Advanced Search

Python - Stampa i links di una pagina HTML

/ Published in: Python
Save to your folder(s)

Expand | Embed | Plain Text

Copy this code and paste it in your HTML 
  1. import re,sgmllib,sys,urllib
  2.  
  3. class Parser(sgmllib.SGMLParser):
  4.  
  5.     def start_a(self, attr):
  6.  
  7.         regx = re.compile('[Hh][Tt][Tt][Pp].*\....$')
  8.         href = [v for a, v in attr if a == 'href']
  9.         try:
  10.             if regx.match(href[0]): print href[0]
  11.         except:
  12.             pass
  13.  
  14. if __name__ == '__main__':
  15.  
  16.     try:
  17.  
  18.         fd = urllib.urlopen(sys.argv[1])
  19.  
  20.         parser = Parser()
  21.         parser.feed(fd.read())
  22.         parser.close()
  23.  
  24.         fd.close()
  25.  
  26.     except Exception, error:
  27.  
  28.         print 'Errore: ' + str(error)

Report this snippet


Comments

RSS Icon Subscribe to comments

You need to login to post a comment.