{"id":37873,"name":"dhscrapers","description":"A unified interface for scrapers for Digital Humanities resources","url":"https://github.com/centrefordigitalhumanities/dhscrapers","last_synced_at":"2025-09-05T07:35:45.343Z","repository":{"id":267781175,"uuid":"268768066","full_name":"CentreForDigitalHumanities/DHScrapers","owner":"CentreForDigitalHumanities","description":"A unified interface for scrapers for Digital Humanities resources","archived":false,"fork":false,"pushed_at":"2025-06-26T08:01:22.000Z","size":4554,"stargazers_count":0,"open_issues_count":3,"forks_count":0,"subscribers_count":4,"default_branch":"develop","last_synced_at":"2025-06-26T08:37:21.752Z","etag":null,"topics":["digtial-humanities","python","scraping"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CentreForDigitalHumanities.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"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}},"created_at":"2020-06-02T10:15:36.000Z","updated_at":"2025-05-28T09:57:24.000Z","dependencies_parsed_at":"2025-03-27T15:34:29.352Z","dependency_job_id":"c3d15041-ee3d-455e-a6a0-e522efa166e8","html_url":"https://github.com/CentreForDigitalHumanities/DHScrapers","commit_stats":null,"previous_names":["centrefordigitalhumanities/dhlab-scrapers","centrefordigitalhumanities/dhscraper"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/CentreForDigitalHumanities/DHScrapers","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FDHScrapers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FDHScrapers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FDHScrapers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FDHScrapers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CentreForDigitalHumanities","download_url":"https://codeload.github.com/CentreForDigitalHumanities/DHScrapers/tar.gz/refs/heads/develop","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2FDHScrapers/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273727524,"owners_count":25157131,"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":"2025-09-05T02:00:09.113Z","response_time":402,"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":"CentreForDigitalHumanities","name":"Centre for Digital Humanities","uuid":"87316747","kind":"organization","description":"Interdisciplinary centre for research and education in computational and data-driven methods in the humanities.","email":"cdh@uu.nl","website":"https://cdh.uu.nl/","location":"Netherlands","twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/87316747?v=4","repositories_count":39,"last_synced_at":"2024-04-24T06:02:37.702Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/CentreForDigitalHumanities","funding_links":[],"total_stars":20,"followers":12,"following":0,"created_at":"2022-11-08T06:06:11.908Z","updated_at":"2024-04-24T06:02:55.424Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CentreForDigitalHumanities","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CentreForDigitalHumanities/repositories"},"packages":[],"commits":{"id":7848788,"full_name":"centrefordigitalhumanities/dhscrapers","default_branch":"develop","committers":[{"name":"Alex Hebing","email":"a.h.j.hebing@uu.nl","login":null,"count":88},{"name":"BeritJanssen","email":"berit.janssen@gmail.com","login":"BeritJanssen","count":14},{"name":"unknown","email":"robert@correcthosting.nl","login":"robertcorrecthosting","count":9},{"name":"Giorgos Damaskos","email":"g.damaskos@uu.nl","login":"gdamaskos","count":7},{"name":"R. Loeber","email":"r.g.v.loeber@uu.nl","login":"robertloeberdevelopment","count":6},{"name":"José de Kruif","email":"J.dekruif@uu.nl","login":"JosedeKruif","count":3},{"name":"Luka van der Plas","email":"l.p.vanderplas@uu.nl","login":"lukavdplas","count":3},{"name":"Alex Hebing","email":"alexhebing@gmail.com","login":"alexhebing","count":2}],"total_commits":132,"total_committers":8,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":16.5,"dds":0.33333333333333337,"past_year_committers":[{"name":"Giorgos