Huge update

.github/workflows/auto-merge.yml

@@ -6,6 +6,17 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref }}
   cancel-in-progress: true
 jobs:
+  auto-merge-dependabot:
+    runs-on: ubuntu-latest
+    if: ${{ github.actor == 'dependabot[bot]' }}
+    steps:
+      - id: dependabot-metadata
+        uses: dependabot/fetch-metadata@v1
+      - if: ${{ steps.dependabot-metadata.outputs.update-type != 'version-update:semver-major' }}
+        run: gh pr merge --auto --delete-branch --squash "${PR_URL}"
+        env:
+          PR_URL: ${{ github.event.pull_request.html_url }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
   auto-merge-updates:
     runs-on: ubuntu-latest
     if: ${{ github.actor == 'monosans' && startsWith(github.head_ref, 'update/') }}

.github/workflows/ci.yml

@@ -14,3 +14,30 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - run: pipx run pre-commit run --all-files --show-diff-on-failure
+  build:
+    strategy:
+      matrix:
+        os:
+          - ubuntu
+          - macos
+          - windows
+      fail-fast: false
+    runs-on: ${{ matrix.os }}-latest
+    steps:
+      - uses: actions/checkout@v4
+      - run: pipx install poetry
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: poetry
+          check-latest: true
+      - run: poetry install --only main,nuitka --sync --no-root --no-interaction
+      - run: poetry run --no-interaction python -m nuitka --onefile --python-flag='-m' --prefer-source-code --assume-yes-for-downloads --lto=yes proxy_scraper_checker
+      - uses: actions/upload-artifact@v4
+        with:
+          name: artifact-${{ matrix.os }}
+          path: |
+            config.toml
+            proxy_scraper_checker.bin
+            proxy_scraper_checker.exe
+          if-no-files-found: error

.github/workflows/update-dependencies.yml

@@ -12,6 +12,9 @@ jobs:
     strategy:
       matrix:
         include:
+          - cmd: pipx run poetry lock --no-interaction
+            commit-msg: Update poetry.lock
+            branch: update/poetry-lock
           - cmd: pipx run pre-commit autoupdate
             commit-msg: Update .pre-commit-config.yaml
             branch: update/pre-commit-config

.gitignore

@@ -376,7 +376,4 @@ $RECYCLE.BIN/
 
 # End of https://www.toptal.com/developers/gitignore/api/jetbrains+all,linux,macos,python,vim,visualstudiocode,windows
 
-proxies/
-proxies_anonymous/
-proxies_geolocation/
-proxies_geolocation_anonymous/
+out/

.pre-commit-config.yaml

@@ -35,6 +35,13 @@ repos:
           - --scripts-are-modules
         additional_dependencies:
           - aiohttp<4
+          - attrs
+          - certifi
+          - charset-normalizer<4
+          - maxminddb<3
+          - platformdirs<5
           - rich<14
-          - typing-extensions<5
-          - uvloop<0.20; implementation_name == "cpython" and (sys_platform == "darwin" or sys_platform == "linux")
+          - types-aiofiles
+          - typing-extensions<5; python_version < "3.11"
+          - tomli<3; python_version < "3.11"
+          - uvloop<0.20; platform_python_implementation == "CPython" and (sys_platform == "darwin" or sys_platform == "linux")

README.md

@@ -6,27 +6,37 @@
 
 HTTP, SOCKS4, SOCKS5 proxies scraper and checker.
 
-- Asynchronous.
-- Uses regex to search for proxies (ip:port format) on a web page, allowing proxies to be extracted even from json without making changes to the code.
-- It is possible to specify the URL to which to send a request to check the proxy.
-- Can sort proxies by speed.
-- Supports determining the geolocation of the proxy exit node.
 - Can determine if the proxy is anonymous.
+- Supports determining the geolocation of the proxy exit node.
+- Can sort proxies by speed.
+- Uses regex to find proxies of format `protocol://username:password@ip:port` on a web page or in a local file, allowing proxies to be extracted even from json without code changes.
+- Supports proxies with authentication.
+- It is possible to specify the URL to which to send a request to check the proxy.
+- Supports saving to plain text and json.
+- Asynchronous.
 
-You can get proxies obtained using this script in [monosans/proxy-list](https://github.com/monosans/proxy-list).
+You can get proxies obtained using this project in [monosans/proxy-list](https://github.com/monosans/proxy-list).
 
 ## Installation and usage
 
-### Desktop
+### Pre-compiled binary
+
+This is the easiest way, but it is only available for x64 Windows, macOS and Linux. Just download the archive for your OS from <https://nightly.link/monosans/proxy-scraper-checker/workflows/ci/main?preview>, unzip it, edit `config.toml` and run the executable.
 
+If Windows Defender detects an executable file as a virus, please read [this](https://github.com/Nuitka/Nuitka/issues/2495#issuecomment-1762836583).
+
+### Running from source code
+
+#### Desktop
+
+- Install [Python](https://python.org/downloads). The minimum version required is 3.8. The recommended version is 3.11, because 3.12 may not install some libraries in the absence of a C compiler.
 - Download and unpack [the archive with the program](https://github.com/monosans/proxy-scraper-checker/archive/refs/heads/main.zip).
-- Edit `config.ini` to your preference.
-- Install [Python](https://python.org/downloads) (minimum required version is 3.7).
+- Edit `config.toml` to your preference.
 - Run the script that installs dependencies and starts `proxy-scraper-checker`:
   - On Windows run `start.cmd`
   - On Unix-like operating systems run `start.sh`
 
-### Termux
+#### Termux
 
 To use `proxy-scraper-checker` in Termux, knowledge of the Unix command-line interface is required.
 
@@ -35,27 +45,18 @@ To use `proxy-scraper-checker` in Termux, knowledge of the Unix command-line int
   ```bash
   bash <(curl -fsSL 'https://raw.githubusercontent.com/monosans/proxy-scraper-checker/main/install-termux.sh')
   ```
-- Edit `~/proxy-scraper-checker/config.ini` to your preference using a text editor (vim/nano).
+- Edit `~/proxy-scraper-checker/config.toml` to your preference using a text editor (vim/nano).
 - To run `proxy-scraper-checker` use the following command:
   ```bash
   cd ~/proxy-scraper-checker && sh start-termux.sh
   ```
 
-## Checking local proxy lists
-
-To check the local proxy lists, start the Python HTTP server on your local machine by running the `python -m http.server --bind localhost` command in the folder with the proxy lists. After that, add links to the appropriate files in `config.ini`.
+## Something else?
 
-## Folders description
-
-When the script finishes running, the following folders will be created (this behavior can be changed in the config):
-
-- `proxies` - proxies with any anonymity level.
-- `proxies_anonymous` - anonymous proxies.
-- `proxies_geolocation` - same as `proxies`, but includes exit-node's geolocation.
-- `proxies_geolocation_anonymous` - same as `proxies_anonymous`, but includes exit-node's geolocation.
-
-Geolocation format is `ip:port|Country|Region|City`.
+All other info is available in `config.toml` file.
 
 ## License
 
 [MIT](LICENSE)
+
+This product includes GeoLite2 Data created by MaxMind, available from <https://www.maxmind.com>.