hamro-scrapy-playwright 0.1.0__tar.gz

hamro_scrapy_playwright-0.1.0/.gitignore

@@ -0,0 +1,164 @@
+.mise.toml
+.nvim.lua
+storage
+
+# The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore
+
+# 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/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# Visual Studio Code
+#  Ignores the folder created by VS Code when changing workspace settings, doing debugger
+#  configuration, etc. Can be commented out to share Workspace Settings within a team
+.vscode
+
+# Zed editor
+#  Ignores the folder created when setting Project Settings in the Zed editor. Can be commented out
+#  to share Project Settings within a team
+.zed

hamro_scrapy_playwright-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 hamro-scrapy-playwright contributors
+
+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.

hamro_scrapy_playwright-0.1.0/PKG-INFO

@@ -0,0 +1,150 @@
+Metadata-Version: 2.4
+Name: hamro-scrapy-playwright
+Version: 0.1.0
+Summary: Thin extension layer that integrates a pinned custom Chromium build into scrapy-playwright.
+Project-URL: Homepage, https://github.com/jyabadesk/hamro-scrapy-playwright
+Project-URL: Repository, https://github.com/jyabadesk/hamro-scrapy-playwright
+Project-URL: Issues, https://github.com/jyabadesk/hamro-scrapy-playwright/issues
+Author: hamro-scrapy-playwright contributors
+License: MIT
+License-File: LICENSE
+Keywords: chromium,headless,playwright,scraping,scrapy
+Classifier: Development Status :: 4 - Beta
+Classifier: Framework :: Scrapy
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Internet :: WWW/HTTP
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Requires-Dist: httpx>=0.28.0
+Requires-Dist: playwright>=1.40.0
+Requires-Dist: scrapy-playwright>=0.0.46
+Description-Content-Type: text/markdown
+
+# hamro-scrapy-playwright
+
+Thin extension layer that integrates a **pinned custom Chromium build** directly into [scrapy-playwright](https://github.com/scrapy-plugins/scrapy-playwright).
+
+Users only need to swap the Scrapy download handler — existing spiders with `meta={"playwright": True}` keep working unchanged.
+
+## Architecture
+
+```text
+Scrapy
+    │
+    ▼
+CustomChromiumDownloadHandler
+    │
+    ▼
+ScrapyPlaywrightDownloadHandler
+    │
+    ▼
+Playwright
+    │
+    ▼
+Custom Chromium Binary
+```
+
+* Subclasses `ScrapyPlaywrightDownloadHandler`, overrides only `_launch()`.
+* Firefox and WebKit are delegated to upstream scrapy-playwright untouched.
+
+## Requirements
+
+| Requirement | Version |
+|---|---|
+| Python | ≥ 3.11 |
+| OS | Linux x86_64 |
+| scrapy-playwright | ≥ 0.0.46 |
+| playwright | ≥ 1.40.0 |
+| httpx | ≥ 0.28.0 |
+
+## Installation
+
+```bash
+pip install hamro-scrapy-playwright
+```
+
+Or install from source:
+
+```bash
+git clone https://github.com/jyabadesk/hamro-scrapy-playwright.git
+cd hamro-scrapy-playwright
+pip install .
+```
+
+## Usage
+
+In your Scrapy project's `settings.py`:
+
+```python
+DOWNLOAD_HANDLERS = {
+    "http": "scrapy_playwright_custom.handler.CustomChromiumDownloadHandler",
+    "https": "scrapy_playwright_custom.handler.CustomChromiumDownloadHandler",
+}
+
+TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
+
+# Optional: configure Playwright as usual
+PLAYWRIGHT_LAUNCH_OPTIONS = {
+    "headless": True,
+}
+```
+
+That's it. Your spiders keep working unchanged:
+
+```python
+import scrapy
+
+
+class ExampleSpider(scrapy.Spider):
+    name = "example"
+    start_urls = ["https://example.com"]
+
+    def start_requests(self):
+        for url in self.start_urls:
+            yield scrapy.Request(url, meta={"playwright": True})
+
+    def parse(self, response):
+        self.logger.info("Title: %s", response.css("title::text").get())
+```
+
+## How It Works
+
+1. **Platform check** — raises `RuntimeError` on anything other than Linux x86_64.
+2. **Download** — streams the pinned Chromium archive from GitHub Releases (with retries and progress).
+3. **Verify** — mandatory SHA-256 checksum comparison; raises on mismatch.
+4. **Extract** — safe `tar.gz` extraction with path-traversal and symlink protection.
+5. **Discover** — locates the `chrome` / `chromium` executable inside the extracted tree.
+6. **Inject** — wraps Playwright's chromium `BrowserType` to always use the custom binary.
+7. **Launch args** — merges default anti-detection flags with any user-provided arguments.
+
+Browser files are stored in `~/.hamro-browser/`, never inside `site-packages`.
+
+```text
+~/.hamro-browser/
+├── browser/          # extracted Chromium
+├── downloads/        # cached archive
+├── metadata.json     # installed version + executable path
+└── checksum          # SHA-256 digest
+```
+
+## Non-Chromium Browsers
+
+When `PLAYWRIGHT_BROWSER_TYPE` is set to `firefox`, the handler throws a `RuntimeError` as only `chromium` is supported (and `webkit` is delegated to upstream scrapy-playwright with zero changes).
+
+## Building
+
+```bash
+pip install build
+python -m build
+```
+
+## License
+
+MIT

