{"id":11907,"name":"trove-newspaper-harvester","description":null,"url":"https://github.com/wragge/trove-newspaper-harvester","last_synced_at":"2025-09-04T21:32:39.592Z","repository":{"id":59827588,"uuid":"537781331","full_name":"wragge/trove-newspaper-harvester","owner":"wragge","description":null,"archived":false,"fork":false,"pushed_at":"2023-10-23T04:53:19.000Z","size":586,"stargazers_count":2,"open_issues_count":4,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-07-01T14:43:06.284Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/wragge.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":"2022-09-17T11:01:49.000Z","updated_at":"2023-07-11T04:42:33.000Z","dependencies_parsed_at":"2024-10-11T15:56:09.142Z","dependency_job_id":"6d87afe4-611e-4033-b159-4fcfda8596c0","html_url":"https://github.com/wragge/trove-newspaper-harvester","commit_stats":{"total_commits":15,"total_committers":1,"mean_commits":15.0,"dds":0.0,"last_synced_commit":"99cf6c61994216405861088adca3aad755e13411"},"previous_names":[],"tags_count":6,"template":false,"template_full_name":null,"purl":"pkg:github/wragge/trove-newspaper-harvester","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wragge","download_url":"https://codeload.github.com/wragge/trove-newspaper-harvester/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273677123,"owners_count":25148362,"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":"wragge","name":"Tim Sherratt","uuid":"127565","kind":"user","description":"","email":"","website":"https://timsherratt.org","location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/127565?v=4","repositories_count":209,"last_synced_at":"2024-05-01T10:46:27.154Z","metadata":{"has_sponsors_listing":true},"html_url":"https://github.com/wragge","funding_links":["https://github.com/sponsors/wragge"],"total_stars":197,"followers":142,"following":0,"created_at":"2022-11-03T03:47:58.590Z","updated_at":"2024-05-01T10:46:50.915Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wragge","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wragge/repositories"},"packages":[{"id":5258935,"name":"trove-newspaper-harvester","ecosystem":"pypi","description":"Tool for bulk harvests of digitised newspaper articles from Trove","homepage":"https://github.com/wragge/trove-newspaper-harvester","licenses":"MIT License","normalized_licenses":["MIT"],"repository_url":"https://github.com/wragge/trove-newspaper-harvester","keywords_array":["nbdev","jupyter","notebook","python"],"namespace":null,"versions_count":10,"first_release_published_at":"2022-09-21T11:56:38.000Z","latest_release_published_at":"2023-10-23T04:47:06.000Z","latest_release_number":"0.7.2","last_synced_at":"2025-08-31T02:19:43.207Z","created_at":"2022-09-21T12:15:53.279Z","updated_at":"2025-08-31T02:19:43.207Z","registry_url":"https://pypi.org/project/trove-newspaper-harvester/","install_command":"pip install trove-newspaper-harvester --index-url https://pypi.org/simple","documentation_url":"https://trove-newspaper-harvester.readthedocs.io/","metadata":{"funding":null,"documentation":null,"classifiers":["Development Status :: 4 - Beta","Intended Audience :: Developers","License :: OSI Approved :: MIT License","Natural Language :: English","Programming Language :: Python :: 3.10","Programming Language :: Python :: 3.8","Programming Language :: Python :: 3.9"],"normalized_name":"trove-newspaper-harvester","project_status":null},"repo_metadata":{"id":59827588,"uuid":"537781331","full_name":"wragge/trove-newspaper-harvester","owner":"wragge","description":null,"archived":false,"fork":false,"pushed_at":"2023-10-23T04:53:19.000Z","size":586,"stargazers_count":2,"open_issues_count":3,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-05-02T00:21:49.682Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/wragge.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}},"created_at":"2022-09-17T11:01:49.000Z","updated_at":"2023-07-11T04:42:33.000Z","dependencies_parsed_at":"2022-09-22T18:01:43.845Z","dependency_job_id":null,"html_url":"https://github.com/wragge/trove-newspaper-harvester","commit_stats":null,"previous_names":[],"tags_count":6,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wragge","download_url":"https://codeload.github.com/wragge/trove-newspaper-harvester/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":219860191,"owners_count":16556026,"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","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":"wragge","name":"Tim