZWAPROFILEPUSHNAME.ZJID
|
||||
LEFT JOIN ZWAGROUPMEMBER
|
||||
ON ZWAMESSAGE.ZGROUPMEMBER = ZWAGROUPMEMBER.Z_PK
|
||||
WHERE 1=1
|
||||
{chat_filter_include}
|
||||
{chat_filter_exclude}
|
||||
GROUP BY ZCONTACTJID;
|
||||
"""
|
||||
c.execute(contacts_query)
|
||||
|
||||
# Process each contact
|
||||
content = c.fetchone()
|
||||
while content is not None:
|
||||
contact_name = get_contact_name(content)
|
||||
contact_id = content["ZCONTACTJID"]
|
||||
|
||||
# Add or update chat
|
||||
if contact_id not in data:
|
||||
current_chat = data.add_chat(contact_id, ChatStore(Device.IOS, contact_name, media_folder))
|
||||
else:
|
||||
current_chat = data.get_chat(contact_id)
|
||||
current_chat.name = contact_name
|
||||
current_chat.my_avatar = os.path.join(media_folder, "Media/Profile/Photo.jpg")
|
||||
|
||||
# Process avatar images
|
||||
process_contact_avatars(current_chat, media_folder, contact_id)
|
||||
content = c.fetchone()
|
||||
|
||||
# Get message count
|
||||
message_count_query = f"""
|
||||
SELECT count()
|
||||
FROM ZWAMESSAGE
|
||||
INNER JOIN ZWACHATSESSION
|
||||
ON ZWAMESSAGE.ZCHATSESSION = ZWACHATSESSION.Z_PK
|
||||
LEFT JOIN ZWAGROUPMEMBER
|
||||
ON ZWAMESSAGE.ZGROUPMEMBER = ZWAGROUPMEMBER.Z_PK
|
||||
WHERE 1=1
|
||||
{date_filter}
|
||||
{chat_filter_include}
|
||||
{chat_filter_exclude}
|
||||
"""
|
||||
c.execute(message_count_query)
|
||||
total_row_number = c.fetchone()[0]
|
||||
print(f"Processing messages...(0/{total_row_number})", end="\r")
|
||||
|
||||
# Fetch messages
|
||||
messages_query = f"""
|
||||
SELECT ZCONTACTJID,
|
||||
ZWAMESSAGE.Z_PK,
|
||||
ZISFROMME,
|
||||
ZMESSAGEDATE,
|
||||
ZTEXT,
|
||||
ZMESSAGETYPE,
|
||||
ZWAGROUPMEMBER.ZMEMBERJID,
|
||||
ZMETADATA,
|
||||
ZSTANZAID,
|
||||
ZGROUPINFO,
|
||||
ZSENTDATE
|
||||
FROM ZWAMESSAGE
|
||||
LEFT JOIN ZWAGROUPMEMBER
|
||||
ON ZWAMESSAGE.ZGROUPMEMBER = ZWAGROUPMEMBER.Z_PK
|
||||
LEFT JOIN ZWAMEDIAITEM
|
||||
ON ZWAMESSAGE.Z_PK = ZWAMEDIAITEM.ZMESSAGE
|
||||
INNER JOIN ZWACHATSESSION
|
||||
ON ZWAMESSAGE.ZCHATSESSION = ZWACHATSESSION.Z_PK
|
||||
WHERE 1=1
|
||||
{date_filter}
|
||||
{chat_filter_include}
|
||||
{chat_filter_exclude}
|
||||
ORDER BY ZMESSAGEDATE ASC;
|
||||
"""
|
||||
c.execute(messages_query)
|
||||
|
||||
# Process each message
|
||||
i = 0
|
||||
content = c.fetchone()
|
||||
while content is not None:
|
||||
contact_id = content["ZCONTACTJID"]
|
||||
message_pk = content["Z_PK"]
|
||||
is_group_message = content["ZGROUPINFO"] is not None
|
||||
|
||||
# Ensure chat exists
|
||||
if contact_id not in data:
|
||||
current_chat = data.add_chat(contact_id, ChatStore(Device.IOS))
|
||||
process_contact_avatars(current_chat, media_folder, contact_id)
|
||||
else:
|
||||
current_chat = data.get_chat(contact_id)
|
||||
|
||||
# Create message object
|
||||
ts = APPLE_TIME + content["ZMESSAGEDATE"]
|
||||
message = Message(
|
||||
from_me=content["ZISFROMME"],
|
||||
timestamp=ts,
|
||||
time=ts,
|
||||
key_id=content["ZSTANZAID"][:17],
|
||||
timezone_offset=timezone_offset if timezone_offset else CURRENT_TZ_OFFSET,
|
||||
message_type=content["ZMESSAGETYPE"],
|
||||
received_timestamp=APPLE_TIME + content["ZSENTDATE"] if content["ZSENTDATE"] else None,
|
||||
read_timestamp=None # TODO: Add timestamp
|
||||
)
|
||||
|
||||
# Process message data
|
||||
invalid = process_message_data(message, content, is_group_message, data, cursor2)
|
||||
|
||||
# Add valid messages to chat
|
||||
if not invalid:
|
||||
current_chat.add_message(message_pk, message)
|
||||
|
||||
# Update progress
|
||||
i += 1
|
||||
if i % 1000 == 0:
|
||||
print(f"Processing messages...({i}/{total_row_number})", end="\r")
|
||||
content = c.fetchone()
|
||||
|
||||
print(f"Processing messages...({total_row_number}/{total_row_number})", end="\r")
|
||||
|
||||
|
||||
def process_message_data(message, content, is_group_message, data, cursor2):
|
||||
"""Process and set message data from content row."""
|
||||
# Handle group sender info
|
||||
if is_group_message and content["ZISFROMME"] == 0:
|
||||
name = None
|
||||
if content["ZMEMBERJID"] is not None:
|
||||
if content["ZMEMBERJID"] in data:
|
||||
name = data.get_chat(content["ZMEMBERJID"]).name
|
||||
if "@" in content["ZMEMBERJID"]:
|
||||
fallback = content["ZMEMBERJID"].split('@')[0]
|
||||
else:
|
||||
fallback = None
|
||||
else:
|
||||
fallback = None
|
||||
message.sender = name or fallback
|
||||
else:
|
||||
message.sender = None
|
||||
|
||||
# Handle metadata messages
|
||||
if content["ZMESSAGETYPE"] == 6:
|
||||
return process_metadata_message(message, content, is_group_message)
|
||||
|
||||
# Handle quoted replies
|
||||
if content["ZMETADATA"] is not None and content["ZMETADATA"].startswith(b"\x2a\x14") and False:
|
||||
quoted = content["ZMETADATA"][2:19]
|
||||
message.reply = quoted.decode()
|
||||
cursor2.execute(f"""SELECT ZTEXT
|
||||
FROM ZWAMESSAGE
|
||||
WHERE ZSTANZAID LIKE '{message.reply}%'""")
|
||||
quoted_content = cursor2.fetchone()
|
||||
if quoted_content and "ZTEXT" in quoted_content:
|
||||
message.quoted_data = quoted_content["ZTEXT"]
|
||||
else:
|
||||
message.quoted_data = None
|
||||
|
||||
# Handle stickers
|
||||
if content["ZMESSAGETYPE"] == 15:
|
||||
message.sticker = True
|
||||
|
||||
# Process message text
|
||||
process_message_text(message, content)
|
||||
|
||||
return False # Message is valid
|
||||
|
||||
|
||||
def process_metadata_message(message, content, is_group_message):
|
||||
"""Process metadata messages (action_type 6)."""
|
||||
if is_group_message:
|
||||
# Group
|
||||
if content["ZTEXT"] is not None:
|
||||
# Changed name
|
||||
try:
|
||||
int(content["ZTEXT"])
|
||||
except ValueError:
|
||||
msg = f"The group name changed to {content['ZTEXT']}"
|
||||
message.data = msg
|
||||
message.meta = True
|
||||
return False # Valid message
|
||||
else:
|
||||
return True # Invalid message
|
||||
else:
|
||||
message.data = None
|
||||
return False
|
||||
else:
|
||||
message.data = None
|
||||
return False
|
||||
|
||||
|
||||
def process_message_text(message, content):
|
||||
"""Process and format message text content."""
|
||||
if content["ZISFROMME"] == 1:
|
||||
if content["ZMESSAGETYPE"] == 14:
|
||||
msg = "Message deleted"
|
||||
message.meta = True
|
||||
else:
|
||||
msg = content["ZTEXT"]
|
||||
if msg is not None:
|
||||
msg = msg.replace("\r\n", "<br>").replace("\n", "<br>")
|
||||
else:
|
||||
if content["ZMESSAGETYPE"] == 14:
|
||||
msg = "Message deleted"
|
||||
message.meta = True
|
||||
else:
|
||||
msg = content["ZTEXT"]
|
||||
if msg is not None:
|
||||
msg = msg.replace("\r\n", "<br>").replace("\n", "<br>")
|
||||
|
||||
message.data = msg
|
||||
|
||||
|
||||
def media(db, data, media_folder, filter_date, filter_chat, filter_empty, separate_media=False):
|
||||
"""Process media files from WhatsApp messages."""
|
||||
c = db.cursor()
|
||||
|
||||
# Build filter conditions
|
||||
chat_filter_include = get_chat_condition(filter_chat[0], True, ["ZWACHATSESSION.ZCONTACTJID","ZMEMBERJID"], "ZGROUPINFO", "ios")
|
||||
chat_filter_exclude = get_chat_condition(filter_chat[1], False, ["ZWACHATSESSION.ZCONTACTJID", "ZMEMBERJID"], "ZGROUPINFO", "ios")
|
||||
date_filter = f'AND ZMESSAGEDATE {filter_date}' if filter_date is not None else ''
|
||||
|
||||
# Get media count
|
||||
media_count_query = f"""
|
||||
SELECT count()
|
||||
FROM ZWAMEDIAITEM
|
||||
INNER JOIN ZWAMESSAGE
|
||||
ON ZWAMEDIAITEM.ZMESSAGE = ZWAMESSAGE.Z_PK
|
||||
INNER JOIN ZWACHATSESSION
|
||||
ON ZWAMESSAGE.ZCHATSESSION = ZWACHATSESSION.Z_PK
|
||||
LEFT JOIN ZWAGROUPMEMBER
|
||||
ON ZWAMESSAGE.ZGROUPMEMBER = ZWAGROUPMEMBER.Z_PK
|
||||
WHERE 1=1
|
||||
{date_filter}
|
||||
{chat_filter_include}
|
||||
{chat_filter_exclude}
|
||||
"""
|
||||
c.execute(media_count_query)
|
||||
total_row_number = c.fetchone()[0]
|
||||
print(f"\nProcessing media...(0/{total_row_number})", end="\r")
|
||||
|
||||
# Fetch media items
|
||||
media_query = f"""
|
||||
SELECT ZCONTACTJID,
|
||||
ZMESSAGE,
|
||||
ZMEDIALOCALPATH,
|
||||
ZMEDIAURL,
|
||||
ZVCARDSTRING,
|
||||
ZMEDIAKEY,
|
||||
ZTITLE
|
||||
FROM ZWAMEDIAITEM
|
||||
INNER JOIN ZWAMESSAGE
|
||||
ON ZWAMEDIAITEM.ZMESSAGE = ZWAMESSAGE.Z_PK
|
||||
INNER JOIN ZWACHATSESSION
|
||||
ON ZWAMESSAGE.ZCHATSESSION = ZWACHATSESSION.Z_PK
|
||||
LEFT JOIN ZWAGROUPMEMBER
|
||||
ON ZWAMESSAGE.ZGROUPMEMBER = ZWAGROUPMEMBER.Z_PK
|
||||
WHERE ZMEDIALOCALPATH IS NOT NULL
|
||||
{date_filter}
|
||||
{chat_filter_include}
|
||||
{chat_filter_exclude}
|
||||
ORDER BY ZCONTACTJID ASC
|
||||
"""
|
||||
c.execute(media_query)
|
||||
|
||||
# Process each media item
|
||||
mime = MimeTypes()
|
||||
i = 0
|
||||
content = c.fetchone()
|
||||
while content is not None:
|
||||
process_media_item(content, data, media_folder, mime, separate_media)
|
||||
|
||||
# Update progress
|
||||
i += 1
|
||||
if i % 100 == 0:
|
||||
print(f"Processing media...({i}/{total_row_number})", end="\r")
|
||||
content = c.fetchone()
|
||||
|
||||
print(f"Processing media...({total_row_number}/{total_row_number})", end="\r")
|
||||
|
||||
|
||||
def process_media_item(content, data, media_folder, mime, separate_media):
|
||||
"""Process a single media item."""
|
||||
file_path = f"{media_folder}/Message/{content['ZMEDIALOCALPATH']}"
|
||||
current_chat = data.get_chat(content["ZCONTACTJID"])
|
||||
message = current_chat.get_message(content["ZMESSAGE"])
|
||||
message.media = True
|
||||
|
||||
if current_chat.media_base == "":
|
||||
current_chat.media_base = media_folder + "/"
|
||||
|
||||
if os.path.isfile(file_path):
|
||||
message.data = '/'.join(file_path.split("/")[1:])
|
||||
|
||||
# Set MIME type
|
||||
if content["ZVCARDSTRING"] is None:
|
||||
guess = mime.guess_type(file_path)[0]
|
||||
message.mime = guess if guess is not None else "application/octet-stream"
|
||||
else:
|
||||
message.mime = content["ZVCARDSTRING"]
|
||||
|
||||
# Handle separate media option
|
||||
if separate_media:
|
||||
chat_display_name = slugify(current_chat.name or message.sender or content["ZCONTACTJID"].split('@')[0], True)
|
||||
current_filename = file_path.split("/")[-1]
|
||||
new_folder = os.path.join(media_folder, "separated", chat_display_name)
|
||||
Path(new_folder).mkdir(parents=True, exist_ok=True)
|
||||
new_path = os.path.join(new_folder, current_filename)
|
||||
shutil.copy2(file_path, new_path)
|
||||
message.data = '/'.join(new_path.split("\\")[1:])
|
||||
else:
|
||||
# Handle missing media
|
||||
message.data = "The media is missing"
|
||||
message.mime = "media"
|
||||
message.meta = True
|
||||
|
||||
# Add caption if available
|
||||
if content["ZTITLE"] is not None:
|
||||
message.caption = content["ZTITLE"]
|
||||
|
||||
|
||||
def vcard(db, data, media_folder, filter_date, filter_chat, filter_empty):
|
||||
"""Process vCard contacts from WhatsApp messages."""
|
||||
c = db.cursor()
|
||||
|
||||
# Build filter conditions
|
||||
chat_filter_include = get_chat_condition(filter_chat[0], True, ["ZCONTACTJID", "ZMEMBERJID"], "ZGROUPINFO", "ios")
|
||||
chat_filter_exclude = get_chat_condition(filter_chat[1], False, ["ZCONTACTJID", "ZMEMBERJID"], "ZGROUPINFO", "ios")
|
||||
date_filter = f'AND ZWAMESSAGE.ZMESSAGEDATE {filter_date}' if filter_date is not None else ''
|
||||
|
||||
# Fetch vCard mentions
|
||||
vcard_query = f"""
|
||||
SELECT DISTINCT ZWAVCARDMENTION.ZMEDIAITEM,
|
||||
ZWAMEDIAITEM.ZMESSAGE,
|
||||
ZCONTACTJID,
|
||||
ZVCARDNAME,
|
||||
ZVCARDSTRING
|
||||
FROM ZWAVCARDMENTION
|
||||
INNER JOIN ZWAMEDIAITEM
|
||||
ON ZWAVCARDMENTION.ZMEDIAITEM = ZWAMEDIAITEM.Z_PK
|
||||
INNER JOIN ZWAMESSAGE
|
||||
ON ZWAMEDIAITEM.ZMESSAGE = ZWAMESSAGE.Z_PK
|
||||
INNER JOIN ZWACHATSESSION
|
||||
ON ZWAMESSAGE.ZCHATSESSION = ZWACHATSESSION.Z_PK
|
||||
LEFT JOIN ZWAGROUPMEMBER
|
||||
ON ZWAMESSAGE.ZGROUPMEMBER = ZWAGROUPMEMBER.Z_PK
|
||||
WHERE 1=1
|
||||
{date_filter}
|
||||
{chat_filter_include}
|
||||
{chat_filter_exclude}
|
||||
"""
|
||||
c.execute(vcard_query)
|
||||
contents = c.fetchall()
|
||||
total_row_number = len(contents)
|
||||
print(f"\nProcessing vCards...(0/{total_row_number})", end="\r")
|
||||
|
||||
# Create vCards directory
|
||||
path = f'{media_folder}/Message/vCards'
|
||||
Path(path).mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Process each vCard
|
||||
for index, content in enumerate(contents):
|
||||
process_vcard_item(content, path, data)
|
||||
print(f"Processing vCards...({index + 1}/{total_row_number})", end="\r")
|
||||
|
||||
|
||||
def process_vcard_item(content, path, data):
|
||||
"""Process a single vCard item."""
|
||||
file_paths = []
|
||||
vcard_names = content["ZVCARDNAME"].split("_$!<Name-Separator>!$_")
|
||||
vcard_strings = content["ZVCARDSTRING"].split("_$!<VCard-Separator>!$_")
|
||||
|
||||
# If this is a list of contacts
|
||||
if len(vcard_names) > len(vcard_strings):
|
||||
vcard_names.pop(0) # Dismiss the first element, which is the group name
|
||||
|
||||
# Save each vCard file
|
||||
for name, vcard_string in zip(vcard_names, vcard_strings):
|
||||
file_name = "".join(x for x in name if x.isalnum())
|
||||
file_name = file_name.encode('utf-8')[:230].decode('utf-8', 'ignore')
|
||||
file_path = os.path.join(path, f"{file_name}.vcf")
|
||||
file_paths.append(file_path)
|
||||
|
||||
if not os.path.isfile(file_path):
|
||||
with open(file_path, "w", encoding="utf-8") as f:
|
||||
f.write(vcard_string)
|
||||
|
||||
# Create vCard summary and update message
|
||||
vcard_summary = "This media include the following vCard file(s):<br>"
|
||||
vcard_summary += " | ".join([f'<a href="{htmle(fp)}">{htmle(name)}</a>' for name, fp in zip(vcard_names, file_paths)])
|
||||
|
||||
message = data.get_chat(content["ZCONTACTJID"]).get_message(content["ZMESSAGE"])
|
||||
message.data = vcard_summary
|
||||
message.mime = "text/x-vcard"
|
||||
message.media = True
|
||||
message.meta = True
|
||||
message.safe = True
|
||||
|
||||
|
||||
def calls(db, data, timezone_offset, filter_chat):
|
||||
"""Process WhatsApp call records."""
|
||||
c = db.cursor()
|
||||
|
||||
# Build filter conditions
|
||||
chat_filter_include = get_chat_condition(filter_chat[0], True, ["ZGROUPCALLCREATORUSERJIDSTRING"], None, "ios")
|
||||
chat_filter_exclude = get_chat_condition(filter_chat[1], False, ["ZGROUPCALLCREATORUSERJIDSTRING"], None, "ios")
|
||||
|
||||
# Get call count
|
||||
call_count_query = f"""
|
||||
SELECT count()
|
||||
FROM ZWACDCALLEVENT
|
||||
WHERE 1=1
|
||||
{chat_filter_include}
|
||||
{chat_filter_exclude}
|
||||
"""
|
||||
c.execute(call_count_query)
|
||||
total_row_number = c.fetchone()[0]
|
||||
if total_row_number == 0:
|
||||
return
|
||||
|
||||
print(f"\nProcessing calls...({total_row_number})", end="\r")
|
||||
|
||||
# Fetch call records
|
||||
calls_query = f"""
|
||||
SELECT ZCALLIDSTRING,
|
||||
ZGROUPCALLCREATORUSERJIDSTRING,
|
||||
ZGROUPJIDSTRING,
|
||||
ZDATE,
|
||||
ZOUTCOME,
|
||||
ZBYTESRECEIVED + ZBYTESSENT AS bytes_transferred,
|
||||
ZDURATION,
|
||||
ZVIDEO,
|
||||
ZMISSED,
|
||||
ZINCOMING
|
||||
FROM ZWACDCALLEVENT
|
||||
INNER JOIN ZWAAGGREGATECALLEVENT
|
||||
ON ZWACDCALLEVENT.Z1CALLEVENTS = ZWAAGGREGATECALLEVENT.Z_PK
|
||||
WHERE 1=1
|
||||
{chat_filter_include}
|
||||
{chat_filter_exclude}
|
||||
"""
|
||||
c.execute(calls_query)
|
||||
|
||||
# Create calls chat
|
||||
chat = ChatStore(Device.ANDROID, "WhatsApp Calls")
|
||||
|
||||
# Process each call
|
||||
content = c.fetchone()
|
||||
while content is not None:
|
||||
process_call_record(content, chat, data, timezone_offset)
|
||||
content = c.fetchone()
|
||||
|
||||
# Add calls chat to data
|
||||
data.add_chat("000000000000000", chat)
|
||||
|
||||
|
||||
def process_call_record(content, chat, data, timezone_offset):
|
||||
"""Process a single call record."""
