# -*- coding:utf-8 -*-
import urllib2
import re
#材料的設定基本上就是設定url,uel_agent,headers的資訊
page =
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 }
#嘗試主程式部分
try:
request = urllib2.Request(url,headers = headers)
response = urllib2.urlopen(request)
content = response.read().decode('utf-8','ignore')#内容=回複的讀取并轉為中文格式
pattern = re.compile('<div.*?author">.*?<a.*?<img.*?>(.*?)</a>.*?<div.*?'+
'content">(.*?)<!--(.*?)-->.*?</div>(.*?)<div class="stats.*?class="number">(.*?)</i>',re.S)#模式=正規表達式的編譯('',re.S)
items = re.findall(pattern,content)#項目=正則的尋找所有(pattern,content)
for item in items:
haveImg = re.search("img",item[])
if not haveImg:
print item[],item[],item[],item[]#列印無圖檔部分
#聯網不上,報錯
except urllib2.URLError, e:
if hasattr(e,"code"):
print e.code
if hasattr(e,"reason"):
print e.reason