{"id":18122,"name":"ia-webscraping","description":"An AWS workflow for collecting webpages from the Internet Archive","url":"https://github.com/utrechtuniversity/ia-webscraping","last_synced_at":"2025-09-04T23:48:28.087Z","repository":{"id":40789208,"uuid":"329035317","full_name":"UtrechtUniversity/ia-webscraping","owner":"UtrechtUniversity","description":"An AWS workflow for collecting webpages from the Internet Archive","archived":false,"fork":false,"pushed_at":"2024-11-05T12:25:38.000Z","size":22477,"stargazers_count":3,"open_issues_count":5,"forks_count":4,"subscribers_count":8,"default_branch":"main","last_synced_at":"2025-07-13T21:32:20.616Z","etag":null,"topics":["aws","internet-archive","python","terraform","web-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/UtrechtUniversity.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":"2021-01-12T15:49:39.000Z","updated_at":"2024-11-05T12:25:42.000Z","dependencies_parsed_at":"2024-11-22T21:41:23.491Z","dependency_job_id":null,"html_url":"https://github.com/UtrechtUniversity/ia-webscraping","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/UtrechtUniversity/ia-webscraping","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UtrechtUniversity%2Fia-webscraping","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UtrechtUniversity%2Fia-webscraping/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UtrechtUniversity%2Fia-webscraping/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UtrechtUniversity%2Fia-webscraping/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/UtrechtUniversity","download_url":"https://codeload.github.com/UtrechtUniversity/ia-webscraping/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UtrechtUniversity%2Fia-webscraping/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273690360,"owners_count":25150630,"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":"UtrechtUniversity","name":"Utrecht University","uuid":"11516575","kind":"organization","description":"The central place for managing code and software for Utrecht University researchers and employees","email":"info.rdm@uu.nl","website":"https://www.uu.nl","location":"Utrecht, The Netherlands","twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/11516575?v=4","repositories_count":85,"last_synced_at":"2023-02-28T15:30:37.374Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/UtrechtUniversity","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-11T17:59:27.702Z","updated_at":"2023-02-28T15:30:37.570Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/UtrechtUniversity","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/UtrechtUniversity/repositories"},"packages":[],"commits":{"id":6641430,"full_name":"utrechtuniversity/ia-webscraping","default_branch":"main","committers":[{"name":"MartineDeVos","email":"mgdevos@gmail.com","login":"MartineDeVos","count":74},{"name":"Robert Jan Bood","email":"robert-jan.bood@surfsara.nl","login":null,"count":25},{"name":"Casper Kaandorp","email":"c.s.kaandorp@uu.nl","login":"cskaandorp","count":16},{"name":"maartenschermer","email":"m.d.schermer@uu.nl","login":"maartenschermer","count":8},{"name":"Mark van Weert","email":"77613120+MarkSurf","login":"MarkSurf","count":3},{"name":"Jip","email":"77623845+JipLeendertse","login":"JipLeendertse","count":2},{"name":"markwe","email":"mark.vanweert@surfsara.nl","login":null,"count":2}],"total_commits":130,"total_committers":7,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":18.571428571428573,"dds":0.4307692307692308,"past_year_committers":[{"name":"Maarten Schermer","email":"m.d.schermer@uu.nl","login":"maartenschermer","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":"2025-07-13T21:12:43.430Z","last_synced_commit":"619c7cd336dc508447d37cd32b56cdcc9a97c453","created_at":"2024-11-22T21:28:25.093Z","updated_at":"2025-07-13T21:12:50.625Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/utrechtuniversity%2Fia-webscraping/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":"utrechtuniversity/ia-webscraping","html_url":"https://github.com/utrechtuniversity/ia-webscraping","last_synced_at":"2025-07-13T21:09:02.234Z","status":null,"issues_count":6,"pull_requests_count":15,"avg_time_to_close_issue":44403502.0,"avg_time_to_close_pull_request":169692.76923076922,"issues_closed_count