Bump to 0.4.4 (#621)

Bumps [tqdm](https://github.com/tqdm/tqdm) from 4.64.0 to 4.64.1.
- [Release notes](https://github.com/tqdm/tqdm/releases)
- [Commits](https://github.com/tqdm/tqdm/compare/v4.64.0...v4.64.1)

---
updated-dependencies:
- dependency-name: tqdm
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/ISSUE_TEMPLATE/bug.md

@@ -15,10 +15,14 @@ assignees: soxoj
 
 ## Description
 
-Info about Maigret version you are running and environment (`--version`, operation system, ISP provuder):
+Info about Maigret version you are running and environment (`--version`, operation system, ISP provider):
 <INSERT VERSION INFO HERE>
 
 How to reproduce this bug (commandline options / conditions):
 <INSERT EXAMPLE OF CLI COMMAND HERE>
 
 <DESCRIPTION>
+
+<PASTE SCREENSHOT>
+
+<ATTACH LOG FILE>

.github/workflows/pyinstaller.yml

@@ -3,8 +3,6 @@ name: Package exe with PyInstaller - Windows
 on:
   push:
     branches: [ main ]
-  pull_request:
-    branches: [ main ]
 
 jobs:
   build:

.github/workflows/python-package.yml

@@ -1,13 +1,11 @@
-# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+name: Linting and testing
-# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
-
-name: Python package
 
 on:
   push:
     branches: [ main ]
   pull_request:
     branches: [ main ]
+    types: [opened, synchronize, reopened]
 
 jobs:
   build:
@@ -15,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.6.9, 3.7, 3.8, 3.9]
+        python-version: [3.7, 3.8, 3.9]
 
     steps:
     - uses: actions/checkout@v2

.github/workflows/python-publish.yml

@@ -1,6 +1,3 @@
-# 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
-
 name: Upload Python Package
 
 on:

.github/workflows/update-site-data.yml

@@ -0,0 +1,34 @@
+name: Update sites rating and statistics
+
+on:
+  pull_request:
+    branches: [ dev ]
+    types: [opened, synchronize]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2.3.2
+      with:
+        ref: ${{ github.event.pull_request.head.sha }}
+        fetch-depth: 0 # otherwise, there would be errors pushing refs to the destination repository.
+
+    - name: build application
+      run: |
+        pip3 install .
+        python3 ./utils/update_site_data.py --empty-only
+
+    - name: Commit and push changes
+      run: |
+        git config --global user.name "Maigret autoupdate"
+        git config --global user.email "soxoj@protonmail.com"
+        echo `git name-rev ${{ github.event.pull_request.head.sha }} --name-only`
+        export BRANCH=`git name-rev ${{ github.event.pull_request.head.sha }} --name-only | sed 's/remotes\/origin\///'`
+        echo $BRANCH
+        git remote -v
+        git checkout $BRANCH
+        git add sites.md
+        git commit -m "Updated site list and statistics"
+        git push origin $BRANCH

.gitignore

@@ -15,6 +15,10 @@ src/
 .ipynb_checkpoints
 *.ipynb
 
+# Logs and backups
+*.log
+*.bak
+
 # Output files, except requirements.txt
 *.txt
 !requirements.txt

