Pythno2.7 lxml xpath

标签：python   pythno2.7   lxml   xpath   

Pythno2.7 lxml  xpath

1：下载setuptools：   https://pypi.python.org/pypi/setuptools，在这里下载Windows(simplified)下边的ez_setup.py 

2：安装：在cmd下执行 python ez_setup.py，如果你安装了很多版本的python，则进入相应版本的文件夹，用对应的python.exe  ez_setup.py

3：下载想要的lxml安装包

https://pypi.python.org/simple/lxml/

32位、64位：

lxml-2.3-py2.7-win-amd64.egg
lxml-2.3-py2.7-win32.egg

4：安装

进入C:\Python27\Scripts

使用命令行：

easy_install  D:\\Downloads\lxml-2.3-py2.7-win-amd64.egg

例子：

#coding:utf-8
import urllib
import urllib2
from lxml import etree as etree
 
if __name__ == "__main__":
       req_url='www.baidu.com'
       headers= {'User-Agent':'"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:26.0)Gecko/20100101 Firefox/26.0"'}
       req= urllib2.Request(req_url, headers = headers)
       content= urllib2.urlopen(req, timeout=60).read()
       ifisinstance(content, unicode):
              pass
       else:
              content= content.decode('GBK')
       htmlSource= etree.HTML(content)
       names= htmlSource.xpath(
u'//*[@id="buildhistory"]/div[2]/table/*[@class="finish_mousenone"]/td[2]')
       fori in names:
              printi.text

# -*- coding: cp936 -*-
 
import urllib
import urllib2
from lxml import etree as etree
 
def InitSogouBranchInfo(req_url=None):
       ifreq_url == None or req_url == '':
              print"req_url == none,return"
              return
       headers= {'User-Agent':'"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:26.0)Gecko/20100101 Firefox/26.0"'}
       req= urllib2.Request(req_url, headers = headers)
       content= urllib2.urlopen(req, timeout=60).read()
       #printcontent
       ifisinstance(content, unicode):
              pass
       else:
              content= content.decode('GBK')
       htmlSource= etree.HTML(content)
       buildResultRaw= htmlSource.xpath(ur'//*[@id="buildhistory"]/div[2]/table/*[@class="finish_mousenone"]')
       #buildTime=htmlSource.xpath(ur'//*[@id="buildhistory"]/div[2]/table/*[@class="finish_mousenone"]/td[2]')
       #buildVersion= htmlSource.xpath(ur'//*[@id="buildhistory"]/div[2]/table/*[@class="finish_mousenone"]/td[3]')
       #buildBranch=htmlSource.xpath(ur'//*[@id="buildhistory"]/div[2]/table/*[@class="finish_mousenone"]/td[6]')
       #buildAuthor=htmlSource.xpath(ur'//*[@id="buildhistory"]/div[2]/table/*[@class="finish_mousenone"]/td[7]')
       #buildDownloadUrl=htmlSource.xpath(ur'//*[@id="buildhistory"]/div[2]/table/*[@class="finish_mousenone"]/td[12]/a')
       result= {
              'buildTime'      :[],
              'buildVersion'  :[],
              'buildBranch'   :[],
              'buildAuthor'   :[],
              'buildDownloadUrl' :[]
       }
       sum= 0
       fortree in buildResultRaw:
              str= ''
              buildTime= tree.xpath(ur'td[2]')
              iflen(buildTime)>0 and not buildTime[0].text==None:
                     str= str + buildTime[0].text+'  '
                     result['buildTime'].append(buildTime[0].text)
              else:
                     result['buildTime'].append("")
             
              buildVersion= tree.xpath(ur'td[3]')
              iflen(buildVersion)>0 and not buildVersion[0].text==None:
                     str= str + buildVersion[0].text+'  '
                     result['buildVersion'].append(buildVersion[0].text)
              else:
                     result['buildVersion'].append("")
             
              buildBranch= tree.xpath(ur'td[6]')
              iflen(buildBranch)>0 and not buildBranch[0].text==None:
                     str= str + buildBranch[0].text+'  '
                     result['buildBranch'].append(buildBranch[0].text)
              else:
                     result['buildBranch'].append("")
             
              buildAuthor= tree.xpath(ur'td[7]')
              iflen(buildAuthor)>0 and not buildAuthor[0].text==None:
                     str= str + buildAuthor[0].text+'  '
                     result['buildAuthor'].append(buildAuthor[0].text)
              else:
                     result['buildAuthor'].append("")
             
              buildDownloadUrl= tree.xpath(ur'td[12]/a/@href')
              ifnot buildDownloadUrl==[]:
                     str= str + buildDownloadUrl[0]+'  '
                     result['buildDownloadUrl'].append(buildDownloadUrl[0])
              else:
                     result['buildDownloadUrl'].append("")
             
              #printstr
              #sum= sum + 1
       #printsum
       returnresult
 
 
if __name__ == "__main__":
       result=InitSogouBranchInfo('http://build.sogou-inc.com/system_build/common_module/project.php?project=ime&class=ime&branch=branch\PinyinDev_R_7_4_Update_Kernel50')
       f= open(r'd:/t.txt','w')
      
       length= len(result['buildVersion'])
       fori in range(0,length):
              printresult['buildDownloadUrl'][i]
 

参考：

http://www.cnblogs.com/zhuyp1015/archive/2012/07/17/2596495.html

http://blog.sina.com.cn/s/blog_641289eb0100yf84.html

http://blog.csdn.net/zhaokuo719/article/details/8209496

http://blog.csdn.net/shirdrn/article/details/7030026

http://bbs.csdn.net/topics/390823000

http://www.cnblogs.com/bluescorpio/archive/2010/05/31/1748503.html

Pythno2.7 lxml xpath

标签：python   pythno2.7   lxml   xpath   

原文地址：http://blog.csdn.net/lileiyang12/article/details/41962385