# -*- coding: utf-8 -*- #解决编码问题
import urllib
import urllib2
import re
import os
import time
page = 1
url = 'http://www.qiushibaike.com/text/page/4/?s=4970196' #爬取的目标网站
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)
# print response.read()
content = response.read().decode('utf-8') #解决编码问题
pattern = re.compile(r'<div.*?class="content".*?<span>(.*?)</span>.*?</div>',re.S) #第一个参数是匹配要爬取的内容,这里使用正则去匹配
items = re.findall(pattern,content)
f=open(r'.article.txt','ab') #txt文件路径
nowTimes = time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) #获取当前时间
f.write('时间:{}
'.format(nowTimes),); #txt文件中写入时间
for i in items:
i.encode('utf-8')
agent_info = u''.join(i).encode('utf-8').strip()
f.writelines('段子:%s%s
'%(str(agent_info),os.linesep)) #分行存入
# f.write('%s'%str(agent_info))
f.close()
# print items
except urllib2.URLError, e:
if hasattr(e,"code"):
print e.code
if hasattr(e,"reason"):
print e.reason
布置定时任务使用crontab。 (具体crontab使用方法可见http://blog.csdn.net/daivon_up/article/details/71266814):