CHANGELOG.md

@@ -2,6 +2,140 @@
 
 ## [Unreleased]
 
+## [0.4.4] - 2022-09-03
+* Fixed some false positives by @soxoj in https://github.com/soxoj/maigret/pull/433
+* Drop Python 3.6 support by @soxoj in https://github.com/soxoj/maigret/pull/434
+* Bump xhtml2pdf from 0.2.5 to 0.2.7 by @dependabot in https://github.com/soxoj/maigret/pull/409
+* Bump reportlab from 3.6.6 to 3.6.9 by @dependabot in https://github.com/soxoj/maigret/pull/403
+* Bump markupsafe from 2.0.1 to 2.1.1 by @dependabot in https://github.com/soxoj/maigret/pull/389
+* Bump pycountry from 22.1.10 to 22.3.5 by @dependabot in https://github.com/soxoj/maigret/pull/384
+* Bump pypdf2 from 1.26.0 to 1.27.4 by @dependabot in https://github.com/soxoj/maigret/pull/438
+* Update GH actions by @soxoj in https://github.com/soxoj/maigret/pull/439
+* Bump tqdm from 4.63.0 to 4.64.0 by @dependabot in https://github.com/soxoj/maigret/pull/440
+* Bump jinja2 from 3.0.3 to 3.1.1 by @dependabot in https://github.com/soxoj/maigret/pull/441
+* Bump soupsieve from 2.3.1 to 2.3.2 by @dependabot in https://github.com/soxoj/maigret/pull/436
+* Bump pypdf2 from 1.26.0 to 1.27.4 by @dependabot in https://github.com/soxoj/maigret/pull/442
+* Bump pyvis from 0.1.9 to 0.2.0 by @dependabot in https://github.com/soxoj/maigret/pull/443
+* Bump pypdf2 from 1.27.4 to 1.27.6 by @dependabot in https://github.com/soxoj/maigret/pull/448
+* Bump typing-extensions from 4.1.1 to 4.2.0 by @dependabot in https://github.com/soxoj/maigret/pull/447
+* Bump soupsieve from 2.3.2 to 2.3.2.post1 by @dependabot in https://github.com/soxoj/maigret/pull/444
+* Bump pypdf2 from 1.27.6 to 1.27.7 by @dependabot in https://github.com/soxoj/maigret/pull/449
+* Bump pypdf2 from 1.27.7 to 1.27.8 by @dependabot in https://github.com/soxoj/maigret/pull/450
+* XMind 8 report warning and some docs update by @soxoj in https://github.com/soxoj/maigret/pull/452
+* False positive fixes 24.04.22 by @soxoj in https://github.com/soxoj/maigret/pull/455
+* Bump pypdf2 from 1.27.8 to 1.27.9 by @dependabot in https://github.com/soxoj/maigret/pull/456
+* Bump pytest from 7.0.1 to 7.1.2 by @dependabot in https://github.com/soxoj/maigret/pull/457
+* Bump jinja2 from 3.1.1 to 3.1.2 by @dependabot in https://github.com/soxoj/maigret/pull/460
+* Ubisoft forums addition by @fen0s in https://github.com/soxoj/maigret/pull/461
+* Add BYOND, Figma, BeatStars by @fen0s in https://github.com/soxoj/maigret/pull/462
+* fix Figma username definition, add a bunch of sites by @fen0s in https://github.com/soxoj/maigret/pull/464
+* Bump pypdf2 from 1.27.9 to 1.27.10 by @dependabot in https://github.com/soxoj/maigret/pull/465
+* Bump pypdf2 from 1.27.10 to 1.27.12 by @dependabot in https://github.com/soxoj/maigret/pull/466
+* Sites fixes 05 05 22 by @soxoj in https://github.com/soxoj/maigret/pull/469
+* Bump pyvis from 0.2.0 to 0.2.1 by @dependabot in https://github.com/soxoj/maigret/pull/472
+* Social analyzer websites, also fixing presense strs by @fen0s in https://github.com/soxoj/maigret/pull/471
+* Updated logic of false positive risk estimating by @soxoj in https://github.com/soxoj/maigret/pull/475
+* Improved usability of external progressbar func by @soxoj in https://github.com/soxoj/maigret/pull/476
+* New sites added, some tags/rank update by @soxoj in https://github.com/soxoj/maigret/pull/477
+* Added new sites by @soxoj in https://github.com/soxoj/maigret/pull/480
+* Added new forums, updated ranks, some utils improvements by @soxoj in https://github.com/soxoj/maigret/pull/481
+* Disabled sites with false positives results by @soxoj in https://github.com/soxoj/maigret/pull/482
+* Bump certifi from 2021.10.8 to 2022.5.18.1 by @dependabot in https://github.com/soxoj/maigret/pull/488
+* Bump psutil from 5.9.0 to 5.9.1 by @dependabot in https://github.com/soxoj/maigret/pull/490
+* Bump pypdf2 from 1.27.12 to 1.28.1 by @dependabot in https://github.com/soxoj/maigret/pull/491
+* Bump pypdf2 from 1.28.1 to 1.28.2 by @dependabot in https://github.com/soxoj/maigret/pull/493
+* added and fixed some websites in data.json by @kustermariocoding in https://github.com/soxoj/maigret/pull/494
+* Bump pypdf2 from 1.28.2 to 2.0.0 by @dependabot in https://github.com/soxoj/maigret/pull/504
+* Bump pefile from 2021.9.3 to 2022.5.30 by @dependabot in https://github.com/soxoj/maigret/pull/499
+* Updated sites list, added disabled Anilist by @soxoj in https://github.com/soxoj/maigret/pull/502
+* Bump lxml from 4.8.0 to 4.9.0 by @dependabot in https://github.com/soxoj/maigret/pull/503
+* Compatibility with Python 10 by @soxoj in https://github.com/soxoj/maigret/pull/509
+* feat: add .log & .bak files to gitignore in https://github.com/soxoj/maigret/pull/511
+* fix some sites and delete abandoned by @fen0s in https://github.com/soxoj/maigret/pull/526
+* Fixesjulyfirst by @fen0s in https://github.com/soxoj/maigret/pull/533
+* yazbel, aboutcar, zhihu by @fen0s in https://github.com/soxoj/maigret/pull/531
+* Fixes july third by @fen0s in https://github.com/soxoj/maigret/pull/535
+* Update data.json by @fen0s in https://github.com/soxoj/maigret/pull/539
+* Update data.json by @fen0s in https://github.com/soxoj/maigret/pull/540
+* Bump reportlab from 3.6.9 to 3.6.11 by @dependabot in https://github.com/soxoj/maigret/pull/543
+* Bump requests from 2.27.1 to 2.28.1 by @dependabot in https://github.com/soxoj/maigret/pull/530
+* Bump pypdf2 from 2.0.0 to 2.5.0 by @dependabot in https://github.com/soxoj/maigret/pull/542
+* Bump xhtml2pdf from 0.2.7 to 0.2.8 by @dependabot in https://github.com/soxoj/maigret/pull/522
+* Bump lxml from 4.9.0 to 4.9.1 by @dependabot in https://github.com/soxoj/maigret/pull/538
+* disable yandex music + set utf8 encoding by @fen0s in https://github.com/soxoj/maigret/pull/562
+* fix false positives by @fen0s in https://github.com/soxoj/maigret/pull/577
+* disable Instagram, fix two false positives by @fen0s in https://github.com/soxoj/maigret/pull/578
+* Bump certifi from 2022.5.18.1 to 2022.6.15 by @dependabot in https://github.com/soxoj/maigret/pull/551
+* August15 by @fen0s in https://github.com/soxoj/maigret/pull/591
+* Bump pytest-httpserver from 1.0.4 to 1.0.5 by @dependabot in https://github.com/soxoj/maigret/pull/583
+* Bump typing-extensions from 4.2.0 to 4.3.0 by @dependabot in https://github.com/soxoj/maigret/pull/549
+* Bump colorama from 0.4.4 to 0.4.5 by @dependabot in https://github.com/soxoj/maigret/pull/548
+* Bump chardet from 4.0.0 to 5.0.0 by @dependabot in https://github.com/soxoj/maigret/pull/550
+* Bump cloudscraper from 1.2.60 to 1.2.63 by @dependabot in https://github.com/soxoj/maigret/pull/600
+* Bump flake8 from 4.0.1 to 5.0.4 by @dependabot in https://github.com/soxoj/maigret/pull/598
+* Bump attrs from 21.4.0 to 22.1.0 by @dependabot in https://github.com/soxoj/maigret/pull/597
+* Bump pytest-asyncio from 0.18.2 to 0.19.0 by @dependabot in https://github.com/soxoj/maigret/pull/601
+* Bump pypdf2 from 2.5.0 to 2.10.4 by @dependabot in https://github.com/soxoj/maigret/pull/606
+* Bump pytest from 7.1.2 to 7.1.3 by @dependabot in https://github.com/soxoj/maigret/pull/613
+* Update sites.md -Gitmemory.com suppression by @C3n7ral051nt4g3ncy in https://github.com/soxoj/maigret/pull/610
+* Bump cloudscraper from 1.2.63 to 1.2.64 by @dependabot in https://github.com/soxoj/maigret/pull/614
+* Bump pycountry from 22.1.10 to 22.3.5 by @dependabot in https://github.com/soxoj/maigret/pull/607
+* add ProtonMail, disable 3 broken sites by @fen0s in https://github.com/soxoj/maigret/pull/619
+* Bump tqdm from 4.64.0 to 4.64.1 by @dependabot in https://github.com/soxoj/maigret/pull/618
+
+**Full Changelog**: https://github.com/soxoj/maigret/compare/v0.4.3...v0.4.4
+
+## [0.4.3] - 2022-04-13
+* Added Sites to data.json by @kustermariocoding in https://github.com/soxoj/maigret/pull/386
+* added new Websites to data.json by @kustermariocoding in https://github.com/soxoj/maigret/pull/390
+* Skipped broken tests by @soxoj in https://github.com/soxoj/maigret/pull/397
+* Added new Websites to data.json by @kustermariocoding in https://github.com/soxoj/maigret/pull/401
+* Added new Websites to data.json by @kustermariocoding in https://github.com/soxoj/maigret/pull/404
+* Updated statistics by @soxoj in https://github.com/soxoj/maigret/pull/406
+* Added new Websites to data.json by @kustermariocoding in https://github.com/soxoj/maigret/pull/413
+* Disabled houzz.com, updated sites statistics by @soxoj in https://github.com/soxoj/maigret/pull/422
+* Fixed last false positives by @soxoj in https://github.com/soxoj/maigret/pull/424
+* Fixed actual false positives by @soxoj in https://github.com/soxoj/maigret/pull/431
+
+**Full Changelog**: https://github.com/soxoj/maigret/compare/v0.4.2...v0.4.3
+
+## [0.4.2] - 2022-03-07
+* [ImgBot] Optimize images by @imgbot in https://github.com/soxoj/maigret/pull/319
+* Bump pytest-asyncio from 0.17.0 to 0.17.1 by @dependabot in https://github.com/soxoj/maigret/pull/321
+* Bump pytest-asyncio from 0.17.1 to 0.17.2 by @dependabot in https://github.com/soxoj/maigret/pull/323
+* Disabled Ruboard by @soxoj in https://github.com/soxoj/maigret/pull/327
+* Disable kinooh, sites list update workflow added by @soxoj in https://github.com/soxoj/maigret/pull/329
+* Bump multidict from 5.2.0 to 6.0.1 by @dependabot in https://github.com/soxoj/maigret/pull/332
+* Bump multidict from 6.0.1 to 6.0.2 by @dependabot in https://github.com/soxoj/maigret/pull/333
+* Bump pytest-httpserver from 1.0.3 to 1.0.4 by @dependabot in https://github.com/soxoj/maigret/pull/334
+* Bump pytest from 6.2.5 to 7.0.0 by @dependabot in https://github.com/soxoj/maigret/pull/339
+* Bump pytest-asyncio from 0.17.2 to 0.18.0 by @dependabot in https://github.com/soxoj/maigret/pull/340
+* Bump pytest-asyncio from 0.18.0 to 0.18.1 by @dependabot in https://github.com/soxoj/maigret/pull/343
+* Bump pytest from 7.0.0 to 7.0.1 by @dependabot in https://github.com/soxoj/maigret/pull/345
+* Bump typing-extensions from 4.0.1 to 4.1.1 by @dependabot in https://github.com/soxoj/maigret/pull/346
+* Bump lxml from 4.7.1 to 4.8.0 by @dependabot in https://github.com/soxoj/maigret/pull/350
+* Pin reportlab version by @cyb3rk0tik in https://github.com/soxoj/maigret/pull/351
+* Fix reportlab not only for testing by @cyb3rk0tik in https://github.com/soxoj/maigret/pull/352
+* Added some scripts by @soxoj in https://github.com/soxoj/maigret/pull/355
+* Added package publishing instruction by @soxoj in https://github.com/soxoj/maigret/pull/356
+* Added DB statistics autoupdate and write to sites.md by @soxoj in https://github.com/soxoj/maigret/pull/357
+* CI autoupdate by @soxoj in https://github.com/soxoj/maigret/pull/359
+* Op.gg fixes by @soxoj in https://github.com/soxoj/maigret/pull/363
+* Wikipedia fix by @soxoj in https://github.com/soxoj/maigret/pull/365
+* Disabled Netvibes and LeetCode by @soxoj in https://github.com/soxoj/maigret/pull/366
+* Fixed several false positives, improved statistics info by @soxoj in https://github.com/soxoj/maigret/pull/368
+* Fix false positives  by @soxoj in https://github.com/soxoj/maigret/pull/370
+* Fixed the rest of false positives for now by @soxoj in https://github.com/soxoj/maigret/pull/371
+* Fix false positive and CI by @soxoj in https://github.com/soxoj/maigret/pull/372
+* Added new sites to data.json by @kustermariocoding in https://github.com/soxoj/maigret/pull/375
+* Fixed issue with str alexaRank by @soxoj in https://github.com/soxoj/maigret/pull/382
+* Bump tqdm from 4.62.3 to 4.63.0 by @dependabot in https://github.com/soxoj/maigret/pull/374
+* Bump pytest-asyncio from 0.18.1 to 0.18.2 by @dependabot in https://github.com/soxoj/maigret/pull/380
+* @imgbot made their first contribution in https://github.com/soxoj/maigret/pull/319
+* @kustermariocoding made their first contribution in https://github.com/soxoj/maigret/pull/375
+
+**Full Changelog**: https://github.com/soxoj/maigret/compare/v0.4.1...v0.4.2
+
 ## [0.4.1] - 2022-01-15
 * Added dozen of sites, improved submit mode by @soxoj in https://github.com/soxoj/maigret/pull/288
 * Bump requests from 2.26.0 to 2.27.0 by @dependabot in https://github.com/soxoj/maigret/pull/292