Damaskos","email":"g.damaskos@uu.nl","login":"gdamaskos","count":7},{"name":"BeritJanssen","email":"berit.janssen@gmail.com","login":"BeritJanssen","count":6}],"past_year_total_commits":13,"past_year_total_committers":2,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":6.5,"past_year_dds":0.46153846153846156,"last_synced_at":"2025-06-19T17:30:37.082Z","last_synced_commit":"2806783e52b7fa4d4dd9d5f13bd4378f902ecb16","created_at":"2024-12-19T20:13:40.006Z","updated_at":"2025-06-19T17:30:37.334Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/centrefordigitalhumanities%2Fdhscrapers/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.343Z","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":"centrefordigitalhumanities/dhscrapers","html_url":"https://github.com/centrefordigitalhumanities/dhscrapers","last_synced_at":"2025-06-18T15:35:06.200Z","status":null,"issues_count":6,"pull_requests_count":2,"avg_time_to_close_issue":21721.0,"avg_time_to_close_pull_request":68214.0,"issues_closed_count":4,"pull_requests_closed_count":1,"pull_request_authors_count":2,"issue_authors_count":4,"avg_comments_per_issue":1.3333333333333333,"avg_comments_per_pull_request":2.0,"merged_pull_requests_count":1,"bot_issues_count":2,"bot_pull_requests_count":0,"past_year_issues_count":3,"past_year_pull_requests_count":1,"past_year_avg_time_to_close_issue":116.0,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":2,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":1,"past_year_issue_authors_count":2,"past_year_avg_comments_per_issue":1.3333333333333333,"past_year_avg_comments_per_pull_request":2.0,"past_year_bot_issues_count":2,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2024-12-19T20:13:41.776Z","updated_at":"2025-09-03T03:11:58.039Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/centrefordigitalhumanities%2Fdhscrapers","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/centrefordigitalhumanities%2Fdhscrapers/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"CONTRIBUTOR":3,"NONE":2},"pull_request_author_associations_count":{"CONTRIBUTOR":3},"issue_authors":{"lukavdplas":2,"JeltevanBoheemen":1,"BeritJanssen":1,"github-actions[bot]":1},"pull_request_authors":{"BeritJanssen":2,"lukavdplas":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.444Z","repositories_count":10082364,"issues_count":31225876,"pull_requests_count":96082853,"authors_count":10694162,"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":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{"CONTRIBUTOR":1,"NONE":1},"past_year_pull_request_author_associations_count":{"CONTRIBUTOR":2},"past_year_issue_authors":{"BeritJanssen":1,"github-actions[bot]":1},"past_year_pull_request_authors":{"BeritJanssen":2},"maintainers":[],"active_maintainers":[]},"events":{"total":{"CreateEvent":3,"ReleaseEvent":1,"IssuesEvent":2,"MemberEvent":2,"IssueCommentEvent":4,"PushEvent":137,"PullRequestEvent":1},"last_year":{"CreateEvent":3,"ReleaseEvent":1,"IssuesEvent":2,"MemberEvent":2,"IssueCommentEvent":4,"PushEvent":137,"PullRequestEvent":1}},"keywords":["digtial-humanities","python","scraping"],"dependencies":[{"ecosystem":"pypi","filepath":"epidat/requirements.txt","sha":null,"kind":"manifest","created_at":"2024-12-12T12:26:55.786Z","updated_at":"2024-12-12T12:26:55.786Z","repository_link":"https://github.com/CentreForDigitalHumanities/DHScrapers/blob/develop/epidat/requirements.txt","dependencies":[{"id":21134693189,"package_name":"lxml","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"iis/requirements.txt","sha":null,"kind":"manifest","created_at":"2024-12-12T12:26:55.975Z","updated_at":"2024-12-12T12:26:55.975Z","repository_link":"https://github.com/CentreForDigitalHumanities/DHScrapers/blob/develop/iis/requirements.txt","dependencies":[{"id":21134693190,"package_name":"lxml","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements.in","sha":null,"kind":"manifest","created_at":"2024-12-12T12:26:56.111Z","updated_at":"2024-12-12T12:26:56.111Z","repository_link":"https://github.com/CentreForDigitalHumanities/DHScrapers/blob/develop/requirements.in","dependencies":[{"id":21134693191,"package_name":"selenium","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21134693192,"package_name":"beautifulsoup4","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21134693193,"package_name":"requests","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21134693194,"package_name":"pytest","