":3,"pull_requests_closed_count":13,"pull_request_authors_count":5,"issue_authors_count":1,"avg_comments_per_issue":0.8333333333333334,"avg_comments_per_pull_request":0.13333333333333333,"merged_pull_requests_count":13,"bot_issues_count":0,"bot_pull_requests_count":2,"past_year_issues_count":0,"past_year_pull_requests_count":1,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":5235.0,"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":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":1,"created_at":"2024-11-22T21:28:27.978Z","updated_at":"2025-09-02T15:52:09.052Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/utrechtuniversity%2Fia-webscraping","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/utrechtuniversity%2Fia-webscraping/issues","issue_labels_count":{},"pull_request_labels_count":{"dependencies":2},"issue_author_associations_count":{"MEMBER":6},"pull_request_author_associations_count":{"MEMBER":8,"COLLABORATOR":6,"NONE":2},"issue_authors":{"MartineDeVos":6},"pull_request_authors":{"MartineDeVos":8,"surf-rbood":3,"dependabot[bot]":2,"maartenschermer":2,"cskaandorp":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-03T00:00:08.273Z","repositories_count":10070672,"issues_count":31254518,"pull_requests_count":95427059,"authors_count":10689179,"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":{"COLLABORATOR":2},"past_year_issue_authors":{},"past_year_pull_request_authors":{"maartenschermer":2},"maintainers":[{"login":"MartineDeVos","count":14,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/MartineDeVos"},{"login":"surf-rbood","count":3,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/surf-rbood"},{"login":"maartenschermer","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/maartenschermer"},{"login":"cskaandorp","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/cskaandorp"}],"active_maintainers":[{"login":"maartenschermer","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/maartenschermer"}]},"events":{"total":{"DeleteEvent":1,"PushEvent":3,"PullRequestEvent":2,"ForkEvent":1,"CreateEvent":1},"last_year":{"DeleteEvent":1,"PushEvent":3,"PullRequestEvent":2,"ForkEvent":1,"CreateEvent":1}},"keywords":["aws","internet-archive","python","terraform","web-scraping"],"dependencies":[{"ecosystem":"pypi","filepath":"code/lambda-cdx/requirements.txt","sha":null,"kind":"manifest","created_at":"2023-01-25T13:31:18.666Z","updated_at":"2023-01-25T13:31:18.666Z","repository_link":"https://github.com/UtrechtUniversity/ia-webscraping/blob/main/code/lambda-cdx/requirements.txt","dependencies":[{"id":7150259259,"package_name":"boto3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7150259260,"package_name":"aiohttp","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"code/lambda-scrape/requirements.txt","sha":null,"kind":"manifest","created_at":"2023-01-25T13:31:18.702Z","updated_at":"2023-01-25T13:31:18.702Z","repository_link":"https://github.com/UtrechtUniversity/ia-webscraping/blob/main/code/lambda-scrape/requirements.txt","dependencies":[{"id":7150259263,"package_name":"boto3","ecosystem":"pypi","requirements":"==1.16.59","direct":true,"kind":"runtime","optional":false},{"id":7150259264,"package_name":"requests","ecosystem":"pypi","requirements":"==2.25.1","direct":true,"kind":"runtime","optional":false},{"id":7150259265,"package_name":"beautifulsoup4","ecosystem":"pypi","requirements":"==4.9.3","direct":true,"kind":"runtime","optional":false},{"id":7150259266,"package_name":"aiohttp","ecosystem":"pypi","requirements":"==3.7.4","direct":true,"kind":"runtime","optional":false},{"id":7150259267,"package_name":"idna","ecosystem":"pypi","requirements":"==2.5","direct":true,"kind":"runtime","optional":false},{"id":7150259268,"package_name":"s3fs","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":4.025351690735149,"created_at":"2025-09-04T15:50:49.331Z","updated_at":"2025-10-07T08:09:16.251Z","avatar_url":"https://github.com/UtrechtUniversity.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":["https://doi.org/10.5281/zenodo.7554441"],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/18122","html_url":"https://science.ecosyste.ms/projects/18122","bibtex_url":"https://science.ecosyste.ms/projects/18122/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/18122/export.apalike"}