{"id":16269265,"url":"https://github.com/thinkwee/nlp_spyders","last_synced_at":"2025-04-08T15:17:32.438Z","repository":{"id":79907437,"uuid":"189819955","full_name":"thinkwee/NLP_Spyders","owner":"thinkwee","description":"Various spyders for crawling NLP corpus","archived":false,"fork":false,"pushed_at":"2019-06-02T08:03:27.000Z","size":15,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-14T11:33:34.938Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/thinkwee.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":"2019-06-02T08:01:31.000Z","updated_at":"2019-06-02T08:03:29.000Z","dependencies_parsed_at":"2023-05-04T14:31:07.976Z","dependency_job_id":null,"html_url":"https://github.com/thinkwee/NLP_Spyders","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/thinkwee%2FNLP_Spyders","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2FNLP_Spyders/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2FNLP_Spyders/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2FNLP_Spyders/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thinkwee","download_url":"https://codeload.github.com/thinkwee/NLP_Spyders/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247867365,"owners_count":21009240,"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":[],"created_at":"2024-10-10T18:07:50.129Z","updated_at":"2025-04-08T15:17:32.420Z","avatar_url":"https://github.com/thinkwee.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NLP_Spyders\n-   各种语料爬虫\n    -   acl_link+acl_pdf：爬取ACL论文，爬取链接和爬取pdf分开写，10到18年约9000多篇\n    -   exec_pdf2txt+pdf2txt：将pdf论文转换为文本\n    -   china_news：爬取中国新闻网，可用于中文文本分类，27类，12年到18年可爬取350w+新闻\n    -   douban_spyder：爬取豆瓣书评，需改进防止被反爬虫\n    -   sina_spyder：爬取新浪新闻，可用于文本分类，类别比例比较不均匀\n    -   wiki_spyder：爬取英文维基百科，可用于链接分析和聚类\n    -   china_news_headline_generation：爬取中国新闻网新闻正文+标题，用于标题生成任务","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthinkwee%2Fnlp_spyders","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthinkwee%2Fnlp_spyders","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthinkwee%2Fnlp_spyders/lists"}