爬取图片
「已注销」 2017-12-16 11:02:46 import re
import urllib.request
def craw(url,page):
html1=urllib.request.urlopen(url).read()
html1=str(html1)
pat1='div id=pilst".+?<div class="page clearfix">'
result1=re.compile(pat1,re.S).findall(html1)
result1=result1[0]
pat2='<img width-"220" height="220" data-img="1" data-lazy-img="//(.+?\.jpg)">'
imagelist=re.compile(pat2).findall(result1)
x=1
for imageurl in imagelist:
imagename="E:/新建文件夹/myweb/"+str(page)+str(x)+".jpg"
imageurl="http://"+imageurl
try:
urllib.request.urlretrieve(imageurl,filename=imagname)
except urllib.error.URLError as e:
if hasattr(e,"code"):
x+=1
x+=1
x+=1
for i in range(1,79):
url="http://list.jd.com/list.html?cat=9987,653,655&page="+str(i)
craw(url,i)
出现以下错误,怎么解决?求大神指导。
Traceback (most recent call last):
File "E:\新建文件夹\myweb\paqutupain.py", line 27, in <module>
craw(url,i)
File "E:\新建文件夹\myweb\paqutupain.py", line 9, in craw
result1=result1[0]
IndexError: list index out of range