Use LLMs to robustly extract web data

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.

⛏️ The extraction engine behind Maigret: turn any profile URL into a structured OSINT record across 150+ sites

news-please - an integrated web crawler and information extractor for news that just works

To extract main article from given URL with Node.js

A sketch extractor for anime/illustration.

An out-of-box human parsing representation extractor.

A (companion) plugin to facilitate the extraction of text from images (OCR) and PDFs.

MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.

A collection of seven Claude Code skills for job hunting that emphasize honest, fact-based CV optimization, STAR stories, cover letters, mock interviews, and more.

Extract clean conversation logs from Claude Code's internal storage

DDL eXtractor functions for PostgreSQL (ddlx)