{"id":13464543,"url":"https://github.com/internetarchive/heritrix3","last_synced_at":"2026-10-19T01:02:13.010Z","repository":{"id":37617114,"uuid":"2623406","full_name":"internetarchive/heritrix3","owner":"internetarchive","description":"Heritrix is the Internet Archive's open-source, extensible, web-scale, archival-quality web crawler project.  ","archived":false,"fork":false,"pushed_at":"2026-10-14T23:22:26.000Z","size":12769,"stargazers_count":3333,"open_issues_count":34,"forks_count":795,"subscribers_count":184,"default_branch":"master","last_synced_at":"2026-10-16T14:37:33.192Z","etag":null,"topics":["heritrix","java","warc","webcrawling"],"latest_commit_sha":null,"homepage":"https://heritrix.readthedocs.io/","language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/internetarchive.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"claude":null,"gemini":null,"cursor":null,"copilot":null,"dco":null,"cla":null,"disclosure":null}},"created_at":"2011-10-21T22:00:17.000Z","updated_at":"2026-10-15T15:09:32.000Z","dependencies_parsed_at":"2026-08-28T03:27:34.484Z","dependency_job_id":null,"html_url":"https://github.com/internetarchive/heritrix3","commit_stats":{"total_commits":2136,"total_committers":66,"mean_commits":32.36363636363637,"dds":0.6947565543071161,"last_synced_commit":"d42e8091a5789617a58875f4271113e25bfdbb15"},"previous_names":[],"tags_count":32,"template":false,"template_full_name":null,"purl":"pkg:github/internetarchive/heritrix3","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/internetarchive%2Fheritrix3","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/internetarchive%2Fheritrix3/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/internetarchive%2Fheritrix3/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/internetarchive%2Fheritrix3/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/internetarchive","download_url":"https://codeload.github.com/internetarchive/heritrix3/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/internetarchive%2Fheritrix3/sbom","scorecard":{"id":491477,"data":{"date":"2025-08-11","repo":{"name":"github.com/internetarchive/heritrix3","commit":"194046d35b9f3e384dffbcee91239fbd793e6bab"},"scorecard":{"version":"v5.2.1-40-gf6ed084d","commit":"f6ed084d17c9236477efd66e5b258b9d4cc7b389"},"score":6.3,"checks":[{"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":"Code-Review","score":0,"reason":"Found 1/26 approved changesets -- score normalized to 0","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":"Security-Policy","score":10,"reason":"security policy file detected","details":["Info: security policy file detected: SECURITY.md:1","Info: Found linked content: SECURITY.md:1","Info: Found disclosure, vulnerability, and/or timelines in security policy: SECURITY.md:1","Info: Found text in security policy: SECURITY.md:1"],"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":"Maintained","score":10,"reason":"30 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 10","details":null,"documentation":{"short":"Determines if the project is \"actively maintained\".","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#maintained"}},{"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":"Token-Permissions","score":10,"reason":"GitHub workflow tokens follow principle of least privilege","details":["Info: topLevel 'contents' permission set to 'read': .github/workflows/docker-image.yml:4","Info: topLevel 'contents' permission set to 'read': .github/workflows/maven.yml:4","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":"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":9,"reason":"license file detected","details":["Info: project has a license file: LICENSE:0","Warn: project license file does not contain an FSF or OSI license."],"documentation":{"short":"Determines if the project has defined a license.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#license"}},{"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":"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":"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":"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":"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/docker-image.yml:15: update your workflow using https://app.stepsecurity.io/secureworkflow/internetarchive/heritrix3/docker-image.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/maven.yml:21: update your workflow using https://app.stepsecurity.io/secureworkflow/internetarchive/heritrix3/maven.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/maven.yml:23: update your workflow using https://app.stepsecurity.io/secureworkflow/internetarchive/heritrix3/maven.