|
||||
ts = APPLE_TIME + int(content["ZDATE"])
|
||||
call = Message(
|
||||
from_me=content["ZINCOMING"] == 0,
|
||||
timestamp=ts,
|
||||
time=ts,
|
||||
key_id=content["ZCALLIDSTRING"],
|
||||
timezone_offset=timezone_offset if timezone_offset else CURRENT_TZ_OFFSET
|
||||
)
|
||||
|
||||
# Set sender info
|
||||
_jid = content["ZGROUPCALLCREATORUSERJIDSTRING"]
|
||||
name = data.get_chat(_jid).name if _jid in data else None
|
||||
if _jid is not None and "@" in _jid:
|
||||
fallback = _jid.split('@')[0]
|
||||
else:
|
||||
fallback = None
|
||||
call.sender = name or fallback
|
||||
|
||||
# Set call metadata
|
||||
call.meta = True
|
||||
call.data = format_call_data(call, content)
|
||||
|
||||
# Add call to chat
|
||||
chat.add_message(call.key_id, call)
|
||||
|
||||
|
||||
def format_call_data(call, content):
|
||||
"""Format call data message based on call attributes."""
|
||||
# Basic call info
|
||||
call_data = (
|
||||
f"A {'group ' if content['ZGROUPJIDSTRING'] is not None else ''}"
|
||||
f"{'video' if content['ZVIDEO'] == 1 else 'voice'} "
|
||||
f"call {'to' if call.from_me else 'from'} "
|
||||
f"{call.sender} was "
|
||||
)
|
||||
|
||||
# Call outcome
|
||||
if content['ZOUTCOME'] in (1, 4):
|
||||
call_data += "not answered." if call.from_me else "missed."
|
||||
elif content['ZOUTCOME'] == 2:
|
||||
call_data += "failed."
|
||||
elif content['ZOUTCOME'] == 0:
|
||||
call_time = convert_time_unit(int(content['ZDURATION']))
|
||||
call_bytes = bytes_to_readable(content['bytes_transferred'])
|
||||
call_data += (
|
||||
f"initiated and lasted for {call_time} "
|
||||
f"with {call_bytes} data transferred."
|
||||
)
|
||||
else:
|
||||
call_data += "in an unknown state."
|
||||
|
||||
return call_data
|
||||
@@ -1,232 +0,0 @@
|
||||
#!/usr/bin/python3
|
||||
|
||||
import shutil
|
||||
import sqlite3
|
||||
import os
|
||||
import getpass
|
||||
from sys import exit
|
||||
from Whatsapp_Chat_Exporter.utility import WhatsAppIdentifier
|
||||
from Whatsapp_Chat_Exporter.bplist import BPListReader
|
||||
try:
|
||||
from iphone_backup_decrypt import EncryptedBackup, RelativePath
|
||||
except ModuleNotFoundError:
|
||||
support_encrypted = False
|
||||
else:
|
||||
support_encrypted = True
|
||||
|
||||
|
||||
class BackupExtractor:
|
||||
"""
|
||||
A class to handle the extraction of WhatsApp data from iOS backups,
|
||||
including encrypted and unencrypted backups.
|
||||
"""
|
||||
|
||||
def __init__(self, base_dir, identifiers, decrypt_chunk_size):
|
||||
self.base_dir = base_dir
|
||||
self.identifiers = identifiers
|
||||
self.decrypt_chunk_size = decrypt_chunk_size
|
||||
|
||||
def extract(self):
|
||||
"""
|
||||
Extracts WhatsApp data from the backup based on whether it's encrypted or not.
|
||||
"""
|
||||
if self._is_encrypted():
|
||||
self._extract_encrypted_backup()
|
||||
else:
|
||||
self._extract_unencrypted_backup()
|
||||
|
||||
def _is_encrypted(self):
|
||||
"""
|
||||
Checks if the iOS backup is encrypted.
|
||||
|
||||
Returns:
|
||||
bool: True if encrypted, False otherwise.
|
||||
"""
|
||||
with sqlite3.connect(os.path.join(self.base_dir, "Manifest.db")) as db:
|
||||
c = db.cursor()
|
||||
try:
|
||||
c.execute("SELECT count() FROM Files")
|
||||
c.fetchone() # Execute and fetch to trigger potential errors
|
||||
except (sqlite3.OperationalError, sqlite3.DatabaseError):
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
def _extract_encrypted_backup(self):
|
||||
"""
|
||||
Handles the extraction of data from an encrypted iOS backup.
|
||||
"""
|
||||
if not support_encrypted:
|
||||
print("You don't have the dependencies to handle encrypted backup.")
|
||||
print("Read more on how to deal with encrypted backup:")
|
||||
print("https://github.com/KnugiHK/Whatsapp-Chat-Exporter/blob/main/README.md#usage")
|
||||
return
|
||||
|
||||
print("Encryption detected on the backup!")
|
||||
password = getpass.getpass("Enter the password for the backup:")
|
||||
self._decrypt_backup(password)
|
||||
self._extract_decrypted_files()
|
||||
|
||||
def _decrypt_backup(self, password):
|
||||
"""
|
||||
Decrypts the iOS backup using the provided password.
|
||||
|
||||
Args:
|
||||
password (str): The password for the encrypted backup.
|
||||
"""
|
||||
print("Trying to decrypt the iOS backup...", end="")
|
||||
self.backup = EncryptedBackup(
|
||||
backup_directory=self.base_dir,
|
||||
passphrase=password,
|
||||
cleanup=False,
|
||||
check_same_thread=False,
|
||||
decrypt_chunk_size=self.decrypt_chunk_size,
|
||||
)
|
||||
print("Done\nDecrypting WhatsApp database...", end="")
|
||||
try:
|
||||
self.backup.extract_file(
|
||||
relative_path=RelativePath.WHATSAPP_MESSAGES,
|
||||
domain_like=self.identifiers.DOMAIN,
|
||||
output_filename=self.identifiers.MESSAGE,
|
||||
)
|
||||
self.backup.extract_file(
|
||||
relative_path=RelativePath.WHATSAPP_CONTACTS,
|
||||
domain_like=self.identifiers.DOMAIN,
|
||||
output_filename=self.identifiers.CONTACT,
|
||||
)
|
||||
self.backup.extract_file(
|
||||
relative_path=RelativePath.WHATSAPP_CALLS,
|
||||
domain_like=self.identifiers.DOMAIN,
|
||||
output_filename=self.identifiers.CALL,
|
||||
)
|
||||
except ValueError:
|
||||
print("Failed to decrypt backup: incorrect password?")
|
||||
exit(7)
|
||||
except FileNotFoundError:
|
||||
print(
|
||||
"Essential WhatsApp files are missing from the iOS backup. "
|
||||
"Perhapse you enabled end-to-end encryption for the backup? "
|
||||
"See https://wts.knugi.dev/docs.html?dest=iose2e"
|
||||
)
|
||||
exit(6)
|
||||
else:
|
||||
print("Done")
|
||||
|
||||
def _extract_decrypted_files(self):
|
||||
"""Extract all WhatsApp files after decryption"""
|
||||
def extract_progress_handler(file_id, domain, relative_path, n, total_files):
|
||||
if n % 100 == 0:
|
||||
print(f"Decrypting and extracting files...({n}/{total_files})", end="\r")
|
||||
return True
|
||||
|
||||
self.backup.extract_files(
|
||||
domain_like=self.identifiers.DOMAIN,
|
||||
output_folder=self.identifiers.DOMAIN,
|
||||
preserve_folders=True,
|
||||
filter_callback=extract_progress_handler
|
||||
)
|
||||
print(f"All required files are decrypted and extracted. ", end="\n")
|
||||
|
||||
def _extract_unencrypted_backup(self):
|
||||
"""
|
||||
Handles the extraction of data from an unencrypted iOS backup.
|
||||
"""
|
||||
self._copy_whatsapp_databases()
|
||||
self._extract_media_files()
|
||||
|
||||
def _copy_whatsapp_databases(self):
|
||||
"""
|
||||
Copies the WhatsApp message, contact, and call databases to the working directory.
|
||||
"""
|
||||
wts_db_path = os.path.join(self.base_dir, self.identifiers.MESSAGE[:2], self.identifiers.MESSAGE)
|
||||
contact_db_path = os.path.join(self.base_dir, self.identifiers.CONTACT[:2], self.identifiers.CONTACT)
|
||||
call_db_path = os.path.join(self.base_dir, self.identifiers.CALL[:2], self.identifiers.CALL)
|
||||
|
||||
if not os.path.isfile(wts_db_path):
|
||||
if self.identifiers is WhatsAppIdentifier:
|
||||
print("WhatsApp database not found.")
|
||||
else:
|
||||
print("WhatsApp Business database not found.")
|
||||
print(
|
||||
"Essential WhatsApp files are missing from the iOS backup. "
|
||||
"Perhapse you enabled end-to-end encryption for the backup? "
|
||||
"See https://wts.knugi.dev/docs.html?dest=iose2e"
|
||||
)
|
||||
exit(1)
|
||||
else:
|
||||
shutil.copyfile(wts_db_path, self.identifiers.MESSAGE)
|
||||
|
||||
if not os.path.isfile(contact_db_path):
|
||||
print("Contact database not found. Skipping...")
|
||||
else:
|
||||
shutil.copyfile(contact_db_path, self.identifiers.CONTACT)
|
||||
|
||||
if not os.path.isfile(call_db_path):
|
||||
print("Call database not found. Skipping...")
|
||||
else:
|
||||
shutil.copyfile(call_db_path, self.identifiers.CALL)
|
||||
|
||||
def _extract_media_files(self):
|
||||
"""
|
||||
Extracts media files from the unencrypted backup.
|
||||
"""
|
||||
_wts_id = self.identifiers.DOMAIN
|
||||
with sqlite3.connect(os.path.join(self.base_dir, "Manifest.db")) as manifest:
|
||||
manifest.row_factory = sqlite3.Row
|
||||
c = manifest.cursor()
|
||||
c.execute(f"SELECT count() FROM Files WHERE domain = '{_wts_id}'")
|
||||
total_row_number = c.fetchone()[0]
|
||||
print(f"Extracting WhatsApp files...(0/{total_row_number})", end="\r")
|
||||
c.execute(
|
||||
f"""
|
||||
SELECT fileID, relativePath, flags, file AS metadata,
|
||||
ROW_NUMBER() OVER(ORDER BY relativePath) AS _index
|
||||
FROM Files
|
||||
WHERE domain = '{_wts_id}'
|
||||
ORDER BY relativePath
|
||||
"""
|
||||
)
|
||||
if not os.path.isdir(_wts_id):
|
||||
os.mkdir(_wts_id)
|
||||
|
||||
row = c.fetchone()
|
||||
while row is not None:
|
||||
if not row["relativePath"]: # Skip empty relative paths
|
||||
row = c.fetchone()
|
||||
continue
|
||||
|
||||
destination = os.path.join(_wts_id, row["relativePath"])
|
||||
hashes = row["fileID"]
|
||||
folder = hashes[:2]
|
||||
flags = row["flags"]
|
||||
|
||||
if flags == 2: # Directory
|
||||
try:
|
||||
os.mkdir(destination)
|
||||
except FileExistsError:
|
||||
pass
|
||||
elif flags == 1: # File
|
||||
shutil.copyfile(os.path.join(self.base_dir, folder, hashes), destination)
|
||||
metadata = BPListReader(row["metadata"]).parse()
|
||||
creation = metadata["$objects"][1]["Birth"]
|
||||
modification = metadata["$objects"][1]["LastModified"]
|
||||
os.utime(destination, (modification, modification))
|
||||
|
||||
if row["_index"] % 100 == 0:
|
||||
print(f"Extracting WhatsApp files...({row['_index']}/{total_row_number})", end="\r")
|
||||
row = c.fetchone()
|
||||
print(f"Extracting WhatsApp files...({total_row_number}/{total_row_number})", end="\n")
|
||||
|
||||
|
||||
def extract_media(base_dir, identifiers, decrypt_chunk_size):
|
||||
"""
|
||||
Extracts WhatsApp data (media, messages, contacts, calls) from an iOS backup.
|
||||
|
||||
Args:
|
||||
base_dir (str): The path to the iOS backup directory.
|
||||
identifiers (WhatsAppIdentifier): An object containing WhatsApp file identifiers.
|
||||
decrypt_chunk_size (int): The chunk size for decryption.
|
||||
"""
|
||||
extractor = BackupExtractor(base_dir, identifiers, decrypt_chunk_size)
|
||||
extractor.extract()
|
||||
|
||||
@@ -1,566 +0,0 @@
|
||||
import sqlite3
|
||||
import jinja2
|
||||
import json
|
||||
import os
|
||||
import unicodedata
|
||||
import re
|
||||
import math
|
||||
from bleach import clean as sanitize
|
||||
from markupsafe import Markup
|
||||
from datetime import datetime, timedelta
|
||||
from enum import IntEnum
|
||||
from Whatsapp_Chat_Exporter.data_model import ChatStore
|
||||
from typing import Dict, List, Optional, Tuple
|
||||
try:
|
||||
from enum import StrEnum, IntEnum
|
||||
except ImportError:
|
||||
# < Python 3.11
|
||||
# This should be removed when the support for Python 3.10 ends.
|
||||
from enum import Enum
|
||||
class StrEnum(str, Enum):
|
||||
pass
|
||||
|
||||
class IntEnum(int, Enum):
|
||||
pass
|
||||
|
||||
MAX_SIZE = 4 * 1024 * 1024 # Default 4MB
|
||||
ROW_SIZE = 0x3D0
|
||||
CURRENT_TZ_OFFSET = datetime.now().astimezone().utcoffset().seconds / 3600
|
||||
|
||||
|
||||
def convert_time_unit(time_second: int) -> str:
|
||||
"""Converts a time duration in seconds to a human-readable string.
|
||||
|
||||
Args:
|
||||
time_second: The time duration in seconds.
|
||||
|
||||
Returns:
|
||||
str: A human-readable string representing the time duration.
|
||||
"""
|
||||
time = str(timedelta(seconds=time_second))
|
||||
if "day" not in time:
|
||||
if time_second < 1:
|
||||
time = "less than a second"
|
||||
elif time_second == 1:
|
||||
time = "a second"
|
||||
elif time_second < 60:
|
||||
time = time[5:][1 if time_second < 10 else 0:] + " seconds"
|
||||
elif time_second == 60:
|
||||
time = "a minute"
|
||||
elif time_second < 3600:
|
||||
time = time[2:] + " minutes"
|
||||
elif time_second == 3600:
|
||||
time = "an hour"
|
||||
else:
|
||||
time += " hour"
|
||||
return time
|
||||
|
||||
|
||||
def bytes_to_readable(size_bytes: int) -> str:
|
||||
"""Converts a file size in bytes to a human-readable string with units.
|
||||
|
||||
From https://stackoverflow.com/a/14822210/9478891
|
||||
Authors: james-sapam & other contributors
|
||||
Licensed under CC BY-SA 3.0
|
||||
See git commit logs for changes, if any.
|
||||
|
||||
Args:
|
||||
size_bytes: The file size in bytes.
|
||||
|
||||
Returns:
|
||||
A human-readable string representing the file size.
|
||||
"""
|
||||
if size_bytes == 0:
|
||||
return "0B"
|
||||
size_name = ("B", "KB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB")
|
||||
i = int(math.floor(math.log(size_bytes, 1024)))
|
||||
p = math.pow(1024, i)
|
||||
s = round(size_bytes / p, 2)
|
||||
return "%s %s" % (s, size_name[i])
|
||||
|
||||
|
||||
def readable_to_bytes(size_str: str) -> int:
|
||||
"""Converts a human-readable file size string to bytes.
|
||||
|
||||
Args:
|
||||
size_str: The human-readable file size string (e.g., "1024KB", "1MB", "2GB").
|
||||
|
||||
Returns:
|
||||
The file size in bytes.
|
||||
|
||||
Raises:
|
||||
ValueError: If the input string is invalid.
|
||||
"""
|
||||
SIZE_UNITS = {
|
||||
'B': 1,
|
||||
'KB': 1024,
|
||||
'MB': 1024**2,
|
||||
'GB': 1024**3,
|
||||
'TB': 1024**4,
|
||||
'PB': 1024**5,
|
||||
'EB': 1024**6,
|
||||
'ZB': 1024**7,
|
||||
'YB': 1024**8
|
||||
}
|
||||
size_str = size_str.upper().strip()
|
||||
number, unit = size_str[:-2].strip(), size_str[-2:].strip()
|
||||
if unit not in SIZE_UNITS or not number.isnumeric():
|
||||
raise ValueError("Invalid input for size_str. Example: 1024GB")
|
||||
return int(number) * SIZE_UNITS[unit]
|
||||
|
||||
|
||||
def sanitize_except(html: str) -> Markup:
|
||||
"""Sanitizes HTML, only allowing <br> tag.
|
||||
|
||||
Args:
|
||||
html: The HTML string to sanitize.
|
||||
|
||||
Returns:
|
||||
A Markup object containing the sanitized HTML.
|
||||
"""
|
||||
return Markup(sanitize(html, tags=["br"]))
|
||||
|
||||
|
||||
def determine_day(last: int, current: int) -> Optional[datetime.date]:
|
||||
"""Determines if the day has changed between two timestamps. Exposed to Jinja's environment.
|
||||
|
||||
Args:
|
||||
last: The timestamp of the previous message.
|
||||
current: The timestamp of the current message.
|
||||
|
||||
Returns:
|
||||
The date of the current message if it's a different day than the last message, otherwise None.
|
||||
"""
|
||||
last = datetime.fromtimestamp(last).date()
|
||||
current = datetime.fromtimestamp(current).date()
|
||||
if last == current:
|
||||
return None
|
||||
else:
|
||||
return current
|
||||
|
||||
|
||||
def check_update():
|
||||
import urllib.request
|
||||
import json
|
||||
import importlib
|
||||
from sys import platform
|
||||
|
||||
PACKAGE_JSON = "https://pypi.org/pypi/whatsapp-chat-exporter/json"
|
||||
try:
|
||||
raw = urllib.request.urlopen(PACKAGE_JSON)
|
||||
except Exception:
|
||||
print("Failed to check for updates.")
|
||||
return 1
|
||||
else:
|
||||
with raw:
|
||||
package_info = json.load(raw)
|
||||
latest_version = tuple(map(int, package_info["info"]["version"].split(".")))
|
||||
__version__ = importlib.metadata.version("whatsapp_chat_exporter")
|
||||
current_version = tuple(map(int, __version__.split(".")))
|
||||
if current_version < latest_version:
|
||||
print("===============Update===============")
|
||||
print("A newer version of WhatsApp Chat Exporter is available.")
|
||||
print("Current version: " + __version__)
|
||||
print("Latest version: " + package_info["info"]["version"])
|
||||
if platform == "win32":
|
||||
print("Update with: pip install --upgrade whatsapp-chat-exporter")
|
||||
else:
|
||||
print("Update with: pip3 install --upgrade whatsapp-chat-exporter")
|
||||
print("====================================")
|
||||
else:
|
||||
print("You are using the latest version of WhatsApp Chat Exporter.")
