Python爬取网上笑话并定时邮件发送--P.S.想经常收笑话的同学，可以邮件我

我的博客

效果如下图

Author : Leon
Email  : yangli0534@yahoo.com
Description: 1 grab a joke from the Internet              2 email to someone on schedule

 

# -*- coding:gb2312 -*-

#!/usr/bin/python
__author__ = 'Leon'

'''
    Author : Leon
    Email  : yangli0534@yahoo.com
    Description: 1 grab a joke from the Internet 
                 2 email to someone on schedule 
                 3 参考了网友李鹏飞关于抓取网页的部分 ，感谢。侵权删
'''
import smtplib
from email.MIMEMultipart import MIMEMultipart
from email.MIMEText import MIMEText
import urllib2
import re
import schedule
import time
import datetime

class randomJoke:

    #初始化方法
    def __init__(self):
        self.url = 'http://lengxiaohua.com/random'
        self.user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
        #初始化headers
        self.headers = { 'User-Agent' : self.user_agent }
        #笑话内容
        self.content = []

    #获取网页源代码
    def getSourceCode(self):
        try:
            request = urllib2.Request(url = self.url, headers=self.headers)
            response = urllib2.urlopen(request)
            sourceCode = response.read().decode('utf-8')
            return sourceCode
        except urllib2.URLError, e:
            if hasattr(e,"reason"):
                print u"网络错误...",e.reason
                return None

    #获取笑话
    def setContent(self):
        sourceCode = self.getSourceCode()
        if not sourceCode:
            print('获取网页内容失败~！')
            quit()
        pattern = re.compile(' <pre.*?js="joke_summary".*?"first_char">(.*?)</span>(.*?)</pre>.*?class="user_info">.*?<a.*?>(.*?)</a>.*?(.*?)',re.S)
        items = re.findall(pattern,sourceCode)
        self.content = items
        #print u"已经爬取源代码...正在解析源代码..."

    #返回笑话
    def getContent(self):
        return self.content

    #打印一则笑话
    def printAJoke(self,number):
        joke = self.content[number]
        print u"作者:%s" %(joke[2])
        print u'发表于:'+ joke[3]
        #item[0]和item[1]组成完整的内容
        print joke[0]+joke[1]

    def getAJoke(self,number):
        joke = self.content[number]
        content = ""
        #content = content+ u"作者:" %(joke[2])
        #print u'发表于:'+ joke[3]
        #item[0]和item[1]组成完整的内容
        content =  joke[0]+joke[1]
        return content
## run the task on chedule
def job():
    global myRandomJoke
    #global server
    global toaddr
    global fromaddr
    global password
    t = datetime.datetime.now()
    content = ""
    content = content+ u"你好，这里是随机笑话！"
    content = content+ "It's "
    content = content+ t.strftime("%A, %d. %B %Y %I:%M%p")+'\n'
    myRandomJoke.setContent()
    #myRandomJoke.printAJoke(2)
    content = content+myRandomJoke.getAJoke(2)
    print content
    msg = MIMEMultipart()
    msg['From'] = fromaddr
    msg['To'] = toaddr
    msg['Subject'] = "Leon send a joke for u on"+t.strftime("%A, %d. %B %Y %I:%M%p")
    
    try:
        body = "YOUR MESSAGE HERE"
        #msg.attach(MIMEText(content, 'plain'))
        #msg.attach(MIMEText(content, 'plain'))
        msg.attach(MIMEText(content,format,'utf-8'))
        text = msg.as_string()
        #server = smtplib.SMTP_SSL("smtp.126.com", 25)# connect to email server
        server = smtplib.SMTP("smtp.126.com")# connect to email server
        server.login(fromaddr,password)
        server.sendmail(fromaddr, toaddr, text)
        server.quit()
        print "send email successfully"
    except:
        print "failed!"

toaddr = "somebody@yahoo.com" # email address to send

fromaddr = "yourname@126.com"
password = "xxxxxxxxxxx"#
#server = smtplib.SMTP('smtp.yahoo.com', 587, None, 30)
#server = smtplib.SMTP_SSL('smtp.googlemail.com', 465)
#server = smtplib.SMTP_SSL("smtp.qq.com", 465)# connect to email server

#server = smtplib.SMTP_SSL("smtp.qq.com", 465)# connect to email server
#server.login(fromaddr,password)
myRandomJoke = randomJoke()
job()
schedule.every(2).minutes.do(job)#run every 2 minutes
#notQuit = True
#print u"你好，这里是随机笑话！"
while True:
    schedule.run_pending()
    time.sleep(10)
    


server.quit()
quit()