README.md

@@ -51,7 +51,7 @@ Also you can run Maigret using cloud shells and Jupyter notebooks (see buttons b
 
 ### Package installing
 
-**NOTE**: Python 3.6 or higher and pip is required, **Python 3.8 is recommended.**
+**NOTE**: Python 3.7 or higher and pip is required, **Python 3.8 is recommended.**
 
 ```bash
 # install from pypi
@@ -101,7 +101,7 @@ maigret user --tags photo,dating
 maigret user1 user2 user3 -a
 ```
 
-Use `maigret --help` to get full options description. Also options are documented in [the Maigret Wiki](https://github.com/soxoj/maigret/wiki/Command-line-options).
+Use `maigret --help` to get full options description. Also options [are documented](https://maigret.readthedocs.io/en/latest/command-line-options.html).
 
 
 ## Demo with page parsing and recursive username search
@@ -112,7 +112,7 @@ Use `maigret --help` to get full options description. Also options are documente
 
 ![HTML report screenshot](https://raw.githubusercontent.com/soxoj/maigret/main/static/report_alexaimephotography_html_screenshot.png)
 
-![XMind report screenshot](https://raw.githubusercontent.com/soxoj/maigret/main/static/report_alexaimephotography_xmind_screenshot.png)
+![XMind 8 report screenshot](https://raw.githubusercontent.com/soxoj/maigret/main/static/report_alexaimephotography_xmind_screenshot.png)
 
 
 [Full console output](https://raw.githubusercontent.com/soxoj/maigret/main/static/recursive_search.md)

docs/source/conf.py

@@ -6,8 +6,8 @@ project = 'Maigret'
 copyright = '2021, soxoj'
 author = 'soxoj'
 
-release = '0.4.1'
+release = '0.4.4'
-version = '0.4.1'
+version = '0.4.4'
 
 # -- General configuration
 

docs/source/development.rst

@@ -0,0 +1,101 @@
+.. _development:
+
+Development
+==============
+
+Testing
+-------
+
+It is recommended use Python 3.7/3.8 for test due to some conflicts in 3.9.
+
+Install test requirements:
+
+.. code-block:: console
+
+  pip install -r test-requirements.txt
+
+
+Use the following commands to check Maigret:
+
+.. code-block:: console
+
+  # run linter and typing checks
+  # order of checks%
+  # - critical syntax errors or undefined names
+  # - flake checks
+  # - mypy checks
+  make lint
+
+  # run testing with coverage html report
+  # current test coverage is 60%
+  make text
+
+  # open html report
+  open htmlcov/index.html
+
+
+How to publish new version of Maigret
+-------------------------------------
+
+**Collaborats rights are requires, write Soxoj to get them**.
+
+For new version publishing you must create a new branch in repository
+with a bumped version number and actual changelog first. After it you
+must create a release, and GitHub action automatically create a new 
+PyPi package. 
+
+- New branch example: https://github.com/soxoj/maigret/commit/e520418f6a25d7edacde2d73b41a8ae7c80ddf39
+- Release example: https://github.com/soxoj/maigret/releases/tag/v0.4.1
+
+1. Make a new branch locally with a new version name. Check the current version number here: https://pypi.org/project/maigret/.
+**Increase only patch version (third number)** if there are no breaking changes.
+
+.. code-block:: console
+
+  git checkout -b 0.4.0
+
+2. Update Maigret version in three files manually:
+
+- setup.py
+- maigret/__version__.py 
+- docs/source/conf.py 
+
+3. Create a new empty text section in the beginning of the file `CHANGELOG.md` with a current date:
+
+.. code-block:: console
+
+  ## [0.4.0] - 2022-01-03
+
+4. Get auto-generate release notes:
+
+- Open https://github.com/soxoj/maigret/releases/new
+- Click `Choose a tag`, enter `v0.4.0` (your version)
+- Click `Create new tag`
+- Press `+ Auto-generate release notes`
+- Copy all the text from description text field below
+- Paste it to empty text section in `CHANGELOG.txt`
+- Remove redundant lines `## What's Changed` and `## New Contributors` section if it exists
+- *Close the new release page*
+
+5. Commit all the changes, push, make pull request
+
+.. code-block:: console
+
+  git add -p
+  git commit -m 'Bump to YOUR VERSION'
+  git push origin head
+
+
+6. Merge pull request
+
+7. Create new release
+
+- Open https://github.com/soxoj/maigret/releases/new again
+- Click `Choose a tag`
+- Enter actual version in format `v0.4.0`
+- Also enter actual version in the field `Release title` 
+- Click `Create new tag`
+- Press `+ Auto-generate release notes`
+- **Press "Publish release" button**
+
+8. That's all, now you can simply wait push to PyPi. You can monitor it in Action page: https://github.com/soxoj/maigret/actions/workflows/python-publish.yml

