{"library":"opendataloader-pdf","title":"OpenDataLoader PDF","description":"A Python wrapper for the opendataloader-pdf Java CLI that extracts structured content and metadata from PDFs, supporting accessibility tags, tables, headings, and strikethrough text. Current version 2.4.3, requires Python >=3.10, released every few months.","language":"python","status":"active","last_verified":"Sat May 09","install":{"commands":["pip install opendataloader-pdf"],"cli":null},"imports":["from opendataloader_pdf import OpenDataLoaderPDF"],"auth":{"required":false,"env_vars":[]},"quickstart":{"code":"from opendataloader_pdf import OpenDataLoaderPDF\n\nloader = OpenDataLoaderPDF(api_key=os.environ.get('API_KEY', ''))\nwith open('document.pdf', 'rb') as f:\n    result = loader.extract(f)\nprint(result['content'][:200])","lang":"python","description":"Initialize the extractor with an API key and extract content from a PDF file.","tag":null,"tag_description":null,"last_tested":null,"results":[]},"compatibility":null}