清华大佬耗费三个月吐血整理的几百G的资源,免费分享!....>>>
#!/usr/bin/env python # -*- coding: utf-8 -*- # by ustcwq # 2015-03-15 import urllib,urllib2,os,time from bs4 import BeautifulSoup start = time.clock() path = os.getcwd()+u'/模板之家抓取的模板/' if not os.path.isdir(path): os.mkdir(path) url = "http://www.cssmoban.com/cssthemes/index_80.shtml" # 源网站中的index后面数字怎么编排的? theme_url ='http://www.cssmoban.com/cssthemes/' response = urllib2.urlopen(url) soup = BeautifulSoup(response) result = soup.select('p[class="title"] a') print result for item in result: link = item['href'] # down_name = item.text # 文件名称 new_url = theme_url+link.split('/')[-1] response = urllib2.urlopen(new_url) soup = BeautifulSoup(response) result = soup.select('.btn a') down_url = result[1]['href'] # 文件链接 local = path+time.strftime('%Y%m%d%H%M%S',time.localtime(time.time()))+'.zip' urllib.urlretrieve(down_url, local) # 远程保存函数 end = time.clock() print u'模板抓取完成!' print u'一共用时:',end-start,u'秒'