爬取百度贴吧图片的小爬虫

#本来想要爬取百度图片的图片，但是发现那些图片都是js加载的，具体怎么爬取现在还不能搞清。。。。，所以就选择了百度贴吧里面的图片　
#!/usr/bin/python
#coding: utf-8

#
# name: download images from baiduTieba
#
#author: Hacker_MJW
#
#date: 2014-02-15
#

import urllib
import urllib2

import re


class reptile:
    
    def __init__(self, url):
        self.url = url
        user_agent = "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)"
        self.headers = {'User-Agent': user_agent}

    def buil_re(self):
        self.p = re.compile("<img.*?class=\"BDE_Image\"\s*src=\"(.*?)\".*?>")

    def open_page(self):
        self.req = urllib2.Request(url=self.url, 
            headers=self.headers
            )
        self.page = urllib2.urlopen(self.req).read().replace('\n', '')
    
    def find(self):
        self.img = self.p.findall(self.page)
    
    def cbk(self):
        self.per = 100.0 * a * b /c
        if self.per > 100:
            self.per = 100
        print '%.2f%%' % self.per

    def download(self, total):    #这里只爬取了一页，如果需要爬去多页的话，找出下一页的链接即可
        n_count = 0
        print self.img
        for img in self.img:
            urllib.urlretrieve(img, "photos\%s.jpg"%str(n_count))
            n_count = n_count + 1
            if n_count > total:
                break
        print "%s张图片下载完成" % str(total)


if __name__ == '__main__':
    img = reptile('http://tieba.baidu.com/p/2791466984')     #这个网址是我自己选的，大家可以换成美女的网址，^_^
    img.buil_re()
    img.open_page()
    img.find()
    img.download(50)

 

转载于:https://www.cnblogs.com/MyselfDancing/p/3551173.html