SHOW:
|
|
- or go back to the newest paste.
| 1 | from BeautifulSoup import BeautifulSoup, SoupStrainer import time, subprocess, httplib2, re import urllib f = urllib.urlopen("google.com";) lis=[] f.read() http = httplib2.Http() status, response = http.request('google.com';) for link in BeautifulSoup(response, parseOnlyThese=SoupStrainer('a')): if link.has_key('href'): s=str(link['href']) x=link['href'].startswith('google.com';) if x: print s lis.append(s) #print lis for m in lis: data = urllib.urlopen(m).read() |
