{"id":21177054,"url":"https://github.com/allenjue/webscraper","last_synced_at":"2025-06-11T09:32:14.770Z","repository":{"id":112864012,"uuid":"526028940","full_name":"AllenJue/webScraper","owner":"AllenJue","description":"A WebScraper that grabs stock data and exports it to a CSV file","archived":false,"fork":false,"pushed_at":"2022-08-21T22:36:45.000Z","size":71,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-14T18:37:30.003Z","etag":null,"topics":["csv-export","htmlunit","webscraping"],"latest_commit_sha":null,"homepage":"","language":"Java","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/AllenJue.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":"2022-08-18T02:40:40.000Z","updated_at":"2023-01-06T23:18:08.000Z","dependencies_parsed_at":null,"dependency_job_id":"72c75ba6-3b65-4fc3-b73d-25c2db510a2d","html_url":"https://github.com/AllenJue/webScraper","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllenJue%2FwebScraper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllenJue%2FwebScraper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllenJue%2FwebScraper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllenJue%2FwebScraper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AllenJue","download_url":"https://codeload.github.com/AllenJue/webScraper/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllenJue%2FwebScraper/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259238931,"owners_count":22826822,"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":["csv-export","htmlunit","webscraping"],"created_at":"2024-11-20T17:14:24.807Z","updated_at":"2025-06-11T09:32:14.743Z","avatar_url":"https://github.com/AllenJue.png","language":"Java","readme":"# webScraper\n\n## Introduction\nThis webScraper is an introductory webScraper project that gathers share information from \n[Fortune 500 companies](https://markets.businessinsider.com/index/components/s\u0026p_500?p=1) and exports the data into a folder of csv files.\n\n## Features\nThe webScraper is currently a precursor to machine learning models that learn from csv datasets. It can currently only scrape info from [this site](https://markets.businessinsider.com/index/components/s\u0026p_500?p=1).\nCsv files will not be recreated if they already exist, and the files are stored in the users //User/Documents/Shared_Data directory.\n\n## Technologies\n* Java 8 or higher\n* HTMLUnit\n* OpenCSV\n* JUnit\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fallenjue%2Fwebscraper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fallenjue%2Fwebscraper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fallenjue%2Fwebscraper/lists"}