使用python的lxml解析html

# coding=gb2312

from lxml import *

import

import urllib2

import as H

def getjarinfo(url):

c=(url)

f=()

doc = H.document_fromstring(f)

tables=("//table[@id='xiazai']")

pinpais=("//td[@id='pinpai']")

jixings=("//div[@id='jixing']")

jars = ("//table[@id='xiazai']//tr[2]/td[1]/a[1]")

for j in range(len(pinpais)):

print jars[j].get('href')

print pinpais[j].text_content()

print jixings[j].text_content()

e=(u"//div[text()='%s']" % u"游戏介绍")

describe=e[0].getnext().text_content()

#r = ("//table[@id='xiazai']//tr[2]/td[1]/a[1]")[0]

#jarurl=('href')

if __name__ == '__main__':

url='http://game./game/'

getjarinfo(url)