{"id":34428,"name":"trafilatura","description":"Python \u0026 Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML","url":"https://github.com/adbar/trafilatura","last_synced_at":"2025-09-05T06:13:36.044Z","repository":{"id":38206633,"uuid":"180136168","full_name":"adbar/trafilatura","owner":"adbar","description":"Python \u0026 Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML","archived":false,"fork":false,"pushed_at":"2025-08-08T13:57:31.000Z","size":35398,"stargazers_count":4627,"open_issues_count":85,"forks_count":308,"subscribers_count":33,"default_branch":"master","last_synced_at":"2025-09-01T16:01:15.459Z","etag":null,"topics":["article-extractor","corpus-builder","corpus-tools","crawler","html-to-markdown","html2text","llm","news-aggregator","news-crawler","nlp","rag","readability","rss-feed","scraping","tei","text-cleaning","text-extraction","text-mining","text-preprocessing","web-scraping"],"latest_commit_sha":null,"homepage":"https://trafilatura.readthedocs.io","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/adbar.png","metadata":{"files":{"readme":"README.md","changelog":"HISTORY.md","contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null},"funding":{"github":["adbar"],"patreon":null,"open_collective":null,"ko_fi":"adbarbaresi","tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"custom":null}},"created_at":"2019-04-08T11:38:48.000Z","updated_at":"2025-09-01T07:21:30.000Z","dependencies_parsed_at":"2024-05-28T16:20:13.935Z","dependency_job_id":"094bed18-c30b-4b59-bdcb-3c6842efc9b7","html_url":"https://github.com/adbar/trafilatura","commit_stats":{"total_commits":1395,"total_committers":39,"mean_commits":35.76923076923077,"dds":"0.10179211469534055","last_synced_commit":"85cd3d8aa1d349e931bdb247fc041c67f1a66f2b"},"previous_names":[],"tags_count":39,"template":false,"template_full_name":null,"purl":"pkg:github/adbar/trafilatura","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adbar","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/sbom","scorecard":{"id":165823,"data":{"date":"2025-08-11","repo":{"name":"github.com/adbar/trafilatura","commit":"5ff6f5cbce378b79570eacab2f0303150eb1d956"},"scorecard":{"version":"v5.2.1-40-gf6ed084d","commit":"f6ed084d17c9236477efd66e5b258b9d4cc7b389"},"score":5.1,"checks":[{"name":"Code-Review","score":5,"reason":"Found 17/30 approved changesets -- score normalized to 5","details":null,"documentation":{"short":"Determines if the project requires human code review before pull requests (aka merge requests) are merged.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#code-review"}},{"name":"Packaging","score":-1,"reason":"packaging workflow not detected","details":["Warn: no GitHub/GitLab publishing workflow detected."],"documentation":{"short":"Determines if the project is published as a package that others can easily download, install, easily update, and uninstall.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#packaging"}},{"name":"Maintained","score":6,"reason":"4 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 6","details":null,"documentation":{"short":"Determines if the project is \"actively maintained\".","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#maintained"}},{"name":"Token-Permissions","score":0,"reason":"detected GitHub workflow tokens with excessive permissions","details":["Info: jobLevel 'contents' permission set to 'read': .github/workflows/codeql.yml:18","Info: jobLevel 'actions' permission set to 'read': .github/workflows/codeql.yml:17","Warn: no topLevel permission defined: .github/workflows/codeql.yml:1","Warn: no topLevel permission defined: .github/workflows/tests.yml:1","Info: no jobLevel write permissions found"],"documentation":{"short":"Determines if the project's workflows follow the principle of least privilege.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#token-permissions"}},{"name":"Dangerous-Workflow","score":10,"reason":"no dangerous workflow patterns detected","details":null,"documentation":{"short":"Determines if the project's GitHub Action workflows avoid dangerous patterns.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#dangerous-workflow"}},{"name":"CII-Best-Practices","score":0,"reason":"no effort to earn an OpenSSF best practices badge detected","details":null,"documentation":{"short":"Determines if the project has an OpenSSF (formerly CII) Best Practices Badge.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#cii-best-practices"}},{"name":"License","score":10,"reason":"license file detected","details":["Info: project has a license file: LICENSE:0","Info: FSF or OSI recognized license: Apache License 2.0: LICENSE:0"],"documentation":{"short":"Determines if the project has defined a license.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#license"}},{"name":"Security-Policy","score":0,"reason":"security policy file not detected","details":["Warn: no security policy file detected","Warn: no security file to analyze","Warn: no security file to analyze","Warn: no security file to analyze"],"documentation":{"short":"Determines if the project has published a security policy.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#security-policy"}},{"name":"Binary-Artifacts","score":10,"reason":"no binaries found in the repo","details":null,"documentation":{"short":"Determines if the project has generated executable (binary) artifacts in the source repository.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#binary-artifacts"}},{"name":"Fuzzing","score":0,"reason":"project is not fuzzed","details":["Warn: no fuzzer integrations found"],"documentation":{"short":"Determines if the project uses fuzzing.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#fuzzing"}},{"name":"Signed-Releases","score":-1,"reason":"no releases found","details":null,"documentation":{"short":"Determines if the project cryptographically signs release artifacts.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#signed-releases"}},{"name":"Vulnerabilities","score":10,"reason":"0 existing vulnerabilities detected","details":null,"documentation":{"short":"Determines if the project has open, known unfixed vulnerabilities.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#vulnerabilities"}},{"name":"Branch-Protection","score":0,"reason":"branch protection not enabled on development/release branches","details":["Warn: branch protection not enabled for branch 'master'"],"documentation":{"short":"Determines if the default and release branches are protected with GitHub's branch protection settings.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#branch-protection"}},{"name":"Pinned-Dependencies","score":0,"reason":"dependency not pinned by hash detected -- score normalized to 0","details":["Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql.yml:28: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/codeql.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql.yml:32: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/codeql.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql.yml:46: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/codeql.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql.yml:59: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/codeql.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/tests.yml:55: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/tests.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/tests.yml:68: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/tests.