python，抓取百度搜索结果

# coding=utf-8

import urllib2
import re
from datetime import *
import time

input_string=raw_input()
url='http://www.baidu.com/s?wd=%s' %input_string
content = urllib2.urlopen(url).read()
content=content.replace('\n','').replace('</table> <div','')
temp=re.findall(r'(?<=id="\d").*?</table>|(?<=id="10").*?</table>',content)

def save(i):
    try:
        title=re.findall(r'<h3.*?<\/h3>',temp[i])
        a=re.compile('<.*?>')
        title=a.sub('',title[0])
        print title
        introduce=re.findall(r'(?<=<\/h3>).*?(?=<br>)',temp[i])
        a=re.compile('<.*?>|共\d+?次编辑')
        introduce=a.sub('',''.join(introduce))
        print introduce
        weburl=re.findall(r'(?<=href=").*?(?=")',temp[i])
        del weburl[1:]
        print ''.join(weburl)
        dates=''.join(re.findall(r'(?<!\d)\d{4}-\d\d?-\d\d?',temp[i]))
        dates=dates.split('-')
        dates = date(int(dates[0]),int(dates[1]),int(dates[2]))  
        print dates.isoformat()
        print '\n'
    except:
        print None

   
if __name__=="__main__":
    for i in range(0,10):
        save(i)

 

转载于:https://www.cnblogs.com/lvxiuquan/archive/2012/07/10/2585135.html