|
||||
return 0
|
||||
|
||||
|
||||
def rendering(
|
||||
output_file_name,
|
||||
template,
|
||||
name,
|
||||
msgs,
|
||||
contact,
|
||||
w3css,
|
||||
chat,
|
||||
headline,
|
||||
next=False,
|
||||
previous=False
|
||||
):
|
||||
if chat.their_avatar_thumb is None and chat.their_avatar is not None:
|
||||
their_avatar_thumb = chat.their_avatar
|
||||
else:
|
||||
their_avatar_thumb = chat.their_avatar_thumb
|
||||
if "??" not in headline:
|
||||
raise ValueError("Headline must contain '??' to replace with name")
|
||||
headline = headline.replace("??", name)
|
||||
with open(output_file_name, "w", encoding="utf-8") as f:
|
||||
f.write(
|
||||
template.render(
|
||||
name=name,
|
||||
msgs=msgs,
|
||||
my_avatar=chat.my_avatar,
|
||||
their_avatar=chat.their_avatar,
|
||||
their_avatar_thumb=their_avatar_thumb,
|
||||
w3css=w3css,
|
||||
next=next,
|
||||
previous=previous,
|
||||
status=chat.status,
|
||||
media_base=chat.media_base,
|
||||
headline=headline
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
class Device(StrEnum):
|
||||
IOS = "ios"
|
||||
ANDROID = "android"
|
||||
EXPORTED = "exported"
|
||||
|
||||
|
||||
def import_from_json(json_file: str, data: Dict[str, ChatStore]):
|
||||
"""Imports chat data from a JSON file into the data dictionary.
|
||||
|
||||
Args:
|
||||
json_file: The path to the JSON file.
|
||||
data: The dictionary to store the imported chat data.
|
||||
"""
|
||||
from Whatsapp_Chat_Exporter.data_model import ChatStore, Message
|
||||
with open(json_file, "r") as f:
|
||||
temp_data = json.loads(f.read())
|
||||
total_row_number = len(tuple(temp_data.keys()))
|
||||
print(f"Importing chats from JSON...(0/{total_row_number})", end="\r")
|
||||
for index, (jid, chat_data) in enumerate(temp_data.items()):
|
||||
chat = ChatStore(chat_data.get("type"), chat_data.get("name"))
|
||||
chat.my_avatar = chat_data.get("my_avatar")
|
||||
chat.their_avatar = chat_data.get("their_avatar")
|
||||
chat.their_avatar_thumb = chat_data.get("their_avatar_thumb")
|
||||
chat.status = chat_data.get("status")
|
||||
for id, msg in chat_data.get("messages").items():
|
||||
message = Message(
|
||||
from_me=msg["from_me"],
|
||||
timestamp=msg["timestamp"],
|
||||
time=msg["time"],
|
||||
key_id=msg["key_id"],
|
||||
received_timestamp=msg.get("received_timestamp"),
|
||||
read_timestamp=msg.get("read_timestamp")
|
||||
)
|
||||
message.media = msg.get("media")
|
||||
message.meta = msg.get("meta")
|
||||
message.data = msg.get("data")
|
||||
message.sender = msg.get("sender")
|
||||
message.safe = msg.get("safe")
|
||||
message.mime = msg.get("mime")
|
||||
message.reply = msg.get("reply")
|
||||
message.quoted_data = msg.get("quoted_data")
|
||||
message.caption = msg.get("caption")
|
||||
message.thumb = msg.get("thumb")
|
||||
message.sticker = msg.get("sticker")
|
||||
chat.add_message(id, message)
|
||||
data[jid] = chat
|
||||
print(f"Importing chats from JSON...({index + 1}/{total_row_number})", end="\r")
|
||||
|
||||
|
||||
def sanitize_filename(file_name: str) -> str:
|
||||
"""Sanitizes a filename by removing invalid and unsafe characters.
|
||||
|
||||
Args:
|
||||
file_name: The filename to sanitize.
|
||||
|
||||
Returns:
|
||||
The sanitized filename.
|
||||
"""
|
||||
return "".join(x for x in file_name if x.isalnum() or x in "- ")
|
||||
|
||||
|
||||
def get_file_name(contact: str, chat: ChatStore) -> Tuple[str, str]:
|
||||
"""Generates a sanitized filename and contact name for a chat.
|
||||
|
||||
Args:
|
||||
contact: The contact identifier (e.g., a phone number or group ID).
|
||||
chat: The ChatStore object for the chat.
|
||||
|
||||
Returns:
|
||||
A tuple containing the sanitized filename and the contact name.
|
||||
|
||||
Raises:
|
||||
ValueError: If the contact format is unexpected.
|
||||
"""
|
||||
if "@" not in contact and contact not in ("000000000000000", "000000000000001", "ExportedChat"):
|
||||
raise ValueError("Unexpected contact format: " + contact)
|
||||
phone_number = contact.split('@')[0]
|
||||
if "-" in contact and chat.name is not None:
|
||||
file_name = ""
|
||||
else:
|
||||
file_name = phone_number
|
||||
|
||||
if chat.name is not None:
|
||||
if file_name != "":
|
||||
file_name += "-"
|
||||
file_name += chat.name.replace("/", "-").replace("\\", "-")
|
||||
name = chat.name
|
||||
else:
|
||||
name = phone_number
|
||||
|
||||
return sanitize_filename(file_name), name
|
||||
|
||||
|
||||
def get_cond_for_empty(enable: bool, jid_field: str, broadcast_field: str) -> str:
|
||||
"""Generates a SQL condition for filtering empty chats.
|
||||
|
||||
Args:
|
||||
enable: True to include non-empty chats, False to include empty chats.
|
||||
jid_field: The name of the JID field in the SQL query.
|
||||
broadcast_field: The column name of the broadcast field in the SQL query.
|
||||
|
||||
Returns:
|
||||
A SQL condition string.
|
||||
"""
|
||||
return f"AND (chat.hidden=0 OR {jid_field}='status@broadcast' OR {broadcast_field}>0)" if enable else ""
|
||||
|
||||
|
||||
def get_chat_condition(filter: Optional[List[str]], include: bool, columns: List[str], jid: Optional[str] = None, platform: Optional[str] = None) -> str:
|
||||
"""Generates a SQL condition for filtering chats based on inclusion or exclusion criteria.
|
||||
|
||||
Args:
|
||||
filter: A list of phone numbers to include or exclude.
|
||||
include: True to include chats that match the filter, False to exclude them.
|
||||
columns: A list of column names to check against the filter.
|
||||
jid: The JID column name (used for group identification).
|
||||
platform: The platform ("android" or "ios") for platform-specific JID queries.
|
||||
|
||||
Returns:
|
||||
A SQL condition string.
|
||||
|
||||
Raises:
|
||||
ValueError: If the column count is invalid or an unsupported platform is provided.
|
||||
"""
|
||||
if filter is not None:
|
||||
conditions = []
|
||||
if len(columns) < 2 and jid is not None:
|
||||
raise ValueError("There must be at least two elements in argument columns if jid is not None")
|
||||
if jid is not None:
|
||||
if platform == "android":
|
||||
is_group = f"{jid}.type == 1"
|
||||
elif platform == "ios":
|
||||
is_group = f"{jid} IS NOT NULL"
|
||||
else:
|
||||
raise ValueError("Only android and ios are supported for argument platform if jid is not None")
|
||||
for index, chat in enumerate(filter):
|
||||
if include:
|
||||
conditions.append(f"{' OR' if index > 0 else ''} {columns[0]} LIKE '%{chat}%'")
|
||||
if len(columns) > 1:
|
||||
conditions.append(f" OR ({columns[1]} LIKE '%{chat}%' AND {is_group})")
|
||||
else:
|
||||
conditions.append(f"{' AND' if index > 0 else ''} {columns[0]} NOT LIKE '%{chat}%'")
|
||||
if len(columns) > 1:
|
||||
conditions.append(f" AND ({columns[1]} NOT LIKE '%{chat}%' AND {is_group})")
|
||||
return f"AND ({' '.join(conditions)})"
|
||||
else:
|
||||
return ""
|
||||
|
||||
|
||||
# Android Specific
|
||||
CRYPT14_OFFSETS = (
|
||||
{"iv": 67, "db": 191},
|
||||
{"iv": 67, "db": 190},
|
||||
{"iv": 66, "db": 99},
|
||||
{"iv": 67, "db": 193},
|
||||
{"iv": 67, "db": 194},
|
||||
{"iv": 67, "db": 158},
|
||||
)
|
||||
|
||||
|
||||
class Crypt(IntEnum):
|
||||
CRYPT15 = 15
|
||||
CRYPT14 = 14
|
||||
CRYPT12 = 12
|
||||
|
||||
|
||||
class DbType(StrEnum):
|
||||
MESSAGE = "message"
|
||||
CONTACT = "contact"
|
||||
|
||||
|
||||
def determine_metadata(content: sqlite3.Row, init_msg: Optional[str]) -> Optional[str]:
|
||||
"""Determines the metadata of a message.
|
||||
|
||||
Args:
|
||||
content (sqlite3.Row): A row from the messages table.
|
||||
init_msg (Optional[str]): The initial message, if any.
|
||||
|
||||
Returns:
|
||||
The metadata as a string or None if the type is unsupported.
|
||||
"""
|
||||
msg = init_msg if init_msg else ""
|
||||
if content["is_me_joined"] == 1: # Override
|
||||
return f"You were added into the group by {msg}"
|
||||
if content["action_type"] == 1:
|
||||
msg += f''' changed the group name to "{content['data']}"'''
|
||||
elif content["action_type"] == 4:
|
||||
msg += " was added to the group"
|
||||
elif content["action_type"] == 5:
|
||||
msg += " left the group"
|
||||
elif content["action_type"] == 6:
|
||||
msg += f" changed the group icon"
|
||||
elif content["action_type"] == 7:
|
||||
msg = "You were removed"
|
||||
elif content["action_type"] == 8:
|
||||
msg += ("WhatsApp Internal Error Occurred: "
|
||||
"you cannot send message to this group")
|
||||
elif content["action_type"] == 9:
|
||||
msg += " created a broadcast channel"
|
||||
elif content["action_type"] == 10:
|
||||
try:
|
||||
old = content['old_jid'].split('@')[0]
|
||||
new = content['new_jid'].split('@')[0]
|
||||
except (AttributeError, IndexError):
|
||||
return None
|
||||
else:
|
||||
msg = f"{old} changed their number to {new}"
|
||||
elif content["action_type"] == 11:
|
||||
msg += f''' created a group with name: "{content['data']}"'''
|
||||
elif content["action_type"] == 12:
|
||||
msg += f" added someone" # TODO: Find out who
|
||||
elif content["action_type"] == 13:
|
||||
return # Someone left the group
|
||||
elif content["action_type"] == 14:
|
||||
msg += f" removed someone" # TODO: Find out who
|
||||
elif content["action_type"] == 15:
|
||||
return # Someone promoted someone as an admin
|
||||
elif content["action_type"] == 18:
|
||||
if msg != "You":
|
||||
msg = f"The security code between you and {msg} changed"
|
||||
else:
|
||||
msg = "The security code in this chat changed"
|
||||
elif content["action_type"] == 19:
|
||||
msg = "This chat is now end-to-end encrypted"
|
||||
elif content["action_type"] == 20:
|
||||
msg = "Someone joined this group by using a invite link" # TODO: Find out who
|
||||
elif content["action_type"] == 27:
|
||||
msg += " changed the group description to:<br>"
|
||||
msg += (content['data'] or "Unknown").replace("\n", '<br>')
|
||||
elif content["action_type"] == 28:
|
||||
try:
|
||||
old = content['old_jid'].split('@')[0]
|
||||
new = content['new_jid'].split('@')[0]
|
||||
except (AttributeError, IndexError):
|
||||
return None
|
||||
else:
|
||||
msg = f"{old} changed their number to {new}"
|
||||
elif content["action_type"] == 46:
|
||||
return # Voice message in PM??? Seems no need to handle.
|
||||
elif content["action_type"] == 47:
|
||||
msg = "The contact is an official business account"
|
||||
elif content["action_type"] == 50:
|
||||
msg = "The contact's account type changed from business to standard"
|
||||
elif content["action_type"] == 56:
|
||||
msg = "Messgae timer was enabled/updated/disabled"
|
||||
elif content["action_type"] == 57:
|
||||
if msg != "You":
|
||||
msg = f"The security code between you and {msg} changed"
|
||||
else:
|
||||
msg = "The security code in this chat changed"
|
||||
elif content["action_type"] == 58:
|
||||
msg = "You blocked this contact"
|
||||
elif content["action_type"] == 67:
|
||||
return # (PM) this contact use secure service from Facebook???
|
||||
elif content["action_type"] == 69:
|
||||
return # (PM) this contact use secure service from Facebook??? What's the difference with 67????
|
||||
else:
|
||||
return # Unsupported
|
||||
return msg
|
||||
|
||||
|
||||
def get_status_location(output_folder: str, offline_static: str) -> str:
|
||||
"""
|
||||
Gets the location of the W3.CSS file, either from web or local storage.
|
||||
|
||||
Args:
|
||||
output_folder (str): The folder where offline static files will be stored.
|
||||
offline_static (str): The subfolder name for static files. If falsy, returns web URL.
|
||||
|
||||
Returns:
|
||||
str: The path or URL to the W3.CSS file.
|
||||
"""
|
||||
w3css = "https://www.w3schools.com/w3css/4/w3.css"
|
||||
if not offline_static:
|
||||
return w3css
|
||||
import urllib.request
|
||||
static_folder = os.path.join(output_folder, offline_static)
|
||||
if not os.path.isdir(static_folder):
|
||||
os.mkdir(static_folder)
|
||||
w3css_path = os.path.join(static_folder, "w3.css")
|
||||
if not os.path.isfile(w3css_path):
|
||||
with urllib.request.urlopen(w3css) as resp:
|
||||
with open(w3css_path, "wb") as f: f.write(resp.read())
|
||||
w3css = os.path.join(offline_static, "w3.css")
|
||||
|
||||
|
||||
def setup_template(template: Optional[str], no_avatar: bool, experimental: bool = False) -> jinja2.Template:
|
||||
"""
|
||||
Sets up the Jinja2 template environment and loads the template.
|
||||
|
||||
Args:
|
||||
template (Optional[str]): Path to custom template file. If None, uses default template.
|
||||
no_avatar (bool): Whether to disable avatar display in the template.
|
||||
experimental (bool, optional): Whether to use experimental template features. Defaults to False.
|
||||
|
||||
Returns:
|
||||
jinja2.Template: The configured Jinja2 template object.
|
||||
"""
|
||||
if template is None or experimental:
|
||||
template_dir = os.path.dirname(__file__)
|
||||
template_file = "whatsapp.html" if not experimental else template
|
||||
else:
|
||||
template_dir = os.path.dirname(template)
|
||||
template_file = os.path.basename(template)
|
||||
template_loader = jinja2.FileSystemLoader(searchpath=template_dir)
|
||||
template_env = jinja2.Environment(loader=template_loader, autoescape=True)
|
||||
template_env.globals.update(
|
||||
determine_day=determine_day,
|
||||
no_avatar=no_avatar
|
||||
)
|
||||
template_env.filters['sanitize_except'] = sanitize_except
|
||||
return template_env.get_template(template_file)
|
||||
|
||||
# iOS Specific
|
||||
APPLE_TIME = 978307200
|
||||
|
||||
|
||||
def slugify(value: str, allow_unicode: bool = False) -> str:
|
||||
"""
|
||||
Convert text to ASCII-only slugs for URL-safe strings.
|
||||
Taken from https://github.com/django/django/blob/master/django/utils/text.py
|
||||
|
||||
Args:
|
||||
value (str): The string to convert to a slug.
|
||||
allow_unicode (bool, optional): Whether to allow Unicode characters. Defaults to False.
|
||||
|
||||
Returns:
|
||||
str: The slugified string with only alphanumerics, underscores, or hyphens.
