【python 淘宝爬虫】淘宝信誉分抓取

一、需求分析
输入旺旺号，获取淘宝卖家的信用分

二、思路
淘宝需要模拟登陆，我们这里抓不到，因此为了绕过登陆，发现了淘一兔，我们可以通过这里，得到淘宝卖家的信用分，结果是一样的。
http://www.taoyizhu.com/

输入旺旺号，需要点击查询，等待几秒，得到查询结果，这里我们用selienum 来做

三、实现源代码（抓取不能太快，否则抓不到）

# encoding: utf-8

from selenium import webdriver
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import pandas as pd
import time
import re
time1=time.time()

driver=webdriver.PhantomJS(executable_path='D:\\Program Files\\Python27\\Scripts\\phantomjs.exe')
driver.set_window_size(800, 600)

########################读取数据############################
data1=pd.read_excel(r'C:/taobao/taobao1.xlsx')
print data1


#######################查询店铺信誉分#############################
seller_credit=[]
for i in range(0,len(data1)):
    key=str(data1.iloc[i,0])
    key1=key.decode("utf-8")
    driver.get("http://www.taoyizhu.com/")
    time.sleep(5)
    driver.find_element_by_id("txt_name").clear()
    driver.find_element_by_id("txt_name").send_keys(key1)
    driver.find_element_by_id('search_btn').click()
    time.sleep(3)
    html2 = driver.page_source
    seller_credit1 = re.findall('<span id="spanUserSellerCount">(.*?)</span>', html2, re.S)
    for each in seller_credit1:
        print key,each
        seller_credit.append(each)


#######################################增加店铺信誉分这一列#############################
data1['店铺信誉分']=seller_credit

print data1


# 写出excel
writer = pd.ExcelWriter(r'C:\\taobao\\taobao1_all.xlsx', engine='xlsxwriter', options={'strings_to_urls': False})
data1.to_excel(writer, index=False)
writer.close()

time2 = time.time()
print u'ok,爬虫结束!'
print u'总共耗时：' + str(time2 - time1) + 's'