13 dependents
| Package | Description | Downloads/month |
|---|---|---|
| Extract embedded metadata from HTML markup | 341K | |
| Remove DIVs, style stuff and normalize HTML preserving structure information | 19K | |
| Parsing of data from web pages. | 19K | |
| 6K | ||
| mini-framework | 2K | |
| headless implementation for the Reasonify Agent | 1K | |
| Sync transactions into your YNAB Unlinked account from a bank generated supporte... | 1K | |
| Document parsing tool for LLM training and Rag | 327 | |
| audit which email addresses can be collected by bots from your sites. | 185 | |
| TrustRAG：The RAG Framework within Reliable input,Trusted output | 121 | |
| 这是一个从 RagFlow 项目的 DeepDoc 模块中抽取出来的专门用于 PDF 解析的 Python 库。它提供了强大的 PDF 文档解析能力，支持 OC... | 114 | |
| Python boilerplate | 78 | |
| 77 |
