| 123456789101112131415161718192021222324252627282930 |
- #!/usr/bin/python3
- import newspaper
- from newspaper import Article,Config
- import sys
- url = "http://feeds.wsjonline.com/~r/wsj/deals/feed/~3/lnaq0DpDaYI/"
- if url == "":
- print("pls url")
- sys.exit(1)
- config = Config()
- config.language='en'
- config.memoize_articles=False
- config.keep_article_html=True
- config.request_timeout=10
- config.fetch_images=False
- config.browser_user_agent="Mozilla/5.0 (X11; Linux x86_64; rv:47.0) Gecko/20100101 Firefox/47.0"
- config.verbose=True
- import wsj
- print(url)
- html=wsj.parse(url)
- a = Article(url=url,config=config)
- a.download(html=html)
- #print("dl")
- a.parse()
- print("parsed")
- print(a.text)
- #
|