test_paid_article.py 664 B

12345678910111213141516171819202122232425262728293031
  1. #!/usr/bin/python3
  2. import newspaper
  3. from newspaper import Article,Config
  4. import sys
  5. url="http://www.forbes.com/pictures/fjle45edkdm/no-1-detroit-michigan/"
  6. if url == "":
  7. print("pls url")
  8. sys.exit(1)
  9. config = Config()
  10. config.language='en'
  11. config.memoize_articles=False
  12. config.keep_article_html=True
  13. config.request_timeout=10
  14. config.fetch_images=False
  15. config.browser_user_agent="Mozilla/5.0 (X11; Linux x86_64; rv:47.0) Gecko/20100101 Firefox/47.0"
  16. config.verbose=True
  17. import forbes as parser
  18. print(url)
  19. html=parser.parse(url)
  20. a = Article(url=url,config=config)
  21. a.download(html=html)
  22. #print("dl")
  23. a.parse()
  24. print(a.title)
  25. print(a.text)
  26. #print(a.html)
  27. #