{"id":23709965,"url":"https://github.com/desktopcleaner/naturemagazinescraper","last_synced_at":"2026-02-06T11:30:21.948Z","repository":{"id":268620499,"uuid":"876374489","full_name":"DesktopCleaner/NatureMagazineScraper","owner":"DesktopCleaner","description":"Scrapes open-access Nature magazine articles and store as txt files.","archived":false,"fork":false,"pushed_at":"2024-12-22T00:13:40.000Z","size":3613,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-30T18:59:18.270Z","etag":null,"topics":["data","nature-magazine","python","scrapper","word-frequency"],"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/DesktopCleaner.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":"2024-10-21T21:28:49.000Z","updated_at":"2024-12-22T00:13:44.000Z","dependencies_parsed_at":"2024-12-17T22:37:04.600Z","dependency_job_id":"5b0e896c-bd4e-4ae7-a422-8d9293b5cce5","html_url":"https://github.com/DesktopCleaner/NatureMagazineScraper","commit_stats":null,"previous_names":["desktopcleaner/naturemagazinescraper"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DesktopCleaner%2FNatureMagazineScraper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DesktopCleaner%2FNatureMagazineScraper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DesktopCleaner%2FNatureMagazineScraper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DesktopCleaner%2FNatureMagazineScraper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DesktopCleaner","download_url":"https://codeload.github.com/DesktopCleaner/NatureMagazineScraper/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239793826,"owners_count":19698053,"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":["data","nature-magazine","python","scrapper","word-frequency"],"created_at":"2024-12-30T18:59:24.043Z","updated_at":"2026-02-06T11:30:21.880Z","avatar_url":"https://github.com/DesktopCleaner.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NatureMagazineScraper\nScrape open-access Nature articles and store them as txt files.\n\n# Key Features\n- User can specify which year's articles to scrape/analyze\n- User can specify maximum word count per word per article to reduce over-counting\n\n## scraper.py\nScrape articles using `Beautiful Soup` and store them as text files\n\n## analyzer.py\nParse scrapped articles and sum up word counts\n\n## data_cleaner.py\nClean common words and other baised words\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdesktopcleaner%2Fnaturemagazinescraper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdesktopcleaner%2Fnaturemagazinescraper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdesktopcleaner%2Fnaturemagazinescraper/lists"}