{"id":20736954,"url":"https://github.com/4rnv/scrappy","last_synced_at":"2026-06-04T17:31:11.444Z","repository":{"id":231608007,"uuid":"782202262","full_name":"4rnv/Scrappy","owner":"4rnv","description":"Script to scrap URLs from a webpage and archive them on the Wayback machine.","archived":false,"fork":false,"pushed_at":"2024-04-04T20:56:37.000Z","size":1,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-18T01:21:47.571Z","etag":null,"topics":["python","scraper","wayback-machine"],"latest_commit_sha":null,"homepage":"","language":"Python","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/4rnv.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}},"created_at":"2024-04-04T20:45:18.000Z","updated_at":"2024-04-16T19:32:45.000Z","dependencies_parsed_at":"2024-04-04T21:52:52.856Z","dependency_job_id":null,"html_url":"https://github.com/4rnv/Scrappy","commit_stats":null,"previous_names":["4rnv/scrappy"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/4rnv%2FScrappy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/4rnv%2FScrappy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/4rnv%2FScrappy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/4rnv%2FScrappy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/4rnv","download_url":"https://codeload.github.com/4rnv/Scrappy/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243023445,"owners_count":20223421,"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"}},"keywords":["python","scraper","wayback-machine"],"created_at":"2024-11-17T06:12:50.579Z","updated_at":"2025-03-11T11:25:28.560Z","avatar_url":"https://github.com/4rnv.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"A Python script to scrape URLs from a webpage and archive them to the Wayback machine. Uses Beautiful Soup to parse a page for anchor tags and then saves them using the Archive.org API. The name is supposed to be scrap.py as in scrapping plus python.\n\n# Usage\n\nClone or ZIP this repo. Install the modules mentioned in `requirements.txt` using `pip install -r requirements.txt`. Then run the script in your terminal and follow the screen instructions.\n\n\nIMPORTANT: `time.sleep(5)` delays archival of each URL for 5 seconds. This is to avoid overloading the API with excess requests, due to which sometimes the server refuses the connection. A healthy gap between each request prevents that.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F4rnv%2Fscrappy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2F4rnv%2Fscrappy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F4rnv%2Fscrappy/lists"}