13 dependents
| Package | Description | Downloads/month |
|---|---|---|
| news-please - an integrated web crawler and information extractor for news that ... | 118K | |
| A Playwright-based web scraper with persistent caching, parallel scraping, progr... | 69K | |
| Local Deep Research achieves ~95% on SimpleQA benchmark (tested with Qwen 3.6). ... | 15K | |
| Extract place names from a URL or text, and add context to those names -- for ex... | 3K | |
| BERTrend analyses topic evolution over time using state-of-the-art transformer m... | 2K | |
| An MCP server to access RSS feeds of Google News and Google Trends | 2K | |
| The NewsLookout web scraping application with NLP and data pre-processing | 753 | |
| 432 | ||
| Extract the main content from a webpage using zendriver, readability-lxml, and B... | 327 | |
| A Python utility library for defining and constructing Agno Agents, Teams, and W... | 269 | |
| CLI tool to extract article content from URL and save as PDF | 102 | |
| A pipe-based news article scraping and metadata extraction library | 98 | |
| MCP server for Google News and Google Trends | 98 |