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/tests.yml:76: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/tests.yml/master?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/tests.yml:114: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/tests.yml/master?enable=pin","Warn: pipCommand not pinned by hash: .github/workflows/tests.yml:61","Warn: pipCommand not pinned by hash: .github/workflows/tests.yml:80","Warn: pipCommand not pinned by hash: .github/workflows/tests.yml:99","Info:   0 out of   7 GitHub-owned GitHubAction dependencies pinned","Info:   0 out of   1 third-party GitHubAction dependencies pinned","Info:   0 out of   3 pipCommand dependencies pinned"],"documentation":{"short":"Determines if the project has declared and pinned the dependencies of its build process.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#pinned-dependencies"}},{"name":"SAST","score":10,"reason":"SAST tool is run on all commits","details":["Info: SAST configuration detected: CodeQL","Info: all commits (30) are checked with a SAST tool"],"documentation":{"short":"Determines if the project uses static code analysis.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#sast"}}]},"last_synced_at":"2025-08-16T14:49:34.550Z","repository_id":38206633,"created_at":"2025-08-16T14:49:34.550Z","updated_at":"2025-08-16T14:49:34.550Z"},"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273632913,"owners_count":25140772,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-04T02:00:08.968Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"owner":{"login":"adbar","name":"Adrien Barbaresi","uuid":"2125866","kind":"user","description":"Research scientist – natural language processing, web scraping and text analytics. Mostly with Python.","email":"","website":"adrien.barbaresi.eu","location":"Berlin","twitter":"adbarbaresi","company":"Berlin-Brg. Academy of Sciences (BBAW)","icon_url":"https://avatars.githubusercontent.com/u/2125866?u=e2eeeb3384ab9391f598ade37d4388ad23199ebd\u0026v=4","repositories_count":37,"last_synced_at":"2024-06-11T15:59:25.206Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/adbar","funding_links":[],"total_stars":3746,"followers":360,"following":281,"created_at":"2022-11-04T01:56:16.102Z","updated_at":"2024-06-11T15:59:26.956Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adbar","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adbar/repositories"},"packages":[{"id":2952567,"name":"trafilatura","ecosystem":"pypi","description":"Python \u0026 Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML.","homepage":"https://trafilatura.readthedocs.io","licenses":"Apache 2.0","normalized_licenses":["Apache-2.0"],"repository_url":"https://github.com/adbar/trafilatura","keywords_array":["corpus","html2text","news-crawler","natural-language-processing","scraper","tei-xml","text-extraction","webscraping","web-scraping"],"namespace":null,"versions_count":50,"first_release_published_at":"2019-07-17T11:13:14.000Z","latest_release_published_at":"2024-12-03T15:23:21.000Z","latest_release_number":"2.0.0","last_synced_at":"2025-09-04T03:30:58.732Z","created_at":"2022-04-10T12:53:21.234Z","updated_at":"2025-09-04T15:44:57.710Z","registry_url":"https://pypi.org/project/trafilatura/","install_command":"pip install trafilatura --index-url https://pypi.org/simple","documentation_url":"https://trafilatura.readthedocs.io/","metadata":{"funding":null,"documentation":null,"classifiers":["Development Status :: 5 - Production/Stable","Environment :: Console","Intended Audience :: Developers","Intended Audience :: Education","Intended Audience :: Information Technology","Intended Audience :: Science/Research","License :: OSI Approved :: Apache Software License","Operating System :: MacOS","Operating System :: Microsoft","Operating System :: POSIX","Programming Language :: Python","Programming Language :: Python :: 3","Programming Language :: Python :: 3.10","Programming Language :: Python :: 3.11","Programming Language :: Python :: 3.12","Programming Language :: Python :: 3.13","Programming Language :: Python :: 3.8","Programming Language :: Python :: 3.9","Topic :: Internet :: WWW/HTTP","Topic :: Scientific/Engineering :: Information Analysis","Topic :: Security","Topic :: Text Editors :: Text Processing","Topic :: Text Processing :: Linguistic","Topic :: Text Processing :: Markup :: HTML","Topic :: Text Processing :: Markup :: Markdown","Topic :: Text Processing :: Markup :: XML","Topic :: Utilities"],"normalized_name":"trafilatura","project_status":null},"repo_metadata":{"id":38206633,"uuid":"180136168","full_name":"adbar/trafilatura","owner":"adbar","description":"Python \u0026 Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML","archived":false,"fork":false,"pushed_at":"2025-08-08T13:57:31.000Z","size":35398,"stargazers_count":4627,"open_issues_count":85,"forks_count":308,"subscribers_count":33,"default_branch":"master","last_synced_at":"2025-09-01T16:01:15.459Z","etag":null,"topics":["article-extractor","corpus-builder","corpus-tools","crawler","html-to-markdown","html2text","llm","news-aggregator","news-crawler","nlp","rag","readability","rss-feed","scraping","tei","text-cleaning","text-extraction","text-mining","text-preprocessing","web-scraping"],"latest_commit_sha":null,"homepage":"https://trafilatura.readthedocs.io","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/adbar.png","metadata":{"files":{"readme":"README.md","changelog":"HISTORY.md","contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null},"funding":{"github":["adbar"],"patreon":null,"open_collective":null,"ko_fi":"adbarbaresi","tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"custom":null}},"created_at":"2019-04-08T11:38:48.000Z","updated_at":"2025-09-01T07:21:30.000Z","dependencies_parsed_at":"2024-05-28T16:20:13.935Z","dependency_job_id":"094bed18-c30b-4b59-bdcb-3c6842efc9b7","html_url":"https://github.com/adbar/trafilatura","commit_stats":{"total_commits":1395,"total_committers":39,"mean_commits":35.76923076923077,"dds":"0.10179211469534055","last_synced_commit":"85cd3d8aa1d349e931bdb247fc041c67f1a66f2b"},"previous_names":[],"tags_count":39,"template":false,"template_full_name":null,"purl":"pkg:github/adbar/trafilatura","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adbar","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/sbom","scorecard":{"id":165823,"data":{"date":"2025-08-11","repo":{"name":"github.com/adbar/trafilatura","commit":"5ff6f5cbce378b79570eacab2f0303150eb1d956"},"scorecard":{"version":"v5.2.1-40-gf6ed084d","commit":"f6ed084d17c9236477efd66e5b258b9d4cc7b389"},"score":5.1,"checks":[{"name":"Code-Review","score":5,"reason":"Found 17/30 approved changesets -- score normalized to 5","details":null,"documentation":{"short":"Determines if the project requires human code review before pull requests (aka merge requests) are merged.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#code-review"}},{"name":"Packaging","score":-1,"reason":"packaging workflow not detected","details":["Warn: no GitHub/GitLab publishing workflow detected."],"documentation":{"short":"Determines if the project is published as a package that others can easily download, install, easily update, and uninstall.