python实现简单爬虫--爬图片
#!/usr/bin/env python#encoding:utf-8
import urllib
import re
def getHtml(url):
'''获取到url的html内容'''
page = urllib.urlopen(url)
html = page.read()
return html
html1 = getHtml('http://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gbk&word=%C3%C0%C5%AE&ala=1&fr=ala&alatpl=cover&pos=0')
# print html1
# print re.findall(r'"objURL":"(.+?\.jpg)"',html1)
def downloadImg(html1):
'''下载页面里的jpg图片'''
reg = r'"objURL":"(.+?\.jpg)"'
#预编译正则表达式提高运行速度
imgreg = re.compile(reg)
urllist = re.findall(imgreg,html1)
num = 0
#for循环遍历下载每个图片
for i in urllist:
urllib.urlretrieve(i,'%s.jpg' % num)
num+=1
downloadImg(html1)
页:
[1]