爬取图片
-——
爬取百度贴吧的图片:
# coding=utf-8
import urllib
import re
def getHtml(url):
page = urllib.urlopen(url)
html = page.read()
return html
def getImg(html):
reg = r’src=”(.+?\.jpg)” pic_ext’
imgre = re. compile(reg)
imglist = re. findall(imgre,html)
x = 0
for imgurl in imglist:
urllib.urlretrieve(imgurl,’%s.jpg’ % x)
x+=1
html = getHtml(“http://tieba.baidu.com/p/2460150866“)
print getImg(html)
#————————————————————————————————————————————————————-
爬取豆瓣的图片:
#!/usr/bin/python
# encoding:utf-8
import urllib2
import re
a = urllib2.urlopen(‘https://movie.douban.com/').read()
b = re.findall(r’https://.+\\.jpg‘, a)
i = 0
try:
for c in b:
f = open(str(i) + ‘.jpg’, ‘wb’)
req = urllib2.urlopen(c)
buf = req.read()
f. write(buf)
i += 1
f.close()
except Exception as e:
print e
还没有评论,来说两句吧...