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#packaging"}},{"name":"Maintained","score":6,"reason":"4 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 6","details":null,"documentation":{"short":"Determines if the project is \"actively maintained\".","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#maintained"}},{"name":"Token-Permissions","score":0,"reason":"detected GitHub workflow tokens with excessive permissions","details":["Info: jobLevel 'contents' permission set to 'read': .github/workflows/codeql.yml:18","Info: jobLevel 'actions' permission set to 'read': .github/workflows/codeql.yml:17","Warn: no topLevel permission defined: .github/workflows/codeql.yml:1","Warn: no topLevel permission defined: .github/workflows/tests.yml:1","Info: no jobLevel write permissions found"],"documentation":{"short":"Determines if the project's workflows follow the principle of least privilege.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#token-permissions"}},{"name":"Dangerous-Workflow","score":10,"reason":"no dangerous workflow patterns detected","details":null,"documentation":{"short":"Determines if the project's GitHub Action workflows avoid dangerous patterns.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#dangerous-workflow"}},{"name":"CII-Best-Practices","score":0,"reason":"no effort to earn an OpenSSF best practices badge detected","details":null,"documentation":{"short":"Determines if the project has an OpenSSF (formerly CII) Best Practices Badge.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#cii-best-practices"}},{"name":"License","score":10,"reason":"license file detected","details":["Info: project has a license file: LICENSE:0","Info: FSF or OSI recognized license: Apache License 2.0: LICENSE:0"],"documentation":{"short":"Determines if the project has defined a license.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#license"}},{"name":"Security-Policy","score":0,"reason":"security policy file not detected","details":["Warn: no security policy file detected","Warn: no security file to analyze","Warn: no security file to analyze","Warn: no security file to analyze"],"documentation":{"short":"Determines if the project has published a security policy.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#security-policy"}},{"name":"Binary-Artifacts","score":10,"reason":"no binaries found in the repo","details":null,"documentation":{"short":"Determines if the project has generated executable (binary) artifacts in the source repository.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#binary-artifacts"}},{"name":"Fuzzing","score":0,"reason":"project is not fuzzed","details":["Warn: no fuzzer integrations found"],"documentation":{"short":"Determines if the project uses fuzzing.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#fuzzing"}},{"name":"Signed-Releases","score":-1,"reason":"no releases found","details":null,"documentation":{"short":"Determines if the project cryptographically signs release artifacts.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#signed-releases"}},{"name":"Vulnerabilities","score":10,"reason":"0 existing vulnerabilities detected","details":null,"documentation":{"short":"Determines if the project has open, known unfixed vulnerabilities.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#vulnerabilities"}},{"name":"Branch-Protection","score":0,"reason":"branch protection not enabled on development/release branches","details":["Warn: branch protection not enabled for branch 'master'"],"documentation":{"short":"Determines if the default and release branches are protected with GitHub's branch protection settings.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#branch-protection"}},{"name":"Pinned-Dependencies","score":0,"reason":"dependency not pinned by hash detected -- score normalized to 0","details":["Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql.yml:28: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/codeql.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql.yml:32: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/codeql.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql.yml:46: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/codeql.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/codeql.yml:59: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/codeql.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/tests.yml:55: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/tests.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/tests.yml:68: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/tests.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/tests.yml:76: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/tests.yml/master?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/tests.yml:114: update your workflow using https://app.stepsecurity.io/secureworkflow/adbar/trafilatura/tests.yml/master?enable=pin","Warn: pipCommand not pinned by hash: .github/workflows/tests.yml:61","Warn: pipCommand not pinned by hash: .github/workflows/tests.yml:80","Warn: pipCommand not pinned by hash: .github/workflows/tests.yml:99","Info:   0 out of   7 GitHub-owned GitHubAction dependencies pinned","Info:   0 out of   1 third-party GitHubAction dependencies pinned","Info:   0 out of   3 pipCommand dependencies pinned"],"documentation":{"short":"Determines if the project has declared and pinned the dependencies of its build process.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#pinned-dependencies"}},{"name":"SAST","score":10,"reason":"SAST tool is run on all commits","details":["Info: SAST configuration detected: CodeQL","Info: all commits (30) are checked with a SAST tool"],"documentation":{"short":"Determines if the project uses static code analysis.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#sast"}}]},"last_synced_at":"2025-08-16T14:49:34.550Z","repository_id":38206633,"created_at":"2025-08-16T14:49:34.550Z","updated_at":"2025-08-16T14:49:34.550Z"},"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273632913,"owners_count":25140772,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-04T02:00:08.968Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"},"owner_record":{"login":"adbar","name":"Adrien Barbaresi","uuid":"2125866","kind":"user","description":"Research scientist – natural language processing, web scraping and text analytics. Mostly with Python.","email":"","website":"adrien.barbaresi.eu","location":"Berlin","twitter":"adbarbaresi","company":"Berlin-Brg. Academy of Sciences (BBAW)","icon_url":"https://avatars.githubusercontent.com/u/2125866?u=e2eeeb3384ab9391f598ade37d4388ad23199ebd\u0026v=4","repositories_count":37,"last_synced_at":"2024-06-11T15:59:25.206Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/adbar","funding_links":[],"total_stars":3746,"followers":360,"following":281,"created_at":"2022-11-04T01:56:16.102Z","updated_at":"2024-06-11T15:59:26.956Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adbar","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adbar/repositories"},"tags":[{"name":"v2.0.0","sha":"c6e834030779f0fb59aa3888c2f3222101bbdd0f","kind":"commit","published_at":"2024-12-03T15:23:03.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v2.0.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v2.0.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v2.0.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v2.0.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v2.0.0/manifests"},{"name":"v1.12.2","sha":"f57ef0b64b4cf96904e377eb012ebb38f097c518","kind":"commit","published_at":"2024-09-10T12:42:56.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.12.2","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.12.2","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.12.2","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.12.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.12.2/manifests"},{"name":"v1.12.1","sha":"14c79c062bc331632de7a164477b45522b2150d0","kind":"commit","published_at":"2024-08-20T10:58:11.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.12.1","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.12.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.12.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.12.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.12.1/manifests"},{"name":"v1.12.0","sha":"c60395cc3dcaadf5c66a393aeebec447f2dad7a0","kind":"commit","published_at":"2024-07-30T14:56:09.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.12.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.12.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.12.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.12.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.12.0/manifests"},{"name":"v1.11.0","sha":"60647e5eeff77df9ef4b7432a936f580736b3075","kind":"commit","published_at":"2024-06-27T13:59:56.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.11.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.11.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.11.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.11.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.11.0/manifests"},{"name":"v1.10.0","sha":"b36b6fad68b02cef00d615c5a061e78b52504e6b","kind":"commit","published_at":"2024-05-30T15:45:28.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.10.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.10.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.10.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.10.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.10.0/manifests"},{"name":"v1.9.0","sha":"11255bdfbddf1548fcd3714440a3e2f6128bde89","kind":"commit","published_at":"2024-05-02T10:17:52.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.9.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.9.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.9.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.9.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.9.0/manifests"},{"name":"v1.8.1","sha":"d9d47a71bc6c4a684e398d4939da25fb3cc670be","kind":"commit","published_at":"2024-04-03T11:47:18.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.8.1","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.8.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.8.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.8.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.8.1/manifests"},{"name":"v1.8.0","sha":"ff38644e41341c20f8f13e970b0e94f83fa4a0ef","kind":"commit","published_at":"2024-03-20T15:24:17.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.8.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.8.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.8.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.8.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.8.0/manifests"},{"name":"v1.7.0","sha":"97dc088190506f46651fca86c50c333832c82a03","kind":"commit","published_at":"2024-01-25T13:04:55.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.7.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.7.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.7.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.7.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.7.0/manifests"},{"name":"v1.6.4","sha":"85cd3d8aa1d349e931bdb247fc041c67f1a66f2b","kind":"commit","published_at":"2024-01-08T14:28:02.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.6.4","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.6.4","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.6.4","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.6.4","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.6.4/manifests"},{"name":"v1.6.3","sha":"e7b57234702b764abe1e0a1dfea4ef63e543e61a","kind":"commit","published_at":"2023-11-28T12:42:03.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.6.3","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.6.3","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.6.3","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.6.3","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.6.3/manifests"},{"name":"v1.6.2","sha":"5ce31d9f6c8d4854ce169678499326355c8d1cee","kind":"commit","published_at":"2023-09-06T15:40:27.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.6.2","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.6.2","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.6.2","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.6.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.6.2/manifests"},{"name":"v1.6.1","sha":"d85d58445bbfbe4bd484f08be956ca263a339e17","kind":"commit","published_at":"2023-06-15T12:53:11.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.6.1","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.6.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.6.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.6.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.6.1/manifests"},{"name":"v1.6.0","sha":"0bce2189288f4211e561c46083d7952fa65a7b72","kind":"commit","published_at":"2023-05-11T10:54:29.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.6.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.6.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.6.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.6.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.6.0/manifests"},{"name":"v1.5.0","sha":"2639b2417c6db8e4df1d4f3b42f454076f7fa140","kind":"commit","published_at":"2023-03-30T14:39:45.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.5.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.5.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.5.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.5.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.5.0/manifests"},{"name":"v1.4.1","sha":"14d9782891c2b4d6ff3eb0e00de2e9a11f01b43a","kind":"commit","published_at":"2023-01-19T16:52:45.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.4.1","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.4.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.4.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.4.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.4.1/manifests"},{"name":"v1.4.0","sha":"f9e35aac266e827591e0a20d63b690df64ceb093","kind":"commit","published_at":"2022-10-18T13:45:00.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.4.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.4.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.4.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.4.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.4.0/manifests"},{"name":"v1.3.0","sha":"c3f9a9f92f393f9f76e30b0d497ddb4119ba089b","kind":"commit","published_at":"2022-07-29T14:35:44.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.3.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.3.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.3.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.3.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.3.0/manifests"},{"name":"v1.2.2","sha":"168e660514a2ced3f7e902cd50476010f33d2337","kind":"commit","published_at":"2022-05-18T15:45:32.