PDF & DOCX to Markdown — Document Extractor for LLM/RAG

fetchbase/document-to-markdown

Convert PDF and Word (DOCX) documents into clean Markdown, text, or JSON. Smart PDF paragraph reflow, page markers for RAG citations, full DOCX structure (headings, lists, tables), custom auth headers. No browser — parses in seconds. Charged per page processed — no startup fee.

Split any PDF into individual pages instantly. Extract all pages, specific pages (1,3,5), or ranges (1-5). Handles up to 50,000 pages. Flat $0.005 per run. Perfect first step for document processing pipelines — chain with OCR, table extraction, and text analysis actors.

Extract text, metadata, and page-by-page content from PDF files. Provide PDF URLs and get structured JSON with full text, per-page text, page count, author, title, creation date, and more. Export as JSON, CSV, or Excel. No browser or proxy needed.

DEA Controlled Substance Registrant Actions Crawler

jungle_synthesizer/dea-arcos-prescriber-crawler

Crawl DEA administrative actions, registration revocations, suspensions, and controlled-substance applications from the Federal Register API. Extracts DEA registration numbers, action types, registrant names, and states for opioid litigation, pharma sales, and compliance.

PDF to Text API | Document Extraction for LLMs & RAG

andok/pdf-text-converter

Convert bulk PDF documents via URL into clean, raw text. The perfect document scraper for LLMs, vector databases, and RAG pipelines.

Read scanned PDFs and get clean text per page, with a confidence score for each one. Pages that already carry a text layer are read directly and never billed as OCR, so mixed batches come back faster, more accurately and cheaper.

Rust Input Function Example

lukaskrivka/rust-input-function-example

Dynamically compile and run input-provided page function. Like Cheerio Scraper but in Rust.

PDF Structured Table Extractor

automation-lab/pdf-structured-table-extractor

Extract structured tables from public PDF URLs into JSON rows and coordinate-aware cells with page provenance, confidence scores, and parsing warnings.

German Insolvency (insolvenzbekanntmachungen.de) Scraper

lexis-solutions/german-insolvency-announcements-scraper

Scrape official German insolvency announcements from neu.insolvenzbekanntmachungen.de. Extract full texts, dates, courts & companies with filters for states, subjects & dates. Ideal for credit risk, BI & legal research.

Belgisch Staatsblad Scraper — Belgian Official Gazette

studio-amba/staatsblad-scraper

Scrape publications from the Belgian Official Gazette (Belgisch Staatsblad / Moniteur Belge). Laws, royal decrees, ministerial orders with NUMAC IDs and PDF links.

LinkedIn Ads Library Scraper - No Cookies

silentflow/linkedin-ads-scraper

Scrape LinkedIn Ads Library without cookies or login. Extract ad creatives, targeting data, impressions, and advertiser info. Search by keywords, scrape specific ads, or get all ads from any company.