{"id":165393,"name":null,"description":"A universal scraper that grabs text from multiple types of webpages.","url":"https://github.com/caimeng2/uniscraper","last_synced_at":"2025-09-09T19:43:51.953Z","repository":{"id":44143851,"uuid":"344634683","full_name":"caimeng2/UniScraper","owner":"caimeng2","description":"A universal scraper that grabs text from multiple types of webpages.","archived":false,"fork":false,"pushed_at":"2025-02-11T08:26:23.000Z","size":97883,"stargazers_count":6,"open_issues_count":5,"forks_count":31,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-30T04:45:36.382Z","etag":null,"topics":["text-mining","web-scraper"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/caimeng2.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-03-04T23:13:45.000Z","updated_at":"2025-02-11T08:26:28.000Z","dependencies_parsed_at":"2025-02-16T14:48:57.581Z","dependency_job_id":null,"html_url":"https://github.com/caimeng2/UniScraper","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/caimeng2/UniScraper","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/caimeng2%2FUniScraper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/caimeng2%2FUniScraper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/caimeng2%2FUniScraper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/caimeng2%2FUniScraper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/caimeng2","download_url":"https://codeload.github.com/caimeng2/UniScraper/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/caimeng2%2FUniScraper/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274349895,"owners_count":25268980,"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":"2025-09-09T02:00:10.223Z","response_time":80,"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":"caimeng2","name":"Meng Cai","uuid":"51100838","kind":"user","description":"","email":"","website":null,"location":null,"twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/51100838?u=0f5e851908baa2202d90a90882b7c98baaa73ecd\u0026v=4","repositories_count":3,"last_synced_at":"2023-05-30T15:28:50.837Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/caimeng2","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2023-05-30T15:28:50.849Z","updated_at":"2023-05-30T15:28:50.849Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/caimeng2","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/caimeng2/repositories"},"packages":[],"commits":{"id":2978856,"full_name":"caimeng2/uniscraper","default_branch":"main","committers":[{"name":"Cai, Meng","email":"mengcai24601@gmail.com","login":"caimeng2","count":27},{"name":"Jack","email":"jackbutzu@gmail.com","login":"butzujac","count":3},{"name":"Dirk Colbry","email":"colbrydi@msu.edu","login":"colbrydi","count":2},{"name":"schmi710","email":"55195426+schmi710","login":"schmi710","count":1},{"name":"Baozbao","email":"72121435+chenqili2020","login":"chenqili2020","count":1},{"name":"trachtsa","email":"trachtsa@msu.edu","login":"trachtsa","count":1},{"name":"singhjy1","email":"singhjy1@msu.edu","login":"singhjy1","count":1},{"name":"krupczaka","email":"krupczak@msu.edu","login":"krupczaka","count":1},{"name":"Yash Manne","email":"manneyas@msu.edu","login":"yashmanne","count":1},{"name":"Ishaan Pathak","email":"pathakis@msu.edu","login":"pathakis","count":1}],"total_commits":39,"total_committers":10,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":3.9,"dds":0.3076923076923077,"past_year_committers":[{"name":"Jack","email":"jackbutzu@gmail.com","login":"butzujac","count":3}],"past_year_total_commits":3,"past_year_total_committers":1,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":3.0,"past_year_dds":0.0,"last_synced_at":"2025-07-30T04:11:28.269Z","last_synced_commit":"4934657d5174a65562613e6b0a637fd0dd292b2d","created_at":"2024-10-12T19:08:49.352Z","updated_at":"2025-07-30T04:12:27.029Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/caimeng2%2Funiscraper/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-09T00:17:06.873Z","repositories_count":5535263,"commits_count":872887976,"contributors_count":32192420,"owners_count":918625,"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":"caimeng2/uniscraper","html_url":"https://github.com/caimeng2/uniscraper","last_synced_at":"2025-08-31T16:46:29.987Z","status":null,"issues_count":11,"pull_requests_count":12,"avg_time_to_close_issue":17301998.14285714,"avg_time_to_close_pull_request":12187949.181818182,"issues_closed_count":7,"pull_requests_closed_count":11,"pull_request_authors_count":10,"issue_authors_count":11,"avg_comments_per_issue":0.6363636363636364,"avg_comments_per_pull_request":0.0,"merged_pull_requests_count":10,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":2,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":33398.0,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":2,"past_year_pull_request_authors_count":1,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":0.0,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":2,"created_at":"2024-10-12T19:08:49.618Z","updated_at":"2025-08-31T16:46:29.988Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/caimeng2%2Funiscraper","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/caimeng2%2Funiscraper/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":6,"CONTRIBUTOR":4},"pull_request_author_associations_count":{"CONTRIBUTOR":9,"NONE":3},"issue_authors":{"alyaqou1":1,"bowerm37":1,"haasjack":1,"skowalski34":1,"schmi710":1,"morri726":1,"chenqili2020":1,"fjevtic46":1,"singhjy1":1,"krupczaka":1},"pull_request_authors":{"colbrydi":2,"butzujac":2,"pathakis":1,"yashmanne":1,"trachtsa":1,"krupczaka":1,"schmi710":1,"morri726":1,"chenqili2020":1,"fjevtic46":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.939Z","repositories_count":10077562,"issues_count":31305350,"pull_requests_count":95961714,"authors_count":10691973,"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":{"NONE":1,"CONTRIBUTOR":1},"past_year_issue_authors":{},"past_year_pull_request_authors":{"butzujac":2},"maintainers":[],"active_maintainers":[]},"events":{"total":{"WatchEvent":1,"PullRequestEvent":1,"ForkEvent":1},"last_year":{"WatchEvent":1,"PullRequestEvent":1,"ForkEvent":1}},"keywords":["text-mining","web-scraper"],"dependencies":[{"ecosystem":"conda","filepath":"environment.yml","sha":null,"kind":"manifest","created_at":"2025-02-16T14:48:51.911Z","updated_at":"2025-02-16T14:48:51.911Z","repository_link":"https://github.com/caimeng2/UniScraper/blob/main/environment.yml","dependencies":[{"id":21900206763,"package_name":"bs4","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":21900206859,"package_name":"jupyter","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":21900206899,"package_name":"nltk","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":21900207148,"package_name":"pandas","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":21900207149,"package_name":"pdoc3","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":21900207226,"package_name":"pip","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":21900207227,"package_name":"pylint","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":21900207778,"package_name":"pytest","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false},{"id":21900207779,"package_name":"requests","ecosystem":"conda","requirements":"","direct":true,"kind":"runtime","optional":false}]}],"score":4.700480365792417,"created_at":"2025-09-09T01:09:51.736Z","updated_at":"2025-10-07T08:39:09.428Z","avatar_url":"https://github.com/caimeng2.png","language":"Jupyter Notebook","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":["sdg"],"project_url":"https://science.ecosyste.ms/api/v1/projects/165393","html_url":"https://science.ecosyste.ms/projects/165393"}