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.2.2","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.2.2","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.2.2","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.2.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.2.2/manifests"},{"name":"v1.2.1","sha":"1bb5fee6a4812e53b6597053c25efde995174d79","kind":"commit","published_at":"2022-05-02T10:18:02.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.2.1","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.2.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.2.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.2.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.2.1/manifests"},{"name":"v1.2.0","sha":"daf5d8de9836aaf9f6d0b39297cb5b55c8459364","kind":"commit","published_at":"2022-03-07T11:41:56.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.2.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.2.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.2.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.2.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.2.0/manifests"},{"name":"v1.1.0","sha":"776eb916df9c7b9f7fb75e06aa765fd7d638ff42","kind":"commit","published_at":"2022-02-21T16:19:53.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.1.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.1.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.1.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.1.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.1.0/manifests"},{"name":"v1.0.0","sha":"d7846a63d392bec20316dfc51a678dcf3d5e6888","kind":"commit","published_at":"2021-11-30T17:19:53.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v1.0.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v1.0.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v1.0.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.0.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v1.0.0/manifests"},{"name":"v0.9.3","sha":"05462658532471bd57652735792072898e79c233","kind":"commit","published_at":"2021-10-21T17:20:25.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.9.3","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.9.3","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.9.3","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.9.3","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.9.3/manifests"},{"name":"v0.9.2","sha":"85e28c6d4aac6c2406d2397bed95626cc1262cba","kind":"commit","published_at":"2021-10-06T16:05:27.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.9.2","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.9.2","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.9.2","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.9.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.9.2/manifests"},{"name":"v0.9.1","sha":"9357319e5fbeff1bcea20acb618af874e2cd7dbb","kind":"commit","published_at":"2021-08-02T16:02:55.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.9.1","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.9.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.9.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.9.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.9.1/manifests"},{"name":"v0.9.0","sha":"369cc3ab76c352ff2c81b987bfca68e59302f722","kind":"commit","published_at":"2021-06-15T16:00:58.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.9.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.9.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.9.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.9.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.9.0/manifests"},{"name":"v0.8.2","sha":"25698ebc93e1625f81f2d1f2300caf27425df33e","kind":"commit","published_at":"2021-04-21T15:34:43.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.8.2","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.8.2","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.8.2","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.8.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.8.2/manifests"},{"name":"v0.8.1","sha":"ab5b9aff3c2912ffef4d60496a08982f51b98338","kind":"commit","published_at":"2021-03-11T16:09:36.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.8.1","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.8.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.8.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.8.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.8.1/manifests"},{"name":"v0.8.0","sha":"77cefc2eff5651ffa74f1454645ffaca22e807b6","kind":"commit","published_at":"2021-02-19T18:01:02.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.8.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.8.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.8.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.8.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.8.0/manifests"},{"name":"v0.7.0","sha":"c67f2252623c16efe86a966e52158fab78e4242f","kind":"commit","published_at":"2021-01-04T13:41:01.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.7.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.7.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.7.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.7.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.7.0/manifests"},{"name":"v0.6.1","sha":"216f545a644234646529fd1b777d72db2bf8a683","kind":"commit","published_at":"2020-12-02T14:24:02.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.6.1","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.6.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.6.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.6.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.6.1/manifests"},{"name":"v0.6.0","sha":"e9b58339cd615e9fda16de1cf0e290aecd8b8a8a","kind":"commit","published_at":"2020-11-06T15:14:44.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.6.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.6.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.6.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.6.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.6.0/manifests"},{"name":"v0.5.2","sha":"8787420e486f6f55538a9052f04e1274b1dc9ff0","kind":"commit","published_at":"2020-09-22T11:13:48.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.5.2","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.5.2","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.5.2","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.5.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.5.2/manifests"},{"name":"v0.5.1","sha":"6fbb5b62f6dc4b41704449484dacff650db2fe52","kind":"commit","published_at":"2020-07-15T11:57:47.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.5.1","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.5.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.5.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.5.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.5.1/manifests"},{"name":"v0.5.0","sha":"6416fb4088e4cea9ee3ddbb5aacd60b61aac6520","kind":"commit","published_at":"2020-06-02T16:40:28.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.5.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.5.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.5.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.5.