python抓取指定网站内容并分析BeautifulSoup




		
		
			代码如下
			
Python
			
			#!/usr/bin/env python
# coding=utf-8

from bs4 import BeautifulSoup

import urllib2
import socket

response=urllib2.urlopen('http://www.503error.com',timeout=10)
html_data=response.read()
print html_data

soup=BeautifulSoup(html_data)
print soup.prettify()
print 'start to analayse---------------'
#for tag in soup.find_all(rel="bookmark"):
 #   print tag

#print 'entry-title-----------------------'
#for tag in soup.find_all(class_="entry-title"):
   # print tag

title_soup=soup.find_all(class_='entry-title')
#print 'firt-article----------------'
#print title_soup[0]

tag_a = title_soup[0].a.contents


print '网站http://www.503error.com最新的文章为:',tag_a[0]
			
				
					
				
					1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
				
						#!/usr/bin/env python
# coding=utf-8
 
from bs4 import BeautifulSoup
 
import urllib2
import socket
 
response=urllib2.urlopen('http://www.503error.com',timeout=10)
html_data=response.read()
print html_data
 
soup=BeautifulSoup(html_data)
print soup.prettify()
print 'start to analayse---------------'
#for tag in soup.find_all(rel="bookmark"):
 #   print tag
 
#print 'entry-title-----------------------'
#for tag in soup.find_all(class_="entry-title"):
   # print tag
 
title_soup=soup.find_all(class_='entry-title')
#print 'firt-article----------------'
#print title_soup[0]
 
tag_a = title_soup[0].a.contents
 
 
print '网站http://www.503error.com最新的文章为:',tag_a[0]