{"id":15785,"name":"corpus-scraper","description":"Automated corpus data collection for several online word-in-context corpuses","url":"https://github.com/centrefordigitalhumanities/corpus-scraper","last_synced_at":"2025-09-04T22:58:08.654Z","repository":{"id":83257914,"uuid":"24453651","full_name":"CentreForDigitalHumanities/corpus-scraper","owner":"CentreForDigitalHumanities","description":"Automated corpus data collection for several online word-in-context corpuses","archived":false,"fork":false,"pushed_at":"2024-04-05T09:42:57.000Z","size":82,"stargazers_count":4,"open_issues_count":1,"forks_count":1,"subscribers_count":11,"default_branch":"develop","last_synced_at":"2025-08-13T03:37:24.621Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"JavaScript","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.txt","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":"2014-09-25T10:24:34.000Z","updated_at":"2024-04-04T15:36:44.000Z","dependencies_parsed_at":null,"dependency_job_id":"077740f2-9617-40c5-a469-561266b0a6d1","html_url":"https://github.com/CentreForDigitalHumanities/corpus-scraper","commit_stats":null,"previous_names":["centrefordigitalhumanities/corpus-scraper"],"tags_count":9,"template":false,"template_full_name":null,"purl":"pkg:github/CentreForDigitalHumanities/corpus-scraper","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2Fcorpus-scraper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2Fcorpus-scraper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2Fcorpus-scraper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2Fcorpus-scraper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CentreForDigitalHumanities","download_url":"https://codeload.github.com/CentreForDigitalHumanities/corpus-scraper/tar.gz/refs/heads/develop","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CentreForDigitalHumanities%2Fcorpus-scraper/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273685605,"owners_count":25149722,"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":"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":4156694,"full_name":"centrefordigitalhumanities/corpus-scraper","default_branch":"master","committers":null,"total_commits":null,"total_committers":null,"total_bot_commits":null,"total_bot_committers":null,"mean_commits":null,"dds":null,"past_year_committers":null,"past_year_total_commits":null,"past_year_total_committers":null,"past_year_total_bot_commits":null,"past_year_total_bot_committers":null,"past_year_mean_commits":null,"past_year_dds":null,"last_synced_at":null,"last_synced_commit":null,"created_at":"2024-11-06T09:12:37.003Z","updated_at":"2024-11-06T09:12:37.003Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/centrefordigitalhumanities%2Fcorpus-scraper/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.936Z","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/corpus-scraper","html_url":"https://github.com/centrefordigitalhumanities/corpus-scraper","last_synced_at":"2025-08-13T18:35:23.670Z","status":"error","issues_count":7,"pull_requests_count":1,"avg_time_to_close_issue":6419417.333333333,"avg_time_to_close_pull_request":60054.0,"issues_closed_count":6,"pull_requests_closed_count":1,"pull_request_authors_count":1,"issue_authors_count":2,"avg_comments_per_issue":0.5714285714285714,"avg_comments_per_pull_request":3.0,"merged_pull_requests_count":1,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":1,"past_year_pull_requests_count":1,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":60054.0,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":1,"past_year_pull_request_authors_count":1,"past_year_issue_authors_count":1,"past_year_avg_comments_per_issue":0.0,"past_year_avg_comments_per_pull_request":3.0,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":1,"created_at":"2024-11-06T09:12:38.049Z","updated_at":"2025-09-01T08:50:31.573Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/centrefordigitalhumanities%2Fcorpus-scraper","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/centrefordigitalhumanities%2Fcorpus-scraper/issues","issue_labels_count":{"enhancement":3},"pull_request_labels_count":{},"issue_author_associations_count":{"CONTRIBUTOR":7},"pull_request_author_associations_count":{"NONE":1,"CONTRIBUTOR":1},"issue_authors":{"jgonggrijp":6,"ar-jan":1},"pull_request_authors":{"ar-jan":2},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-01T00:00:07.725Z","repositories_count":9935075,"issues_count":29403681,"pull_requests_count":84877004,"authors_count":9228796,"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":{},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"MemberEvent":2},"last_year":{"MemberEvent":2}},"keywords":[],"dependencies":[],"score":null,"created_at":"2025-09-04T15:50:46.753Z","updated_at":"2025-10-07T08:08:32.156Z","avatar_url":"https://github.com/CentreForDigitalHumanities.png","language":"JavaScript","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/15785","html_url":"https://science.ecosyste.ms/projects/15785"}