python爬虫系列之爬京东手机数据

python抓京东手机数据

作者:vpoet

mail:vpoet_sir@163.com

#coding=utf-8

import urllib2

from lxml import etree

import re


if __name__ == '__main__':
    
    main_url = """http://search.jd.com/Search?keyword=%%E6%%89%%8B%%E6%%9C%%BA&enc=utf-8&suggest=0#keyword=%%E6%%89%%8B%%E6%%9C%%BA&enc=utf-8&qrst=1&ps=addr&rt=1&stop=1&sttr=1&cid3=655&click=3-                655&psort=3&page=%s"""
    
    page_num = 1
    
    for page in range(page_num):
        
        html_url = main_url % page
        
        Res = urllib2.urlopen(html_url)
        
        Htm = Res.read()
        
        #print Htm

        tree = etree.HTML(Htm);
 
        #phone_names = tree.xpath("//div[@id='plist']/ul/li/div[@class='lh-wrap']/div[@class='p-name']/a/text()")   
        
    #x = 1
        #for phone_name in phone_names: 
            #print phone_name+'	'+str(x)+'
'

        #x=x+1
    
 

    #phone_pic_urls = tree.xpath("//div[@class='lh-wrap']/div[@class='p-img']/a/img")

    #for phone_pic_url in phone_pic_urls: 
        #print phone_pic_url.values()[3]

    #phone_prices = tree.xpath("//div[@class='p-price']/strong")  
    phone_prices = tree.xpath("//*[@id='plist']/ul[@class='list-h clearfix']/li/div/div[@class='p-price']/strong") 
        
    x = 1

        for phone_price in phone_prices: 
            print phone_price.values()[1]+'	'+str(x)+'
'
        x = x + 1


    #phone_comments = tree.xpath("//div[@class='extra']/a/text()")  
        
        #for phone_comment in phone_comments: 
            #print "评价数"
        #comment_num = re.findall(r'.{2}(d+).{3}',phone_comment)
        #print comment_num[0]


    #phone_good_comments = tree.xpath("//div[@class='extra']/span[@class='reputation']/text()")  
        
        #for phone_good_comment in phone_good_comments: 
            #print "好评率"
        #comment_good_num = re.findall(r'((d{2})%.{2})',phone_good_comment)
        #print comment_good_num[0]


    print "over"

这个没写完，先保存在这里。有时间再完成