example.py 741 B

12345678910111213141516171819202122232425262728293031
  1. import os
  2. import sys
  3. import requests
  4. from bs4 import BeautifulSoup
  5. import lxml
  6. parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
  7. sys.path.insert(0, parentdir)
  8. # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
  9. # Before run this example, Please run 'run.py'.!!
  10. # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
  11. def get_proxy():
  12. r = requests.get('http://127.0.0.1:5000/get')
  13. proxy = BeautifulSoup(r.text, "lxml").get_text()
  14. return proxy
  15. def crawl(url, proxy):
  16. proxies = {'http': proxy}
  17. r = requests.get(url, proxies=proxies)
  18. return r.text
  19. def main():
  20. proxy = get_proxy()
  21. html = crawl('http://docs.jinkan.org/docs/flask/', proxy)
  22. print(html)
  23. if __name__ == '__main__':
  24. main()