finance-news-miner

To identify hot investment sectors from financial news articles, this Skill uses Python feedparser and BeautifulSoup to extract sector keywords, detect price-movement signals, and compute heat scores from configurable RSS and web sources. It aggregates mention counts over a set window to produce a JSON report.

Yes, you can use BeautifulSoup and requests to scrape financial news for stock mention analysis. This Skill relies on those dependencies alongside feedparser to parse configured Chinese and international sources, extract stock keywords, and detect textual price-up or price-down signals for short-term trend detection.

The best way to detect short-term market trends from RSS feeds without market-data APIs is to apply text mining to extract sector and stock keywords. This Skill processes RSS sources with feedparser, counts positive mentions, and computes heat scores to rank frequently mentioned sectors and strong-performing stocks.

To extract price-movement signals and compute heat scores for stocks mentioned in news, this Skill detects textual price-up and price-down signals from articles. It counts positive mentions, aggregates these signals per sector and stock, and calculates a heat score to rank candidates in a JSON report.

Yes, this financial news mining approach supports both Chinese and international web sources. The Skill applies its sector and stock keyword extraction pipelines to configured RSS and web feeds from both markets to surface short-term themes and price-movement signals.

A limitation of using web scraping for sector analysis instead of market-data APIs is that detection relies entirely on textual price-movement signals and keyword mentions rather than real-time quantitative market data. Users must verify surfaced hot sectors and candidate stocks from the JSON report before trading.