Python抓取百度搜索结果
Python 用来做一些简单的工作还是不错的，一个练手的代码，抓取百度关键字搜索的结果# coding=utf-8
import urllib2 as url
import string
import urllib
import re
def baidu_search(keyword):
p= {'wd': keyword}
res=url.urlopen("http://www.baidu.com/s?"+urllib.urlencode(p))
html=res.read()
return html
def getList(regex,text):
arr = []
res = re.findall(regex, text)
if res:
for r in res:
arr.append(r)
return arr
def getMatch(regex,text):
res = re.findall(regex, text)
if res:
return res
return ""
def clearTag(text):
p = re.compile(u']+>')
retval = p.sub("",text)
return retval
html = baidu_search('天下无贼')
content = unicode(html, 'utf-8','ignore')
arrList = getList(u".*?", content)
for item in arrList:
regex = u"(.*?)"
link = getMatch(regex,item)
url = link
title = clearTag(link).encode('utf8')
print url
print title
页:
[1]