|
||||
"""
|
||||
value = str(value)
|
||||
if allow_unicode:
|
||||
value = unicodedata.normalize('NFKC', value)
|
||||
else:
|
||||
value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode('ascii')
|
||||
value = re.sub(r'[^\w\s-]', '', value.lower())
|
||||
return re.sub(r'[-\s]+', '-', value).strip('-_')
|
||||
|
||||
|
||||
class WhatsAppIdentifier(StrEnum):
|
||||
MESSAGE = "7c7fba66680ef796b916b067077cc246adacf01d" # AppDomainGroup-group.net.whatsapp.WhatsApp.shared-ChatStorage.sqlite
|
||||
CONTACT = "b8548dc30aa1030df0ce18ef08b882cf7ab5212f" # AppDomainGroup-group.net.whatsapp.WhatsApp.shared-ContactsV2.sqlite
|
||||
CALL = "1b432994e958845fffe8e2f190f26d1511534088" # AppDomainGroup-group.net.whatsapp.WhatsApp.shared-CallHistory.sqlite
|
||||
DOMAIN = "AppDomainGroup-group.net.whatsapp.WhatsApp.shared"
|
||||
|
||||
|
||||
class WhatsAppBusinessIdentifier(StrEnum):
|
||||
MESSAGE = "724bd3b98b18518b455a87c1f3ac3a0d189c4466" # AppDomainGroup-group.net.whatsapp.WhatsAppSMB.shared-ChatStorage.sqlite
|
||||
CONTACT = "d7246a707f51ddf8b17ee2dddabd9e0a4da5c552" # AppDomainGroup-group.net.whatsapp.WhatsAppSMB.shared-ContactsV2.sqlite
|
||||
CALL = "b463f7c4365eefc5a8723930d97928d4e907c603" # AppDomainGroup-group.net.whatsapp.WhatsAppSMB.shared-CallHistory.sqlite
|
||||
DOMAIN = "AppDomainGroup-group.net.whatsapp.WhatsAppSMB.shared"
|
||||
|
||||
class JidType(IntEnum):
|
||||
PM = 0
|
||||
GROUP = 1
|
||||
SYSTEM_BROADCAST = 5
|
||||
STATUS = 11
|
||||
@@ -1,82 +0,0 @@
|
||||
import vobject
|
||||
from typing import List, TypedDict
|
||||
|
||||
|
||||
class ExportedContactNumbers(TypedDict):
|
||||
full_name: str
|
||||
numbers: List[str]
|
||||
|
||||
|
||||
class ContactsFromVCards:
|
||||
def __init__(self) -> None:
|
||||
self.contact_mapping = []
|
||||
|
||||
def is_empty(self):
|
||||
return self.contact_mapping == []
|
||||
|
||||
def load_vcf_file(self, vcf_file_path: str, default_country_code: str):
|
||||
self.contact_mapping = read_vcards_file(vcf_file_path, default_country_code)
|
||||
|
||||
def enrich_from_vcards(self, chats):
|
||||
for number, name in self.contact_mapping:
|
||||
# short number must be a bad contact, lets skip it
|
||||
if len(number) <= 5:
|
||||
continue
|
||||
|
||||
for chat in filter_chats_by_prefix(chats, number).values():
|
||||
if not hasattr(chat, 'name') or (hasattr(chat, 'name') and chat.name is None):
|
||||
setattr(chat, 'name', name)
|
||||
|
||||
|
||||
def read_vcards_file(vcf_file_path, default_country_code: str):
|
||||
contacts = []
|
||||
with open(vcf_file_path, mode="r", encoding="utf-8") as f:
|
||||
reader = vobject.readComponents(f)
|
||||
for row in reader:
|
||||
if hasattr(row, 'fn'):
|
||||
name = str(row.fn.value)
|
||||
elif hasattr(row, 'n'):
|
||||
name = str(row.n.value)
|
||||
else:
|
||||
name = None
|
||||
if not hasattr(row, 'tel') or name is None:
|
||||
continue
|
||||
contact: ExportedContactNumbers = {
|
||||
"full_name": name,
|
||||
"numbers": list(map(lambda tel: tel.value, row.tel_list)),
|
||||
}
|
||||
contacts.append(contact)
|
||||
|
||||
return map_number_to_name(contacts, default_country_code)
|
||||
|
||||
|
||||
def filter_chats_by_prefix(chats, prefix: str):
|
||||
return {k: v for k, v in chats.items() if k.startswith(prefix)}
|
||||
|
||||
|
||||
def map_number_to_name(contacts, default_country_code: str):
|
||||
mapping = []
|
||||
for contact in contacts:
|
||||
for index, num in enumerate(contact['numbers']):
|
||||
normalized = normalize_number(num, default_country_code)
|
||||
if len(contact['numbers']) > 1:
|
||||
name = f"{contact['full_name']} ({index+1})"
|
||||
else:
|
||||
name = contact['full_name']
|
||||
mapping.append((normalized, name))
|
||||
return mapping
|
||||
|
||||
|
||||
def normalize_number(number: str, country_code: str):
|
||||
# Clean the number
|
||||
number = ''.join(c for c in number if c.isdigit() or c == "+")
|
||||
|
||||
# A number that starts with a + or 00 means it already have a country code
|
||||
for starting_char in ('+', "00"):
|
||||
if number.startswith(starting_char):
|
||||
return number[len(starting_char):]
|
||||
|
||||
# leading zero should be removed
|
||||
if starting_char == '0':
|
||||
number = number[1:]
|
||||
return country_code + number # fall back
|
||||
@@ -1,20 +0,0 @@
|
||||
# from contacts_names_from_vcards import readVCardsFile
|
||||
|
||||
from Whatsapp_Chat_Exporter.vcards_contacts import normalize_number, read_vcards_file
|
||||
|
||||
|
||||
def test_readVCardsFile():
|
||||
assert len(read_vcards_file("contacts.vcf", "973")) > 0
|
||||
|
||||
def test_create_number_to_name_dicts():
|
||||
pass
|
||||
|
||||
def test_fuzzy_match_numbers():
|
||||
pass
|
||||
|
||||
def test_normalize_number():
|
||||
assert normalize_number('0531234567', '1') == '1531234567'
|
||||
assert normalize_number('001531234567', '2') == '1531234567'
|
||||
assert normalize_number('+1531234567', '34') == '1531234567'
|
||||
assert normalize_number('053(123)4567', '34') == '34531234567'
|
||||
assert normalize_number('0531-234-567', '58') == '58531234567'
|
||||
@@ -1,329 +0,0 @@
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<title>Whatsapp - {{ name }}</title>
|
||||
<meta charset="UTF-8">
|
||||
<link rel="stylesheet" href="{{w3css}}">
|
||||
<style>
|
||||
html, body {
|
||||
font-size: 12px;
|
||||
scroll-behavior: smooth;
|
||||
}
|
||||
header {
|
||||
position: fixed;
|
||||
z-index: 20;
|
||||
border-bottom: 2px solid #e3e6e7;
|
||||
font-size: 2em;
|
||||
font-weight: bolder;
|
||||
background-color: white;
|
||||
padding: 20px 0 20px 0;
|
||||
}
|
||||
footer {
|
||||
border-top: 2px solid #e3e6e7;
|
||||
padding: 20px 0 20px 0;
|
||||
}
|
||||
article {
|
||||
width:500px;
|
||||
margin:100px auto;
|
||||
z-index:10;
|
||||
font-size: 15px;
|
||||
word-wrap: break-word;
|
||||
}
|
||||
img, video {
|
||||
max-width:100%;
|
||||
}
|
||||
div.reply{
|
||||
font-size: 13px;
|
||||
text-decoration: none;
|
||||
}
|
||||
div:target::before {
|
||||
content: '';
|
||||
display: block;
|
||||
height: 115px;
|
||||
margin-top: -115px;
|
||||
visibility: hidden;
|
||||
}
|
||||
div:target {
|
||||
border-style: solid;
|
||||
border-width: 2px;
|
||||
animation: border-blink 0.5s steps(1) 5;
|
||||
border-color: rgba(0,0,0,0)
|
||||
}
|
||||
table {
|
||||
width: 100%;
|
||||
}
|
||||
@keyframes border-blink {
|
||||
0% {
|
||||
border-color: #2196F3;
|
||||
}
|
||||
50% {
|
||||
border-color: rgba(0,0,0,0);
|
||||
}
|
||||
}
|
||||
.avatar {
|
||||
border-radius:50%;
|
||||
overflow:hidden;
|
||||
max-width: 64px;
|
||||
max-height: 64px;
|
||||
}
|
||||
.name {
|
||||
color: #3892da;
|
||||
}
|
||||
.pad-left-10 {
|
||||
padding-left: 10px;
|
||||
}
|
||||
.pad-right-10 {
|
||||
padding-right: 10px;
|
||||
}
|
||||
.reply_link {
|
||||
color: #168acc;
|
||||
}
|
||||
.blue {
|
||||
color: #70777a;
|
||||
}
|
||||
.sticker {
|
||||
max-width: 100px !important;
|
||||
max-height: 100px !important;
|
||||
}
|
||||
</style>
|
||||
<base href="{{ media_base }}" target="_blank">
|
||||
</head>
|
||||
<body>
|
||||
<header class="w3-center w3-top">
|
||||
{{ headline }}
|
||||
{% if status is not none %}
|
||||
<br>
|
||||
<span class="w3-small">{{ status }}</span>
|
||||
{% endif %}
|
||||
</header>
|
||||
<article class="w3-container">
|
||||
<div class="table">
|
||||
{% set last = {'last': 946688461.001} %}
|
||||
{% for msg in msgs -%}
|
||||
<div class="w3-row w3-padding-small w3-margin-bottom" id="{{ msg.key_id }}">
|
||||
{% if determine_day(last.last, msg.timestamp) is not none %}
|
||||
<div class="w3-center w3-padding-16 blue">{{ determine_day(last.last, msg.timestamp) }}</div>
|
||||
{% if last.update({'last': msg.timestamp}) %}{% endif %}
|
||||
{% endif %}
|
||||
{% if msg.from_me == true %}
|
||||
<div class="w3-row">
|
||||
<div class="w3-left blue">{{ msg.time }}</div>
|
||||
<div class="name w3-right-align pad-left-10">You</div>
|
||||
</div>
|
||||
<div class="w3-row">
|
||||
{% if not no_avatar and my_avatar is not none %}
|
||||
<div class="w3-col m10 l10">
|
||||
{% else %}
|
||||
<div class="w3-col m12 l12">
|
||||
{% endif %}
|
||||
<div class="w3-right-align">
|
||||
{% if msg.reply is not none %}
|
||||
<div class="reply">
|
||||
<span class="blue">Replying to </span>
|
||||
<a href="#{{msg.reply}}" target="_self" class="reply_link no-base">
|
||||
{% if msg.quoted_data is not none %}
|
||||
"{{msg.quoted_data}}"
|
||||
{% else %}
|
||||
this message
|
||||
{% endif %}
|
||||
</a>
|
||||
</div>
|
||||
{% endif %}
|
||||
{% if msg.meta == true or msg.media == false and msg.data is none %}
|
||||
<div class="w3-panel w3-border-blue w3-pale-blue w3-rightbar w3-leftbar w3-threequarter w3-center">
|
||||
{% if msg.safe %}
|
||||
<p>{{ msg.data | safe or 'Not supported WhatsApp internal message' }}</p>
|
||||
{% else %}
|
||||
<p>{{ msg.data or 'Not supported WhatsApp internal message' }}</p>
|
||||
{% endif %}
|
||||
</div>
|
||||
{% if msg.caption is not none %}
|
||||
<div class="w3-container">
|
||||
{{ msg.caption | urlize(none, true, '_blank') }}
|
||||
</div>
|
||||
{% endif %}
|
||||
{% else %}
|
||||
{% if msg.media == false %}
|
||||
{{ msg.data | sanitize_except() | urlize(none, true, '_blank') }}
|
||||
{% else %}
|
||||
{% if "image/" in msg.mime %}
|
||||
<a href="{{ msg.data }}">
|
||||
<img src="{{ msg.thumb if msg.thumb is not none else msg.data }}" {{ 'class="sticker"' | safe if msg.sticker }} loading="lazy"/>
|
||||
</a>
|
||||
{% elif "audio/" in msg.mime %}
|
||||
<audio controls="controls" autobuffer="autobuffer">
|
||||
<source src="{{ msg.data }}" />
|
||||
</audio>
|
||||
{% elif "video/" in msg.mime %}
|
||||
<video class="lazy" autobuffer {% if msg.message_type|int == 13 or msg.message_type|int == 11 %}autoplay muted loop playsinline{%else%}controls{% endif %}>
|
||||
<source type="{{ msg.mime }}" data-src="{{ msg.data }}" />
|
||||
</video>
|
||||
{% elif "/" in msg.mime %}
|
||||
<div class="w3-panel w3-border-blue w3-pale-blue w3-rightbar w3-leftbar w3-threequarter w3-center">
|
||||
<p>The file cannot be displayed here, however it should be located at <a href="./{{ msg.data }}">here</a></p>
|
||||
</div>
|
||||
{% else %}
|
||||
{% filter escape %}{{ msg.data }}{% endfilter %}
|
||||
{% endif %}
|
||||
{% if msg.caption is not none %}
|
||||
<div class="w3-container">
|
||||
{{ msg.caption | urlize(none, true, '_blank') }}
|
||||
</div>
|
||||
{% endif %}
|
||||
{% endif %}
|
||||
{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
{% if not no_avatar and my_avatar is not none %}
|
||||
<div class="w3-col m2 l2 pad-left-10">
|
||||
<a href="{{ my_avatar }}">
|
||||
<img src="{{ my_avatar }}" onerror="this.style.display='none'" class="avatar" loading="lazy">
|
||||
</a>
|
||||
</div>
|
||||
{% endif %}
|
||||
</div>
|
||||
{% else %}
|
||||
<div class="w3-row">
|
||||
<div class="w3-left pad-right-10 name">
|
||||
{% if msg.sender is not none %}
|
||||
{{ msg.sender }}
|
||||
{% else %}
|
||||
{{ name }}
|
||||
{% endif %}
|
||||
</div>
|
||||
<div class="w3-right-align blue">{{ msg.time }}</div>
|
||||
</div>
|
||||
<div class="w3-row">
|
||||
{% if not no_avatar %}
|
||||
<div class="w3-col m2 l2">
|
||||
{% if their_avatar is not none %}
|
||||
<a href="{{ their_avatar }}"><img src="{{ their_avatar_thumb or '' }}" onerror="this.style.display='none'" class="avatar" loading="lazy"></a>
|
||||
{% else %}
|
||||
<img src="{{ their_avatar_thumb or '' }}" onerror="this.style.display='none'" class="avatar" loading="lazy">
|
||||
{% endif %}
|
||||
</div>
|
||||
<div class="w3-col m10 l10">
|
||||
{% else %}
|
||||
<div class="w3-col m12 l12">
|
||||
{% endif %}
|
||||
<div class="w3-left-align">
|
||||
{% if msg.reply is not none %}
|
||||
<div class="reply">
|
||||
<span class="blue">Replying to </span>
|
||||
<a href="#{{msg.reply}}" target="_self" class="reply_link no-base">
|
||||
{% if msg.quoted_data is not none %}
|
||||
"{{msg.quoted_data}}"
|
||||
{% else %}
|
||||
this message
|
||||
{% endif %}
|
||||
</a>
|
||||
</div>
|
||||
{% endif %}
|
||||
{% if msg.meta == true or msg.media == false and msg.data is none %}
|
||||
<div class="w3-panel w3-border-blue w3-pale-blue w3-rightbar w3-leftbar w3-threequarter w3-center">
|
||||
{% if msg.safe %}
|
||||
<p>{{ msg.data | safe or 'Not supported WhatsApp internal message' }}</p>
|
||||
{% else %}
|
||||
<p>{{ msg.data or 'Not supported WhatsApp internal message' }}</p>
|
||||
{% endif %}
|
||||
</div>
|
||||
{% if msg.caption is not none %}
|
||||
<div class="w3-container">
|
||||
{{ msg.caption | urlize(none, true, '_blank') }}
|
||||
</div>
|
||||
{% endif %}
|
||||
{% else %}
|
||||
{% if msg.media == false %}
|
||||
{{ msg.data | sanitize_except() | urlize(none, true, '_blank') }}
|
||||
{% else %}
|
||||
{% if "image/" in msg.mime %}
|
||||
<a href="{{ msg.data }}">
|
||||
<img src="{{ msg.thumb if msg.thumb is not none else msg.data }}" {{ 'class="sticker"' | safe if msg.sticker }} loading="lazy"/>
|
||||
</a>
|
||||
{% elif "audio/" in msg.mime %}
|
||||
<audio controls="controls" autobuffer="autobuffer">
|
||||
<source src="{{ msg.data }}" />
|
||||
</audio>
|
||||
{% elif "video/" in msg.mime %}
|
||||
<video class="lazy" autobuffer {% if msg.message_type|int == 13 or msg.message_type|int == 11 %}autoplay muted loop playsinline{%else%}controls{% endif %}>
|
||||
<source type="{{ msg.mime }}" data-src="{{ msg.data }}" />
|
||||
</video>
|
||||
{% elif "/" in msg.mime %}
|
||||
<div class="w3-panel w3-border-blue w3-pale-blue w3-rightbar w3-leftbar w3-threequarter w3-center">
|
||||
<p>The file cannot be displayed here, however it should be located at <a href="./{{ msg.data }}">here</a></p>
|
||||
</div>
|
||||
{% else %}
|
||||
{% filter escape %}{{ msg.data }}{% endfilter %}
|
||||
{% endif %}
|
||||
{% if msg.caption is not none %}
|
||||
<div class="w3-container">
|
||||
{{ msg.caption | urlize(none, true, '_blank') }}
|
||||
</div>
|
||||
{% endif %}
|
||||
{% endif %}
|
||||
{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
{% endif %}
|
||||
</div>
|
||||
{% endfor %}
|
||||
</div>
|
||||
</article>
|
||||
<footer class="w3-center">
|
||||
<h2>
|
||||
{% if previous %}
|
||||
<a href="./{{ previous }}" target="_self">Previous</a>
|
||||
{% endif %}
|
||||
<h2>
|
||||
{% if next %}
|
||||
<a href="./{{ next }}" target="_self">Next</a>
|
||||
{% else %}
|
||||
End of History
|
||||
{% endif %}
|
||||
</h2>
|
||||
<br>
|
||||
Portions of this page are reproduced from <a href="https://web.dev/articles/lazy-loading-video">work</a> created and <a href="https://developers.google.com/readme/policies">shared by Google</a> and used according to terms described in the <a href="https://www.apache.org/licenses/LICENSE-2.0">Apache 2.0 License</a>.