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.5.0/manifests"},{"name":"v0.4.1","sha":"311da8c5a4b26d48f7895936de14da11599c6e2b","kind":"commit","published_at":"2020-04-23T13:18:22.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.4.1","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.4.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.4.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.4.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.4.1/manifests"},{"name":"v0.1.0","sha":"23ac1b958fb8de86c7b7dfb3bfbabd90e00b7e49","kind":"commit","published_at":"2019-09-25T17:50:12.000Z","download_url":"https://codeload.github.com/adbar/trafilatura/tar.gz/v0.1.0","html_url":"https://github.com/adbar/trafilatura/releases/tag/v0.1.0","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/adbar/trafilatura@v0.1.0","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.1.0","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/tags/v0.1.0/manifests"}]},"repo_metadata_updated_at":"2025-09-04T15:44:57.710Z","dependent_packages_count":71,"downloads":1365602,"downloads_period":"last-month","dependent_repos_count":63,"rankings":{"downloads":0.6771095553381273,"dependent_repos_count":1.8666534940143593,"dependent_packages_count":0.23984917250134938,"stargazers_count":1.4913888915275813,"forks_count":3.7873245298149665,"docker_downloads_count":2.3739487015775653,"average":1.739379057462325},"purl":"pkg:pypi/trafilatura","advisories":[],"docker_usage_url":"https://docker.ecosyste.ms/usage/pypi/trafilatura","docker_dependents_count":13,"docker_downloads_count":9653,"usage_url":"https://repos.ecosyste.ms/usage/pypi/trafilatura","dependent_repositories_url":"https://repos.ecosyste.ms/api/v1/usage/pypi/trafilatura/dependencies","status":null,"funding_links":["https://github.com/sponsors/adbar","https://ko-fi.com/adbarbaresi"],"critical":null,"issue_metadata":{"last_synced_at":"2025-09-02T11:01:53.552Z","issues_count":259,"pull_requests_count":420,"avg_time_to_close_issue":12214947.23125,"avg_time_to_close_pull_request":784367.4587628866,"issues_closed_count":160,"pull_requests_closed_count":388,"pull_request_authors_count":53,"issue_authors_count":141,"avg_comments_per_issue":2.3474903474903477,"avg_comments_per_pull_request":1.8976190476190475,"merged_pull_requests_count":315,"bot_issues_count":0,"bot_pull_requests_count":50,"past_year_issues_count":51,"past_year_pull_requests_count":81,"past_year_avg_time_to_close_issue":1375194.4736842106,"past_year_avg_time_to_close_pull_request":274893.0606060606,"past_year_issues_closed_count":19,"past_year_pull_requests_closed_count":66,"past_year_pull_request_authors_count":23,"past_year_issue_authors_count":36,"past_year_avg_comments_per_issue":0.7058823529411765,"past_year_avg_comments_per_pull_request":1.8641975308641976,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":3,"past_year_merged_pull_requests_count":58,"issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/issues","maintainers":[{"login":"adbar","count":331,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/adbar"}],"active_maintainers":[{"login":"adbar","count":72,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/adbar"}]},"versions_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/trafilatura/versions","version_numbers_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/trafilatura/version_numbers","dependent_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/trafilatura/dependent_packages","related_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/trafilatura/related_packages","maintainers":[{"uuid":"adbar","login":"adbar","name":null,"email":null,"url":null,"packages_count":6,"html_url":"https://pypi.org/user/adbar/","role":null,"created_at":"2023-01-19T17:27:25.870Z","updated_at":"2023-01-19T17:27:25.870Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/maintainers/adbar/packages"}],"registry":{"name":"pypi.org","url":"https://pypi.org","ecosystem":"pypi","default":true,"packages_count":725006,"maintainers_count":308320,"namespaces_count":0,"keywords_count":238006,"github":"pypi","metadata":{"funded_packages_count":50519},"icon_url":"https://github.com/pypi.png","created_at":"2022-04-04T15:19:23.364Z","updated_at":"2025-09-05T05:40:58.860Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages","maintainers_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/maintainers","namespaces_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/namespaces"}}],"commits":{"id":674151,"full_name":"adbar/trafilatura","default_branch":"master","committers":[{"name":"Adrien Barbaresi","email":"barbaresi@bbaw.de","login":"adbar","count":1253},{"name":"Felipe Hertzer","email":"felipeaugustohertzer@gmail.com","login":null,"count":59},{"name":"Felipe Hertzer","email":"felipehertzer","login":"felipehertzer","count":16},{"name":"Vincent Barbaresi","email":"vincent.barbaresi@gmail.com","login":null,"count":11},{"name":"Luise K","email":"luise.sj.koehler@gmail.com","login":null,"count":8},{"name":"LukasBBAW","email":"60229375+LukasBBAW","login":"LukasBBAW","count":5},{"name":"Phong Nguyen","email":"phongtnit@gmail.com","login":null,"count":4},{"name":"Ido Shamun","email":"idoesh1@gmail.com","login":null,"count":3},{"name":"André Mácola","email":"andremacola@gmail.com","login":null,"count":3},{"name":"Ellie Lockhart","email":"69021568+EllieLockhart","login":"EllieLockhart","count":2},{"name":"Edward Krueger","email":"edkrueger@gmail.com","login":null,"count":2},{"name":"Tony Yang","email":"tonyyanga@gmail.com","login":null,"count":2},{"name":"Korben","email":"korben@korben.info","login":null,"count":1},{"name":"Kunal Sareen","email":"kunal.sareen@anu.edu.au","login":null,"count":1},{"name":"Luise Koehler","email":"luise.koehler@bbaw.de","login":null,"count":1},{"name":"Martin Müller","email":"mail@mueller-martin.net","login":null,"count":1},{"name":"Aleks Bunin","email":"sashkab","login":"sashkab","count":1},{"name":"Hergen Lehmann","email":"38007156+HeLehm","login":"HeLehm","count":1},{"name":"sourcery-ai[bot]","email":"58596630+sourcery-ai[bot]","login":"sourcery-ai[bot]","count":1},{"name":"feltcat","email":"58396817+feltcat","login":"feltcat","count":1},{"name":"dsgibbons","email":"82195909+dsgibbons","login":"dsgibbons","count":1},{"name":"dependabot[bot]","email":"49699333+dependabot[bot]","login":"dependabot[bot]","count":1},{"name":"deedy5","email":"65482418+deedy5","login":"deedy5","count":1},{"name":"Mark Mayo","email":"mark@there.co.nz","login":"marksmayo","count":1},{"name":"Mathieu Dhondt","email":"laundro@gmail.com","login":null,"count":1},{"name":"Michael Rienstra","email":"mrienstra@gmail.com","login":null,"count":1},{"name":"Phong Nguyen","email":"phongnguyen@Phongs-MacBook-Pro.local","login":null,"count":1},{"name":"Raphael Geronimi","email":"raphael.geronimi@gmail.com","login":null,"count":1},{"name":"Sean Madden","email":"maddesea@oregonstate.edu","login":null,"count":1},{"name":"Sourcery AI","email":"bot@sourcery.ai","login":null,"count":1},{"name":"Steve Dondley","email":"s@dondley.com","login":null,"count":1},{"name":"Tom Wojcik","email":"me@tomwojcik.com","login":null,"count":1},{"name":"Adrien Barbaresi","email":"adrien.barbaresi@oeaw.ac.at","login":null,"count":1},{"name":"Andrzej Witecki","email":"awwitecki@gmail.com","login":null,"count":1},{"name":"Ashik Paul","email":"ashikpaul17@gmail.com","login":null,"count":1},{"name":"Elwin","email":"abc602456615@163.com","login":null,"count":1},{"name":"François