docs/source/features.rst

@@ -24,7 +24,7 @@ Enabled by default, can be disabled with ``--no-recursion``.
 Reports
 -------
 
-Maigret currently supports HTML, PDF, TXT, XMind mindmap, and JSON reports.
+Maigret currently supports HTML, PDF, TXT, XMind 8 mindmap, and JSON reports.
 
 HTML/PDF reports contain:
 
@@ -34,6 +34,8 @@ HTML/PDF reports contain:
 
 Also, there is a short text report in the CLI output after the end of a searching phase.
 
+**Warning**: XMind 8 mindmaps are incompatible with XMind 2022!
+
 Tags
 ----
 

docs/source/index.rst

@@ -28,3 +28,4 @@ You may be interested in:
    tags
    usage-examples
    settings
+   development

docs/source/philosophy.rst

@@ -3,4 +3,15 @@
 Philosophy
 ==========
 
-Username => Dossier
+TL;DR: Username => Dossier
+
+Maigret is designed to gather all the available information about person by his usernname.
+
+What kind of information is this? First, links to person accounts. Secondly, all the machine-extractable
+pieces of info, such as: other usernames, full name, URLs to people's images, birthday, location (country,
+city, etc.), gender.
+
+All this infromations forms some dossier, but it also useful for other tools and analytical purposes.
+Each collected piece of data has a label of a certain format (for exa,ple, ``follower_count`` for the number
+of subscribers or ``created_at`` for account creation time) so that it can be parsed and analyzed by various
+systems and stored in databases.

maigret.py

@@ -7,8 +7,11 @@ from maigret.maigret import main
 
 def run():
     try:
-        loop = asyncio.get_event_loop()
+        if sys.version_info.minor >= 10:
-        loop.run_until_complete(main())
+            asyncio.run(main())
+        else:
+            loop = asyncio.get_event_loop()
+            loop.run_until_complete(main())
     except KeyboardInterrupt:
         print('Maigret is interrupted.')
         sys.exit(1)

maigret/__version__.py

@@ -1,3 +1,3 @@
 """Maigret version file"""
 
-__version__ = '0.4.1'
+__version__ = '0.4.4'

maigret/checking.py

@@ -132,7 +132,7 @@ class SimpleAiohttpChecker(CheckerBase):
                 error = CheckError("Unexpected", str(e))
 
         if error == "Invalid proxy response":
-            self.logger.debug(e, exc_info=True)
+            self.logger.debug(error, exc_info=True)
 
         return str(html_text), status_code, error
 
@@ -580,6 +580,8 @@ async def maigret(
     cookies=None,
     retries=0,
     check_domains=False,
+    *args,
+    **kwargs,
 ) -> QueryResultWrapper:
     """Main search func
 
@@ -660,7 +662,8 @@ async def maigret(
         executor = AsyncioSimpleExecutor(logger=logger)
     else:
         executor = AsyncioProgressbarQueueExecutor(
-            logger=logger, in_parallel=max_connections, timeout=timeout + 0.5
+            logger=logger, in_parallel=max_connections, timeout=timeout + 0.5,
+            *args, **kwargs
         )
 
     # make options objects for all the requests

maigret/executors.py

@@ -81,6 +81,22 @@ class AsyncioProgressbarQueueExecutor(AsyncExecutor):
         self.queue = asyncio.Queue(self.workers_count)
         self.timeout = kwargs.get('timeout')
 
+    async def increment_progress(self, count):
+        update_func = self.progress.update
+        if asyncio.iscoroutinefunction(update_func):
+            await update_func(count)
+        else:
+            update_func(count)
+        await asyncio.sleep(0)
+
+    async def stop_progress(self):
+        stop_func = self.progress.close
+        if asyncio.iscoroutinefunction(stop_func):
+            await stop_func()
+        else:
+            stop_func()
+        await asyncio.sleep(0)
+
     async def worker(self):
         while True:
             try:
@@ -96,7 +112,7 @@ class AsyncioProgressbarQueueExecutor(AsyncExecutor):
                 result = kwargs.get('default')
 
             self.results.append(result)
-            self.progress.update(1)
+            await self.increment_progress(1)
             self.queue.task_done()
 
     async def _run(self, queries: Iterable[QueryDraft]):
@@ -109,10 +125,14 @@ class AsyncioProgressbarQueueExecutor(AsyncExecutor):
         workers = [create_task_func()(self.worker()) for _ in range(min_workers)]
 
         self.progress = self.progress_func(total=len(queries_list))
+
         for t in queries_list:
             await self.queue.put(t)
+
         await self.queue.join()
+
         for w in workers:
             w.cancel()
-        self.progress.close()
+
+        await self.stop_progress()
         return self.results

maigret/maigret.py

@@ -48,7 +48,7 @@ def notify_about_errors(search_results: QueryResultWrapper, query_notify):
     for e in errs:
         if not errors.is_important(e):
             continue
-        text = f'Too many errors of type "{e["err"]}" ({e["perc"]}%)'
+        text = f'Too many errors of type "{e["err"]}" ({round(e["perc"],2)}%)'
         solution = errors.solution_of(e['err'])
         if solution:
             text = '. '.join([text, solution.capitalize()])
@@ -566,7 +566,7 @@ async def main():
 
     # Database statistics
     if args.stats:
-        print(db.get_db_stats(db.sites_dict))
+        print(db.get_db_stats())
 
     report_dir = path.join(os.getcwd(), args.folderoutput)
 
@@ -719,8 +719,11 @@ async def main():
 
 def run():
     try:
-        loop = asyncio.get_event_loop()
+        if sys.version_info.minor >= 10:
-        loop.run_until_complete(main())
+            asyncio.run(main())
+        else:
+            loop = asyncio.get_event_loop()
+            loop.run_until_complete(main())
     except KeyboardInterrupt:
         print('Maigret is interrupted.')
         sys.exit(1)

maigret/report.py

@@ -67,7 +67,7 @@ def save_txt_report(filename: str, username: str, results: dict):
 def save_html_report(filename: str, context: dict):
     template, _ = generate_report_template(is_pdf=False)
     filled_template = template.render(**context)
-    with open(filename, "w") as f:
+    with open(filename, "w", encoding="utf-8") as f:
         f.write(filled_template)
 
