爬虫抓取新闻模块提取库推荐newspaper

安装

pip3 install newspaper3k

使用

from newspaper import Article

url = 'http://www.example.com/path/to/article'
article = Article(url)
article.download()
article.parse()

text = article.text # 获取新闻正文
images = article.images # 获取新闻图片