Initial Context Extractor: extension + Playwright/Camoufox package

Ship a shared markdown/prompt core used by a Brave/Chrome MV3 extension and a Python automation API, with pytest coverage, CI, and packaging smoke.
2026-07-15 14:52:22 -04:00
commit c91cd221d1
30 changed files with 2611 additions and 0 deletions
@@ -0,0 +1,40 @@
+"""Minimal example: capture context from a page using Camoufox (anti-detect Firefox).
+
+Camoufox hands you a normal Playwright Page, so ExtractorSession works
+unmodified. No `main_world_eval` or init-script workarounds are needed here:
+capture uses Playwright's native page.on(...) hooks (not JS injection), and
+markdown extraction only *reads* the DOM, which works fine in Camoufox's
+default isolated world.
+
+Run:
+    pip install -e ./automation[camoufox]
+    python automation/examples/scrape_camoufox.py https://example.com
+"""
+
+import sys
+
+from camoufox import Camoufox
+
+from context_extractor import ExtractorSession
+
+
+def main() -> None:
+    url = sys.argv[1] if len(sys.argv) > 1 else "https://example.com"
+
+    with Camoufox(headless=True, geoip=True) as browser:
+        page = browser.new_page()
+
+        session = ExtractorSession(page)
+
+        page.goto(url, wait_until="domcontentloaded")
+        page.wait_for_timeout(1000)  # let SPA fetches settle
+
+        print(session.build_ai_prompt())
+
+        # Or grab pieces individually:
+        # extracted = session.extract_markdown("#main-content")
+        # store = session.get_store()  # {"console": [...], "errors": [...], "network": [...]}
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,31 @@
+"""Async variant, using AsyncCamoufox + AsyncExtractorSession.
+
+Run:
+    pip install -e ./automation[camoufox]
+    python automation/examples/scrape_camoufox_async.py https://example.com
+"""
+
+import asyncio
+import sys
+
+from camoufox.async_api import AsyncCamoufox
+
+from context_extractor import AsyncExtractorSession
+
+
+async def main() -> None:
+    url = sys.argv[1] if len(sys.argv) > 1 else "https://example.com"
+
+    async with AsyncCamoufox(headless=True, geoip=True) as browser:
+        page = await browser.new_page()
+
+        session = AsyncExtractorSession(page)
+
+        await page.goto(url, wait_until="domcontentloaded")
+        await page.wait_for_timeout(1000)
+
+        print(await session.build_ai_prompt())
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,35 @@
+"""Minimal example: capture context from a page using plain Playwright + Chromium.
+
+Run:
+    pip install -e ./automation
+    playwright install chromium
+    python automation/examples/scrape_chromium.py https://example.com
+"""
+
+import sys
+
+from playwright.sync_api import sync_playwright
+
+from context_extractor import ExtractorSession
+
+
+def main() -> None:
+    url = sys.argv[1] if len(sys.argv) > 1 else "https://example.com"
+
+    with sync_playwright() as p:
+        browser = p.chromium.launch(headless=True)
+        page = browser.new_page()
+
+        # Attach capture *before* navigating so console/network from the very
+        # first load are seen.
+        session = ExtractorSession(page)
+
+        page.goto(url, wait_until="networkidle")
+
+        print(session.build_ai_prompt())  # selector=None -> whole <body>
+
+        browser.close()
+
+
+if __name__ == "__main__":
+    main()