python抓取网页图片示例(python爬虫)
本文导语: 代码如下:#-*- encoding: utf-8 -*-'''Created on 2014-4-24 @author: Leon Wong''' import urllib2import urllibimport reimport timeimport osimport uuid #获取二级页面urldef findUrl2(html): re1 = r'http://tuchong.com/d+/d+/|http://w+(?# @blocknum: 已经下载的数据块# ...
#-*- encoding: utf-8 -*-
'''
Created on 2014-4-24
@author: Leon Wong
'''
import urllib2
import urllib
import re
import time
import os
import uuid
#获取二级页面url
def findUrl2(html):
re1 = r'http://tuchong.com/d+/d+/|http://w+(?# @blocknum: 已经下载的数据块
# @blocksize: 数据块的大小
# @totalsize: 远程文件的大小
# '''
# print str(blocknum),str(blocksize),str(totalsize)
# if blocknum * blocksize >= totalsize:
# print '下载完成'
def quitit():
print "Bye!"
exit(0)
if __name__ == '__main__':
print ''' *****************************************
** Welcome to Spider for TUCHONG **
** Created on 2014-4-24 **
** @author: Leon Wong **
*****************************************'''
pageNo = raw_input("Input the page number you want to scratch (1-100),please input 'quit' if you want to quit>")
while not pageNo.isdigit() or int(pageNo) > 100 :
if pageNo == 'quit':quitit()
print "Param is invalid , please try again."
pageNo = raw_input("Input the page number you want to scratch >")
#针对图虫人像模块来爬取
html = getHtml("http://tuchong.com/tags/%E4%BA%BA%E5%83%8F/?page="+str(pageNo))
detllst = findUrl2(html)
for detail in detllst:
html2 = getHtml(detail)
download(html2,pageNo)
print "Finished."