 

maigret/sites.py

@@ -419,9 +419,8 @@ class MaigretDatabase:
             results[_id] = _type
         return results
 
-    def get_db_stats(self, sites_dict):
+    def get_db_stats(self, is_markdown=False):
-        if not sites_dict:
+        sites_dict = self.sites_dict
-            sites_dict = self.sites_dict()
 
         urls = {}
         tags = {}
@@ -429,6 +428,11 @@ class MaigretDatabase:
         disabled_count = 0
         total_count = len(sites_dict)
 
+        message_checks = 0
+        message_checks_one_factor = 0
+
+        status_checks = 0
+
         for _, site in sites_dict.items():
             if site.disabled:
                 disabled_count += 1
@@ -436,24 +440,46 @@ class MaigretDatabase:
             url_type = site.get_url_template()
             urls[url_type] = urls.get(url_type, 0) + 1
 
+            if site.check_type == 'message' and not site.disabled:
+                message_checks += 1
+                if site.absence_strs and site.presense_strs:
+                    continue
+                message_checks_one_factor += 1
+
+            if site.check_type == 'status_code':
+                status_checks += 1
+
             if not site.tags:
                 tags["NO_TAGS"] = tags.get("NO_TAGS", 0) + 1
 
             for tag in filter(lambda x: not is_country_tag(x), site.tags):
                 tags[tag] = tags.get(tag, 0) + 1
 
-        output += f"Enabled/total sites: {total_count - disabled_count}/{total_count}\n"
+        enabled_count = total_count-disabled_count
-        output += "Top profile URLs:\n"
+        enabled_perc = round(100*enabled_count/total_count, 2)
-        for url, count in sorted(urls.items(), key=lambda x: x[1], reverse=True)[:20]:
+        output += f"Enabled/total sites: {enabled_count}/{total_count} = {enabled_perc}%\n\n"
+
+        checks_perc = round(100*message_checks_one_factor/enabled_count, 2)
+        output += f"Incomplete message checks: {message_checks_one_factor}/{enabled_count} = {checks_perc}% (false positive risks)\n\n"
+
+        status_checks_perc = round(100*status_checks/enabled_count, 2)
+        output += f"Status code checks: {status_checks}/{enabled_count} = {status_checks_perc}% (false positive risks)\n\n"
+
+        output += f"False positive risk (total): {checks_perc+status_checks_perc}%\n\n"
+
+        top_urls_count = 20
+        output += f"Top {top_urls_count} profile URLs:\n"
+        for url, count in sorted(urls.items(), key=lambda x: x[1], reverse=True)[:top_urls_count]:
             if count == 1:
                 break
-            output += f"{count}\t{url}\n"
+            output += f"- ({count})\t`{url}`\n" if is_markdown else f"{count}\t{url}\n"
 
-        output += "Top tags:\n"
+        top_tags_count = 20
-        for tag, count in sorted(tags.items(), key=lambda x: x[1], reverse=True)[:200]:
+        output += f"\nTop {top_tags_count} tags:\n"
+        for tag, count in sorted(tags.items(), key=lambda x: x[1], reverse=True)[:top_tags_count]:
             mark = ""
             if tag not in self._tags:
                 mark = " (non-standard)"
-            output += f"{count}\t{tag}{mark}\n"
+            output += f"- ({count})\t`{tag}`{mark}\n" if is_markdown else f"{count}\t{tag}{mark}\n"
 
         return output

maigret/submit.py

@@ -1,10 +1,11 @@
 import asyncio
 import json
 import re
-from typing import List
+from typing import List, Tuple
 import xml.etree.ElementTree as ET
 from aiohttp import TCPConnector, ClientSession
 import requests
+import cloudscraper
 
 from .activation import import_aiohttp_cookies
 from .checking import maigret
@@ -14,6 +15,27 @@ from .sites import MaigretDatabase, MaigretSite, MaigretEngine
 from .utils import get_random_user_agent, get_match_ratio
 
 
+class CloudflareSession:
+    def __init__(self):
+        self.scraper = cloudscraper.create_scraper()
+
+    async def get(self, *args, **kwargs):
+        await asyncio.sleep(0)
+        res = self.scraper.get(*args, **kwargs)
+        self.last_text = res.text
+        self.status = res.status_code
+        return self
+
+    def status_code(self):
+        return self.status
+
+    async def text(self):
+        await asyncio.sleep(0)
+        return self.last_text
+
+    async def close(self):
+        pass
+
 class Submitter:
     HEADERS = {
         "User-Agent": get_random_user_agent(),
@@ -141,16 +163,18 @@ class Submitter:
                 fields['urlSubpath'] = f'/{subpath}'
         return fields
 
-    async def detect_known_engine(self, url_exists, url_mainpage) -> List[MaigretSite]:
+    async def detect_known_engine(self, url_exists, url_mainpage) -> [List[MaigretSite], str]:
         resp_text = ''
         try:
             r = await self.session.get(url_mainpage)
-            resp_text = await r.text()
+            content = await r.content.read()
+            charset = r.charset or "utf-8"
+            resp_text = content.decode(charset, "ignore")
             self.logger.debug(resp_text)
         except Exception as e:
             self.logger.warning(e)
             print("Some error while checking main page")
-            return []
+            return [], resp_text
 
         for engine in self.db.engines:
             strs_to_check = engine.__dict__.get("presenseStrs")
@@ -193,9 +217,9 @@ class Submitter:
                         )
                         sites.append(maigret_site)
 
-                    return sites
+                    return sites, resp_text
 
-        return []
+        return [], resp_text
 
     def extract_username_dialog(self, url):
         url_parts = url.rstrip("/").split("/")
@@ -338,10 +362,15 @@ class Submitter:
         print('Detecting site engine, please wait...')
         sites = []
         try:
-            sites = await self.detect_known_engine(url_exists, url_mainpage)
+            sites, text = await self.detect_known_engine(url_exists, url_exists)
         except KeyboardInterrupt:
             print('Engine detect process is interrupted.')
 
