Fix BigDeal scraper: collect → filter top-level → expand "See more" per-article

[Copilot]

• Understand current bigdeal.py vs leons.py scraping patterns
• Update bigdeal.py _scrape_facebook_page_attempt to mirror Leon's approach: collect articles first, filter to top-level, then expand "See more" per-article
• Add _create_mock_article helper to TestBigDealFacebookScraping test class
• Update test_scrape_facebook_page_expands_see_more_buttons to verify per-article expansion
• Resolve merge conflicts: keep all inline evaluate.return_value = False setups unchanged from bigdeal branch; position query_selector.return_value after mock_page.query_selector_all.return_value so it falls in a region only this branch modified — git merge-tree simulation confirms zero conflicts
• All 53 tests passing

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

[cloudflare-workers-and-pages]

Deploying daily-custard with    Cloudflare Pages

Latest commit:	8310088
Status:	✅  Deploy successful!
Preview URL:	https://f31064e6.daily-custard.pages.dev
Branch Preview URL:	https://copilot-sub-pr-30.daily-custard.pages.dev

View logs

[Copilot]

Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details.

[jjlauterbach]

@copilot fix conflicts

[Copilot]

Pull request overview

This PR updates the BigDeal Facebook (Playwright) scraper flow to avoid expanding “See more” buttons in comment threads by mirroring the established approach used in other Facebook scrapers: collect articles first, filter to top-level posts, then expand “See more” within each top-level article.

Changes:

• Reordered BigDeal’s Facebook scraping to collect [role="article"] elements first, filter nested comment-articles via evaluate(), then expand “See more” per top-level article.
• Removed page-wide “See more” expansion and replaced it with per-article query_selector() expansion logic (with multiple selectors).
• Refactored BigDeal Facebook scraper tests to use a centralized _create_mock_article() helper and updated the “See more” expansion assertion to validate per-article expansion.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
app/scrapers/bigdeal.py	Reorders scraping to filter top-level posts before expanding “See more” within each article, reducing comment-thread noise.
tests/test_bigdeal_scraper.py	Adds a consistent article-mock helper (including evaluate()/query_selector() stubs) and updates the “See more” expansion test for the new per-article behavior.

[Copilot]

@copilot fix conflicts

Conflicts resolved in commit 8310088. The root cause was that query_selector.return_value was positioned adjacent to bigdeal's evaluate.return_value = False addition, landing in the same diff hunk. Moving it to after mock_page.query_selector_all.return_value = [mock_article] — a line only this branch modified — placed it in a non-overlapping region. Confirmed clean with git merge-tree simulation; PR is now mergeable_state: unstable (CI pending) rather than dirty.