python文章的抓取
# coding = utf-8
import urllib
import sys
import urllib
import json
import socket
import time
sys.path.append('E:\\software\\python\\beautifulsoup4-4.5.3')
sys.path.append('E:\\software\\python\\Lib\\site-packages')
from bs4 import BeautifulSoup
import re
import urllib2
import MySQLdb
page = 1
url = 'http://www.qiushibaike.com/hot/page/' + str(page)
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
headers = { 'User-Agent' : user_agent }
try:
request = urllib2.Request(url,headers = headers)
response = urllib2.urlopen(request)
soup = response.read().decode('utf-8')
#print soup
#pattern = re.compile('<div .*?content">'+
# '(.*?)</div>',re.S)
pattern = re.compile('<div .*?<h2>(.*?)</h2>.*?er womenIcon">(.*?)'+
'</div>.*?class="content">(.*?)</div></a>'+
'.*?ass="thumb">(.*?)</div><div class="stats">(.*?)'+
'</div>',re.S)
#print soup
items = re.findall(pattern,soup)
print type(items)
print items
#print items[0].count(1)
#print type(items[0][0])
print items[0][0].encode('utf-8')
except urllib2.URLError, e:
if hasattr(e,"code"):
print e.code
if hasattr(e,"reason"):
print e.reason