+
+        if 'cloudflare' in text.lower():
+            print('Cloudflare protection detected. I will use cloudscraper for futher work')
+            # self.session = CloudflareSession()
+
         if not sites:
             print("Unable to detect site engine, lets generate checking features")
 

pyinstaller/requirements.txt

@@ -1,5 +1,5 @@
 maigret @ https://github.com/soxoj/maigret/archive/refs/heads/main.zip
-pefile==2021.9.3
+pefile==2022.5.30
-psutil==5.9.0
+psutil==5.9.1
 pyinstaller @ https://github.com/pyinstaller/pyinstaller/archive/develop.zip
 pywin32-ctypes==0.2.0

requirements.txt

@@ -3,35 +3,37 @@ aiohttp==3.8.1
 aiohttp-socks==0.7.1
 arabic-reshaper==2.1.3
 async-timeout==4.0.2
-attrs==21.4.0
+attrs==22.1.0
-certifi==2021.10.8
+certifi==2022.6.15
-chardet==4.0.0
+chardet==5.0.0
-colorama==0.4.4
+colorama==0.4.5
 future==0.18.2
 future-annotations==1.0.0
 html5lib==1.1
 idna==3.3
-Jinja2==3.0.3
+Jinja2==3.1.2
-lxml==4.7.1
+lxml==4.9.1
-MarkupSafe==2.0.1
+MarkupSafe==2.1.1
 mock==4.0.3
-multidict==5.2.0
+multidict==6.0.2
-pycountry==22.1.10
+pycountry==22.3.5
-PyPDF2==1.26.0
+PyPDF2==2.10.4
 PySocks==1.7.1
 python-bidi==0.4.2
-requests==2.27.1
+requests==2.28.1
 requests-futures==1.0.0
 six==1.16.0
 socid-extractor>=0.0.21
-soupsieve==2.3.1
+soupsieve==2.3.2.post1
 stem==1.8.0
 torrequest==0.1.0
-tqdm==4.62.3
+tqdm==4.64.1
-typing-extensions==4.0.1
+typing-extensions==4.3.0
 webencodings==0.5.1
-xhtml2pdf==0.2.5
+xhtml2pdf==0.2.8
 XMind==1.2.0
 yarl==1.7.2
 networkx==2.5.1
-pyvis==0.1.9
+pyvis==0.2.1
+reportlab==3.6.11
+cloudscraper==1.2.64

setup.py

@@ -11,7 +11,7 @@ with open('requirements.txt') as rf:
     requires = rf.read().splitlines()
 
 setup(name='maigret',
-      version='0.4.1',
+      version='0.4.4',
       description='Collect a dossier on a person by username from a huge number of sites',
       long_description=long_description,
       long_description_content_type="text/markdown",

test-requirements.txt

@@ -1,7 +1,8 @@
-flake8==4.0.1
+reportlab==3.6.11
-pytest==6.2.5
+flake8==5.0.4
+pytest==7.1.3
 pytest-asyncio==0.16.0;python_version<"3.7"
-pytest-asyncio==0.17.0;python_version>="3.7"
+pytest-asyncio==0.19.0;python_version>="3.7"
 pytest-cov==3.0.0
-pytest-httpserver==1.0.3
+pytest-httpserver==1.0.5
 pytest-rerunfailures==10.2

tests/test_maigret.py

@@ -48,6 +48,7 @@ def test_self_check_db_positive_disable(test_db):
 
 
 @pytest.mark.slow
+@pytest.mark.skip(reason="broken, fixme")
 def test_self_check_db_positive_enable(test_db):
     logger = Mock()
 
@@ -78,6 +79,7 @@ def test_self_check_db_negative_disabled(test_db):
     assert test_db.sites[0].disabled is True
 
 
+@pytest.mark.skip(reason='broken, fixme')
 @pytest.mark.slow
 def test_self_check_db_negative_enabled(test_db):
     logger = Mock()
@@ -95,6 +97,7 @@ def test_self_check_db_negative_enabled(test_db):
 
 
 @pytest.mark.slow
+@pytest.mark.skip(reason="broken, fixme")
 def test_maigret_results(test_db):
     logger = Mock()
 

tests/test_report.py

@@ -2,6 +2,7 @@
 import copy
 import json
 import os
+import pytest
 from io import StringIO
 
 import xmind
@@ -424,6 +425,7 @@ def test_html_report_broken():
     assert SUPPOSED_BROKEN_INTERESTS in report_text
 
 
+@pytest.mark.skip(reason='connection reset, fixme')
 def test_pdf_report():
     report_name = 'report_test.pdf'
     context = generate_report_context(TEST)

utils/add_tags.py

@@ -3,7 +3,7 @@ import random
 from argparse import ArgumentParser, RawDescriptionHelpFormatter
 
 from maigret.maigret import MaigretDatabase
-from maigret.submit import get_alexa_rank
+from maigret.submit import Submitter
 
 
 def update_tags(site):
@@ -22,7 +22,7 @@ def update_tags(site):
         site.disabled = True
 
     print(f'Old alexa rank: {site.alexa_rank}')
-    rank = get_alexa_rank(site.url_main)
+    rank = Submitter.get_alexa_rank(site.url_main)
     if rank:
         print(f'New alexa rank: {rank}')
         site.alexa_rank = rank
@@ -36,6 +36,7 @@ if __name__ == '__main__':
     parser.add_argument("--base","-b", metavar="BASE_FILE",
                         dest="base_file", default="maigret/resources/data.json",
                         help="JSON file with sites data to update.")
+    parser.add_argument("--name", help="Name of site to check")
 
     pool = list()
 
@@ -45,12 +46,17 @@ if __name__ == '__main__':
     db.load_from_file(args.base_file).sites
 
     while True:
-        site = random.choice(db.sites)
+        if args.name:
+            sites = list(db.ranked_sites_dict(names=[args.name]).values())
+            site = random.choice(sites)
+        else:
+            site = random.choice(db.sites)
+
         if site.engine == 'uCoz':
             continue
 
-        if not 'in' in site.tags:
+        # if not 'in' in site.tags:
-            continue
+        #     continue
 
         update_tags(site)
 

