spider.py

#!/usr/bin/env python

"""This Spider find the images on http://jandan.net/ooxx and 
download it to local directory"""

import urllib
import urllib2
import re

# Edit this variant to name the download images
index = 1000

def getImagesByUrl(url):

    global index
    html = urllib2.urlopen(url).read()

    regex = re.compile(r'<img src="(.+?)" />')
    imgUrls = regex.findall(html)


    for i in range(0, len(imgUrls)):

        localpath = '/cygdrive/c/nginx-1.2.7/html/21/images/'

        if imgUrls[i].endswith('.jpg') is True:
            print str(index) + '.jpg ' + imgUrls[i]
            localpath = localpath + str(index) + '.jpg';
        elif imgUrls[i].endswith('.gif') is True:
            print str(index) + '.gif ' + imgUrls[i]
            localpath = localpath + str(index) + '.gif';
        elif imgUrls[i].endswith('.png') is True:
            print str(index) + '.png ' + imgUrls[i]
            localpath = localpath + str(index) + '.png';
        else:
            continue

        try:
            urllib.urlretrieve(imgUrls[i], localpath)
            print 'ok'
        except:
            print 'fault'

        index = index + 1

if __name__ == '__main__':
    for i in range(100, 150):
        getImagesByUrl('http://jandan.net/ooxx/page-' + str(i) + '#comments')