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/maven.yml:28: update your workflow using https://app.stepsecurity.io/secureworkflow/internetarchive/heritrix3/maven.yml/master?enable=pin","Warn: containerImage not pinned by hash: docker/Dockerfile:3","Warn: containerImage not pinned by hash: docker/Dockerfile.contrib:3","Info:   0 out of   4 GitHub-owned GitHubAction dependencies pinned","Info:   0 out of   2 containerImage 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":6,"reason":"SAST tool is not run on all commits -- score normalized to 6","details":["Warn: 4 commits out of 6 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"}},{"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"}}]},"last_synced_at":"2025-08-19T19:16:42.858Z","repository_id":37617114,"created_at":"2025-08-19T19:16:42.858Z","updated_at":"2025-08-19T19:16:42.858Z"},"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":344872684,"owners_count":38344170,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-10-03T21:59:58.778Z","status":"online","status_checked_at":"2026-10-18T02:00:06.448Z","response_time":63,"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"}},"keywords":["heritrix","java","warc","webcrawling"],"created_at":"2024-07-31T14:00:45.827Z","updated_at":"2026-10-19T01:02:13.002Z","avatar_url":"https://github.com/internetarchive.png","language":"Java","funding_links":[],"categories":["All","Java","java","Download utilities","Web Archiving","Programming Languages","网络爬虫"],"sub_categories":["Web Archiving","Crawlers \u0026 Capture","Java","语音合成"],"readme":"# Heritrix\n[![Maven Central Version](https://img.shields.io/maven-central/v/org.archive/heritrix)](https://img.shields.io/maven-central/v/org.archive/heritrix)\n[![Docker](https://img.shields.io/docker/v/iipc/heritrix/latest?label=docker)](https://hub.docker.com/r/iipc/heritrix)\n[![Javadoc](https://javadoc.io/badge2/org.archive/heritrix/javadoc.svg)](https://www.javadoc.io/doc/org.archive.heritrix/heritrix-engine)\n[![LICENSE](https://img.shields.io/badge/license-Apache-blue.svg?style=flat-square)](./LICENSE)\n\n## Introduction\n\nHeritrix is the Internet Archive's open-source, extensible, web-scale, archival-quality web crawler project. Heritrix (sometimes spelled heretrix, or misspelled or missaid as heratrix/heritix/heretix/heratix) is an archaic word for heiress (woman who inherits). Since our crawler seeks to collect and preserve the digital artifacts of our culture for the benefit of future researchers and generations, this name seemed apt.\n\n## Crawl Operators!\n\nHeritrix is designed to respect the [`robots.txt`](http://www.robotstxt.org/robotstxt.html) exclusion directives and [META nofollow tags](http://www.robotstxt.org/meta.html). Please consider the\nload your crawl will place on seed sites and set politeness policies accordingly. Also, always identify your crawl with contact information in the `User-Agent` so sites that may be adversely affected by your crawl can contact you or adapt their server behavior accordingly.\n\n## Documentation\n\n- [Getting Started](https://heritrix.readthedocs.io/en/latest/getting-started.html)\n- [Operating Heritrix](https://heritrix.readthedocs.io/en/latest/operating.html)\n- [Configuring Crawl Jobs](https://heritrix.readthedocs.io/en/latest/configuring-jobs.html)\n- [Bean Reference](https://heritrix.readthedocs.io/en/latest/bean-reference.html)\n- [Wiki](https://github.com/internetarchive/heritrix3/wiki)\n\n## Developer Documentation\n\n- [Developer Manual](http://crawler.archive.org/articles/developer_manual/index.html)\n- [REST API documentation](https://heritrix.readthedocs.io/en/latest/api.html)\n- JavaDoc: [engine](https://www.javadoc.io/doc/org.archive.heritrix/heritrix-engine), [modules](https://www.javadoc.io/doc/org.archive.heritrix/heritrix-modules), [commons](https://www.javadoc.io/doc/org.archive.heritrix/heritrix-commons), [contrib](https://www.javadoc.io/doc/org.archive.heritrix/heritrix-contrib)\n\n\n## Latest Releases\n\nInformation about releases can be found [here](https://github.com/internetarchive/heritrix3/wiki#latest-releases).\n\n## License\n\nHeritrix is free software; you can redistribute it and/or modify it under the terms of the [Apache License, Version 2.0](http://www.apache.org/licenses/LICENSE-2.0)\n\nSome individual source code files are subject to or offered under other licenses. See the included [`LICENSE.txt`](./LICENSE) file for more information.\n\nHeritrix is distributed with the libraries it depends upon. The libraries can be found under the `lib` directory in the release distribution, and are used under the terms of their respective licenses, which are included alongside the libraries in the `lib` directory.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finternetarchive%2Fheritrix3","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finternetarchive%2Fheritrix3","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finternetarchive%2Fheritrix3/lists"}