spacepaste

Paste details

reply | raw | toggle line wrapping

  1.  
  2. import urllib2
  3. import re
  4. from os.path import basename
  5. from urlparse import urlsplit
  7. url = "http://tieba.baidu.com/p/683991021"
  8. def getPage(url):
  9. url=url+"?see_lz=1"
  10. urlContent = urllib2.urlopen(url).read()
  11. page='<span class="red">(.*?)</span>'
  12. thePage=re.findall(page,urlContent)
  13. return int(thePage[0])
  14. def downImg(url):
  15. urlContent = urllib2.urlopen(url).read()
  16. spans='<cc>(.*?)</cc>'
  17. ss=re.findall(spans,urlContent)
  18. obImgs=','.join(ss)
  19. imgUrls = re.findall('img .*?src="(.*?)"', obImgs)
  20. for imgUrl in imgUrls:
  21. try:
  22. imgData = urllib2.urlopen(imgUrl).read()
  23. fileName = basename(urlsplit(imgUrl)[2])
  24. output = open(fileName,'wb')
  25. output.write(imgData)
  26. output.close()
  27. except:
  28. print "Er.."
  29. def downLoad(url):
  30. numb=getPage(url)
  31. cont=0
  32. print "There are "+str(numb)+" pages."
  33. while cont<numb:
  34. cont+=1
  35. print "Downloading "+url+"?see_lz=1&pn="+str(cont)+"..."
  36. downImg(url+"?see_lz=1&pn="+str(cont))
  37. print 'Completed!'
  38. downLoad(url)
  39.  
Powered by spacepaste. Paste removal.