Schmidts","email":"francois.schmidts@gmail.com","login":null,"count":1},{"name":"ck","email":"glacierck@126.com","login":null,"count":1},{"name":"Yomguithereal","email":"guillaumeplique@gmail.com","login":null,"count":1}],"total_commits":1395,"total_committers":39,"total_bot_commits":2,"total_bot_committers":2,"mean_commits":35.76923076923077,"dds":0.10179211469534055,"past_year_committers":[{"name":"Adrien Barbaresi","email":"adbar","login":"adbar","count":77},{"name":"Felipe Hertzer","email":"felipehertzer","login":"felipehertzer","count":5},{"name":"Ido Shamun","email":"idoesh1@gmail.com","login":null,"count":3},{"name":"André Mácola","email":"andremacola@gmail.com","login":null,"count":3},{"name":"Vincent Barbaresi","email":"vincent.barbaresi@gmail.com","login":null,"count":2},{"name":"Tony Yang","email":"tonyyanga@gmail.com","login":null,"count":2},{"name":"Edward Krueger","email":"edkrueger@gmail.com","login":null,"count":2},{"name":"Steve Dondley","email":"s@dondley.com","login":null,"count":1},{"name":"Sean Madden","email":"maddesea@oregonstate.edu","login":null,"count":1},{"name":"Luise K","email":"luise.sj.koehler@gmail.com","login":null,"count":1},{"name":"Korben","email":"korben@korben.info","login":null,"count":1},{"name":"Andrzej Witecki","email":"awwitecki@gmail.com","login":null,"count":1},{"name":"feltcat","email":"58396817+feltcat","login":"feltcat","count":1},{"name":"Mark Mayo","email":"mark@there.co.nz","login":"marksmayo","count":1},{"name":"Hergen Lehmann","email":"38007156+HeLehm","login":"HeLehm","count":1},{"name":"Aleks Bunin","email":"sashkab","login":"sashkab","count":1}],"past_year_total_commits":103,"past_year_total_committers":16,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":6.4375,"past_year_dds":0.2524271844660194,"last_synced_at":"2024-01-19T11:38:40.365Z","last_synced_commit":"85cd3d8aa1d349e931bdb247fc041c67f1a66f2b","created_at":"2023-03-09T10:36:35.436Z","updated_at":"2024-01-19T11:38:40.365Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-03T00:00:08.276Z","repositories_count":5480019,"commits_count":853389012,"contributors_count":31098138,"owners_count":906558,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"adbar/trafilatura","html_url":"https://github.com/adbar/trafilatura","last_synced_at":"2025-09-02T11:01:53.552Z","status":null,"issues_count":259,"pull_requests_count":420,"avg_time_to_close_issue":12214947.23125,"avg_time_to_close_pull_request":784367.4587628866,"issues_closed_count":160,"pull_requests_closed_count":388,"pull_request_authors_count":53,"issue_authors_count":141,"avg_comments_per_issue":2.3474903474903477,"avg_comments_per_pull_request":1.8976190476190475,"merged_pull_requests_count":315,"bot_issues_count":0,"bot_pull_requests_count":50,"past_year_issues_count":51,"past_year_pull_requests_count":81,"past_year_avg_time_to_close_issue":1375194.4736842106,"past_year_avg_time_to_close_pull_request":274893.0606060606,"past_year_issues_closed_count":19,"past_year_pull_requests_closed_count":66,"past_year_pull_request_authors_count":23,"past_year_issue_authors_count":36,"past_year_avg_comments_per_issue":0.7058823529411765,"past_year_avg_comments_per_pull_request":1.8641975308641976,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":3,"past_year_merged_pull_requests_count":58,"created_at":"2023-05-15T01:46:10.187Z","updated_at":"2025-09-03T06:22:59.833Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/adbar%2Ftrafilatura/issues","issue_labels_count":{"enhancement":55,"bug":47,"question":37,"feedback":20,"documentation":15,"maintenance":15,"wontfix":4,"duplicate":3,"up for grabs":3,"good first issue":2,"evaluation":2,"dependencies":1},"pull_request_labels_count":{"dependencies":51,"feedback":2},"issue_author_associations_count":{"NONE":167,"OWNER":64,"CONTRIBUTOR":29},"pull_request_author_associations_count":{"OWNER":267,"CONTRIBUTOR":137,"NONE":44},"issue_authors":{"adbar":64,"alroythalus":12,"fortyfourforty":9,"andremacola":7,"Honesty-of-the-Cavernous-Tissue":5,"zirkelc":4,"felipehertzer":4,"naktinis":3,"pieterhartel":3,"DesBw":3,"krstp":3,"edkrueger":3,"majcl":2,"lord-alfred":2,"ibestvina":2,"TheRabidWolverine":2,"vodkaslime":2,"hamsarajan":2,"charleshan":2,"klvbdmh":2,"Guthman":2,"Yomguithereal":2,"clach04":2,"adri1wald":1,"robertour":1,"mirfan899":1,"LaundroMat":1,"szj2ys":1,"ArturasDruteika":1,"coderwpf":1,"dmoklaf":1,"pandemosth":1,"claudehenchoz":1,"niksite":1,"simplexx":1,"scaramouche88":1,"theabhinavdas":1,"cdfuller":1,"naftalibeder":1,"Rapid1898-code":1,"s-jse":1,"slavaGanzin":1,"BramVanroy":1,"pchalasani":1,"ezscode":1,"vprelovac":1,"Lucabenj":1,"julienlambert42":1,"nthomas-whistic":1,"beefyandbeef":1,"obeone":1,"BenBraft99":1,"unsleepy22":1,"PLPeeters":1,"rwinterschlaf":1,"idoshamun":1,"hugoobauer":1,"GaetanLepage":1,"hitesh1997":1,"GICodeWarrior":1,"fraseInc":1,"kianwilcox":1,"masylum":1,"vtempest":1,"stdweird":1,"georgedorn":1,"savchenko":1,"frenzymadness":1,"alex-bender":1,"mikhainin":1,"armsp":1,"regstuff":1,"L-cloud":1,"RedHotUnicorn":1,"chitralverma":1,"arcombe012":1,"asjsrep":1,"sampathmende":1,"FaFre":1,"Ryannees":1,"CNXDZS":1,"vulinh48936":1,"Stevod":1,"co2nunes":1,"thsunkid":1,"efecan-circlelabs":1,"Storm0921":1,"ethael":1,"rahulbot":1,"dark2star":1,"boxabirds":1,"DavidNemeskey":1,"CyberneticTurtle":1,"AnishPimpley":1,"vrnch":1,"reinoldus":1,"rbhalla":1,"tkapias":1,"andyskipper":1,"Jufik":1,"steineggerroland":1,"Philrobots":1,"kondounagi":1,"chrisgoddard":1,"rithvikshetty":1,"github-mickael-leclerc":1,"Psynbiotik":1,"joschu":1,"basilioss":1,"ChangyaoTian":1,"LeMoussel":1,"tejeshbhalla":1,"billziss-gh":1,"conceptofmind":1,"feltcat":1,"bezir":1,"JER-CE":1,"praveng":1,"marban":1,"rkiacnhg":1,"NiClassic":1,"thebigbone":1,"noobistz":1,"sdondley":1,"awwitecki":1,"shivanker":1,"kinoute":1,"MTB-nsartor":1,"dantetemplar":1,"ziodave":1,"saki021989":1,"Fabiha15":1,"jaekunchoi":1,"hyshandler":1,"snarb":1,"phongtnit":1,"Amaimersion":1,"proteusbr1":1,"zackw":1,"fakerybakery":1,"jackHedaya":1},"pull_request_authors":{"adbar":267,"dependabot[bot]":51,"felipehertzer":19,"unsleepy22":13,"knit-bee":10,"vbarbaresi":6,"andremacola":4,"gremid":4,"zirkelc":3,"idoshamun":3,"UVMvmfee":2,"ra312":2,"steineggerroland":2,"naktinis":2,"co-odw":2,"LydiaKoerber":2,"Honesty-of-the-Cavernous-Tissue":2,"AdamQuadmon":2,"dmoklaf":2,"mcflem06":2,"hugoobauer":2,"reinoldus":2,"eyupcanakman":2,"tommytyc":2,"RainRat":2,"swetepete":2,"nzw0301":2,"crackcomm":2,"edkrueger":2,"mikhainin":2,"vtempest":2,"PLPeeters":2,"seanswyi":2,"jpigla":2,"dlwh":2,"richard-epsilla":1,"tonyyanga":1,"sourcery-ai[bot]":1,"HawkClaws":1,"HeLehm":1,"awwitecki":1,"wu-seong":1,"Maddesea":1,"Korben00":1,"eltociear":1,"sdondley":1,"arcombe012":1,"masumsoft":1,"sashkab":1,"deedy5":1,"cclauss":1,"Spasfonx":1,"marksmayo":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-03T00:00:08.273Z","repositories_count":10065497,"issues_count":31124289,"pull_requests_count":94727574,"authors_count":10687451,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{"enhancement":7,"bug":7,"maintenance":6,"documentation":3,"question":3,"feedback":2},"past_year_pull_request_labels_count":{"dependencies":5},"past_year_issue_author_associations_count":{"NONE":31,"OWNER":16,"CONTRIBUTOR":7},"past_year_pull_request_author_associations_count":{"OWNER":56,"CONTRIBUTOR":32,"NONE":22},"past_year_issue_authors":{"adbar":16,"DesBw":3,"andyskipper":1,"klvbdmh":1,"krstp":1,"LaundroMat":1,"L-cloud":1,"LeMoussel":1,"NiClassic":1,