{"id":68792,"library":"jalfresi-justext","title":"JusText","description":"A Go port of the jusText algorithm for extracting main content from HTML pages.","status":"active","version":"0.0.0-20221106200834-be571e3e3052","language":"go","source_language":null,"source_url":"https://github.com/JalfResi/justext","tags":["html","content","extraction","text","nlp"],"install":[{"cmd":"go get github.com/JalfResi/justext","lang":"bash","label":"Install github.com/JalfResi/justext"}],"dependencies":[],"imports":[{"symbol":"justext","correct":"github.com/JalfResi/justext"}],"quickstart":{"code":"package main\n\nimport (\n\t\"fmt\"\n\t\"github.com/JalfResi/justext\"\n\t\"strings\"\n)\n\nfunc main() {\n\thtml := \"

Main content

\"\n\tparagraphs, _ := justext.JusText(strings.NewReader(html), nil)\n\tfor _, p := range paragraphs {\n\t\tfmt.Println(p.Text)\n\t}\n}","lang":"go","description":"Extracts main content paragraphs from an HTML string."},"warnings":[],"env_vars":null,"search_vec":"'algorithm':8 'content':12,17 'extract':10,18 'go':3 'html':14,16 'justext':1,7 'main':11 'nlp':20 'page':15 'port':4 'text':19","created_at":"2026-06-17T17:53:56.570606+00:00","updated_at":"2026-06-17T17:53:56.570606+00:00","problems":[],"ecosystem":"go","meta_description":null,"install_score":null,"quickstart_score":null,"quickstart_tag":null,"pypi_latest":null,"cli_name":null,"cli_version":null,"type":"library","homepage":"https://github.com/JalfResi/justext","github":"https://github.com/JalfResi/justext","docs":"https://pkg.go.dev/github.com/JalfResi/justext#section-documentation","changelog":null,"pypi":null,"npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"categories":["utility"],"base_url":null,"auth_type":null,"provenance":{"verified_status":null,"verified_at":null,"last_verified":"2026-06-17","next_check":"2026-12-14","install_tag":null}}