Python 爬百度帖吧图片

来源:互联网 发布:灰原哀 知乎 编辑:程序博客网 时间:2024/05/16 13:48
import reimport urllibimport urllib.requestdef getHtml(url):    page = urllib.request.urlopen(url)    html = page.read()    return htmldef getImg(html):    reg = r'src="(http://imgsrc.baidu.com/forum/.+?\.jpg)"'    imgre = re.compile(reg)    imglist = re.findall(imgre,bytes.decode(html))    return imglisthtml = getHtml("http://tieba.baidu.com/p/3581437281")imgurl = getImg(html)print (len(imgurl))x=100for i in imgurl:urllib.request.urlretrieve(i,"%s.jpg" % str(x))x=x+1

0 0