python爬虫抓取色影无忌月赛获奖图片

因为平时爱好摄影，所以喜欢看看色影无忌论坛的获奖摄影作品，所以写了个小script用来抓取上面的获奖图片，亲自测试可以使用。

# -*- coding: UTF-8 -*-

#作者Rocky Chen
import re, urllib, sys, os, time, urllib2, cookielib, string

class Download:
    def __init__(self, url):
        self.url=url

    def getPhotos(self):
        #获取的是跳转收的各个页面的图片 如： http://vision.xitek.com/monthly/yuesaipingxuan/201404/14-149893.html
        user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
        header = { 'User-Agent' : user_agent }
        req=urllib2.Request(self.url,headers=header);
        resp=urllib2.urlopen(req)
        web_content=resp.read()
        print web_content
        all_link = re.findall(r'<div class="mshow"><a href="(.+?)" target="_blank">', web_content)
        print all_link
        print "All link done"
        for link in all_link:
            print "One link"
            print  link
            req1=urllib2.Request(link,headers=header)
            resp1=urllib2.urlopen(req1)
            web_content_each=resp1.read()
            print web_content_each
            my_photos=re.findall(r'<img class="mimg" .+? src="(.+?)" .+? border=0/></div>',web_content_each)
            print my_photos

            for my_photo in my_photos:

                file_name_obj=re.findall(r'http://.+?/(\w+.jpg)',my_photo)
                file_name=file_name_obj[0]
                print file_name
                urllib.urlretrieve(my_photo,file_name)
                time.sleep(4)

def Usage():
    print "Usage: xitek_month_match.py http://--Help"

if __name__ == "__main__":

    if len(sys.argv)<1:
        Usage()
        exit()

    reload(sys)
    sys.setdefaultencoding('utf-8')
    for arg in sys.argv[1:]:
        print arg
        xitek=Download(arg)
        xitek.getPhotos()

    print "Done"

自动抓取一月到十二月的获奖图片