use BeautifulSoup to crow jandant

jandan_spider.py

#!/usr/bin/python
#-*- coding: utf-8 -*-
#encoding=utf-8

import urllib
import urllib2
import os
import time
from BeautifulSoup import BeautifulSoup

def getAllImageLink(targetlink):
    html = urllib2.urlopen(targetlink).read()
    soup = BeautifulSoup(html)
    print(targetlink)
    liResult = soup.findAll('ol', attrs={'class': "commentlist"})
    nextHtml = soup.find('a', attrs={'class': 'previous-comment-page'}).get('href')

    for li in liResult:
        imageEntityArray = li.findAll('img')
        for image in imageEntityArray:
            link = image.get("src")
            imageName = time.time()
            currentPath = os.path.dirname(os.path.realpath(__file__))

            if not os.path.exists(currentPath + '/ooxx'):
                os.makedirs(currentPath + '/ooxx')

            filePath = currentPath + '/ooxx/%s.jpg' % imageName
            if not os.path.exists(filePath):
                try:
                    urllib.urlretrieve(link, filePath)
                except:
                    pass
                # print filePath

    getAllImageLink(nextHtml)


if __name__ == '__main__':
    # print os.path.dirname(os.path.realpath(__file__))
    getAllImageLink('http://jandan.net/ooxx')