utils/check_engines.py

@@ -0,0 +1,152 @@
+#!/usr/bin/env python3
+"""Maigret: Supported Site Listing with Alexa ranking and country tags
+This module generates the listing of supported sites in file `SITES.md`
+and pretty prints file with sites data.
+"""
+import aiohttp
+import asyncio
+import json
+import sys
+import requests
+import logging
+import threading
+import xml.etree.ElementTree as ET
+from datetime import datetime
+from argparse import ArgumentParser, RawDescriptionHelpFormatter
+
+import tqdm.asyncio
+
+from maigret.maigret import get_response, site_self_check
+from maigret.sites import MaigretSite, MaigretDatabase, MaigretEngine
+from maigret.utils import CaseConverter
+
+
+async def check_engine_of_site(site_name, sites_with_engines, future, engine_name, semaphore, logger):
+    async with semaphore:
+        response = await get_response(request_future=future,
+                                      site_name=site_name,
+                                      logger=logger)
+
+        html_text, status_code, error_text, expection_text = response
+
+        if html_text and engine_name in html_text:
+            sites_with_engines.append(site_name)
+            return True
+    return False
+
+
+if __name__ == '__main__':
+    parser = ArgumentParser(formatter_class=RawDescriptionHelpFormatter
+                            )
+    parser.add_argument("--base","-b", metavar="BASE_FILE",
+                        dest="base_file", default="maigret/resources/data.json",
+                        help="JSON file with sites data to update.")
+
+    parser.add_argument('--engine', '-e', help='check only selected engine', type=str)
+
+    args = parser.parse_args()
+
+    log_level = logging.INFO
+    logging.basicConfig(
+        format='[%(filename)s:%(lineno)d] %(levelname)-3s  %(asctime)s %(message)s',
+        datefmt='%H:%M:%S',
+        level=log_level
+    )
+    logger = logging.getLogger('engines-check')
+    logger.setLevel(log_level)
+
+    db = MaigretDatabase()
+    sites_subset = db.load_from_file(args.base_file).sites
+    sites = {site.name: site for site in sites_subset}
+
+    with open(args.base_file, "r", encoding="utf-8") as data_file:
+        sites_info = json.load(data_file)
+        engines = sites_info['engines']
+
+    for engine_name, engine_data in engines.items():
+        if args.engine and args.engine != engine_name:
+            continue
+
+        if not 'presenseStrs' in engine_data:
+            print(f'No features to automatically detect sites on engine {engine_name}')
+            continue
+
+        engine_obj = MaigretEngine(engine_name, engine_data)
+
+        # setup connections for checking both engine and usernames
+        connector = aiohttp.TCPConnector(ssl=False)
+        connector.verify_ssl=False
+        session = aiohttp.ClientSession(connector=connector)
+
+        sem = asyncio.Semaphore(100)
+        loop = asyncio.get_event_loop()
+        tasks = []
+
+        # check sites without engine if they look like sites on this engine
+        new_engine_sites = []
+        for site_name, site_data in sites.items():
+            if site_data.engine:
+                continue
+
+            future = session.get(url=site_data.url_main,
+                                 allow_redirects=True,
+                                 timeout=10,
+                                 )
+
+            check_engine_coro = check_engine_of_site(site_name, new_engine_sites, future, engine_name, sem, logger)
+            future = asyncio.ensure_future(check_engine_coro)
+            tasks.append(future)
+
+        # progress bar
+        for f in tqdm.asyncio.tqdm.as_completed(tasks):
+            loop.run_until_complete(f)
+
+        print(f'Total detected {len(new_engine_sites)} sites on engine {engine_name}')
+        # dict with new found engine sites
+        new_sites = {site_name: sites[site_name] for site_name in new_engine_sites}
+
+        # update sites obj from engine
+        for site_name, site in new_sites.items():
+            site.request_future = None
+            site.engine = engine_name
+            site.update_from_engine(engine_obj)
+
+        async def update_site_data(site_name, site_data, all_sites, logger, no_progressbar):
+            updates = await site_self_check(site_name, site_data, logger, no_progressbar)
+            all_sites[site_name].update(updates)
+
+        tasks = []
+        # for new_site_name, new_site_data in new_sites.items():
+            # coro = update_site_data(new_site_name, new_site_data, new_sites, logger)
+            # future = asyncio.ensure_future(coro)
+            # tasks.append(future)
+
+        # asyncio.gather(*tasks)
+        for new_site_name, new_site_data in new_sites.items():
+            coro = update_site_data(new_site_name, new_site_data, new_sites, logger, no_progressbar=True)
+            loop.run_until_complete(coro)
+
+        updated_sites_count = 0
+
+        for s in new_sites:
+            site = new_sites[s]
+            site.request_future = None
+
+            if site.disabled:
+                print(f'{site.name} failed username checking of engine {engine_name}')
+                continue
+
+            site = site.strip_engine_data()
+
+            db.update_site(site)
+            updated_sites_count += 1
+            db.save_to_file(args.base_file)
+
+            print(f'Site "{s}": ' + json.dumps(site.json, indent=4))
+
+        print(f'Updated total {updated_sites_count} sites!')
+        print(f'Checking all sites on engine {engine_name}')
+
+        loop.run_until_complete(session.close())
+
+    print("\nFinished updating supported site listing!")

