{"library":"extruct","type":"library","category":null,"description":"Extruct is a Python library for extracting embedded metadata from HTML markup. It currently supports W3C's HTML Microdata, embedded JSON-LD, Microformat (via mf2py), Facebook's Open Graph, experimental RDFa (via rdflib), and Dublin Core Metadata (DC-HTML-2003). The library is actively maintained with its current stable version being 0.18.0.","language":"python","status":"active","version":"0.18.0","tags":["web scraping","metadata extraction","html parsing","json-ld","microdata","opengraph","rdfa"],"last_verified":"Sun May 24","install":[{"cmd":"pip install extruct","imports":["from extruct import extract","from w3lib.html import get_base_url","from extruct.opengraph import OpenGraphExtractor"]},{"cmd":"pip install 'extruct[cli]'","imports":[]}],"homepage":null,"github":"https://github.com/scrapinghub/extruct","docs":null,"changelog":null,"pypi":"https://pypi.org/project/extruct/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":100,"avg_install_s":4.8,"avg_import_s":1.56,"wheel_type":"sdist"},"url":"https://checklist.day/v1/registry/extruct/compatibility"}}