爬虫爬取清纯妹子图

　

妹子图片

爬取清纯妹子 爬取图片，保存D盘下的image。

不多说废话，直接上码。我偷偷打码了 0.0

#!/usr/bin/Python
# -*- coding: utf-8 -*-


import urllib2
import urllib
import random
import socket
from bs4 import BeautifulSoup
from time import sleep

user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; windows NT)'
headers = { 'User-Agent' : user_agent }
f = open("2.txt","w")
i = 0
a = 0
while i<1:
    url = 'http://www.mmjpg.com/home/'+str(i)
    socket.setdefaulttimeout(5)
    req = urllib2.request(url, headers = headers)
    content_stream = urllib2.urlopen(req)
    content_stream = content_stream.read()
    soup = BeautifulSoup(content_stream,'html5lib')
    soupa = soup.select("ul > li > a")
    # soupa = soupa['src']
    print soupa
    for j in soupa:
        # print j['href']
        name = j.select('img')[0]
        # print name['alt']
        url = j['href']
        socket.setdefaulttimeout(5)
        req = urllib2.Request(url, headers = headers)
        try:
            content_stream = urllib2.urlopen(req)
            content_stream = content_stream.read()
            soup = BeautifulSoup(content_stream,'html5lib')
            soup = soup.select('#page > a')
            imgs = soup[-2].get_text()
            print imgs
            lists = 1
            while lists<=int(imgs):
                print lists
                url = j['href']
                socket.setdefaulttimeout(5)
                req = urllib2.Request(url+'/'+str(lists), headers = headers)
                try:
                    content_stream = urllib2.urlopen(req)
                    content_stream = content_stream.read()
                    soup = BeautifulSoup(content_stream,'html5lib')
                    soupa = soup.select('#content img')[0]
                    print soupa
                    lists+=1
                    f.write(soupa['src'].encode('utf-8').strip()+'\n')
                    path = 'D:\\image\\'+name['alt']+str(lists)+'.jpg'
                    urllib.urlretrieve(soupa['src'],path)
                    sleep(random.uniform(0.5,1))
                except Exception,e:
                    print u'漏掉一张图片' 
                    sleep(random.uniform(0.5,1))

        except Exception,e:
            print u'漏掉一个妹子' 
            sleep(random.uniform(0.5,1))

    i+=1

相关阅读

爬取妹子图网站的图片

网站：http://www.meizitu.com/ 目标：用BeautifulSoup解析网页源代码，获取图片． 图片链接： # /home/wl/PycharmProjects/untitled

如何使用图章制作专家软件制作电子图章

现在图章的使用可以说是很广泛的，不管是个人还是企业都或多或少有着他们自己专属的图章，更多的是运用在商户，个人爱好喜欢制作图章的