echo2.py

# -*- coding: utf-8 -*-    #解決編碼問題
import urllib
import urllib2
import re
import os
import time

page = 1
url = 'http://www.qiushibaike.com/text/page/4/?s=4970196'     #爬取的目標網站
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')  #解決編碼問題
    pattern = re.compile(r'<div.*?class="content".*?<span>(.*?)</span>.*?</div>',re.S)  #第一個引數是匹配要爬取的內容,這裡使用正則去匹配
    items = re.findall(pattern,content)   
    f=open(r'.\article.txt','ab')       #txt檔案路徑
    nowTimes = time.strftime('%Y-%m-%d %H:%M:%S'
 
,time.localtime(time.time()))    #獲取當前時間
    f.write('時間:{}\n\n'.format(nowTimes),);   #txt檔案中寫入時間
    for i in items:
        i.encode('utf-8')
        agent_info = u''.join(i).encode('utf-8').strip()
        f.writelines('段子:%s%s\n'%(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

* */1 * * * /usr/bin/python /home/dengwen/desktop/echo2.py

執行結果:

本篇文章如對您有用請點選關注哦~，謝謝!