Sherratt","uuid":"127565","kind":"user","description":"","email":"","website":"https://timsherratt.org","location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/127565?v=4","repositories_count":209,"last_synced_at":"2024-05-01T10:46:27.154Z","metadata":{"has_sponsors_listing":true},"html_url":"https://github.com/wragge","funding_links":["https://github.com/sponsors/wragge"],"total_stars":197,"followers":142,"following":0,"created_at":"2022-11-03T03:47:58.590Z","updated_at":"2024-05-01T10:46:50.915Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wragge","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wragge/repositories"},"tags":[{"name":"v0.7.2","sha":"e4bc31e2dfc173a522cb74a2a813e9dcf6b0760a","kind":"commit","published_at":"2023-10-23T04:49:17.000Z","download_url":"https://codeload.github.com/wragge/trove-newspaper-harvester/tar.gz/v0.7.2","html_url":"https://github.com/wragge/trove-newspaper-harvester/releases/tag/v0.7.2","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.7.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.7.2/manifests"},{"name":"v0.7.1","sha":"2c57e80162c8de13766ce2dbaa538db0483452ab","kind":"commit","published_at":"2023-08-29T07:33:28.000Z","download_url":"https://codeload.github.com/wragge/trove-newspaper-harvester/tar.gz/v0.7.1","html_url":"https://github.com/wragge/trove-newspaper-harvester/releases/tag/v0.7.1","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.7.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.7.1/manifests"},{"name":"v0.6.6","sha":"946429fece54c1f0f52f67da0c6e9ed87f302a64","kind":"commit","published_at":"2023-04-05T03:06:44.000Z","download_url":"https://codeload.github.com/wragge/trove-newspaper-harvester/tar.gz/v0.6.6","html_url":"https://github.com/wragge/trove-newspaper-harvester/releases/tag/v0.6.6","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.6.6","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.6.6/manifests"},{"name":"v0.6.5","sha":"99cf6c61994216405861088adca3aad755e13411","kind":"commit","published_at":"2022-10-11T11:38:53.000Z","download_url":"https://codeload.github.com/wragge/trove-newspaper-harvester/tar.gz/v0.6.5","html_url":"https://github.com/wragge/trove-newspaper-harvester/releases/tag/v0.6.5","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.6.5","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.6.5/manifests"},{"name":"v0.6.3","sha":"8a12b9aae567b94c8f6d95cb5d05c166d559fae8","kind":"commit","published_at":"2022-09-27T12:10:30.000Z","download_url":"https://codeload.github.com/wragge/trove-newspaper-harvester/tar.gz/v0.6.3","html_url":"https://github.com/wragge/trove-newspaper-harvester/releases/tag/v0.6.3","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.6.3","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.6.3/manifests"},{"name":"v0.6.2","sha":"763a747d8288c257c6fab80d0bc6fa6f58b60f37","kind":"commit","published_at":"2022-09-22T05:09:26.000Z","download_url":"https://codeload.github.com/wragge/trove-newspaper-harvester/tar.gz/v0.6.2","html_url":"https://github.com/wragge/trove-newspaper-harvester/releases/tag/v0.6.2","dependencies_parsed_at":null,"dependency_job_id":null,"tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.6.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/tags/v0.6.2/manifests"}]},"repo_metadata_updated_at":"2024-10-11T15:56:14.515Z","dependent_packages_count":0,"downloads":23,"downloads_period":"last-month","dependent_repos_count":1,"rankings":{"downloads":33.91348807105092,"dependent_repos_count":21.683777526269527,"dependent_packages_count":10.02790209562548,"stargazers_count":27.79305537469264,"forks_count":29.771363679016744,"docker_downloads_count":null,"average":24.63791734933106},"purl":"pkg:pypi/trove-newspaper-harvester","advisories":[],"docker_usage_url":"https://docker.ecosyste.ms/usage/pypi/trove-newspaper-harvester","docker_dependents_count":null,"docker_downloads_count":null,"usage_url":"https://repos.ecosyste.ms/usage/pypi/trove-newspaper-harvester","dependent_repositories_url":"https://repos.ecosyste.ms/api/v1/usage/pypi/trove-newspaper-harvester/dependencies","status":null,"funding_links":["https://github.com/sponsors/wragge"],"critical":null,"issue_metadata":{"last_synced_at":"2024-10-11T15:55:53.065Z","issues_count":8,"pull_requests_count":0,"avg_time_to_close_issue":5457776.8,"avg_time_to_close_pull_request":null,"issues_closed_count":5,"pull_requests_closed_count":0,"pull_request_authors_count":0,"issue_authors_count":1,"avg_comments_per_issue":0.25,"avg_comments_per_pull_request":null,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":2,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":1,"past_year_avg_comments_per_issue":0.5,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/issues","maintainers":[{"login":"wragge","count":8,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/wragge"}],"active_maintainers":[{"login":"wragge","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/wragge"}]},"versions_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/trove-newspaper-harvester/versions","version_numbers_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/trove-newspaper-harvester/version_numbers","dependent_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/trove-newspaper-harvester/dependent_packages","related_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/trove-newspaper-harvester/related_packages","maintainers":[{"uuid":"wragge","login":"wragge","name":null,"email":null,"url":null,"packages_count":6,"html_url":"https://pypi.org/user/wragge/","role":null,"created_at":"2022-11-18T15:49:43.861Z","updated_at":"2022-11-18T15:49:43.861Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/maintainers/wragge/packages"}],"registry":{"name":"pypi.org","url":"https://pypi.org","ecosystem":"pypi","default":true,"packages_count":724909,"maintainers_count":308243,"namespaces_count":0,"keywords_count":237984,"github":"pypi","metadata":{"funded_packages_count":50481},"icon_url":"https://github.com/pypi.png","created_at":"2022-04-04T15:19:23.364Z","updated_at":"2025-09-04T05:23:51.177Z","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":689628,"full_name":"wragge/trove-newspaper-harvester","default_branch":"main","committers":[{"name":"Tim Sherratt","email":"tim@discontents.com.au","login":"wragge","count":21}],"total_commits":21,"total_committers":1,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":21.0,"dds":0.0,"past_year_committers":[],"past_year_total_commits":0,"past_year_total_committers":0,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":0.0,"past_year_dds":0.0,"last_synced_at":"2025-07-02T16:13:13.020Z","last_synced_commit":"e4bc31e2dfc173a522cb74a2a813e9dcf6b0760a","created_at":"2023-03-09T11:19:29.658Z","updated_at":"2025-07-02T16:13:13.021Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/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":"wragge/trove-newspaper-harvester","html_url":"https://github.com/wragge/trove-newspaper-harvester","last_synced_at":"2025-07-01T14:30:44.260Z","status":null,"issues_count":9,"pull_requests_count":0,"avg_time_to_close_issue":5457776.8,"avg_time_to_close_pull_request":null,"issues_closed_count":5,"pull_requests_closed_count":0,"pull_request_authors_count":0,"issue_authors_count":2,"avg_comments_per_issue":0.2222222222222222,"avg_comments_per_pull_request":null,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":1,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":1,"past_year_avg_comments_per_issue":0.0,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2023-05-15T04:55:12.775Z","updated_at":"2025-08-31T20:05:15.478Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/wragge%2Ftrove-newspaper-harvester/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"OWNER":8,"NONE":1},"pull_request_author_associations_count":{},"issue_authors":{"wragge":8,"5p4r74cu5":1},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.939Z","repositories_count":10080966,"issues_count":31268296,"pull_requests_count":96067200,"authors_count":10693694,"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":{"NONE":1},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{"5p4r74cu5":1},"past_year_pull_request_authors":{},"maintainers":[{"login":"wragge","count":8,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/wragge"}],"active_maintainers":[]},"events":{"total":{"IssuesEvent":1},"last_year":{"IssuesEvent":1}},"keywords":[],"dependencies":[{"ecosystem":"actions","filepath":".github/workflows/deploy.yaml","sha":null,"kind":"manifest","created_at":"2024-10-11T15:56:09.049Z","updated_at":"2024-10-11T15:56:09.049Z","repository_link":"https://github.com/wragge/trove-newspaper-harvester/blob/main/.github/workflows/deploy.yaml","dependencies":[{"id":20209616314,"package_name":"fastai/workflows/quarto-ghp","ecosystem":"actions","requirements":"master","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2024-10-11T15:56:09.126Z","updated_at":"2024-10-11T15:56:09.126Z","repository_link":"https://github.com/wragge/trove-newspaper-harvester/blob/main/setup.py","dependencies":[]}],"score":5.0106352940962555,"created_at":"2025-09-04T15:50:39.642Z","updated_at":"2025-10-07T08:07:19.049Z","avatar_url":"https://github.com/wragge.png","language":"Jupyter Notebook","category":null,"sub_category":null,"monthly_downloads":23,"funding_links":["https://github.com/sponsors/wragge?o=esb"],"readme_doi_urls":["https://doi.org/10.5281/zenodo.7103174"],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/11907","html_url":"https://science.ecosyste.ms/projects/11907","bibtex_url":"https://science.ecosyste.ms/projects/11907/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/11907/export.apalike"}