Extract text, RAG-ready markdown, and tables from PDF URLs. Every detected table becomes its own CSV-ready dataset record. No OCR; scanned pages are flagged, never guessed.
2
Users / 30d
29
Runs / 30d
—
Rating
Updated 15 Sept 2026
Apify builder
@inn_corp
Leaderboard position
out of 6,248
New Actors / 30d
#243
Total Actors
#885
Active users / 30d
#1325
Total users
#2379
Runs / 30d
#1622
Total runs
#3391
Portfolio stats
New Actors / 30d
11
Total Actors
11
Active users / 30d
12
+9 since first snapshot
Total users
23
Runs / 30d
232
+229 since first snapshot
Total runs
274
Portfolio history
Daily publishing
11
Each bar represents one UTC day.
Actor portfolio
11 matching of 11 Actors · page 1 of 1
Extract text, RAG-ready markdown, and tables from PDF URLs. Every detected table becomes its own CSV-ready dataset record. No OCR; scanned pages are flagged, never guessed.
2
Users / 30d
29
Runs / 30d
—
Rating
Transcribe audio and video you supply, or public podcast RSS/Atom feed episodes, with Whisper (faster-whisper, int8) running inside the Actor. Plain text, SRT, VTT, and optional approximate word timestamps. No scraped platform video.
1
Users / 30d
21
Runs / 30d
Search Bluesky posts by keyword or hashtag, or fetch posts by URL, via Bluesky's official public API. Posts only by design: no follower harvesting, no profile scraping. Deleted posts are never returned.
1
Users / 30d
21
Runs / 30d
Fetch RSS and Atom feeds and return clean digest records. Optional cross-run new-items-only mode for scheduled AI-agent monitoring.
1
Users / 30d
20
Runs / 30d
Fetch open job postings from Greenhouse, Lever, and Ashby company career boards via their own public JSON APIs. One normalized record schema across all three platforms. No personal data, contact info in descriptions stripped by default.
1
Users / 30d
20
Runs / 30d
Fetch live prediction markets from Polymarket's public Gamma API and Kalshi's public markets API. One clean record per market: question, outcomes, prices, volume, liquidity, status, and URL. No account or API key required for either source.
1
Users / 30d
20
Runs / 30d
Full-page or viewport screenshots (PNG/JPEG/WebP/PDF) from a real headless Chrome browser, with a wait-for-selector option for JS-heavy pages.
1
Users / 30d
20
Runs / 30d
Extract company financials (revenue, net income, EPS, assets, cash flow) from SEC XBRL company facts by ticker or CIK. Official SEC data, values never invented.
1
Users / 30d
21
Runs / 30d
Fetch SEC EDGAR company filings by ticker or CIK. Returns filing metadata and optional document text. Official SEC data, no personal data.
1
Users / 30d
21
Runs / 30d
Run Google's own open-source Lighthouse against a list of URLs in a real headless Chrome. Get Performance, Accessibility, Best Practices, and SEO scores plus Core Web Vitals (LCP, CLS, TBT, FCP) per URL, with top opportunities and a hosted full report.
1
Users / 30d
19
Runs / 30d
Parse XML sitemaps into clean URL records. Gzip support, nested sitemap-index recursion with a sane depth cap, lastmod/pattern filtering. Reads only files a site published for exactly this purpose.
1
Users / 30d
20
Runs / 30d
—
Rating
—
Rating
—
Rating
—
Rating
—
Rating
—
Rating
—
Rating
—
Rating
—
Rating
—
Rating