|
||||
</footer>
|
||||
<script>
|
||||
document.addEventListener("DOMContentLoaded", function() {
|
||||
var lazyVideos = [].slice.call(document.querySelectorAll("video.lazy"));
|
||||
|
||||
if ("IntersectionObserver" in window) {
|
||||
var lazyVideoObserver = new IntersectionObserver(function(entries, observer) {
|
||||
entries.forEach(function(video) {
|
||||
if (video.isIntersecting) {
|
||||
for (var source in video.target.children) {
|
||||
var videoSource = video.target.children[source];
|
||||
if (typeof videoSource.tagName === "string" && videoSource.tagName === "SOURCE") {
|
||||
videoSource.src = videoSource.dataset.src;
|
||||
}
|
||||
}
|
||||
|
||||
video.target.load();
|
||||
video.target.classList.remove("lazy");
|
||||
lazyVideoObserver.unobserve(video.target);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
lazyVideos.forEach(function(lazyVideo) {
|
||||
lazyVideoObserver.observe(lazyVideo);
|
||||
});
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script>
|
||||
// Prevent the <base> tag from affecting links with the class "no-base"
|
||||
document.querySelectorAll('.no-base').forEach(link => {
|
||||
link.addEventListener('click', function(event) {
|
||||
const href = this.getAttribute('href');
|
||||
if (href.startsWith('#')) {
|
||||
window.location.hash = href;
|
||||
event.preventDefault();
|
||||
}
|
||||
});
|
||||
});
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -1,467 +0,0 @@
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<title>Whatsapp - {{ name }}</title>
|
||||
<meta charset="UTF-8">
|
||||
<script src="https://cdn.tailwindcss.com"></script>
|
||||
<script>
|
||||
tailwind.config = {
|
||||
theme: {
|
||||
extend: {
|
||||
colors: {
|
||||
whatsapp: {
|
||||
light: '#e7ffdb',
|
||||
DEFAULT: '#25D366',
|
||||
dark: '#075E54',
|
||||
chat: '#efeae2',
|
||||
'chat-light': '#f0f2f5',
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
</script>
|
||||
<style>
|
||||
body, html {
|
||||
height: 100%;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
scroll-behavior: smooth !important;
|
||||
}
|
||||
.chat-list {
|
||||
height: calc(100vh - 120px);
|
||||
overflow-y: auto;
|
||||
}
|
||||
.message-list {
|
||||
height: calc(100vh - 90px);
|
||||
overflow-y: auto;
|
||||
}
|
||||
@media (max-width: 640px) {
|
||||
.chat-list, .message-list {
|
||||
height: calc(100vh - 108px);
|
||||
}
|
||||
}
|
||||
header {
|
||||
position: fixed;
|
||||
z-index: 20;
|
||||
border-bottom: 2px solid #e3e6e7;
|
||||
font-size: 2em;
|
||||
font-weight: bolder;
|
||||
background-color: white;
|
||||
padding: 20px 0 20px 0;
|
||||
}
|
||||
footer {
|
||||
margin-top: 10px;
|
||||
border-top: 2px solid #e3e6e7;
|
||||
padding: 20px 0 20px 0;
|
||||
}
|
||||
article {
|
||||
width:430px;
|
||||
margin: auto;
|
||||
z-index:10;
|
||||
font-size: 15px;
|
||||
word-wrap: break-word;
|
||||
}
|
||||
img, video, audio{
|
||||
max-width:100%;
|
||||
box-sizing: border-box;
|
||||
}
|
||||
div.reply{
|
||||
font-size: 13px;
|
||||
text-decoration: none;
|
||||
}
|
||||
div:target::before {
|
||||
content: '';
|
||||
display: block;
|
||||
height: 115px;
|
||||
margin-top: -115px;
|
||||
visibility: hidden;
|
||||
}
|
||||
div:target {
|
||||
animation: 3s highlight;
|
||||
}
|
||||
.avatar {
|
||||
border-radius:50%;
|
||||
overflow:hidden;
|
||||
max-width: 64px;
|
||||
max-height: 64px;
|
||||
}
|
||||
.name {
|
||||
color: #3892da;
|
||||
}
|
||||
.pad-left-10 {
|
||||
padding-left: 10px;
|
||||
}
|
||||
.pad-right-10 {
|
||||
padding-right: 10px;
|
||||
}
|
||||
.reply_link {
|
||||
color: #168acc;
|
||||
}
|
||||
.blue {
|
||||
color: #70777a;
|
||||
}
|
||||
.sticker {
|
||||
max-width: 100px !important;
|
||||
max-height: 100px !important;
|
||||
}
|
||||
@keyframes highlight {
|
||||
from {
|
||||
background-color: rgba(37, 211, 102, 0.1);
|
||||
}
|
||||
to {
|
||||
background-color: transparent;
|
||||
}
|
||||
}
|
||||
.search-input {
|
||||
transform: translateY(-100%);
|
||||
transition: transform 0.3s ease-in-out;
|
||||
}
|
||||
.search-input.active {
|
||||
transform: translateY(0);
|
||||
}
|
||||
.reply-box:active {
|
||||
background-color:rgb(200 202 205 / var(--tw-bg-opacity, 1));
|
||||
}
|
||||
.info-box-tooltip {
|
||||
--tw-translate-x: -50%;
|
||||
transform: translate(var(--tw-translate-x), var(--tw-translate-y)) rotate(var(--tw-rotate)) skewX(var(--tw-skew-x)) skewY(var(--tw-skew-y)) scaleX(var(--tw-scale-x)) scaleY(var(--tw-scale-y));
|
||||
}
|
||||
</style>
|
||||
<script>
|
||||
function search(event) {
|
||||
keywords = document.getElementById("mainHeaderSearchInput").value;
|
||||
hits = [];
|
||||
document.querySelectorAll(".message-text").forEach(elem => {
|
||||
if (elem.innerText.trim().includes(keywords)){
|
||||
hits.push(elem.parentElement.parentElement.id);
|
||||
}
|
||||
})
|
||||
console.log(hits);
|
||||
}
|
||||
</script>
|
||||
<base href="{{ media_base }}" target="_blank">
|
||||
</head>
|
||||
<body>
|
||||
<article class="h-screen bg-whatsapp-chat-light">
|
||||
<div class="w-full flex flex-col">
|
||||
<div class="p-3 bg-whatsapp-dark flex items-center justify-between border-l border-[#d1d7db]">
|
||||
<div class="flex items-center">
|
||||
{% if not no_avatar %}
|
||||
<div class="w3-col m2 l2">
|
||||
{% if their_avatar is not none %}
|
||||
<a href="{{ their_avatar }}"><img src="{{ their_avatar_thumb or '' }}" onerror="this.style.display='none'" class="w-10 h-10 rounded-full mr-3" loading="lazy"></a>
|
||||
{% else %}
|
||||
<img src="{{ their_avatar_thumb or '' }}" onerror="this.style.display='none'" class="w-10 h-10 rounded-full mr-3" loading="lazy">
|
||||
{% endif %}
|
||||
</div>
|
||||
{% endif %}
|
||||
<div>
|
||||
<h2 class="text-white font-medium">{{ headline }}</h2>
|
||||
{% if status is not none %}<p class="text-[#8696a0] text-xs">{{ status }}</p>{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
<div class="flex space-x-4">
|
||||
<!-- <button id="searchButton">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" class="h-5 w-5 text-[#aebac1]" fill="none" viewBox="0 0 24 24" stroke="currentColor">
|
||||
<path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M21 21l-6-6m2-5a7 7 0 11-14 0 7 7 0 0114 0z" />
|
||||
</svg>
|
||||
</button> -->
|
||||
<!-- <svg xmlns="http://www.w3.org/2000/svg" class="h-5 w-5 text-[#aebac1]" fill="none" viewBox="0 0 24 24" stroke="currentColor">
|
||||
<path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M15 19l-7-7 7-7" />
|
||||
</svg> -->
|
||||
{% if previous %}
|
||||
<a href="./{{ previous }}" target="_self">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" class="h-5 w-5 text-[#aebac1]" fill="none" viewBox="0 0 24 24" stroke="currentColor">
|
||||
<path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M15 5l-7 7 7 7" />
|
||||
</svg>
|
||||
</a>
|
||||
{% endif %}
|
||||
{% if next %}
|
||||
<a href="./{{ next }}" target="_self">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" class="h-5 w-5 text-[#aebac1]" fill="none" viewBox="0 0 24 24" stroke="currentColor">
|
||||
<path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M9 5l7 7-7 7" />
|
||||
</svg>
|
||||
</a>
|
||||
{% endif %}
|
||||
</div>
|
||||
<!-- Search Input Overlay -->
|
||||
<div id="mainSearchInput" class="search-input absolute article top-0 bg-whatsapp-dark p-3 flex items-center space-x-3">
|
||||
<button id="closeMainSearch" class="text-[#aebac1]">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" class="h-6 w-6" fill="none" viewBox="0 0 24 24" stroke="currentColor">
|
||||
<path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M15 19l-7-7 7-7" />
|
||||
</svg>
|
||||
</button>
|
||||
<input type="text" placeholder="Search..." class="flex-1 bg-[#1f2c34] text-white rounded-lg px-3 py-1 focus:outline-none" id="mainHeaderSearchInput" onkeyup="search(event)">
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="flex-1 p-5 message-list">
|
||||
<div class="flex flex-col space-y-2">
|
||||
<!--Date-->
|
||||
{% set last = {'last': 946688461.001} %}
|
||||
{% for msg in msgs -%}
|
||||
{% if determine_day(last.last, msg.timestamp) is not none %}
|
||||
<div class="flex justify-center">
|
||||
<div class="bg-[#e1f2fb] rounded-lg px-2 py-1 text-xs text-[#54656f]">
|
||||
{{ determine_day(last.last, msg.timestamp) }}
|
||||
</div>
|
||||
</div>
|
||||
{% if last.update({'last': msg.timestamp}) %}{% endif %}
|
||||
{% endif %}
|
||||
<!--Actual messages-->
|
||||
{% if msg.from_me == true %}
|
||||
<div class="flex justify-end items-center group" id="{{ msg.key_id }}">
|
||||
<div class="opacity-0 group-hover:opacity-100 transition-opacity duration-200 relative mr-2">
|
||||
<div class="relative">
|
||||
<div class="relative group/tooltip">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" class="h-5 w-5 text-[#8696a0] hover:text-[#54656f] cursor-pointer" fill="none" viewBox="0 0 24 24" stroke="currentColor">
|
||||
<use href="#info-icon"></use>
|
||||
</svg>
|
||||
<div class="absolute bottom-full info-box-tooltip mb-2 hidden group-hover/tooltip:block z-50">
|
||||
<div class="bg-black text-white text-xs rounded py-1 px-2 whitespace-nowrap">
|
||||
Delivered at {{msg.received_timestamp or 'unknown'}}
|
||||
{% if msg.read_timestamp is not none %}
|
||||
<br>Read at {{ msg.read_timestamp }}
|
||||
{% endif %}
|
||||
</div>
|
||||
<div class="absolute top-full right-3 -mt-1 border-4 border-transparent border-t-black"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="bg-whatsapp-light rounded-lg p-2 max-w-[80%] shadow-sm">
|
||||
{% if msg.reply is not none %}
|
||||
<a href="#{{msg.reply}}" target="_self" class="no-base">
|
||||
<div class="mb-2 p-1 bg-whatsapp-chat-light rounded border-l-4 border-whatsapp text-sm reply-box">
|
||||
<p class="text-whatsapp font-medium text-xs">Replying to</p>
|
||||
<p class="text-[#111b21] text-xs truncate">
|
||||
{% if msg.quoted_data is not none %}
|
||||
"{{msg.quoted_data}}"
|
||||
{% else %}
|
||||
this message
|
||||
{% endif %}
|
||||
</p>
|
||||
</div>
|
||||
</a>
|
||||
{% endif %}
|
||||
<p class="text-[#111b21] text-sm message-text">
|
||||
{% if msg.meta == true or msg.media == false and msg.data is none %}
|
||||
<div class="flex justify-center mb-2">
|
||||
<div class="bg-[#FFF3C5] rounded-lg px-3 py-2 text-sm text-[#856404] flex items-center">
|
||||
{% if msg.safe %}
|
||||
{{ msg.data | safe or 'Not supported WhatsApp internal message' }}
|
||||
{% else %}
|
||||
{{ msg.data or 'Not supported WhatsApp internal message' }}
|
||||
{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
{% if msg.caption is not none %}
|
||||
<p>{{ msg.caption | urlize(none, true, '_blank') }}</p>
|
||||
{% endif %}
|
||||
{% else %}
|
||||
{% if msg.media == false %}
|
||||
{{ msg.data | sanitize_except() | urlize(none, true, '_blank') }}
|
||||
{% else %}
|
||||
{% if "image/" in msg.mime %}
|
||||
<a href="{{ msg.data }}">
|
||||
<img src="{{ msg.thumb if msg.thumb is not none else msg.data }}" {{ 'class="sticker"' | safe if msg.sticker }} loading="lazy"/>
|
||||
</a>
|
||||
{% elif "audio/" in msg.mime %}
|
||||
<audio controls="controls" autobuffer="autobuffer">
|
||||
<source src="{{ msg.data }}" />
|
||||
</audio>
|
||||
{% elif "video/" in msg.mime %}
|
||||
<video class="lazy" autobuffer {% if msg.message_type|int == 13 or msg.message_type|int == 11 %}autoplay muted loop playsinline{%else%}controls{% endif %}>
|
||||
<source type="{{ msg.mime }}" data-src="{{ msg.data }}" />
|
||||
</video>
|
||||
{% elif "/" in msg.mime %}
|
||||
The file cannot be displayed here, however it should be located at <a href="./{{ msg.data }}">here</a>
|
||||
{% else %}
|
||||
{% filter escape %}{{ msg.data }}{% endfilter %}
|
||||
{% endif %}
|
||||
{% if msg.caption is not none %}
|
||||
{{ msg.caption | urlize(none, true, '_blank') }}
|
||||
{% endif %}
|
||||
{% endif %}
|
||||
{% endif %}
|
||||
</p>
|
||||
<p class="text-[10px] text-[#667781] text-right mt-1">{{ msg.time }}</p>
|
||||
</div>
|
||||
</div>
|
||||
{% else %}
|
||||
<div class="flex justify-start items-center group" id="{{ msg.key_id }}">
|
||||
<div class="bg-white rounded-lg p-2 max-w-[80%] shadow-sm">
|
||||
{% if msg.reply is not none %}
|
||||
<a href="#{{msg.reply}}" target="_self" class="no-base">
|
||||
<div class="mb-2 p-1 bg-whatsapp-chat-light rounded border-l-4 border-whatsapp text-sm reply-box">
|
||||
<p class="text-whatsapp font-medium text-xs">Replying to</p>
|
||||
<p class="text-[#808080] text-xs truncate">
|
||||
{% if msg.quoted_data is not none %}
|
||||
{{msg.quoted_data}}
|
||||
{% else %}
|
||||
this message
|
||||
{% endif %}
|
||||
</p>
|
||||
</div>
|
||||
</a>
|
||||
{% endif %}
|
||||
<p class="text-[#111b21] text-sm">
|
||||
{% if msg.meta == true or msg.media == false and msg.data is none %}
|
||||
<div class="flex justify-center mb-2">
|
||||
<div class="bg-[#FFF3C5] rounded-lg px-3 py-2 text-sm text-[#856404] flex items-center">
|
||||
{% if msg.safe %}
|
||||
{{ msg.data | safe or 'Not supported WhatsApp internal message' }}
|
||||
{% else %}
|
||||
{{ msg.data or 'Not supported WhatsApp internal message' }}
|
||||
{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
{% if msg.caption is not none %}
|
||||
<p>{{ msg.caption | urlize(none, true, '_blank') }}</p>
|
||||
{% endif %}
|
||||
{% else %}
|
||||
{% if msg.media == false %}
|
||||
{{ msg.data | sanitize_except() | urlize(none, true, '_blank') }}
|
||||
{% else %}
|
||||
{% if "image/" in msg.mime %}
|
||||
<a href="{{ msg.data }}">
|
||||
<img src="{{ msg.thumb if msg.thumb is not none else msg.data }}" {{ 'class="sticker"' | safe if msg.sticker }} loading="lazy"/>
|
||||
</a>
|
||||
{% elif "audio/" in msg.mime %}
|
||||
<audio controls="controls" autobuffer="autobuffer">
|
||||
<source src="{{ msg.data }}" />
|
||||
</audio>
|
||||
{% elif "video/" in msg.mime %}
|
||||
<video class="lazy" autobuffer {% if msg.message_type|int == 13 or msg.message_type|int == 11 %}autoplay muted loop playsinline{%else%}controls{% endif %}>
|
||||
<source type="{{ msg.mime }}" data-src="{{ msg.data }}" />
|
||||
</video>
|
||||
{% elif "/" in msg.mime %}
|
||||
The file cannot be displayed here, however it should be located at <a href="./{{ msg.data }}">here</a>
|
||||
{% else %}
|
||||
{% filter escape %}{{ msg.data }}{% endfilter %}
|
||||
{% endif %}
|
||||
{% if msg.caption is not none %}
|
||||
{{ msg.caption | urlize(none, true, '_blank') }}
|
||||
{% endif %}
|
||||
{% endif %}
|
||||
{% endif %}
|
||||
</p>
|
||||
<div class="flex items-baseline text-[10px] text-[#667781] mt-1 gap-2">
|
||||
<span class="flex-shrink-0">
|
||||
{% if msg.sender is not none %}
|
||||
{{ msg.sender }}
|
||||
{% endif %}
|
||||
</span>
|
||||
<span class="flex-grow min-w-[4px]"></span>
|
||||
<span class="flex-shrink-0">{{ msg.time }}</span>
|
||||
</div>
|
||||
</div>
|
||||
<!-- <div class="opacity-0 group-hover:opacity-100 transition-opacity duration-200 relative ml-2">
|
||||
<div class="relative">
|
||||
<div class="relative group/tooltip">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" class="h-5 w-5 text-[#8696a0] hover:text-[#54656f] cursor-pointer" fill="none" viewBox="0 0 24 24" stroke="currentColor">
|
||||
<use href="#info-icon"></use>
|
||||
</svg>
|
||||
<div class="absolute bottom-full info-box-tooltip mb-2 hidden group-hover/tooltip:block z-50">
|
||||
<div class="bg-black text-white text-xs rounded py-1 px-2 whitespace-nowrap">
|
||||
Received at {{msg.received_timestamp or 'unknown'}}
|
||||
</div>
|
||||
<div class="absolute top-full right-3 ml-1 border-4 border-transparent border-t-black"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div> -->
|
||||
</div>
|
||||
{% endif %}
|
||||
{% endfor %}
|
||||
</div>
|
||||
<footer>
|
||||
<h2 class="text-center">
|
||||
{% if not next %}
|
||||
End of History
|
||||
{% endif %}
|
||||
</h2>
|
||||
<br>
|
||||
Portions of this page are reproduced from <a href="https://web.dev/articles/lazy-loading-video">work</a> created and <a href="https://developers.google.com/readme/policies">shared by Google</a> and used according to terms described in the <a href="https://www.apache.org/licenses/LICENSE-2.0">Apache 2.0 License</a>.
|
||||
</footer>
|
||||
<svg style="display: none;">
|
||||
<!-- Tooltip info icon -->
|
||||
<symbol id="info-icon" viewBox="0 0 24 24">
|
||||
<path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M13 16h-1v-4h-1m1-4h.01M21 12a9 9 0 11-18 0 9 9 0 0118 0z" />
|
||||
</symbol>
|
||||
</svg>
|
||||
</div>
|
||||
</article>
|
||||
</body>
|
||||
<script>
|
||||
// Search functionality
|
||||
const searchButton = document.getElementById('searchButton');
|
||||
const mainSearchInput = document.getElementById('mainSearchInput');
|
||||
const closeMainSearch = document.getElementById('closeMainSearch');
|
||||
const mainHeaderSearchInput = document.getElementById('mainHeaderSearchInput');
|
||||
|
||||
// Function to show search input
|
||||
const showSearch = () => {
|
||||
mainSearchInput.classList.add('active');
|
||||
mainHeaderSearchInput.focus();
|
||||
};
|
||||
|
||||
// Function to hide search input
|
||||
const hideSearch = () => {
|
||||
mainSearchInput.classList.remove('active');
|
||||
mainHeaderSearchInput.value = '';
|
||||
};
|
||||
|
||||
// Event listeners
|
||||
searchButton.addEventListener('click', showSearch);
|
||||
closeMainSearch.addEventListener('click', hideSearch);
|
||||
|
||||
// Handle ESC key
|
||||
document.addEventListener('keydown', (event) => {
|
||||
if (event.key === 'Escape' && mainSearchInput.classList.contains('active')) {
|
||||
hideSearch();
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script>
|
||||
document.addEventListener("DOMContentLoaded", function() {
|
||||
var lazyVideos = [].slice.call(document.querySelectorAll("video.lazy"));
|
||||
|
||||
if ("IntersectionObserver" in window) {
|
||||
var lazyVideoObserver = new IntersectionObserver(function(entries, observer) {
|
||||
entries.forEach(function(video) {
|
||||
if (video.isIntersecting) {
|
||||
for (var source in video.target.children) {
|
||||
var videoSource = video.target.children[source];
|
||||
if (typeof videoSource.tagName === "string" && videoSource.tagName === "SOURCE") {
|
||||
videoSource.src = videoSource.dataset.src;
|
||||
}
|
||||
}
|
||||
|
||||
video.target.load();
|
||||
video.target.classList.remove("lazy");
|
||||
lazyVideoObserver.unobserve(video.target);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
lazyVideos.forEach(function(lazyVideo) {
|
||||
lazyVideoObserver.observe(lazyVideo);
|
||||
});
|
||||
}
|
||||
});
|
||||
</script>
|
||||
<script>
|
||||
// Prevent the <base> tag from affecting links with the class "no-base"
|
||||
document.querySelectorAll('.no-base').forEach(link => {
|
||||
link.addEventListener('click', function(event) {
|
||||
const href = this.getAttribute('href');
|
||||
if (href.startsWith('#')) {
|
||||
window.location.hash = href;
|
||||
event.preventDefault();
|
||||
}
|
||||
});
|
||||
});
|
||||
</script>
|
||||
</html>
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 15 KiB |
BIN
Binary file not shown.
