Isaac

XiangJinYu

AI & ML interests

Agent, LLM, RL

Recent Activity

Organizations

None yet

XiangJinYu's activity

reacted to singhsidhukuldeep's post with πŸ‘ 12 months ago
view post
Post
2383
Are you tired of writing scripts to scrape data from the web? πŸ˜“

ScrapeGraphAI is here for you! πŸŽ‰

ScrapeGraphAI is an OPEN-SOURCE web scraping Python library that uses LLM and direct graph logic to create scraping pipelines for websites and local documents (XML, HTML, JSON, etc.). πŸŒπŸ“Š

Just say which information you want to extract (in human language) and the library will do it for you! πŸ—£οΈπŸš€

It supports GPT, Gemini, and open-source models like Mistral. πŸ”

A few things that I could not find in the docs but would be amazing to see 🀞:
- Captcha handling πŸ”
- Persistent data output formatting πŸ“
- Streaming output πŸ“‘
- ExplanationπŸ˜‚ of the tag line: "ScrapeGraphAI: You Only Scrape Once" What does that even mean? 🀣 Is this YOLO? πŸ€”

Link: https://github.com/VinciGit00/Scrapegraph-ai
Demo code: https://github.com/amrrs/scrapegraph-code/blob/main/sourcegraph.ipynb
Β·