Google has introduced LangExtract, an open-source Python library designed to help developers extract structured information from unstructured text using large language models such as the Gemini ...

Document intelligence framework for Python - Extract text, metadata, and structured data from PDFs, images, Office documents, and more. Built on Pandoc, PDFium, and Tesseract.

Cloudflare has accused Perplexity of bypassing website restrictions that explicitly block AI scraping. Perplexity's bot has now been delisted.

BookTrack A basic Python application to scrape book listings from a Big Bookseller and save results to a local SQLite database. You can also export the database contents to an XLSX file.