bobseares-2/seleniumbase-website-scraper
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

write README.md

Browse Source
This commit is contained in:
a2a-cloud
2026-06-08 23:17:11 +00:00
parent 1d0473b3a2
commit 3edcce41c6
1 changed files with 6 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@@ -44,12 +44,13 @@ Returns fields include: {status, items, pages_visited, html_captures, screenshot
An LLM-powered planner that iterates scrapes until a goal is satisfied or a safety/stop condition occurs. An LLM-powered planner that iterates scrapes until a goal is satisfied or a safety/stop condition occurs.
Inputs: Inputs:
- goal — natural-language target (e.g., "Collect quotes text and authors from the first 2 pages"). - goal — natural-language target (e.g., "Collect quotes text and authors from the first 2 pages").
- url — start page (absolute http/https). Same-origin only for all iterations. - start_url — start page (absolute http/https). Same-origin only for all iterations unless allowed_domains is provided.
- selectors — optional initial CSS selector map (defaults to {"title": "title"}). - seed_selectors — optional initial CSS selector map (defaults to {"title": "title"}).
- min_items — stop when this many items have been collected. - max_steps — planner steps (hard-capped at 3 improvements).
- max_iterations — planner budget (default 5, hard-capped at 3 improvements per runtime notes). - max_pages — pages per scrape pass (default 1, capped by agent config).
- per_pass_max_pages — pages per scrape pass (default 1, capped by agent config). - max_runtime_seconds — total runtime budget across steps.
- wait_seconds, output_format, headless, user_agent, respect_robots, rate_limit_seconds, screenshot — mirror scrape_website. - wait_seconds, output_format, headless, user_agent, respect_robots, rate_limit_seconds, screenshot — mirror scrape_website.
- allowed_domains — optional whitelist; else restricted to same-origin.
Outputs: Outputs:
- status — ok | no_items | blocked_by_robots_txt | manual_intervention_required | browser_runtime_unavailable | error - status — ok | no_items | blocked_by_robots_txt | manual_intervention_required | browser_runtime_unavailable | error