url-parser
url_crawler
High-Concurrency URL Web Page Content Fetching Service. 高并发URL网页内容抓取服务。
- 5
- Python
- Apache-2.0
- 12 mo ago
InformaTruth
Multi-agent fake news detection system built on a fine-tuned RoBERTa classifier with FLAN-T5 explanations, prompt-injection sanitisation on scraped content, heuristic hallucination-risk scoring, parallelized fallback search, and a human review queue that tracks model versus human agreement.
- 2
- Jupyter Notebook
- MIT
- 5 wk ago
Sort3r
A simple Bash script to extract, normalize, and deduplicate URLs from a file.
- 3
- Shell
- GPL-3.0
- 9 mo ago
soundcloud-scraper
SoundCloud Scraper — free, open-source SoundCloud scraper. Unlimited tracks, artists, plays, likes & charts as clean JSON, no API key, no proxies.
- 1
- Python
- MIT
- 2 d ago
