清华大佬耗费三个月吐血整理的几百G的资源，免费分享！....>>>

#coding:utf-8
import urllib2
import re
from bs4 import BeautifulSoup
class fanli():
    def __init__(self):
        self.usr_agent='Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.86 Safari/537.36'
        self.headers={'usr_agent',self.usr_agent}
        self.p=1
        self.pageIndex=1
    def getHtml(self,p,pageIndex):
        try:
            url='http://zhide.fanli.com/index/ajaxGetItem?cat_id=0&tag=&page='+str(pageIndex)+'-'+str(p)+'&area=0&tag_id=0&shop_id=0'
            request=urllib2.Request(url)
            page=urllib2.urlopen(request)
            html=page.read()
            return html
        except urllib2.URLError,e:
            if hasattr(e,'reason'):
                print u'连接失败',e.reason
                return None
    def getItems(self):
        with open('fanli.txt','a') as f:
            f.write('商品名称'+'|'+'分类'+'|'+'推荐人'+'|'+'好评数'+'|'+'差评数'+'\n')
        for pageIndex in range(1,51):
            for p in range(1,11):
                html=self.getHtml(pageIndex,p)#IndexError：list index out of range在第11页出现的问题
                html=self.getHtml(pageIndex,p)
                rep=re.compile(' J_tklink_tmall')
                data=rep.sub('',html)
                soup=BeautifulSoup(data)
                name_list=soup.find_all('a',class_='J-item-track nodelog')#商品名称
                fenlei_list=soup.find_all('a',class_='nine')#分类
                usr_list=soup.find_all('div', class_='item-user')#推荐人
                yes_list=soup.find_all('a',class_='l item-vote-yes J-item-vote-yes')#好评
                no_list=soup.find_all('a',class_='l item-vote-no J-item-vote-no')#差评
                f=open('fanli.txt','a')
                for i in range(0,5):
                    f.write(name_list[i].get_text(strip=True).encode("utf-8")+'|'\
                        +fenlei_list[i].get_text(strip=True).encode("utf-8")+'|'\
                        +usr_list[i].get_text(strip=True).encode("utf-8")+'|'\
                        +yes_list[i].get_text(strip=True).encode("utf-8")+'|'\
                        +no_list[i].get_text(strip=True).encode("utf-8")+'|'+'\n')
                f.close()
spider=fanli()
spider.getItems()