"PLPeeters":1,"regstuff":1,"reinoldus":1,"Ryannees":1,"savchenko":1,"steineggerroland":1,"thsunkid":1,"unsleepy22":1,"vodkaslime":1,"vrnch":1,"ziodave":1,"arcombe012":1,"beefyandbeef":1,"BenBraft99":1,"billziss-gh":1,"BramVanroy":1,"cdfuller":1,"CNXDZS":1,"dmoklaf":1,"ezscode":1,"FaFre":1,"felipehertzer":1,"GaetanLepage":1,"georgedorn":1,"GICodeWarrior":1,"Guthman":1,"hitesh1997":1,"ibestvina":1},"past_year_pull_request_authors":{"adbar":56,"unsleepy22":13,"dependabot[bot]":5,"PLPeeters":2,"seanswyi":2,"vtempest":2,"mcflem06":2,"vbarbaresi":2,"Honesty-of-the-Cavernous-Tissue":2,"dmoklaf":2,"AdamQuadmon":2,"gremid":2,"crackcomm":2,"nzw0301":2,"reinoldus":2,"eyupcanakman":2,"steineggerroland":2,"ra312":2,"UVMvmfee":2,"arcombe012":1,"masumsoft":1,"felipehertzer":1,"deedy5":1},"maintainers":[{"login":"adbar","count":331,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/adbar"}],"active_maintainers":[{"login":"adbar","count":72,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/adbar"}]},"events":{"total":{"CreateEvent":20,"ReleaseEvent":1,"IssuesEvent":61,"WatchEvent":921,"DeleteEvent":20,"IssueCommentEvent":156,"PushEvent":77,"PullRequestReviewCommentEvent":27,"PullRequestReviewEvent":25,"PullRequestEvent":67,"ForkEvent":56},"last_year":{"CreateEvent":20,"ReleaseEvent":1,"IssuesEvent":61,"WatchEvent":921,"DeleteEvent":20,"IssueCommentEvent":156,"PushEvent":77,"PullRequestReviewCommentEvent":27,"PullRequestReviewEvent":25,"PullRequestEvent":67,"ForkEvent":56}},"keywords":["article-extractor","corpus-builder","corpus-tools","crawler","html-to-markdown","html2text","llm","news-aggregator","news-crawler","nlp","rag","readability","rss-feed","scraping","tei","text-cleaning","text-extraction","text-mining","text-preprocessing","web-scraping"],"dependencies":[{"ecosystem":"pypi","filepath":"docs/requirements.txt","sha":null,"kind":"manifest","created_at":"2022-07-19T18:03:49.287Z","updated_at":"2022-07-19T18:03:49.287Z","repository_link":"https://github.com/adbar/trafilatura/blob/master/docs/requirements.txt","dependencies":[{"id":260250922,"package_name":"sphinx","ecosystem":"pypi","requirements":"\u003e=5.0.2","direct":true,"kind":"runtime","optional":false},{"id":260250923,"package_name":"pydata-sphinx-theme","ecosystem":"pypi","requirements":"\u003e=0.9.0","direct":true,"kind":"runtime","optional":false},{"id":260250924,"package_name":"docutils","ecosystem":"pypi","requirements":"\u003e=0.18.1","direct":true,"kind":"runtime","optional":false},{"id":260250925,"package_name":"trafilatura","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2022-07-19T18:03:49.571Z","updated_at":"2022-07-19T18:03:49.571Z","repository_link":"https://github.com/adbar/trafilatura/blob/master/setup.py","dependencies":[{"id":260252597,"package_name":"certifi","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":260252598,"package_name":"charset_normalizer","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":260252599,"package_name":"courlan","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":260252600,"package_name":"htmldate","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":260252601,"package_name":"justext","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":260252602,"package_name":"lxml","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":260252603,"package_name":"urllib3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"tests/eval-requirements.txt","sha":null,"kind":"manifest","created_at":"2022-07-19T18:03:49.922Z","updated_at":"2022-07-19T18:03:49.922Z","repository_link":"https://github.com/adbar/trafilatura/blob/master/tests/eval-requirements.txt","dependencies":[{"id":260255367,"package_name":"trafilatura","ecosystem":"pypi","requirements":"==1.2.2","direct":true,"kind":"test","optional":false},{"id":260255368,"package_name":"beautifulsoup4","ecosystem":"pypi","requirements":"==4.11.1","direct":true,"kind":"test","optional":false},{"id":260255369,"package_name":"boilerpy3","ecosystem":"pypi","requirements":"==1.0.6","direct":true,"kind":"test","optional":false},{"id":260255370,"package_name":"goose3","ecosystem":"pypi","requirements":"==3.1.11","direct":true,"kind":"test","optional":false},{"id":260255371,"package_name":"html2text","ecosystem":"pypi","requirements":"==2020.1.16","direct":true,"kind":"test","optional":false},{"id":260255372,"package_name":"html-text","ecosystem":"pypi","requirements":"==0.5.2","direct":true,"kind":"test","optional":false},{"id":260255373,"package_name":"inscriptis","ecosystem":"pypi","requirements":"==2.2.0","direct":true,"kind":"test","optional":false},{"id":260255374,"package_name":"justext","ecosystem":"pypi","requirements":"==3.0.0","direct":true,"kind":"test","optional":false},{"id":260255375,"package_name":"newspaper3k","ecosystem":"pypi","requirements":"==0.2.8","direct":true,"kind":"test","optional":false},{"id":260255376,"package_name":"news-please","ecosystem":"pypi","requirements":"==1.5.22","direct":true,"kind":"test","optional":false},{"id":260255377,"package_name":"readabilipy","ecosystem":"pypi","requirements":"==0.2.0","direct":true,"kind":"test","optional":false},{"id":260255378,"package_name":"readability-lxml","ecosystem":"pypi","requirements":"==0.8.1","direct":true,"kind":"test","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/codeql.yml","sha":null,"kind":"manifest","created_at":"2023-02-12T04:15:26.826Z","updated_at":"2023-02-12T04:15:26.826Z","repository_link":"https://github.com/adbar/trafilatura/blob/master/.github/workflows/codeql.yml","dependencies":[{"id":7569831791,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":7569831792,"package_name":"github/codeql-action/init","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":7569831793,"package_name":"github/codeql-action/autobuild","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":7569831794,"package_name":"github/codeql-action/analyze","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/tests.yml","sha":null,"kind":"manifest","created_at":"2023-02-12T04:15:27.309Z","updated_at":"2023-02-12T04:15:27.309Z","repository_link":"https://github.com/adbar/trafilatura/blob/master/.github/workflows/tests.yml","dependencies":[{"id":7569837748,"package_name":"actions/setup-python","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":7569837753,"package_name":"actions/cache","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":7569837756,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false},{"id":7569837759,"package_name":"codecov/codecov-action","ecosystem":"actions","requirements":"v3","direct":true,"kind":"composite","optional":false}]}],"score":26.25568670851022,"created_at":"2025-09-04T15:51:07.815Z","updated_at":"2025-10-07T08:14:24.741Z","avatar_url":"https://github.com/adbar.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":1365602,"funding_links":["https://github.com/sponsors/adbar","https://ko-fi.com/adbarbaresi"],"readme_doi_urls":["https://doi.org/10.5281/zenodo.3460969"],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":["webscraping","opengraph","metadata-extraction","information-extraction","date-parser","datetime","digital-forensics","entity-extraction","forensics-tools","lemmatization"],"project_url":"https://science.ecosyste.ms/api/v1/projects/34428","html_url":"https://science.ecosyste.ms/projects/34428","bibtex_url":"https://science.ecosyste.ms/projects/34428/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/34428/export.apalike"}