{"id":19239219,"url":"https://github.com/atomotic/heritrix-docker","last_synced_at":"2026-02-10T17:39:29.248Z","repository":{"id":146672860,"uuid":"11720664","full_name":"atomotic/heritrix-docker","owner":"atomotic","description":"docker container with heritrix crawler","archived":false,"fork":false,"pushed_at":"2014-01-15T14:09:23.000Z","size":140,"stargazers_count":4,"open_issues_count":1,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-08-07T00:39:09.571Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/atomotic.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2013-07-28T14:23:16.000Z","updated_at":"2016-03-20T10:19:05.000Z","dependencies_parsed_at":"2023-03-24T23:34:35.109Z","dependency_job_id":null,"html_url":"https://github.com/atomotic/heritrix-docker","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/atomotic/heritrix-docker","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomotic%2Fheritrix-docker","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomotic%2Fheritrix-docker/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomotic%2Fheritrix-docker/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomotic%2Fheritrix-docker/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/atomotic","download_url":"https://codeload.github.com/atomotic/heritrix-docker/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomotic%2Fheritrix-docker/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29309593,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-10T16:09:25.305Z","status":"ssl_error","status_checked_at":"2026-02-10T16:08:52.170Z","response_time":65,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":[],"created_at":"2024-11-09T16:38:07.254Z","updated_at":"2026-02-10T17:39:29.200Z","avatar_url":"https://github.com/atomotic.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"heritrix-docker\n===============\n\ndocker container with #webarchiving crawler **heritrix-3.2.0**\n\n### run\n\n- build\n \n\t\tdocker build -t atomotic/heritrix github.com/atomotic/heritrix-docker\n\n- create a persistent job directory on the host\n\n\t\tmkdir jobs\n\n- run the container on host:8443\n\n\t\tdocker run -d -p 8443:8443 -v $(pwd)/jobs:/opt/heritrix-3.2.0/jobs atomotic/heritrix heritrix-start.sh\n\n- access the web interface\n\n\t\topen https://localhost:8443\n\t\n\t* user **heritrix**\n\t* password **heritrix**\n\n\n#### TODO\n- improve the basic job crawler-beans.cxml (specify external seeds.txt file)\n- add utilities to deal with warc files\n  * https://github.com/internetarchive/warctools\n  * https://github.com/internetarchive/CDX-Writer\n  * https://github.com/alard/warc-proxy\n  * wget-lua from archiveteam\n  * https://github.com/alard/warctozip\n  * https://github.com/ukwa/warc-explorer\n  * https://github.com/martinsbalodis/warc-content\n  * https://github.com/ianmilligan1/Historian-WARC-1\n  * https://github.com/alard/megawarc\n  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatomotic%2Fheritrix-docker","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fatomotic%2Fheritrix-docker","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatomotic%2Fheritrix-docker/lists"}