{"id":18553977,"url":"https://github.com/bodrovis-learning/scrapingbee-load-site-data-model-training","last_synced_at":"2025-08-05T23:11:44.615Z","repository":{"id":245705469,"uuid":"819012953","full_name":"bodrovis-learning/ScrapingBee-Load-Site-Data-Model-Training","owner":"bodrovis-learning","description":"How to scrape all text from a website for LLM training","archived":false,"fork":false,"pushed_at":"2024-07-04T12:22:13.000Z","size":24,"stargazers_count":0,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-15T11:50:40.334Z","etag":null,"topics":["python3","scraping","web-scraping"],"latest_commit_sha":null,"homepage":"https://www.scrapingbee.com/blog/how-to-scrape-all-text-from-a-website-for-llm-ai-training/","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/bodrovis-learning.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,"zenodo":null}},"created_at":"2024-06-23T14:26:33.000Z","updated_at":"2024-07-04T12:22:16.000Z","dependencies_parsed_at":"2025-05-15T11:44:34.403Z","dependency_job_id":"ca4914a4-e8e5-481e-abd7-acf2c1786a66","html_url":"https://github.com/bodrovis-learning/ScrapingBee-Load-Site-Data-Model-Training","commit_stats":null,"previous_names":["bodrovis-learning/scrapingbee-load-site-data-model-training"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bodrovis-learning/ScrapingBee-Load-Site-Data-Model-Training","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bodrovis-learning%2FScrapingBee-Load-Site-Data-Model-Training","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bodrovis-learning%2FScrapingBee-Load-Site-Data-Model-Training/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bodrovis-learning%2FScrapingBee-Load-Site-Data-Model-Training/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bodrovis-learning%2FScrapingBee-Load-Site-Data-Model-Training/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bodrovis-learning","download_url":"https://codeload.github.com/bodrovis-learning/ScrapingBee-Load-Site-Data-Model-Training/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bodrovis-learning%2FScrapingBee-Load-Site-Data-Model-Training/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262319705,"owners_count":23293070,"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":["python3","scraping","web-scraping"],"created_at":"2024-11-06T21:19:07.916Z","updated_at":"2025-06-27T19:36:37.853Z","avatar_url":"https://github.com/bodrovis-learning.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# How to scrape all text from a website for LLM training\n\nhttps://www.scrapingbee.com/blog/how-to-scrape-all-text-from-a-website-for-llm-ai-training/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbodrovis-learning%2Fscrapingbee-load-site-data-model-training","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbodrovis-learning%2Fscrapingbee-load-site-data-model-training","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbodrovis-learning%2Fscrapingbee-load-site-data-model-training/lists"}