init commit

.gitignore

@@ -0,0 +1,147 @@
+_proc/
+_quarto.yml
+sidebar.yml
+Gemfile.lock
+token
+_docs/
+conda/
+.last_checked
+.gitconfig
+*.bak
+*.log
+*~
+~*
+_tmp*
+tmp*
+tags
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+.vscode
+*.swp
+
+# osx generated files
+.DS_Store
+.DS_Store?
+.Trashes
+ehthumbs.db
+Thumbs.db
+.idea
+
+# pytest
+.pytest_cache
+
+# tools/trust-doc-nbs
+docs_src/.last_checked
+
+# symlinks to fastai
+docs_src/fastai
+tools/fastai
+
+# link checker
+checklink/cookies.txt
+
+# .gitconfig is now autogenerated
+.gitconfig
+
+_docs

README.md

@@ -0,0 +1,37 @@
+# playwrightnb
+
+This is a Python module that lets you use sync mode Playwright interactively, inside a Jupyter notebook.
+
+To use it:
+
+```python
+from playwrightnb import get_page
+page = get_page()
+page.goto('http://example.org');
+# ... do things with `page`...
+page.stop()
+```
+
+Unlike non-jupyter usage, you don't use a context manager, but instead use `stop` when you're done to close the browser session (or to be more precise -- internally we still use a context manager, but we patch it to not auto-close). `get_page` only returns the page object, not the browser or playwright objects. You should still be able to perform most common web scraping tasks effectively, such as:
+
+- Navigating to pages using `page.goto()`
+- Waiting for elements to load with `page.wait_for_selector()`
+- Extracting data from the page using methods like `page.query_selector()`, `page.query_selector_all()`, `page.text_content()`, etc.
+- Interacting with elements using `page.click()`, `page.type()`, `page.hover()`, and more
+- Evaluating JavaScript with `page.evaluate()`
+
+However, there are a few capabilities you might miss out on without direct access to the browser or playwright objects:
+
+1. Launching multiple browser contexts or pages simultaneously
+2. Configuring browser-specific settings or permissions
+3. Accessing browser-level methods like `browser.new_page()` or `browser.close()`
+
+For most scraping scenarios, having the page object alone should suffice. But if you need more advanced control, use the following code as a starting point (which is identical to the source of `get_page`):
+
+```python
+with sync_playwright() as p:
+    browser = p.chromium.launch(*args, **kw)
+    page = browser.new_context().new_page()
+    page.stop = p.stop
+```
+

playwrightnb/__init__.py

@@ -0,0 +1,30 @@
+import nest_asyncio,asyncio
+from playwright.sync_api import PlaywrightContextManager, sync_playwright
+from fastcore.utils import patch
+
+nest_asyncio.apply()
+
+PlaywrightContextManager.orig_pcm = PlaywrightContextManager.__enter__
+_orig_exit = PlaywrightContextManager.__exit__
+
+@patch
+def __enter__(self:PlaywrightContextManager):
+    def _exit(): _orig_exit(self)
+    orig = asyncio.BaseEventLoop.is_running
+    asyncio.BaseEventLoop.is_running = lambda self: False
+    try:
+        res = self.orig_pcm()
+        res.stop = _exit
+        return res
+    finally: asyncio.BaseEventLoop.is_running = orig
+
+@patch
+def __exit__(self:PlaywrightContextManager, *args, **kwargs): pass
+
+def get_page(*args, **kw):
+    "Get a new page in a Chromium browser, passing any arguments to `launch`"
+    with sync_playwright() as p:
+        page = p.chromium.launch(*args, **kw).new_context().new_page()
+        page.stop = p.stop
+        return page
+

pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=42", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "playwrightnb"
+version = "0.1.0"
+description = "Use sync mode Playwright interactively, inside a Jupyter notebook"
+readme = "README.md"
+license = { file = "LICENSE" }
+authors = [
+    { name = "Jeremy Howard", email = "info@fast.ai" }
+]
+requires-python = ">=3.7, <4"
+dependencies = [ "nest-asyncio", "fastcore", "playwright" ]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License"
+]
+