|
Before Width: | Height: | Size: 126 KiB After Width: | Height: | Size: 116 KiB |
+710
@@ -0,0 +1,710 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<meta name="title" content="WhatsApp Chat Exporter">
|
||||
<meta name="description" content="Export your WhatsApp conversations from Android and iOS/iPadOS devices to HTML, JSON, or text formats. Supports encrypted backups (Crypt12, Crypt14, Crypt15) and customizable templates.">
|
||||
<meta name="keywords" content="WhatsApp, WhatsApp Chat Exporter, WhatsApp export tool, WhatsApp backup decryption, Crypt12, Crypt14, Crypt15, WhatsApp database parser, WhatsApp chat history, HTML export, JSON export, text export, customizable templates, media handling, vCard import, Python tool, open source, MIT license">
|
||||
<meta name="robots" content="index, follow">
|
||||
<meta name="author" content="KnugiHK">
|
||||
<meta name="license" content="MIT">
|
||||
<meta name="generator" content="Python">
|
||||
<title>WhatsApp Chat Exporter</title>
|
||||
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
|
||||
<style>
|
||||
:root {
|
||||
--primary-color: #128C7E;
|
||||
--secondary-color: #25D366;
|
||||
--dark-color: #075E54;
|
||||
--light-color: #DCF8C6;
|
||||
--text-color: #333;
|
||||
--light-text: #777;
|
||||
--code-bg: #f6f8fa;
|
||||
--border-color: #e1e4e8;
|
||||
}
|
||||
|
||||
* {
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
box-sizing: border-box;
|
||||
}
|
||||
|
||||
body {
|
||||
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
|
||||
line-height: 1.6;
|
||||
color: var(--text-color);
|
||||
background-color: #f9f9f9;
|
||||
}
|
||||
|
||||
.container {
|
||||
max-width: 1200px;
|
||||
margin: 0 auto;
|
||||
padding: 0 20px;
|
||||
}
|
||||
|
||||
header {
|
||||
background-color: var(--primary-color);
|
||||
color: white;
|
||||
padding: 60px 0 40px;
|
||||
text-align: center;
|
||||
box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
|
||||
}
|
||||
|
||||
header h1 {
|
||||
font-size: 2.8rem;
|
||||
margin-bottom: 16px;
|
||||
}
|
||||
|
||||
.badges {
|
||||
margin: 20px 0;
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
flex-wrap: wrap;
|
||||
gap: 10px;
|
||||
}
|
||||
|
||||
.badge {
|
||||
display: inline-block;
|
||||
margin: 5px;
|
||||
}
|
||||
|
||||
.tagline {
|
||||
font-size: 1.2rem;
|
||||
max-width: 800px;
|
||||
margin: 0 auto;
|
||||
padding: 0 20px;
|
||||
}
|
||||
|
||||
.main-content {
|
||||
background: white;
|
||||
padding: 40px 0;
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
.inner-content {
|
||||
padding: 0 30px;
|
||||
max-width: 900px;
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
h2 {
|
||||
color: var(--dark-color);
|
||||
margin: 30px 0 15px;
|
||||
padding-bottom: 8px;
|
||||
border-bottom: 2px solid var(--light-color);
|
||||
font-size: 1.8rem;
|
||||
}
|
||||
|
||||
h3 {
|
||||
color: var(--dark-color);
|
||||
margin: 25px 0 15px;
|
||||
font-size: 1.4rem;
|
||||
}
|
||||
|
||||
h4 {
|
||||
color: var(--dark-color);
|
||||
margin: 20px 0 10px;
|
||||
font-size: 1.2rem;
|
||||
}
|
||||
|
||||
p, ul, ol {
|
||||
margin-bottom: 16px;
|
||||
}
|
||||
|
||||
ul, ol {
|
||||
padding-left: 25px;
|
||||
}
|
||||
|
||||
a {
|
||||
color: var(--primary-color);
|
||||
text-decoration: none;
|
||||
}
|
||||
|
||||
a:hover {
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
.alert {
|
||||
background-color: #f8f9fa;
|
||||
border-left: 4px solid #f0ad4e;
|
||||
padding: 15px;
|
||||
margin-bottom: 20px;
|
||||
border-radius: 3px;
|
||||
}
|
||||
|
||||
.alert--tip {
|
||||
border-color: var(--secondary-color);
|
||||
background-color: rgba(37, 211, 102, 0.1);
|
||||
}
|
||||
|
||||
.alert--note {
|
||||
border-color: #0088cc;
|
||||
background-color: rgba(0, 136, 204, 0.1);
|
||||
}
|
||||
.markdown-alert {
|
||||
background-color: #f8f9fa;
|
||||
border-left: 4px solid #f0ad4e;
|
||||
padding: 15px;
|
||||
margin-bottom: 20px;
|
||||
border-radius: 3px;
|
||||
}
|
||||
|
||||
.markdown-alert-note {
|
||||
border-color: #0088cc;
|
||||
background-color: rgba(0, 136, 204, 0.1);
|
||||
}
|
||||
|
||||
.markdown-alert-tip {
|
||||
border-color: var(--secondary-color);
|
||||
background-color: rgba(37, 211, 102, 0.1);
|
||||
}
|
||||
|
||||
.markdown-alert-important {
|
||||
border-color: #d9534f;
|
||||
background-color: rgba(217, 83, 79, 0.1);
|
||||
}
|
||||
|
||||
.markdown-alert-warning {
|
||||
border-color: #f0ad4e;
|
||||
background-color: rgba(240, 173, 78, 0.1);
|
||||
}
|
||||
|
||||
.markdown-alert-caution {
|
||||
border-color: #ff9800;
|
||||
background-color: rgba(255, 152, 0, 0.1);
|
||||
}
|
||||
|
||||
.markdown-alert p {
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
.markdown-alert-title {
|
||||
font-weight: 600;
|
||||
margin-bottom: 8px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 8px;
|
||||
}
|
||||
pre {
|
||||
background-color: var(--code-bg);
|
||||
border-radius: 6px;
|
||||
padding: 16px;
|
||||
overflow-x: auto;
|
||||
margin: 16px 0;
|
||||
border: 1px solid var(--border-color);
|
||||
}
|
||||
|
||||
code {
|
||||
font-family: SFMono-Regular, Consolas, Liberation Mono, Menlo, monospace;
|
||||
font-size: 85%;
|
||||
background-color: var(--code-bg);
|
||||
padding: 0.2em 0.4em;
|
||||
border-radius: 3px;
|
||||
}
|
||||
|
||||
pre code {
|
||||
padding: 0;
|
||||
background-color: transparent;
|
||||
}
|
||||
|
||||
.screenshot {
|
||||
max-width: 100%;
|
||||
border-radius: 8px;
|
||||
box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
|
||||
margin: 20px 0;
|
||||
border: 1px solid var(--border-color);
|
||||
}
|
||||
|
||||
.feature-grid {
|
||||
display: grid;
|
||||
grid-template-columns: repeat(auto-fill, minmax(280px, 1fr));
|
||||
gap: 20px;
|
||||
margin: 30px 0;
|
||||
}
|
||||
|
||||
.feature-card {
|
||||
background: white;
|
||||
border-radius: 8px;
|
||||
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);
|
||||
padding: 20px;
|
||||
border: 1px solid var(--border-color);
|
||||
transition: transform 0.3s ease;
|
||||
}
|
||||
|
||||
.feature-card:hover {
|
||||
transform: translateY(-5px);
|
||||
box-shadow: 0 5px 15px rgba(0, 0, 0, 0.1);
|
||||
}
|
||||
|
||||
.feature-icon {
|
||||
font-size: 2rem;
|
||||
color: var(--primary-color);
|
||||
margin-bottom: 15px;
|
||||
}
|
||||
|
||||
.feature-title {
|
||||
font-weight: 600;
|
||||
margin-bottom: 10px;
|
||||
}
|
||||
|
||||
footer {
|
||||
background-color: var(--dark-color);
|
||||
color: white;
|
||||
text-align: center;
|
||||
padding: 30px 0;
|
||||
margin-top: 50px;
|
||||
}
|
||||
|
||||
.btn {
|
||||
display: inline-block;
|
||||
background-color: var(--primary-color);
|
||||
color: white;
|
||||
padding: 10px 20px;
|
||||
border-radius: 4px;
|
||||
text-decoration: none;
|
||||
font-weight: 500;
|
||||
transition: background-color 0.3s ease;
|
||||
margin: 5px;
|
||||
}
|
||||
|
||||
.btn:hover {
|
||||
background-color: var(--dark-color);
|
||||
text-decoration: none;
|
||||
}
|
||||
|
||||
.btn-secondary {
|
||||
background-color: white;
|
||||
color: var(--primary-color);
|
||||
border: 1px solid var(--primary-color);
|
||||
}
|
||||
|
||||
.btn-secondary:hover {
|
||||
background-color: var(--light-color);
|
||||
color: var(--dark-color);
|
||||
}
|
||||
|
||||
.action-buttons {
|
||||
margin: 30px 0;
|
||||
text-align: center;
|
||||
}
|
||||
|
||||
.table-of-contents {
|
||||
background-color: #f8f9fa;
|
||||
border: 1px solid var(--border-color);
|
||||
border-radius: 6px;
|
||||
padding: 15px 25px;
|
||||
margin: 30px 0;
|
||||
}
|
||||
|
||||
.table-of-contents h3 {
|
||||
margin-top: 0;
|
||||
margin-bottom: 10px;
|
||||
}
|
||||
|
||||
.table-of-contents ul {
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
.help-text {
|
||||
color: var(--light-text);
|
||||
font-size: 0.9rem;
|
||||
}
|
||||
|
||||
.device-section {
|
||||
padding: 15px;
|
||||
border: 1px solid var(--border-color);
|
||||
border-radius: 6px;
|
||||
margin-bottom: 20px;
|
||||
background-color: #fff;
|
||||
}
|
||||
|
||||
@media (max-width: 768px) {
|
||||
header {
|
||||
padding: 40px 0 30px;
|
||||
}
|
||||
|
||||
header h1 {
|
||||
font-size: 2.2rem;
|
||||
}
|
||||
|
||||
.tagline {
|
||||
font-size: 1.1rem;
|
||||
}
|
||||
|
||||
.feature-grid {
|
||||
grid-template-columns: 1fr;
|
||||
}
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<header>
|
||||
<div class="container">
|
||||
<h1>WhatsApp Chat Exporter</h1>
|
||||
<div class="badges">
|
||||
<a href="https://pypi.org/project/whatsapp-chat-exporter/" class="badge"><img src="https://img.shields.io/pypi/v/whatsapp-chat-exporter?label=Latest%20in%20PyPI" alt="Latest in PyPI"></a>
|
||||
<a href="https://github.com/KnugiHK/WhatsApp-Chat-Exporter/blob/main/LICENSE" class="badge"><img src="https://img.shields.io/pypi/l/whatsapp-chat-exporter?color=427B93" alt="License MIT"></a>
|
||||
<a href="https://pypi.org/project/Whatsapp-Chat-Exporter/" class="badge"><img src="https://img.shields.io/pypi/pyversions/Whatsapp-Chat-Exporter" alt="Python"></a>
|
||||
<a href="https://matrix.to/#/#wtsexporter:matrix.org" class="badge"><img src="https://img.shields.io/matrix/wtsexporter:matrix.org.svg?label=Matrix%20Chat%20Room" alt="Matrix Chat Room"></a>
|
||||
</div>
|
||||
<p class="tagline">A customizable Android and iPhone Whatsapp database parser that will give you the history of your Whatsapp conversations in HTML and JSON</p>
|
||||
<div class="action-buttons">
|
||||
<a href="https://github.com/KnugiHK/WhatsApp-Chat-Exporter" class="btn"><i class="fab fa-github"></i> GitHub</a>
|
||||
<a href="https://pypi.org/project/whatsapp-chat-exporter/" class="btn btn-secondary"><i class="fab fa-python"></i> PyPI</a>
|
||||
</div>
|
||||
</div>
|
||||
</header>
|
||||
|
||||
<div class="main-content">
|
||||
<div class="inner-content">
|
||||
<section id="features">
|
||||
<h2>Key Features</h2>
|
||||
|
||||
<div class="feature-grid">
|
||||
<div class="feature-card">
|
||||
<div class="feature-icon"><i class="fas fa-mobile-alt"></i></div>
|
||||
<h3 class="feature-title">Cross-Platform</h3>
|
||||
<p>Support for both Android and iOS/iPadOS WhatsApp databases</p>
|
||||
</div>
|
||||
|
||||
<div class="feature-card">
|
||||
<div class="feature-icon"><i class="fas fa-lock"></i></div>
|
||||
<h3 class="feature-title">Backup Decryption</h3>
|
||||
<p>Support for Crypt12, Crypt14, and Crypt15 (End-to-End) encrypted backups</p>
|
||||
</div>
|
||||
|
||||
<div class="feature-card">
|
||||
<div class="feature-icon"><i class="fas fa-file-export"></i></div>
|
||||
<h3 class="feature-title">Multiple Formats</h3>
|
||||
<p>Export your chats in HTML, JSON, and text formats</p>
|
||||
</div>
|
||||
|
||||
<div class="feature-card">
|
||||
<div class="feature-icon"><i class="fas fa-paint-brush"></i></div>
|
||||
<h3 class="feature-title">Customizable</h3>
|
||||
<p>Use custom HTML templates and styling for your chat exports</p>
|
||||
</div>
|
||||
|
||||
<div class="feature-card">
|
||||
<div class="feature-icon"><i class="fas fa-images"></i></div>
|
||||
<h3 class="feature-title">Media Support</h3>
|
||||
<p>Properly handles and organizes your media files in the exports</p>
|
||||
</div>
|
||||
|
||||
<div class="feature-card">
|
||||
<div class="feature-icon"><i class="fas fa-filter"></i></div>
|
||||
<h3 class="feature-title">Filtering Options</h3>
|
||||
<p>Filter chats by date, phone number, and more</p>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<div class="readme-content">
|
||||
<h1>Whatsapp-Chat-Exporter</h1>
|
||||
<p>A customizable Android and iPhone Whatsapp database parser that will give you the history of your Whatsapp conversations in HTML and JSON. Inspired by <a href="https://telegram.org/blog/export-and-more">Telegram Chat Export Tool</a>. </p>
|
||||
<div class="markdown-alert markdown-alert-tip">
|
||||
<p class="markdown-alert-title"><svg class="octicon octicon-light-bulb mr-2" viewBox="0 0 16 16" width="16" height="16" aria-hidden="true"><path d="M8 1.5c-2.363 0-4 1.69-4 3.75 0 .984.424 1.625.984 2.304l.214.253c.223.264.47.556.673.848.284.411.537.896.621 1.49a.75.75 0 0 1-1.484.211c-.04-.282-.163-.547-.37-.847a8.456 8.456 0 0 0-.542-.68c-.084-.1-.173-.205-.268-.32C3.201 7.75 2.5 6.766 2.5 5.25 2.5 2.31 4.863 0 8 0s5.5 2.31 5.5 5.25c0 1.516-.701 2.5-1.328 3.259-.095.115-.184.22-.268.319-.207.245-.383.453-.541.681-.208.3-.33.565-.37.847a.751.751 0 0 1-1.485-.212c.084-.593.337-1.078.621-1.489.203-.292.45-.584.673-.848.075-.088.147-.173.213-.253.561-.679.985-1.32.985-2.304 0-2.06-1.637-3.75-4-3.75ZM5.75 12h4.5a.75.75 0 0 1 0 1.5h-4.5a.75.75 0 0 1 0-1.5ZM6 15.25a.75.75 0 0 1 .75-.75h2.5a.75.75 0 0 1 0 1.5h-2.5a.75.75 0 0 1-.75-.75Z"></path></svg>Tip</p>
|
||||
<p>If you plan to uninstall WhatsApp or delete your WhatsApp account, please make a backup of your WhatsApp database. You may want to use this exporter again on the same database in the future as the exporter develops.</p>
|
||||
</div>
|
||||
<p>If you would like to support this project, all you need to do is to contribute or share this project! If you think otherwise and want to make a donation, please refer to the <a href="https://blog.knugi.com/DONATE.html">Donation Guide</a>.</p>
|
||||
<p>To contribute, see the <a href="https://github.com/KnugiHK/WhatsApp-Chat-Exporter/blob/main/CONTRIBUTING.md">Contributing Guidelines</a>.</p>
|
||||
<h1>Usage</h1>
|
||||
<div class="markdown-alert markdown-alert-note">
|
||||
<p class="markdown-alert-title"><svg class="octicon octicon-info mr-2" viewBox="0 0 16 16" width="16" height="16" aria-hidden="true"><path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8Zm8-6.5a6.5 6.5 0 1 0 0 13 6.5 6.5 0 0 0 0-13ZM6.5 7.75A.75.75 0 0 1 7.25 7h1a.75.75 0 0 1 .75.75v2.75h.25a.75.75 0 0 1 0 1.5h-2a.75.75 0 0 1 0-1.5h.25v-2h-.25a.75.75 0 0 1-.75-.75ZM8 6a1 1 0 1 1 0-2 1 1 0 0 1 0 2Z"></path></svg>Note</p>
|
||||
<p>Usage in README may be removed in the future. Check the usage in <a href="https://github.com/KnugiHK/Whatsapp-Chat-Exporter/wiki">Wiki</a></p>
|
||||
<p>Click <a href="https://github.com/KnugiHK/WhatsApp-Chat-Exporter/wiki/Android-Usage#crypt15-end-to-end-encrypted-backup">here</a> for the most trivia way for exporting from Android</p>
|
||||
</div>
|
||||
<p>First, install the exporter by:</p>
|
||||
<pre><code class="language-shell">pip install whatsapp-chat-exporter
|
||||
pip install whatsapp-chat-exporter[android_backup] :; # Optional, if you want it to support decrypting Android WhatsApp backup.
