跟着鬼哥学爬虫-5-更新妹子图库质量，提高微信群聊发图速度

跟着鬼哥学爬虫-5-更新妹子图库质量，提高微信群聊发图速度

第三篇中的图库，群里大家都说质量稍微次一点，现在重新爬了个网站更新一下。

比上一篇的代码也优化了一点，对于自动保存的文件名，采用数字方式直接保存，方便后期在微信群中调用发送。

# -*- coding: utf-8 -*-
from bs4 import BeautifulSoup

import urllib2

import re


def getGirlUrl(n):

    url = 'http://www.4j4j.cn/beauty/tag_3_'+str(n)+'.html'

    print url

    response = urllib2.urlopen(url)

    html = response.read()

    soup1 = BeautifulSoup(html, "lxml")

    someData = soup1.select("div.i-list li a img")

    allUrls=[]

    for some in someData:

        allUrls.append(some['data-original'])

    return allUrls


def download(url):

    global number

    number +=1

    print number
    path = '/home/suz/midgirls/'
    content = urllib2.urlopen(url).read()

    filename = path+str(number)+'.jpg'
    print '下载---'+filename
    f = open(filename,'w+')
    f.write(content)
    f.close()





if __name__ == "__main__":

    number=1

    getGirlUrl(1)

    for i in range(1,75):

        urls=getGirlUrl(i)

        for u in range(1,len(urls)):

            download(urls[u])

        print '正在爬第'+str(i)+'页'

    print '爬完了～～！'

效果图：