爬虫jd

import urllib.request;  #载入urllib.request,用于获取页面html源代码
from pandas import Series;  #载入series包
from pandas import DataFrame;   #载入dataframe包
from bs4 import BeautifulSoup;  #载入beautifulsoup包
import json; #载入json包

response = urllib.request.urlopen('http://item.jd.com/2957726.html'); #获取html源代码
html = response.read(); #将源代码转入html
soup = BeautifulSoup(html); #解析html
data = DataFrame(columns=['Feature', 'Property']) #创建空白dataframe用于装载爬取信息

divSoup = soup.find(id="product-detail-2")  #通过分析，发现规格参数所在部分id
trs = divSoup.find_all('tr');

for tr in trs :
    tds = tr.find_all('td');
    if len(tds)==2: #列表有两个值的时才执行爬取
        f=tds[0].getText();
        p=tds[1].getText();  
        data = data.append(
            Series(
                [f, p], 
                index=['Feature', 'Property']
            ), ignore_index=True
        );

response = urllib.request.urlopen('http://p.3.cn/prices/get?skuid=J_2244423');
jsonString = response.read();
jsonObject = json.loads(jsonString.decode())
jsonObject[0]['p']  #解析p的值，即价格

df.to_csv("D:\\df.csv"); #导出结果