|
||||
</code></pre>
|
||||
<p>Then, create a working directory in somewhere you want</p>
|
||||
<pre><code class="language-shell">mkdir working_wts
|
||||
cd working_wts
|
||||
</code></pre>
|
||||
<div class="markdown-alert markdown-alert-tip">
|
||||
<p class="markdown-alert-title"><svg class="octicon octicon-light-bulb mr-2" viewBox="0 0 16 16" width="16" height="16" aria-hidden="true"><path d="M8 1.5c-2.363 0-4 1.69-4 3.75 0 .984.424 1.625.984 2.304l.214.253c.223.264.47.556.673.848.284.411.537.896.621 1.49a.75.75 0 0 1-1.484.211c-.04-.282-.163-.547-.37-.847a8.456 8.456 0 0 0-.542-.68c-.084-.1-.173-.205-.268-.32C3.201 7.75 2.5 6.766 2.5 5.25 2.5 2.31 4.863 0 8 0s5.5 2.31 5.5 5.25c0 1.516-.701 2.5-1.328 3.259-.095.115-.184.22-.268.319-.207.245-.383.453-.541.681-.208.3-.33.565-.37.847a.751.751 0 0 1-1.485-.212c.084-.593.337-1.078.621-1.489.203-.292.45-.584.673-.848.075-.088.147-.173.213-.253.561-.679.985-1.32.985-2.304 0-2.06-1.637-3.75-4-3.75ZM5.75 12h4.5a.75.75 0 0 1 0 1.5h-4.5a.75.75 0 0 1 0-1.5ZM6 15.25a.75.75 0 0 1 .75-.75h2.5a.75.75 0 0 1 0 1.5h-2.5a.75.75 0 0 1-.75-.75Z"></path></svg>Tip</p>
|
||||
<p>macOS users should grant <em>Full Disk Access</em> to Terminal in the <em>Security & Privacy</em> settings before using the exporter.</p>
|
||||
</div>
|
||||
<h2>Working with Android</h2>
|
||||
<h3>Unencrypted WhatsApp database</h3>
|
||||
<p>Extract the WhatsApp database with whatever means, one possible means is to use the <a href="https://github.com/KnugiHK/WhatsApp-Key-DB-Extractor">WhatsApp-Key-DB-Extractor</a>. Note that the extractor only works on Android 4.0 to 13.</p>
|
||||
<p>After you obtain your WhatsApp database, copy the WhatsApp database and media folder to the working directory. The database is called msgstore.db. If you also want the name of your contacts, get the contact database, which is called wa.db. And copy the WhatsApp (Media) directory from your phone directly.</p>
|
||||
<p>And now, you should have something like this in the working directory.</p>
|
||||
<p><img src="imgs/android_structure.png" alt="Android folder structure"></p>
|
||||
<h4>Extracting</h4>
|
||||
<p>Simply invoke the following command from shell.</p>
|
||||
<pre><code class="language-sh">wtsexporter -a
|
||||
</code></pre>
|
||||
<h4>Enriching Contact from vCard</h4>
|
||||
<p>The default WhatsApp contact database typically contained contact names extracted from your phone, which the exporter used to map your chats. However, in some reported cases, the database may have never been populated. In such case, you can export your contacts to a vCard file from your phone or a cloud provider like Google Contacts. Then, install the necessary dependency and run the following command from the shell:</p>
|
||||
<pre><code class="language-sh">pip install whatsapp-chat-exporter["vcards"]
|
||||
wtsexporter -a --enrich-from-vcards contacts.vcf --default-country-code 852
|
||||
</code></pre>
|
||||
<h3>Encrypted Android WhatsApp Backup</h3>
|
||||
<p>In order to support the decryption, install pycryptodome if it is not installed</p>
|
||||
<pre><code class="language-sh">pip install pycryptodome # Or
|
||||
pip install whatsapp-chat-exporter["android_backup"] # install along with this software
|
||||
</code></pre>
|
||||
<div class="markdown-alert markdown-alert-tip">
|
||||
<p class="markdown-alert-title"><svg class="octicon octicon-light-bulb mr-2" viewBox="0 0 16 16" width="16" height="16" aria-hidden="true"><path d="M8 1.5c-2.363 0-4 1.69-4 3.75 0 .984.424 1.625.984 2.304l.214.253c.223.264.47.556.673.848.284.411.537.896.621 1.49a.75.75 0 0 1-1.484.211c-.04-.282-.163-.547-.37-.847a8.456 8.456 0 0 0-.542-.68c-.084-.1-.173-.205-.268-.32C3.201 7.75 2.5 6.766 2.5 5.25 2.5 2.31 4.863 0 8 0s5.5 2.31 5.5 5.25c0 1.516-.701 2.5-1.328 3.259-.095.115-.184.22-.268.319-.207.245-.383.453-.541.681-.208.3-.33.565-.37.847a.751.751 0 0 1-1.485-.212c.084-.593.337-1.078.621-1.489.203-.292.45-.584.673-.848.075-.088.147-.173.213-.253.561-.679.985-1.32.985-2.304 0-2.06-1.637-3.75-4-3.75ZM5.75 12h4.5a.75.75 0 0 1 0 1.5h-4.5a.75.75 0 0 1 0-1.5ZM6 15.25a.75.75 0 0 1 .75-.75h2.5a.75.75 0 0 1 0 1.5h-2.5a.75.75 0 0 1-.75-.75Z"></path></svg>Tip</p>
|
||||
<p>Crypt15 is now the easiest way to decrypt a backup. If you have the 32 bytes hex key generated when you enable End-to-End encrypted backup, you can use it to decrypt the backup. If you do not have the 32 bytes hex key, you can still use the key file extracted just like extacting key file for Crypt12 and Crypt14 to decrypt the backup.</p>
|
||||
</div>
|
||||
<h4>Crypt12 or Crypt14</h4>
|
||||
<p>You will need the decryption key file from your phone. If you have root access, you can find it as <code>/data/data/com.whatsapp/files/key</code>. Otherwise, if you used WhatsApp-Key-DB-Extractor before, it will appear in the WhatsApp backup directory as <code>WhatsApp/Databases/.nomedia</code>.</p>
|
||||
<p>Place the decryption key file (key) and the encrypted WhatsApp Backup (msgstore.db.crypt14) in the working directory. If you also want the name of your contacts, get the contact database, which is called wa.db. And copy the WhatsApp (Media) directory from your phone directly.</p>
|
||||
<p>And now, you should have something like this in the working directory.</p>
|
||||
<p><img src="imgs/android_structure_backup.png" alt="Android folder structure with WhatsApp Backup"></p>
|
||||
<h4>Extracting</h4>
|
||||
<p>Simply invoke the following command from shell.</p>
|
||||
<pre><code class="language-sh">wtsexporter -a -k key -b msgstore.db.crypt14
|
||||
</code></pre>
|
||||
<h4>Crypt15 (End-to-End Encrypted Backup)</h4>
|
||||
<p>To support Crypt15 backup, install javaobj-py3 if it is not installed</p>
|
||||
<pre><code class="language-sh">pip install javaobj-py3 # Or
|
||||
pip install whatsapp-chat-exporter["crypt15"] # install along with this software
|
||||
</code></pre>
|
||||
<p>Before proceeding with this method, you must first create an end-to-end encrypted backup. For detailed instructions, refer to <a href="https://faq.whatsapp.com/490592613091019">WhatsApp's help center</a>.</p>
|
||||
<p>Once you have copied the backup files to your computer, place the encrypted WhatsApp backup file (msgstore.db.crypt15) into the working directory. If you also wish to include your contacts' names, obtain the contact database file, named wa.db. Additionally, copy the WhatsApp Media folder directly from your phone.</p>
|
||||
<p>If you do not have the 32 bytes hex key (64 hexdigits), place the decryption key file (encrypted_backup.key) extracted from Android. If you gave the 32 bytes hex key, simply put the key in the shell.</p>
|
||||
<p>Now, you should have something like this in the working directory (if you do not have 32 bytes hex key).</p>
|
||||
<p><img src="imgs/android_structure_backup_crypt15.png" alt="Android folder structure with WhatsApp Crypt15 Backup"></p>
|
||||
<h5>Extracting</h5>
|
||||
<p>If you do not have 32 bytes hex key but have the key file available, simply invoke the following command from shell.</p>
|
||||
<pre><code class="language-sh">wtsexporter -a -k encrypted_backup.key -b msgstore.db.crypt15
|
||||
</code></pre>
|
||||
<p>If you have the 32 bytes hex key, simply put the hex key in the -k option and invoke the command from shell like this:</p>
|
||||
<pre><code class="language-sh">wtsexporter -a -k 133735053b5204b08e5c3823423399aa30ff061435ab89bc4e6713969cda1337 -b msgstore.db.crypt15
|
||||
</code></pre>
|
||||
<h2>Working with iOS/iPadOS (iPhone or iPad)</h2>
|
||||
<p>Do an iPhone/iPad Backup with iTunes/Finder first.</p>
|
||||
<ul>
|
||||
<li>iPhone backup on Mac: <a href="https://support.apple.com/HT211229">https://support.apple.com/HT211229</a></li>
|
||||
<li>iPhone backup on Windows: <a href="https://support.apple.com/HT212156">https://support.apple.com/HT212156</a></li>
|
||||
<li>iPad backup: <a href="https://support.apple.com/guide/ipad/ipad9a74df05xx/ipados">https://support.apple.com/guide/ipad/ipad9a74df05xx/ipados</a></li>
|
||||
</ul>
|
||||
<h3>Encrypted iOS/iPadOS Backup</h3>
|
||||
<div class="markdown-alert markdown-alert-note">
|
||||
<p class="markdown-alert-title"><svg class="octicon octicon-info mr-2" viewBox="0 0 16 16" width="16" height="16" aria-hidden="true"><path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8Zm8-6.5a6.5 6.5 0 1 0 0 13 6.5 6.5 0 0 0 0-13ZM6.5 7.75A.75.75 0 0 1 7.25 7h1a.75.75 0 0 1 .75.75v2.75h.25a.75.75 0 0 1 0 1.5h-2a.75.75 0 0 1 0-1.5h.25v-2h-.25a.75.75 0 0 1-.75-.75ZM8 6a1 1 0 1 1 0-2 1 1 0 0 1 0 2Z"></path></svg>Note</p>
|
||||
<p>If you are working on unencrypted iOS/iPadOS backup, skip this.</p>
|
||||
</div>
|
||||
<p>If you want to work on an encrypted iOS/iPadOS Backup, you should install <code>iphone_backup_decrypt</code> from <a href="https://github.com/KnugiHK/iphone_backup_decrypt">KnugiHK/iphone_backup_decrypt</a> before you run the <code>ios_media_handler.py</code>.</p>
|
||||
<pre><code class="language-sh">pip install git+https://github.com/KnugiHK/iphone_backup_decrypt
|
||||
</code></pre>
|
||||
<div class="markdown-alert markdown-alert-note">
|
||||
<p class="markdown-alert-title"><svg class="octicon octicon-info mr-2" viewBox="0 0 16 16" width="16" height="16" aria-hidden="true"><path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8Zm8-6.5a6.5 6.5 0 1 0 0 13 6.5 6.5 0 0 0 0-13ZM6.5 7.75A.75.75 0 0 1 7.25 7h1a.75.75 0 0 1 .75.75v2.75h.25a.75.75 0 0 1 0 1.5h-2a.75.75 0 0 1 0-1.5h.25v-2h-.25a.75.75 0 0 1-.75-.75ZM8 6a1 1 0 1 1 0-2 1 1 0 0 1 0 2Z"></path></svg>Note</p>
|
||||
<p>You will need to disable the built-in end-to-end encryption for WhatsApp backups. See <a href="https://faq.whatsapp.com/490592613091019#turn-off-end-to-end-encrypted-backup">WhatsApp's FAQ</a> for how to do it.</p>
|
||||
</div>
|
||||
<h3>Extracting</h3>
|
||||
<p>To extract messages from iOS/iPadOS backups, run the following command in the shell, making sure to replace the username and device ID with the correct values. Keep in mind that there are at least two possible paths for the backups on Windows.</p>
|
||||
<h4>Windows</h4>
|
||||
<pre><code class="language-powershell"># Possible path one
|
||||
wtsexporter -i -b "C:\Users\[Username]\AppData\Roaming\Apple Computer\MobileSync\Backup\[device id]"
|
||||
|
||||
# Possible path two
|
||||
wtsexporter -i -b "C:\Users\[Username]\Apple\MobileSync\Backup\[device id]"
|
||||
</code></pre>
|
||||
<h4>Mac</h4>
|
||||
<pre><code class="language-sh">wtsexporter -i -b ~/Library/Application\ Support/MobileSync/Backup/[device id]
|
||||
</code></pre>
|
||||
<h2>Results</h2>
|
||||
<p>After extracting, you will get this:</p>
|
||||
<p><img src="imgs/pm.png" alt="Private Message"></p>
|
||||
<h2>Working with Business</h2>
|
||||
<p>If you are working with WhatsApp Business, add the <code>--business</code> flag to the command</p>
|
||||
<pre><code class="language-sh">wtsexporter -a --business ...other flags
|
||||
wtsexporter -i --business ...other flags
|
||||
</code></pre>
|
||||
<h2>More options</h2>
|
||||
<p>Invoke the wtsexporter with --help option will show you all options available.</p>
|
||||
<pre><code class="language-sh">> wtsexporter --help
|
||||
usage: wtsexporter [-h] [--debug] [-a] [-i] [-e EXPORTED] [-w WA] [-m MEDIA] [-b BACKUP] [-d DB]
|
||||
[-k [KEY]] [--call-db [CALL_DB_IOS]] [--wab WAB] [-o OUTPUT] [-j [JSON]]
|
||||
[--txt [TEXT_FORMAT]] [--no-html] [--size [SIZE]] [--no-reply] [--avoid-encoding-json]
|
||||
[--pretty-print-json [PRETTY_PRINT_JSON]] [--tg] [--per-chat] [--import] [-t TEMPLATE]
|
||||
[--offline OFFLINE] [--no-avatar] [--old-theme] [--headline HEADLINE] [-c]
|
||||
[--create-separated-media] [--time-offset {-12 to 14}] [--date DATE]
|
||||
[--date-format FORMAT] [--include [phone number ...]] [--exclude [phone number ...]]
|
||||
[--dont-filter-empty] [--enrich-from-vcards ENRICH_FROM_VCARDS]
|
||||
[--default-country-code DEFAULT_COUNTRY_CODE] [--incremental-merge]
|
||||
[--source-dir SOURCE_DIR] [--target-dir TARGET_DIR] [-s] [--check-update]
|
||||
[--check-update-pre] [--assume-first-as-me] [--business]
|
||||
[--decrypt-chunk-size DECRYPT_CHUNK_SIZE]
|
||||
[--max-bruteforce-worker MAX_BRUTEFORCE_WORKER] [--no-banner] [--fix-dot-files]
|
||||
|
||||
A customizable Android and iOS/iPadOS WhatsApp database parser that will give you the history of your
|
||||
WhatsApp conversations in HTML and JSON. Android Backup Crypt12, Crypt14 and Crypt15 supported.
|
||||
|
||||
options:
|
||||
-h, --help show this help message and exit
|
||||
--debug Enable debug mode
|
||||
|
||||
Device Type:
|
||||
-a, --android Define the target as Android
|
||||
-i, --ios Define the target as iPhone/iPad
|
||||
-e, --exported EXPORTED
|
||||
Define the target as exported chat file and specify the path to the file
|
||||
|
||||
Input Files:
|
||||
-w, --wa WA Path to contact database (default: wa.db/ContactsV2.sqlite)
|
||||
-m, --media MEDIA Path to WhatsApp media folder (default: WhatsApp)
|
||||
-b, --backup BACKUP Path to Android (must be used together with -k)/iOS WhatsApp backup
|
||||
-d, --db DB Path to database file (default:
|
||||
msgstore.db/7c7fba66680ef796b916b067077cc246adacf01d)
|
||||
-k, --key [KEY] Path to key file. If this option is set for crypt15 backup but nothing is
|
||||
specified, you will be prompted to enter the key.
|
||||
--call-db [CALL_DB_IOS]
|
||||
Path to call database (default: 1b432994e958845fffe8e2f190f26d1511534088) iOS only
|
||||
--wab, --wa-backup WAB
|
||||
Path to contact database in crypt15 format
|
||||
|
||||
Output Options:
|
||||
-o, --output OUTPUT Output to specific directory (default: result)
|
||||
-j, --json [JSON] Save the result to a single JSON file (default if present: result.json)
|
||||
--txt [TEXT_FORMAT] Export chats in text format similar to what WhatsApp officially provided (default
|
||||
if present: result/)
|
||||
--no-html Do not output html files
|
||||
--size, --output-size, --split [SIZE]
|
||||
Maximum (rough) size of a single output file in bytes, 0 for auto
|
||||
--no-reply Do not process replies (iOS only) (default: handle replies)
|
||||
|
||||
JSON Options:
|
||||
--avoid-encoding-json
|
||||
Don't encode non-ascii characters in the output JSON files
|
||||
--pretty-print-json [PRETTY_PRINT_JSON]
|
||||
Pretty print the output JSON.
|
||||
--tg, --telegram Output the JSON in a format compatible with Telegram export (implies json-per-
|
||||
chat)
|
||||
--per-chat Output the JSON file per chat
|
||||
--import Import JSON file and convert to HTML output
|
||||
|
||||
HTML Options:
|
||||
-t, --template TEMPLATE
|
||||
Path to custom HTML template
|
||||
--offline OFFLINE Relative path to offline static files
|
||||
--no-avatar Do not render avatar in HTML output
|
||||
--old-theme Use the old Telegram-alike theme
|
||||
--headline HEADLINE The custom headline for the HTML output. Use '??' as a placeholder for the chat
|
||||
name
|
||||
|
||||
Media Handling:
|
||||
-c, --move-media Move the media directory to output directory if the flag is set, otherwise copy it
|
||||
--create-separated-media
|
||||
Create a copy of the media seperated per chat in <MEDIA>/separated/ directory
|
||||
|
||||
Filtering Options:
|
||||
--time-offset {-12 to 14}
|
||||
Offset in hours (-12 to 14) for time displayed in the output
|
||||
--date DATE The date filter in specific format (inclusive)
|
||||
--date-format FORMAT The date format for the date filter
|
||||
--include [phone number ...]
|
||||
Include chats that match the supplied phone number
|
||||
--exclude [phone number ...]
|
||||
Exclude chats that match the supplied phone number
|
||||
--dont-filter-empty By default, the exporter will not render chats with no valid message. Setting this
|
||||
flag will cause the exporter to render those. This is useful if chat(s) are
|
||||
missing from the output
|
||||
|
||||
Contact Enrichment:
|
||||
--enrich-from-vcards ENRICH_FROM_VCARDS
|
||||
Path to an exported vcf file from Google contacts export. Add names missing from
|
||||
WhatsApp's default database
|
||||
--default-country-code DEFAULT_COUNTRY_CODE
|
||||
Use with --enrich-from-vcards. When numbers in the vcf file does not have a
|
||||
country code, this will be used. 1 is for US, 66 for Thailand etc. Most likely use
|
||||
the number of your own country
|
||||
|
||||
Incremental Merging:
|
||||
--incremental-merge Performs an incremental merge of two exports. Requires setting both --source-dir
|
||||
and --target-dir. The chats (JSON files only) and media from the source directory
|
||||
will be merged into the target directory. No chat messages or media will be
|
||||
deleted from the target directory; only new chat messages and media will be added
|
||||
to it. This enables chat messages and media to be deleted from the device to free
|
||||
up space, while ensuring they are preserved in the exported backups.
|
||||
--source-dir SOURCE_DIR
|
||||
Sets the source directory. Used for performing incremental merges.
|
||||
--target-dir TARGET_DIR
|
||||
Sets the target directory. Used for performing incremental merges.
|
||||
|
||||
Miscellaneous:
|
||||
-s, --showkey Show the HEX key used to decrypt the database
|
||||
--check-update Check for updates (require Internet access)
|
||||
--check-update-pre Check for updates including pre-releases (require Internet access)
|
||||
--assume-first-as-me Assume the first message in a chat as sent by me (must be used together with -e)
|
||||
--business Use Whatsapp Business default files (iOS only)
|
||||
--decrypt-chunk-size DECRYPT_CHUNK_SIZE
|
||||
Specify the chunk size for decrypting iOS backup, which may affect the decryption
|
||||
speed.
|
||||
--max-bruteforce-worker MAX_BRUTEFORCE_WORKER
|
||||
Specify the maximum number of worker for bruteforce decryption.
|
||||
--no-banner Do not show the banner
|
||||
--fix-dot-files Fix files with a dot at the end of their name (allowing the outputs be stored in
|
||||
FAT filesystems)
|
||||
|
||||
WhatsApp Chat Exporter: 0.13.0 Licensed with MIT. See https://wts.knugi.dev/docs?dest=osl for all open
|
||||
source licenses.
|
||||
</code></pre>
|
||||
<h1>Verifying Build Integrity</h1>
|
||||
<p>To ensure that the binaries provided in the releases were built directly from this source code via GitHub Actions and have not been tampered with, GitHub Artifact Attestations is used. You can verify the authenticity of any pre-built binaries using the GitHub CLI.</p>
|
||||
<div class="markdown-alert markdown-alert-note">
|
||||
<p class="markdown-alert-title"><svg class="octicon octicon-info mr-2" viewBox="0 0 16 16" width="16" height="16" aria-hidden="true"><path d="M0 8a8 8 0 1 1 16 0A8 8 0 0 1 0 8Zm8-6.5a6.5 6.5 0 1 0 0 13 6.5 6.5 0 0 0 0-13ZM6.5 7.75A.75.75 0 0 1 7.25 7h1a.75.75 0 0 1 .75.75v2.75h.25a.75.75 0 0 1 0 1.5h-2a.75.75 0 0 1 0-1.5h.25v-2h-.25a.75.75 0 0 1-.75-.75ZM8 6a1 1 0 1 1 0-2 1 1 0 0 1 0 2Z"></path></svg>Note</p>
|
||||
<p>Requires version 0.13.0 or newer. Legacy binaries are unsupported.</p>
|
||||
</div>
|
||||
<h3>Using Bash (Linux/WSL/macOS)</h3>
|
||||
<pre><code class="language-bash">for file in wtsexporter*; do ; gh attestation verify "$file" -R KnugiHK/WhatsApp-Chat-Exporter; done
|
||||
</code></pre>
|
||||
<h3>Using PowerShell (Windows)</h3>
|
||||
<pre><code class="language-powershell">gci "wtsexporter*" | % { gh attestation verify $_.FullName -R KnugiHK/WhatsApp-Chat-Exporter }
|
||||
</code></pre>
|
||||
<h1>Python Support Policy</h1>
|
||||
<p>This project officially supports all non-EOL (End-of-Life) versions of Python. Once a Python version reaches EOL, it is dropped in the next release. See <a href="https://devguide.python.org/versions/">Python's EOL Schedule</a>.</p>
|
||||
<h1>Legal Stuff & Disclaimer</h1>
|
||||
<p>This is a MIT licensed project.</p>
|
||||
<p>The Telegram Desktop's export is the reference for whatsapp.html in this repo.</p>
|
||||
<p><code>bplist.py</code> was released by Vladimir "Farcaller" Pouzanov under MIT license.</p>
|
||||
<p>Please also refer to any files prefixed with <code>LICENSE</code> to obtain copies of the various licenses.</p>
|
||||
<p>WhatsApp Chat Exporter is not affiliated, associated, authorized, endorsed by, or in any way officially connected with the WhatsApp LLC, or any of its subsidiaries or its affiliates. The official WhatsApp LLC website can be found at <a href="https://www.whatsapp.com/">https://www.whatsapp.com/</a>.</p>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
<div class="action-buttons">
|
||||
<a href="https://github.com/KnugiHK/WhatsApp-Chat-Exporter" class="btn"><i class="fab fa-github"></i> View on GitHub</a>
|
||||
<a href="https://pypi.org/project/whatsapp-chat-exporter/" class="btn btn-secondary"><i class="fab fa-python"></i> PyPI Package</a>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<footer>
|
||||
<div class="container">
|
||||
<p>© 2021-2026 WhatsApp Chat Exporter</p>
|
||||
<p>Licensed under MIT License</p>
|
||||
<p>
|
||||
<a href="https://github.com/KnugiHK/WhatsApp-Chat-Exporter" style="color: white; margin: 0 10px;"><i class="fab fa-github fa-lg"></i></a>
|
||||
<a href="https://matrix.to/#/#wtsexporter:matrix.org" style="color: white; margin: 0 10px;"><i class="fas fa-comments fa-lg"></i></a>
|
||||
</p>
|
||||
<p><small>Last updated: 5/18/2026</small></p>
|
||||
</div>
|
||||
</footer>
|
||||
|
||||
<script>
|
||||
// Simple script to handle smooth scrolling for anchor links
|
||||
document.querySelectorAll('a[href^="#"]').forEach(anchor => {
|
||||
anchor.addEventListener('click', function(e) {
|
||||
e.preventDefault();
|
||||
|
||||
const targetId = this.getAttribute('href');
|
||||
const targetElement = document.querySelector(targetId);
|
||||
|
||||
if (targetElement) {
|
||||
window.scrollTo({
|
||||
top: targetElement.offsetTop - 20,
|
||||
behavior: 'smooth'
|
||||
});
|
||||
}
|
||||
});
|
||||
});
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -1,61 +0,0 @@
|
||||
[build-system]
|
||||
requires = ["setuptools", "wheel"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "whatsapp-chat-exporter"
|
||||
version = "0.12.0"
|
||||
description = "A Whatsapp database parser that provides history of your Whatsapp conversations in HTML and JSON. Android, iOS, iPadOS, Crypt12, Crypt14, Crypt15 supported."