hamro_scrapy_playwright-0.1.0/README.md

@@ -0,0 +1,121 @@
+# hamro-scrapy-playwright
+
+Thin extension layer that integrates a **pinned custom Chromium build** directly into [scrapy-playwright](https://github.com/scrapy-plugins/scrapy-playwright).
+
+Users only need to swap the Scrapy download handler — existing spiders with `meta={"playwright": True}` keep working unchanged.
+
+## Architecture
+
+```text
+Scrapy
+    │
+    ▼
+CustomChromiumDownloadHandler
+    │
+    ▼
+ScrapyPlaywrightDownloadHandler
+    │
+    ▼
+Playwright
+    │
+    ▼
+Custom Chromium Binary
+```
+
+* Subclasses `ScrapyPlaywrightDownloadHandler`, overrides only `_launch()`.
+* Firefox and WebKit are delegated to upstream scrapy-playwright untouched.
+
+## Requirements
+
+| Requirement | Version |
+|---|---|
+| Python | ≥ 3.11 |
+| OS | Linux x86_64 |
+| scrapy-playwright | ≥ 0.0.46 |
+| playwright | ≥ 1.40.0 |
+| httpx | ≥ 0.28.0 |
+
+## Installation
+
+```bash
+pip install hamro-scrapy-playwright
+```
+
+Or install from source:
+
+```bash
+git clone https://github.com/jyabadesk/hamro-scrapy-playwright.git
+cd hamro-scrapy-playwright
+pip install .
+```
+
+## Usage
+
+In your Scrapy project's `settings.py`:
+
+```python
+DOWNLOAD_HANDLERS = {
+    "http": "scrapy_playwright_custom.handler.CustomChromiumDownloadHandler",
+    "https": "scrapy_playwright_custom.handler.CustomChromiumDownloadHandler",
+}
+
+TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
+
+# Optional: configure Playwright as usual
+PLAYWRIGHT_LAUNCH_OPTIONS = {
+    "headless": True,
+}
+```
+
+That's it. Your spiders keep working unchanged:
+
+```python
+import scrapy
+
+
+class ExampleSpider(scrapy.Spider):
+    name = "example"
+    start_urls = ["https://example.com"]
+
+    def start_requests(self):
+        for url in self.start_urls:
+            yield scrapy.Request(url, meta={"playwright": True})
+
+    def parse(self, response):
+        self.logger.info("Title: %s", response.css("title::text").get())
+```
+
+## How It Works
+
+1. **Platform check** — raises `RuntimeError` on anything other than Linux x86_64.
+2. **Download** — streams the pinned Chromium archive from GitHub Releases (with retries and progress).
+3. **Verify** — mandatory SHA-256 checksum comparison; raises on mismatch.
+4. **Extract** — safe `tar.gz` extraction with path-traversal and symlink protection.
+5. **Discover** — locates the `chrome` / `chromium` executable inside the extracted tree.
+6. **Inject** — wraps Playwright's chromium `BrowserType` to always use the custom binary.
+7. **Launch args** — merges default anti-detection flags with any user-provided arguments.
+
+Browser files are stored in `~/.hamro-browser/`, never inside `site-packages`.
+
+```text
+~/.hamro-browser/
+├── browser/          # extracted Chromium
+├── downloads/        # cached archive
+├── metadata.json     # installed version + executable path
+└── checksum          # SHA-256 digest
+```
+
+## Non-Chromium Browsers
+
+When `PLAYWRIGHT_BROWSER_TYPE` is set to `firefox`, the handler throws a `RuntimeError` as only `chromium` is supported (and `webkit` is delegated to upstream scrapy-playwright with zero changes).
+
+## Building
+
+```bash
+pip install build
+python -m build
+```
+
+## License
+
+MIT

hamro_scrapy_playwright-0.1.0/pyproject.toml

@@ -0,0 +1,60 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "hamro-scrapy-playwright"
+version = "0.1.0"
+description = "Thin extension layer that integrates a pinned custom Chromium build into scrapy-playwright."
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.11"
+authors = [
+    { name = "hamro-scrapy-playwright contributors" },
+]
+keywords = [
+    "scrapy",
+    "playwright",
+    "chromium",
+    "scraping",
+    "headless",
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Framework :: Scrapy",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: POSIX :: Linux",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Internet :: WWW/HTTP",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Typing :: Typed",
+]
+dependencies = [
+    "scrapy-playwright>=0.0.46",
+    "playwright>=1.40.0",
+    "httpx>=0.28.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/jyabadesk/hamro-scrapy-playwright"
+Repository = "https://github.com/jyabadesk/hamro-scrapy-playwright"
+Issues = "https://github.com/jyabadesk/hamro-scrapy-playwright/issues"
+
+[tool.hatch.build.targets.wheel]
+packages = ["scrapy_playwright_custom"]
+
+[tool.mypy]
+python_version = "3.11"
+strict = true
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true
+disallow_incomplete_defs = true
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]

hamro_scrapy_playwright-0.1.0/scrapy_playwright_custom/__init__.py

@@ -0,0 +1,3 @@
+"""hamro-scrapy-playwright: pinned custom Chromium for scrapy-playwright."""
+
+__version__: str = "0.1.0"