python爬某个网站的图片

时间：2021-09-09 11:04:00
# _*_ coding: gbk _*_

import urllib

import urllib2

import re

class Spider:

    def getImage(self,html):

        request=urllib2.Request(html);

        page=urllib2.urlopen(html);

        html=page.read();

        pattern=r'src="http:.*\.jpg'

        imglist=re.findall(pattern,html);

        cnt=0

        for i in imglist:

            print i[5:];

            urllib.urlretrieve(i[5:], 'E:\\images\%s.jpg' % cnt);

            cnt+=1

            if cnt==2:

                break;

        print 'the end'

if __name__=="__main__":

    print 'hello'

    s=Spider();

    #html=r"http://baike.baidu.com/link?url=pj6QaA2Zyrxx2WcD4f7vN50LWVIZjJUKYdnnLGMOWnmInlALGH4dXmU86hE3Ar-jmaiahjf2MiEZ3n_0WCOUlFuKwVfYZNKnBwxidD1cC3i";

    html=r"http://baike.baidu.com/link?url=rHaKx7RPBWuR4MxzY0BPhwbLKH4DEdwKPN8EYH-78Zzm7IMUuFTYM0eUZw-j27lHxDxyyNiqkjUg4JG8FvyjNUsuqiTzLixsNSXUtTWiOpQqrtxbf4hkj-n6gF1Nyn4D"

    s.getImage(html);

　　

python从某个网站上面爬很多图片的url,主要是从百度风云榜上面爬的，男演员，女演员，男歌手，女歌手，总共200张

# _*_ coding: gbk _*_

import urllib

import urllib2

import re

import os

class Spider:

    def getImage(self,html):

        request=urllib2.Request(html);

        page=urllib2.urlopen(html);

        html=page.read();

        pattern=r'href="http:.*简介'

        imglist=re.findall(pattern,html);

        with open(r'e:\\images\\paths.txt','w+') as f:

            for i in imglist:

                print i[6:len(i)-6];

                f.write(i[6:len(i)-6]);

                f.write('\n')

        print len(imglist)

        print 'the end'  

if __name__=="__main__":

    print 'hello'

    s=Spider();

    #html=r"http://baike.baidu.com/link?url=pj6QaA2Zyrxx2WcD4f7vN50LWVIZjJUKYdnnLGMOWnmInlALGH4dXmU86hE3Ar-jmaiahjf2MiEZ3n_0WCOUlFuKwVfYZNKnBwxidD1cC3i";

    html=r'http://top.baidu.com/buzz?b=18&qq-pf-to=pcqq.group'

    s.getImage(html);

　　

相关文章