#/usr/bin/python 
from urllib import request 
from lxml import etree 
from selenium import webdriver 
import time 
 
# 京東手機商品頁面 
url = "http://item.jd.com/1312640.html" 
 
# 下面的xslt是通過集搜客的謀數(shù)臺圖形界面自動生成的 
xslt_root = etree.XML("""\ 
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" > 
<xsl:template match="/"> 
<商品> 
<xsl:apply-templates select="http://*[@id='itemInfo' and count(.//*[@id='summary-price']/div[position()=2]/strong/text())>0 and count(.//*[@id='name']/h1/text())>0]" mode="商品"/> 
</商品> 
</xsl:template> 
 
<xsl:template match="http://*[@id='itemInfo' and count(.//*[@id='summary-price']/div[position()=2]/strong/text())>0 and count(.//*[@id='name']/h1/text())>0]" mode="商品"> 
<item> 
<價格> 
<xsl:value-of select="*//*[@id='summary-price']/div[position()=2]/strong/text()"/> 
<xsl:value-of select="*[@id='summary-price']/div[position()=2]/strong/text()"/> 
<xsl:if test="@id='summary-price'"> 
<xsl:value-of select="div[position()=2]/strong/text()"/> 
</xsl:if> 
</價格> 
<名稱> 
<xsl:value-of select="*//*[@id='name']/h1/text()"/> 
<xsl:value-of select="*[@id='name']/h1/text()"/> 
<xsl:if test="@id='name'"> 
<xsl:value-of select="h1/text()"/> 
</xsl:if> 
</名稱> 
</item> 
</xsl:template> 
</xsl:stylesheet>""") 
 
# 使用webdriver.PhantomJS 
browser = webdriver.PhantomJS(executable_path='C:\\phantomjs-2.1.1-windows\\bin\\phantomjs.exe') 
browser.get(url) 
time.sleep(3) 
 
transform = etree.XSLT(xslt_root) 
 
# 執(zhí)行js得到整個dom 
html = browser.execute_script("return document.documentElement.outerHTML") 
doc = etree.HTML(html) 
# 用xslt從dom中提取需要的字段 
result_tree = transform(doc) 
print(result_tree)