import urllib
import urllib2
import os
import re
import sys
def schedule(a,b,c):
per = 100.0 * a * b / c
if per > 100 :
per = 100
print '%.2f%%' % per
def getHtml(url):
page = urllib.urlopen(url)
html = page.read()
return html
def downloadImg(html, num, foldername):
picpath = '%s' % (foldername)
if not os.path.exists(picpath):
os.makedirs(picpath)
target = picpath+'/%s.jpg' % num
myItems = re.findall('<p><a href="http:\/\/www.mzitu.com/.*&＃63;"><img src="(.*&＃63;)" alt=".*&＃63;"></a></p>',html,re.S)
print 'Downloading image to location: ' + target
urllib.urlretrieve(myItems[0], target, schedule)
def findPage(html):
myItems = re.findall('<span>(\d*)</span>', html, re.S)
return myItems.pop()
def findList(html):
myItems = re.findall('<h2><a href="http://www.mzitu.com/(\d*)" title="(.*&＃63;)" target="_blank">.*&＃63;</a></h2>', html, re.S) return myItems
def totalDownload(modelUrl):
listHtml5 = getHtml(modelUrl)
listCOntent= findList(listHtml)
for list in listContent:
totalNum = findPage(html)
for num in range(1, int(totalNum)+1):
if num == 1:
html5 = getHtml(url)
downloadImg(html5, str(num), str(list[1]))
else:
html5 = getHtml(url)
downloadImg(html5, str(num), str(list[1]))
if __name__ == '__main__':
for model in range(1, int(findPage(listHtml))+1):
if model == 1:
totalDownload(modelUrl)
else:
totalDownload(modelUrl)
print "Download has finished."
京公网安备 11010802041100号 | 京ICP备19059560号-4 | PHP1.CN 第一PHP社区 版权所有 