|
||||
readme = "README.md"
|
||||
authors = [
|
||||
{ name = "KnugiHK", email = "hello@knugi.com" }
|
||||
]
|
||||
license = { text = "MIT" }
|
||||
keywords = [
|
||||
"android", "ios", "parsing", "history", "iphone", "message", "crypt15",
|
||||
"customizable", "whatsapp", "android-backup", "messages", "crypt14",
|
||||
"crypt12", "whatsapp-chat-exporter", "whatsapp-export", "iphone-backup",
|
||||
"whatsapp-database", "whatsapp-database-parser", "whatsapp-conversations"
|
||||
]
|
||||
classifiers = [
|
||||
"Programming Language :: Python :: 3 :: Only",
|
||||
"Programming Language :: Python :: 3.9",
|
||||
"Programming Language :: Python :: 3.10",
|
||||
"Programming Language :: Python :: 3.11",
|
||||
"Programming Language :: Python :: 3.12",
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"Operating System :: OS Independent",
|
||||
"Development Status :: 4 - Beta",
|
||||
"Environment :: Console",
|
||||
"Intended Audience :: End Users/Desktop",
|
||||
"Topic :: Communications :: Chat",
|
||||
"Topic :: Utilities",
|
||||
"Topic :: Database"
|
||||
]
|
||||
requires-python = ">=3.9"
|
||||
dependencies = [
|
||||
"jinja2",
|
||||
"bleach"
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
android_backup = ["pycryptodome", "javaobj-py3"]
|
||||
crypt12 = ["pycryptodome"]
|
||||
crypt14 = ["pycryptodome"]
|
||||
crypt15 = ["pycryptodome", "javaobj-py3"]
|
||||
all = ["pycryptodome", "javaobj-py3", "vobject"]
|
||||
everything = ["pycryptodome", "javaobj-py3", "vobject"]
|
||||
backup = ["pycryptodome", "javaobj-py3"]
|
||||
vcards = ["vobject", "pycryptodome", "javaobj-py3"]
|
||||
|
||||
[project.scripts]
|
||||
wtsexporter = "Whatsapp_Chat_Exporter.__main__:main"
|
||||
waexporter = "Whatsapp_Chat_Exporter.__main__:main"
|
||||
whatsapp-chat-exporter = "Whatsapp_Chat_Exporter.__main__:main"
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
where = ["."]
|
||||
include = ["Whatsapp_Chat_Exporter"]
|
||||
|
||||
[tool.setuptools.package-data]
|
||||
Whatsapp_Chat_Exporter = ["*.html"]
|
||||
@@ -1,115 +0,0 @@
|
||||
"""
|
||||
This script processes a VCARD file to standardize telephone entries and add a second TEL line with the modified number (removing the extra ninth digit) for contacts with 9-digit subscribers.
|
||||
It handles numbers that may already include a "+55" prefix and ensures that the output format is consistent.
|
||||
Contributed by @magpires https://github.com/KnugiHK/WhatsApp-Chat-Exporter/issues/127#issuecomment-2646660625
|
||||
"""
|
||||
import re
|
||||
import argparse
|
||||
|
||||
def process_phone_number(raw_phone):
|
||||
"""
|
||||
Process the raw phone string from the VCARD and return two formatted numbers:
|
||||
- The original formatted number, and
|
||||
- A modified formatted number with the extra (ninth) digit removed, if applicable.
|
||||
|
||||
Desired output:
|
||||
For a number with a 9-digit subscriber:
|
||||
Original: "+55 {area} {first 5 of subscriber}-{last 4 of subscriber}"
|
||||
Modified: "+55 {area} {subscriber[1:5]}-{subscriber[5:]}"
|
||||
For example, for an input that should represent "027912345678", the outputs are:
|
||||
"+55 27 91234-5678" and "+55 27 1234-5678"
|
||||
|
||||
This function handles numbers that may already include a "+55" prefix.
|
||||
It expects that after cleaning, a valid number (without the country code) should have either 10 digits
|
||||
(2 for area + 8 for subscriber) or 11 digits (2 for area + 9 for subscriber).
|
||||
If extra digits are present, it takes the last 11 (or 10) digits.
|
||||
"""
|
||||
# Store the original input for processing
|
||||
number_to_process = raw_phone.strip()
|
||||
|
||||
# Remove all non-digit characters
|
||||
digits = re.sub(r'\D', '', number_to_process)
|
||||
|
||||
# If the number starts with '55', remove it for processing
|
||||
if digits.startswith("55") and len(digits) > 11:
|
||||
digits = digits[2:]
|
||||
|
||||
# Remove trunk zero if present
|
||||
if digits.startswith("0"):
|
||||
digits = digits[1:]
|
||||
|
||||
# After cleaning, we expect a valid number to have either 10 or 11 digits
|
||||
# If there are extra digits, use the last 11 (for a 9-digit subscriber) or last 10 (for an 8-digit subscriber)
|
||||
if len(digits) > 11:
|
||||
# Here, we assume the valid number is the last 11 digits
|
||||
digits = digits[-11:]
|
||||
elif len(digits) > 10 and len(digits) < 11:
|
||||
# In some cases with an 8-digit subscriber, take the last 10 digits
|
||||
digits = digits[-10:]
|
||||
|
||||
# Check if we have a valid number after processing
|
||||
if len(digits) not in (10, 11):
|
||||
return None, None
|
||||
|
||||
area = digits[:2]
|
||||
subscriber = digits[2:]
|
||||
|
||||
if len(subscriber) == 9:
|
||||
# Format the original number (5-4 split, e.g., "91234-5678")
|
||||
orig_subscriber = f"{subscriber[:5]}-{subscriber[5:]}"
|
||||
# Create a modified version: drop the first digit of the subscriber to form an 8-digit subscriber (4-4 split)
|
||||
mod_subscriber = f"{subscriber[1:5]}-{subscriber[5:]}"
|
||||
original_formatted = f"+55 {area} {orig_subscriber}"
|
||||
modified_formatted = f"+55 {area} {mod_subscriber}"
|
||||
elif len(subscriber) == 8:
|
||||
original_formatted = f"+55 {area} {subscriber[:4]}-{subscriber[4:]}"
|
||||
modified_formatted = None
|
||||
else:
|
||||
# This shouldn't happen given the earlier check, but just to be safe
|
||||
return None, None
|
||||
|
||||
return original_formatted, modified_formatted
|
||||
|
||||
def process_vcard(input_vcard, output_vcard):
|
||||
"""
|
||||
Process a VCARD file to standardize telephone entries and add a second TEL line
|
||||
with the modified number (removing the extra ninth digit) for contacts with 9-digit subscribers.
|
||||
"""
|
||||
with open(input_vcard, 'r', encoding='utf-8') as file:
|
||||
lines = file.readlines()
|
||||
|
||||
output_lines = []
|
||||
|
||||
# Regex to capture any telephone line.
|
||||
# It matches lines starting with "TEL:" or "TEL;TYPE=..." or with prefixes like "item1.TEL:".
|
||||
phone_pattern = re.compile(r'^(?P<prefix>.*TEL(?:;TYPE=[^:]+)?):(?P<number>.*)$')
|
||||
|
||||
for line in lines:
|
||||
stripped_line = line.rstrip("\n")
|
||||
match = phone_pattern.match(stripped_line)
|
||||
if match:
|
||||
raw_phone = match.group("number").strip()
|
||||
orig_formatted, mod_formatted = process_phone_number(raw_phone)
|
||||
if orig_formatted:
|
||||
# Always output using the standardized prefix.
|
||||
output_lines.append(f"TEL;TYPE=CELL:{orig_formatted}\n")
|
||||
else:
|
||||
output_lines.append(line)
|
||||
if mod_formatted:
|
||||
output_lines.append(f"TEL;TYPE=CELL:{mod_formatted}\n")
|
||||
else:
|
||||
output_lines.append(line)
|
||||
|
||||
with open(output_vcard, 'w', encoding='utf-8') as file:
|
||||
file.writelines(output_lines)
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Process a VCARD file to standardize telephone entries and add a second TEL line with the modified number (removing the extra ninth digit) for contacts with 9-digit subscribers."
|
||||
)
|
||||
parser.add_argument('input_vcard', type=str, help='Input VCARD file')
|
||||
parser.add_argument('output_vcard', type=str, help='Output VCARD file')
|
||||
args = parser.parse_args()
|
||||
|
||||
process_vcard(args.input_vcard, args.output_vcard)
|
||||
print(f"VCARD processed and saved to {args.output_vcard}")
|
||||
@@ -1,269 +0,0 @@
|
||||
import subprocess
|
||||
import unittest
|
||||
import tempfile
|
||||
import os
|
||||
from unittest.mock import patch
|
||||
|
||||
from brazilian_number_processing import process_phone_number, process_vcard
|
||||
|
||||
class TestVCardProcessor(unittest.TestCase):
|
||||
|
||||
def test_process_phone_number(self):
|
||||
"""Test the process_phone_number function with various inputs."""
|
||||
|
||||
# Test cases for 9-digit subscriber numbers
|
||||
test_cases_9_digit = [
|
||||
# Standard 11-digit number (2 area + 9 subscriber)
|
||||
("27912345678", "+55 27 91234-5678", "+55 27 1234-5678"),
|
||||
# With country code prefix
|
||||
("5527912345678", "+55 27 91234-5678", "+55 27 1234-5678"),
|
||||
# With plus in country code
|
||||
("+5527912345678", "+55 27 91234-5678", "+55 27 1234-5678"),
|
||||
# With spaces and formatting
|
||||
("+55 27 9 1234-5678", "+55 27 91234-5678", "+55 27 1234-5678"),
|
||||
# With trunk zero
|
||||
("027912345678", "+55 27 91234-5678", "+55 27 1234-5678"),
|
||||
# With country code and trunk zero
|
||||
("+55027912345678", "+55 27 91234-5678", "+55 27 1234-5678"),
|
||||
# With extra digits at the beginning (should use last 11)
|
||||
("99927912345678", "+55 27 91234-5678", "+55 27 1234-5678"),
|
||||
# With extra non-digit characters
|
||||
("+55-27-9.1234_5678", "+55 27 91234-5678", "+55 27 1234-5678"),
|
||||
]
|
||||
|
||||
# Test cases for 8-digit subscriber numbers
|
||||
test_cases_8_digit = [
|
||||
# Standard 10-digit number (2 area + 8 subscriber)
|
||||
("2712345678", "+55 27 1234-5678", None),
|
||||
# With country code prefix
|
||||
("552712345678", "+55 27 1234-5678", None),
|
||||
# With plus in country code
|
||||
("+552712345678", "+55 27 1234-5678", None),
|
||||
# With spaces and formatting
|
||||
("+55 27 1234-5678", "+55 27 1234-5678", None),
|
||||
# With trunk zero
|
||||
("02712345678", "+55 27 1234-5678", None),
|
||||
# With country code and trunk zero
|
||||
("+55 0 27 1234-5678", "+55 27 1234-5678", None),
|
||||
]
|
||||
|
||||
# Edge cases
|
||||
edge_cases = [
|
||||
# Too few digits
|
||||
("271234567", None, None),
|
||||
# Empty string
|
||||
("", None, None),
|
||||
# Non-numeric characters only
|
||||
("abc-def+ghi", None, None),
|
||||
# Single digit
|
||||
("1", None, None),
|
||||
# Unusual formatting but valid number
|
||||
("(+55) [27] 9.1234_5678", "+55 27 91234-5678", "+55 27 1234-5678"),
|
||||
]
|
||||
|
||||
# Run tests for all cases
|
||||
all_cases = test_cases_9_digit + test_cases_8_digit + edge_cases
|
||||
|
||||
for raw_phone, expected_orig, expected_mod in all_cases:
|
||||
with self.subTest(raw_phone=raw_phone):
|
||||
orig, mod = process_phone_number(raw_phone)
|
||||
self.assertEqual(orig, expected_orig)
|
||||
self.assertEqual(mod, expected_mod)
|
||||
|
||||
def test_process_vcard(self):
|
||||
"""Test the process_vcard function with various VCARD formats."""
|
||||
|
||||
# Test case 1: Standard TEL entries
|
||||
vcard1 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Doe;John;;;
|
||||
FN:John Doe
|
||||
TEL:+5527912345678
|
||||
TEL:+552712345678
|
||||
END:VCARD
|
||||
"""
|
||||
expected1 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Doe;John;;;
|
||||
FN:John Doe
|
||||
TEL;TYPE=CELL:+55 27 91234-5678
|
||||
TEL;TYPE=CELL:+55 27 1234-5678
|
||||
TEL;TYPE=CELL:+55 27 1234-5678
|
||||
END:VCARD
|
||||
"""
|
||||
|
||||
# Test case 2: TEL entries with TYPE attributes
|
||||
vcard2 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Smith;Jane;;;
|
||||
FN:Jane Smith
|
||||
TEL;TYPE=CELL:+5527912345678
|
||||
TEL;TYPE=HOME:+552712345678
|
||||
END:VCARD
|
||||
"""
|
||||
expected2 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Smith;Jane;;;
|
||||
FN:Jane Smith
|
||||
TEL;TYPE=CELL:+55 27 91234-5678
|
||||
TEL;TYPE=CELL:+55 27 1234-5678
|
||||
TEL;TYPE=CELL:+55 27 1234-5678
|
||||
END:VCARD
|
||||
"""
|
||||
|
||||
# Test case 3: Complex TEL entries with prefixes
|
||||
vcard3 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Brown;Robert;;;
|
||||
FN:Robert Brown
|
||||
item1.TEL:+5527912345678
|
||||
item2.TEL;TYPE=CELL:+552712345678
|
||||
END:VCARD
|
||||
"""
|
||||
expected3 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Brown;Robert;;;
|
||||
FN:Robert Brown
|
||||
TEL;TYPE=CELL:+55 27 91234-5678
|
||||
TEL;TYPE=CELL:+55 27 1234-5678
|
||||
TEL;TYPE=CELL:+55 27 1234-5678
|
||||
END:VCARD
|
||||
"""
|
||||
|
||||
# Test case 4: Mixed valid and invalid phone numbers
|
||||
vcard4 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:White;Alice;;;
|
||||
FN:Alice White
|
||||
TEL:123
|
||||
TEL:+5527912345678
|
||||
END:VCARD
|
||||
"""
|
||||
expected4 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:White;Alice;;;
|
||||
FN:Alice White
|
||||
TEL:123
|
||||
TEL;TYPE=CELL:+55 27 91234-5678
|
||||
TEL;TYPE=CELL:+55 27 1234-5678
|
||||
END:VCARD
|
||||
"""
|
||||
|
||||
# Test case 5: Multiple contacts with different formats
|
||||
vcard5 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Johnson;Mike;;;
|
||||
FN:Mike Johnson
|
||||
TEL:27912345678
|
||||
END:VCARD
|
||||
BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Williams;Sarah;;;
|
||||
FN:Sarah Williams
|
||||
TEL;TYPE=CELL:2712345678
|
||||
END:VCARD
|
||||
"""
|
||||
expected5 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Johnson;Mike;;;
|
||||
FN:Mike Johnson
|
||||
TEL;TYPE=CELL:+55 27 91234-5678
|
||||
TEL;TYPE=CELL:+55 27 1234-5678
|
||||
END:VCARD
|
||||
BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Williams;Sarah;;;
|
||||
FN:Sarah Williams
|
||||
TEL;TYPE=CELL:+55 27 1234-5678
|
||||
END:VCARD
|
||||
"""
|
||||
|
||||
# Test case 6: VCARD with no phone numbers
|
||||
vcard6 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Davis;Tom;;;
|
||||
FN:Tom Davis
|
||||
EMAIL:tom@example.com
|
||||
END:VCARD
|
||||
"""
|
||||
expected6 = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Davis;Tom;;;
|
||||
FN:Tom Davis
|
||||
EMAIL:tom@example.com
|
||||
END:VCARD
|
||||
"""
|
||||
|
||||
test_cases = [
|
||||
(vcard1, expected1),
|
||||
(vcard2, expected2),
|
||||
(vcard3, expected3),
|
||||
(vcard4, expected4),
|
||||
(vcard5, expected5),
|
||||
(vcard6, expected6)
|
||||
]
|
||||
|
||||
for i, (input_vcard, expected_output) in enumerate(test_cases):
|
||||
with self.subTest(case=i+1):
|
||||
# Create temporary files for input and output
|
||||
with tempfile.NamedTemporaryFile(mode='w+', delete=False, encoding='utf-8') as input_file:
|
||||
input_file.write(input_vcard)
|
||||
input_path = input_file.name
|
||||
|
||||
output_path = input_path + '.out'
|
||||
|
||||
try:
|
||||
# Process the VCARD
|
||||
process_vcard(input_path, output_path)
|
||||
|
||||
# Read and verify the output
|
||||
with open(output_path, 'r', encoding='utf-8') as output_file:
|
||||
actual_output = output_file.read()
|
||||
|
||||
self.assertEqual(actual_output, expected_output)
|
||||
|
||||
finally:
|
||||
# Clean up temporary files
|
||||
if os.path.exists(input_path):
|
||||
os.unlink(input_path)
|
||||
if os.path.exists(output_path):
|
||||
os.unlink(output_path)
|
||||
|
||||
def test_script_argument_handling(self):
|
||||
"""Test the script's command-line argument handling."""
|
||||
|
||||
test_input = """BEGIN:VCARD
|
||||
VERSION:3.0
|
||||
N:Test;User;;;
|
||||
FN:User Test
|
||||
TEL:+5527912345678
|
||||
END:VCARD
|
||||
"""
|
||||
|
||||
# Create a temporary input file
|
||||
with tempfile.NamedTemporaryFile(mode='w+', delete=False, encoding='utf-8') as input_file:
|
||||
input_file.write(test_input)
|
||||
input_path = input_file.name
|
||||
|
||||
output_path = input_path + '.out'
|
||||
|
||||
try:
|
||||
test_args = ['python' if os.name == 'nt' else 'python3', 'brazilian_number_processing.py', input_path, output_path]
|
||||
# We're just testing that the argument parsing works
|
||||
subprocess.call(
|
||||
test_args,
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.STDOUT
|
||||
)
|
||||
# Check if the output file was created
|
||||
self.assertTrue(os.path.exists(output_path))
|
||||
|
||||
finally:
|
||||
# Clean up temporary files
|
||||
if os.path.exists(input_path):
|
||||
os.unlink(input_path)
|
||||
if os.path.exists(output_path):
|
||||
os.unlink(output_path)
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
@@ -1,49 +0,0 @@
|
||||
import hmac
|
||||
import javaobj
|
||||
import zlib
|
||||
from Crypto.Cipher import AES
|
||||
from hashlib import sha256
|
||||
from sys import exit
|
||||
|
||||
|
||||
def _generate_hmac_of_hmac(key_stream):
|
||||
key = hmac.new(
|
||||
hmac.new(
|
||||
b'\x00' * 32,
|
||||
key_stream,
|
||||
sha256
|
||||
).digest(),
|
||||
b"backup encryption\x01",
|
||||
sha256
|
||||
)
|
||||
return key.digest(), key_stream
|
||||
|
||||
|
||||
def _extract_encrypted_key(keyfile):
|
||||
key_stream = b""
|
||||
for byte in javaobj.loads(keyfile):
|
||||
key_stream += byte.to_bytes(1, "big", signed=True)
|
||||
|
||||
return _generate_hmac_of_hmac(key_stream)
|
||||
|
||||
|
||||
key = open("encrypted_backup.key", "rb").read()
|
||||
database = open("wa.db.crypt15", "rb").read()
|
||||
main_key, hex_key = _extract_encrypted_key(key)
|
||||
for i in range(100):
|
||||
iv = database[i:i+16]
|
||||
for j in range(100):
|
||||
cipher = AES.new(main_key, AES.MODE_GCM, iv)
|
||||
db_ciphertext = database[j:]
|
||||
db_compressed = cipher.decrypt(db_ciphertext)
|
||||
try:
|
||||
db = zlib.decompress(db_compressed)
|
||||
except zlib.error:
|
||||
...
|
||||
else:
|
||||
if db[0:6] == b"SQLite":
|
||||
print(f"Found!\nIV: {i}\nOffset: {j}")
|
||||
print(db_compressed[:10])
|
||||
exit()
|
||||
|
||||
print("Not found! Try to increase maximum search.")
|
||||
Reference in New Issue
Block a user