python采集百度百科代码示范

python采集百度百科代码演示

#!/usr/bin/python
# -*- coding: utf-8 -*-
#encoding=utf-8   
#Filename:get_baike.py
import urllib2,re
import sys
def getHtml(url,time=10):
    response = urllib2.urlopen(url,timeout=time)
    html = response.read()
    response.close()
    return html
def clearBlank(html):
    if len(html) == 0 : return ''
    html = re.sub('\r|\n|\t','',html)
    while html.find("  ")!=-1 or html.find(' ')!=-1 :
        html = html.replace(' ',' ').replace('  ',' ')
    return html
if __name__ == '__main__':
	html = getHtml('http://baike.baidu.com/view/994462.htm',10)
	html = html.decode('gb2312','replace').encode('utf-8') #转码
	title_reg = r'<h1 class="title" id="[\d]+">(.*?)</h1>'
	content_reg = r'<div class="card-summary-content">(.*?)</p>'
	title = re.compile(title_reg).findall(html)
	content = re.compile(content_reg).findall(html)
	title[0] = re.sub(r'<[^>]*?>', '', title[0])
	content[0] = re.sub(r'<[^>]*?>', '', content[0])
	print title[0]
	print '#######################'
	print content[0]