爬取网页图片的Python脚本

spider.py

#!usr/bin/python

import urllib
import urllib2
import re


# Edit this variant to name the download images
index = 6000


html = urllib2.urlopen('http://jandan.net/ooxx/page-600#comments').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

print 'Done'