import re
import urllib
import urllib.request
def getHtml(url):
page = urllib.request.urlopen(url)
html = page.read()
return html
def getImg(html):
reg = r'src="(http://imgsrc.baidu.com/forum/.+?\.jpg)"'
imgre = re.compile(reg)
imglist = re.findall(imgre,bytes.decode(html))
return imglist
html = getHtml("http://tieba.baidu.com/p/3581437281")
imgurl = getImg(html)
print (len(imgurl))
x=100
for i in imgurl:
urllib.request.urlretrieve(i,"%s.jpg" % str(x))
x=x+1
Python 爬百度帖吧图片
最新推荐文章于 2021-04-12 11:31:44 发布