python使用urllib和urllib2以及re正则表达式模块，实现查询某个关键词在指定站点的百度排名。
编辑推荐：
php检测页面是否被百度收录
php 获取百度收录和百度快照时间
php 查询百度与google收录情况
php 百度快照、百度收录、百度热词
来看具体的实现代码：
#!/bin/python
#site: www.jb200.com
# -*- coding: utf-8 -*-
#encoding = utf-8
import urllib2
import urllib
import re
from urllib import quote_plus
from urlparse import urlparse
def get_site_word_baidu_rank(siteHost,word,maxScanPageNumber = 10,printSearchLog=False):
def printLog(log):
if printSearchLog:
print log
page = 1
pageSize = 10
siteHost = siteHost.lower()
number = 0
got = False
gotUrl = None
searchUrl = None
while True:
if page == maxScanPageNumber: break
searchUrl = 'http://www.baidu.com/s?wd='+quote_plus(word)+'&pn='+str((page-1)*pageSize)+'&tn=baiduhome_pg&ie=utf-8&usm=2'
printLog('搜索第%d页' % (page,))
data = urllib.urlopen(searchUrl)
html = data.read()
itemPattern = re.compile('<h3 class="t"><a[s]+data-click="[^"]+" href="(?P<url>[^"]+)".*?<span class="g">(?P<urldate>[^<]+)</span>')
matches = itemPattern.finditer(html)
number = 0
for m in matches:
number += 1
urldate = m.group('urldate').strip()
siteUrl = urldate[0:urldate.find(' ')]
itemUrl = '%s%s' % ('http://',siteUrl)
urlObject = urlparse(itemUrl)
if urlObject.netloc.find(':') == -1:host = urlObject.netloc
else :host = urlObject.netloc[0:urlObject.netloc.find(':')]
if host.lower() == siteHost or host.lower().find('.' + siteHost) > -1:
gotUrl = m.group('url')
realUrlFile = urllib2.urlopen(gotUrl)
gotUrl = realUrlFile.geturl()
got = True
break
if got:break
page += 1
if got:
number = (page-1) * pageSize + number
return (number,page,gotUrl,searchUrl)
return None
if __name__ == '__main__':
words = ('程序员','内存溢出','Outofmemory','python','java')
siteHost = 'outofmemory.cn'
for w in words:
result = get_site_word_baidu_rank(siteHost,w,10)
if result:
print w + ':您的网站排在第%d位，在第%d页，排上的链接是%s,搜索页地址%s'%result
else:
print '未找到记录'