Python 爬取煎蛋网妹子图片

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date    : 2017-08-24 10:17:28
# @Author  : EnderZhou (zptxwd@gmail.com)
# @Link    : http://www.cnblogs.com/enderzhou/
# @Version : $Id$

import requests
from bs4 import BeautifulSoup as bs
import threading
import Queue
import urllib

class jiandan_ooxx(threading.Thread):
    def __init__(self,queue):
        threading.Thread.__init__(self)
        self._queue = queue

    def run(self):
        while not self._queue.empty():
            url = self._queue.get_nowait()
            self.spider(url)

    def spider(self,url):
        r = requests.get(url = url)
        soup = bs(r.content,'html.parser')
        imges = soup.find_all(name='img',attrs={})
        lists = []
        for i in imges:
            if 'border' in str(i):
                continue
            elif 'onload' in str(i):
                lists.append(i['org_src'])
                print i['org_src']
                img = 'http:' + i['org_src']
            else:
                lists.append(i['src'])
                print i['src']
                img = 'http:' + i['src']
            name = img.split('/')[-1]
            urllib.urlretrieve(img,filename=name)

def main(number):
    url = 'http://jandan.net/ooxx/page-'
    headers = {}
    queue = Queue.Queue()

    # 此处由最新页面开始爬取，默认爬取最新10页的图片，把number-11改成0即可爬取全部页面的图片。
    for i in xrange(number,number-11,-1):
        queue.put(url+str(i))
    threads = []
    thread_count = 10

    for i in range(thread_count):
        threads.append(jiandan_ooxx(queue))

    for t in threads:
        t.start()
    for t in threads:
        t.join()

if __name__ == '__main__':
    # 获取最新页码并传入main函数
    r = requests.get('http://jandan.net/ooxx')
    soup = bs(r.content,'html.parser')
    string = soup.find_all(name='span',attrs={'class':'current-comment-page'})
    number = int(string[1].string[1:-1]) 
    main(number)