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21134693195,"package_name":"langdetect","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21134693365,"package_name":"gender_guesser","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21134693583,"package_name":"dicttoxml","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21134694398,"package_name":"iso-639","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"lockfile","created_at":"2024-12-12T12:27:01.768Z","updated_at":"2024-12-12T12:27:01.768Z","repository_link":"https://github.com/CentreForDigitalHumanities/DHScrapers/blob/develop/requirements.txt","dependencies":[{"id":21134694402,"package_name":"attrs","ecosystem":"pypi","requirements":"==19.3.0","direct":false,"kind":"runtime","optional":false},{"id":21134694403,"package_name":"beautifulsoup4","ecosystem":"pypi","requirements":"==4.8.2","direct":false,"kind":"runtime","optional":false},{"id":21134694404,"package_name":"certifi","ecosystem":"pypi","requirements":"==2019.11.28","direct":false,"kind":"runtime","optional":false},{"id":21134694405,"package_name":"chardet","ecosystem":"pypi","requirements":"==3.0.4","direct":false,"kind":"runtime","optional":false},{"id":21134694406,"package_name":"dicttoxml","ecosystem":"pypi","requirements":"==1.7.4","direct":false,"kind":"runtime","optional":false},{"id":21134694407,"package_name":"gender-guesser","ecosystem":"pypi","requirements":"==0.4.0","direct":false,"kind":"runtime","optional":false},{"id":21134694408,"package_name":"idna","ecosystem":"pypi","requirements":"==2.9","direct":false,"kind":"runtime","optional":false},{"id":21134694409,"package_name":"importlib-metadata","ecosystem":"pypi","requirements":"==1.5.0","direct":false,"kind":"runtime","optional":false},{"id":21134694410,"package_name":"iso-639","ecosystem":"pypi","requirements":"==0.4.5","direct":false,"kind":"runtime","optional":false},{"id":21134694411,"package_name":"langdetect","ecosystem":"pypi","requirements":"==1.0.8","direct":false,"kind":"runtime","optional":false},{"id":21134694412,"package_name":"more-itertools","ecosystem":"pypi","requirements":"==8.2.0","direct":false,"kind":"runtime","optional":false},{"id":21134694413,"package_name":"packaging","ecosystem":"pypi","requirements":"==20.3","direct":false,"kind":"runtime","optional":false},{"id":21134694414,"package_name":"pluggy","ecosystem":"pypi","requirements":"==0.13.1","direct":false,"kind":"runtime","optional":false},{"id":21134694415,"package_name":"py","ecosystem":"pypi","requirements":"==1.8.1","direct":false,"kind":"runtime","optional":false},{"id":21134694416,"package_name":"pyparsing","ecosystem":"pypi","requirements":"==2.4.6","direct":false,"kind":"runtime","optional":false},{"id":21134694417,"package_name":"pytest","ecosystem":"pypi","requirements":"==5.4.1","direct":false,"kind":"runtime","optional":false},{"id":21134694418,"package_name":"requests","ecosystem":"pypi","requirements":"==2.23.0","direct":false,"kind":"runtime","optional":false},{"id":21134694419,"package_name":"selenium","ecosystem":"pypi","requirements":"==3.141.0","direct":false,"kind":"runtime","optional":false},{"id":21134694420,"package_name":"six","ecosystem":"pypi","requirements":"==1.14.0","direct":false,"kind":"runtime","optional":false},{"id":21134694421,"package_name":"soupsieve","ecosystem":"pypi","requirements":"==2.0","direct":false,"kind":"runtime","optional":false},{"id":21134694422,"package_name":"urllib3","ecosystem":"pypi","requirements":"==1.25.8","direct":false,"kind":"runtime","optional":false},{"id":21134694423,"package_name":"wcwidth","ecosystem":"pypi","requirements":"==0.1.8","direct":false,"kind":"runtime","optional":false},{"id":21134694424,"package_name":"zipp","ecosystem":"pypi","requirements":"==3.1.0","direct":false,"kind":"runtime","optional":false}]}],"score":3.1780538303479453,"created_at":"2025-09-04T15:51:11.709Z","updated_at":"2025-10-07T08:15:33.465Z","avatar_url":"https://github.com/CentreForDigitalHumanities.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/37873","html_url":"https://science.ecosyste.ms/projects/37873","bibtex_url":"https://science.ecosyste.ms/projects/37873/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/37873/export.apalike"}