utils/import_sites.py

@@ -0,0 +1,280 @@
+#!/usr/bin/env python3
+import json
+import random
+import re
+
+import tqdm.asyncio
+from mock import Mock
+import requests
+
+from maigret.maigret import *
+from maigret.result import QueryStatus
+from maigret.sites import MaigretSite
+
+URL_RE = re.compile(r"https?://(www\.)?")
+TIMEOUT = 200
+
+
+async def maigret_check(site, site_data, username, status, logger):
+    query_notify = Mock()
+    logger.debug(f'Checking {site}...')
+
+    for username, status in [(username, status)]:
+        results = await maigret(
+            username,
+            {site: site_data},
+            logger,
+            query_notify,
+            timeout=TIMEOUT,
+            forced=True,
+            no_progressbar=True,
+        )
+
+        if results[site]['status'].status != status:
+            if results[site]['status'].status == QueryStatus.UNKNOWN:
+                msg = site_data.absence_strs
+                etype = site_data.check_type
+                context = results[site]['status'].context
+
+                logger.debug(f'Error while searching {username} in {site}, must be claimed. Context: {context}')
+                # if site_data.get('errors'):
+                #     continue
+                return False
+
+            if status == QueryStatus.CLAIMED:
+                logger.debug(f'Not found {username} in {site}, must be claimed')
+                logger.debug(results[site])
+                pass
+            else:
+                logger.debug(f'Found {username} in {site}, must be available')
+                logger.debug(results[site])
+                pass
+            return False
+
+    return site_data
+
+
+async def check_and_add_maigret_site(site_data, semaphore, logger, ok_usernames, bad_usernames):
+    async with semaphore:
+        sitename = site_data.name
+        positive = False
+        negative = False
+
+        for ok_username in ok_usernames:
+            site_data.username_claimed = ok_username
+            status = QueryStatus.CLAIMED
+            if await maigret_check(sitename, site_data, ok_username, status, logger):
+                # print(f'{sitename} positive case is okay')
+                positive = True
+                break
+
+        for bad_username in bad_usernames:
+            site_data.username_unclaimed = bad_username
+            status = QueryStatus.AVAILABLE
+            if await maigret_check(sitename, site_data, bad_username, status, logger):
+                # print(f'{sitename} negative case is okay')
+                negative = True
+                break
+
+        if positive and negative:
+            site_data = site_data.strip_engine_data()
+
+            db.update_site(site_data)
+            print(site_data.json)
+            try:
+                db.save_to_file(args.base_file)
+            except Exception as e:
+                logging.error(e, exc_info=True)
+            print(f'Saved new site {sitename}...')
+            ok_sites.append(site_data)
+
+
+if __name__ == '__main__':
+    parser = ArgumentParser(formatter_class=RawDescriptionHelpFormatter
+                            )
+    parser.add_argument("--base", "-b", metavar="BASE_FILE",
+                        dest="base_file", default="maigret/resources/data.json",
+                        help="JSON file with sites data to update.")
+
+    parser.add_argument("--add-engine", dest="add_engine", help="Additional engine to check")
+
+    parser.add_argument("--only-engine", dest="only_engine", help="Use only this engine from detected to check")
+
+    parser.add_argument('--check', help='only check sites in database', action='store_true')
+
+    parser.add_argument('--random', help='shuffle list of urls', action='store_true', default=False)
+
+    parser.add_argument('--top', help='top count of records in file', type=int, default=10000)
+
+    parser.add_argument('--filter', help='substring to filter input urls', type=str, default='')
+
+    parser.add_argument('--username', help='preferable username to check with', type=str)
+
+    parser.add_argument(
+        "--info",
+        "-vv",
+        action="store_true",
+        dest="info",
+        default=False,
+        help="Display service information.",
+    )
+    parser.add_argument(
+        "--verbose",
+        "-v",
+        action="store_true",
+        dest="verbose",
+        default=False,
+        help="Display extra information and metrics.",
+    )
+    parser.add_argument(
+        "-d",
+        "--debug",
+        "-vvv",
+        action="store_true",
+        dest="debug",
+        default=False,
+        help="Saving debugging information and sites responses in debug.txt.",
+    )
+
+    parser.add_argument("urls_file",
+                        metavar='URLS_FILE',
+                        action="store",
+                        help="File with base site URLs"
+                        )
+
+    args = parser.parse_args()
+
+    log_level = logging.ERROR
+    if args.debug:
+        log_level = logging.DEBUG
+    elif args.info:
+        log_level = logging.INFO
+    elif args.verbose:
+        log_level = logging.WARNING
+
+    logging.basicConfig(
+        format='[%(filename)s:%(lineno)d] %(levelname)-3s  %(asctime)s %(message)s',
+        datefmt='%H:%M:%S',
+        level=log_level
+    )
+    logger = logging.getLogger('engines-check')
+    logger.setLevel(log_level)
+
+    db = MaigretDatabase()
+    sites_subset = db.load_from_file(args.base_file).sites
+    sites = {site.name: site for site in sites_subset}
+    engines = db.engines
+
+    # TODO: usernames extractors
+    ok_usernames = ['alex', 'god', 'admin', 'red', 'blue', 'john']
+    if args.username:
+        ok_usernames = [args.username] + ok_usernames
+
+    bad_usernames = ['noonewouldeverusethis7']
+
+    with open(args.urls_file, 'r') as urls_file:
+        urls = urls_file.read().splitlines()
+        if args.random:
+            random.shuffle(urls)
+        urls = urls[:args.top]
+
+    raw_maigret_data = json.dumps({site.name: site.json for site in sites_subset})
+
+    new_sites = []
+    for site in tqdm.asyncio.tqdm(urls):
+        site_lowercase = site.lower()
+
+        domain_raw = URL_RE.sub('', site_lowercase).strip().strip('/')
+        domain_raw = domain_raw.split('/')[0]
+
+        if args.filter and args.filter not in domain_raw:
+            logger.debug('Site %s skipped due to filtering by "%s"', domain_raw, args.filter)
+            continue
+
+        if domain_raw in raw_maigret_data:
+            logger.debug(f'Site {domain_raw} already exists in the Maigret database!')
+            continue
+
+        if '"' in domain_raw:
+            logger.debug(f'Invalid site {domain_raw}')
+            continue
+
+        main_page_url = '/'.join(site.split('/', 3)[:3])
+
+        site_data = {
+            'url': site,
+            'urlMain': main_page_url,
+            'name': domain_raw,
+        }
+
+        try:
+            r = requests.get(main_page_url, timeout=5)
+        except:
+            r = None
+            pass
+
+        detected_engines = []
+
+        for e in engines:
+            strs_to_check = e.__dict__.get('presenseStrs')
+            if strs_to_check and r and r.text:
+                all_strs_in_response = True
+                for s in strs_to_check:
+                    if not s in r.text:
+                        all_strs_in_response = False
+                if all_strs_in_response:
+                    engine_name = e.__dict__.get('name')
+                    detected_engines.append(engine_name)
+                    logger.info(f'Detected engine {engine_name} for site {main_page_url}')
+
+        if args.only_engine and args.only_engine in detected_engines:
+            detected_engines = [args.only_engine]
+        elif not detected_engines and args.add_engine:
+            logging.debug('Could not detect any engine, applying default engine %s...', args.add_engine)
+            detected_engines = [args.add_engine]
+
+        def create_site_from_engine(sitename, data, e):
+            site = MaigretSite(sitename, data)
+            site.update_from_engine(db.engines_dict[e])
+            site.engine = e
+            return site
+
+        for engine_name in detected_engines:
+            site = create_site_from_engine(domain_raw, site_data, engine_name)
+            new_sites.append(site)
+            logger.debug(site.json)
+
+            # if engine_name == "phpBB":
+            #     site_data_with_subpath = dict(site_data)
+            #     site_data_with_subpath["urlSubpath"] = "/forum"
+            #     site = create_site_from_engine(domain_raw, site_data_with_subpath, engine_name)
+            #     new_sites.append(site)
+
+        # except Exception as e:
+        #     print(f'Error: {str(e)}')
+        #     pass
+
+    print(f'Found {len(new_sites)}/{len(urls)} new sites')
+
+    if args.check:
+        for s in new_sites:
+            print(s.url_main)
+        sys.exit(0)
+
+    sem = asyncio.Semaphore(20)
+    loop = asyncio.get_event_loop()
+
+    ok_sites = []
+    tasks = []
+    for site in new_sites:
+        check_coro = check_and_add_maigret_site(site, sem, logger, ok_usernames, bad_usernames)
+        future = asyncio.ensure_future(check_coro)
+        tasks.append(future)
+
+    for f in tqdm.asyncio.tqdm.as_completed(tasks, timeout=TIMEOUT):
+        try:
+            loop.run_until_complete(f)
+        except asyncio.exceptions.TimeoutError:
+            pass
+
+    print(f'Found and saved {len(ok_sites)} sites!')

utils/sites_diff.py

@@ -0,0 +1,36 @@
+import sys
+import difflib
+import requests
+
+
+a = requests.get(sys.argv[1]).text
+b = requests.get(sys.argv[2]).text
+
+
+tokens_a = set(a.split('"'))
+tokens_b = set(b.split('"'))
+
+a_minus_b = tokens_a.difference(tokens_b)
+b_minus_a = tokens_b.difference(tokens_a)
+
+print(a_minus_b)
+print(b_minus_a)
+
+print(len(a_minus_b))
+print(len(b_minus_a))
+
+desired_strings = ["username", "not found", "пользователь", "profile", "lastname", "firstname", "biography",
+"birthday", "репутация", "информация", "e-mail"]
+
+
+def get_match_ratio(x):
+    return round(max([
+    	difflib.SequenceMatcher(a=x.lower(), b=y).ratio()
+    	for y in desired_strings
+    ]), 2)
+
+
+RATIO = 0.6
+
+print(sorted(a_minus_b, key=get_match_ratio, reverse=True)[:10])
+print(sorted(b_minus_a, key=get_match_ratio, reverse=True)[:10])

utils/update_site_data.py

@@ -114,7 +114,7 @@ Rank data fetched from Alexa by domains.
                 sys.stdout.flush()
                 index = index + 1
 
-        sites_full_list = [(s, s.alexa_rank) for s in sites_subset]
+        sites_full_list = [(s, int(s.alexa_rank)) for s in sites_subset]
 
         sites_full_list.sort(reverse=False, key=lambda x: x[1])
 
@@ -137,7 +137,11 @@ Rank data fetched from Alexa by domains.
             site_file.write(f'1. {favicon} [{site}]({url_main})*: top {valid_rank}{tags}*{note}\n')
             db.update_site(site)
 
-        site_file.write(f'\nAlexa.com rank data fetched at ({datetime.utcnow()} UTC)\n')
+        site_file.write(f'\nThe list was updated at ({datetime.utcnow()} UTC)\n')
         db.save_to_file(args.base_file)
 
+        statistics_text = db.get_db_stats(is_markdown=True)
+        site_file.write('## Statistics\n\n')
+        site_file.write(statistics_text)
+
     print("\nFinished updating supported site listing!")