 遇到的问题有1.SMTP的问题，和具体的邮箱相关。

2.汉字编码。使用utf-8编码的内容，在一些客户端中无法显示，修改为gbk编码后解决。

经验，尽量使用开发测试完善的package, 会更稳定。比如，这个定时程序，可以用datetime猎取时间然后判断实现，性能不如使用schedule模块。

 

更新

因为发现上述抓取笑话的网站更新不及时，于是更新为糗事百科上抓取文本，更新后的代码如下：

                     # -*- coding:utf-8 -*-

import urllib
import urllib2
import re
import thread
import time
import random
#糗事百科爬虫类，在网友代码基础上修改
class qiushibaike:

    #初始化方法，定义一些变量
    def __init__(self):
        #self.pageIndex = 30
        #user_agent 从火狐 HttpFox中headers查找到
        #self.user_agent = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:45.0)'
        self.user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
        #初始化headers
        self.headers = { 'User-Agent' : self.user_agent }
        #存放段子的变量，每一个元素是每一页的段子们
        self.stories = []
        #存放程序是否继续运行的变量
        self.enable = False
        self.pageStories = []
        
    #传入某一页的索引获得页面代码
    def getPage(self):
        try:
            pageIndex = random.randint(2,35)
            url = 'https://www.qiushibaike.com/text/page/' + str(pageIndex)+'/'
            #构建请求的request
            request = urllib2.Request(url,headers = self.headers)
            #利用urlopen获取页面代码
            response = urllib2.urlopen(request)
            #将页面转化为UTF-8编码
            pageCode = response.read().decode('utf-8')
            return pageCode

        except urllib2.URLError, e:
            if hasattr(e,"reason"):
                print u"连接糗事百科失败,错误原因",e.reason
                return None


    #传入某一页代码，返回本页不带图片的段子列表
    def getPageItems(self):
        pageCode = self.getPage()
        if not pageCode:
            print "页面加载失败...."
            return None
        pattern = re.compile('<div class="author clearfix">.*?href.*?<img src.*?title=.*?<h2>(.*?)</h2>.*?<div class="content">(.*?)</div>.*?<i class="number">(.*?)</i>',re.S)
        items = re.findall(pattern,pageCode)
        #print len(items)
        #print "*****items"
        #用来存储每页的段子们
        self.pageStories = []
        #遍历正则表达式匹配的信息
        i = 0
        for item in items:
            #如果不含有图片，把它加入list中
            #if not haveImg:
                replaceBR = re.compile('<.?span>')
                #将<br/> 用 换行符\n 替换
                text = re.sub(replaceBR,"\n",item[1])
                #item[0]是一个段子的发布者，item[1]是内容，item[2]是发布时间,item[4]是点赞数
                self.pageStories.append([item[0],text,item[2]])

                #strip()作用：去掉转义字符后输出
        #print item[0] +"-------0t"
        #print item[1] +"-------0T"
        #print text + "******TEXT"
        #print item[2] +"-------0t"
       
        #return pageStories

    #加载并提取页面的内容，加入到列表中
    def loadPage(self):
        #如果当前未看的页数少于2页，则加载新一页
        if self.enable == True:
            if len(self.stories) < 2:
                #获取新一页
                #pageStories = self.getPageItems()
                self.getPageItems()
                #将该页的段子存放到全局list中
                if self.pageStories:
                    self.stories.append(self.pageStories)
                    #获取完之后页码索引加一，表示下次读取下一页
                    #self.pageIndex += 1

                #print len(self.stories)
    #调用该方法，每次敲回车打印输出一个段子
    def getOneStory(self):
        #遍历一页的段子

        # for story in pageStories:
        #     #等待用户输入
        #     input = raw_input()
        #     #每当输入回车一次，判断一下是否要加载新页面
        #     self.loadPage()
        #     #如果输入Q则程序结束
        #     if input == "Q":
        #         self.enable = False
        #         return
        #     #print "$$$"
        #     print len(story)
        #     #现在网页已没有发布时间了
        #     #print u"第%d页\t发布人:%s\t发布时间:%s\t赞:%s\n%s" %(page,story[0],story[2],story[3],story[1])
        #     print u"第%d页\t发布人:%s\t赞:%s\n%s" %(page,story[0],story[2],story[1])
        self.loadPage()
        len_page = len(self.pageStories)
        story = self.pageStories[random.randint(0, len_page-1)]
        print u'回车看下一个，Q退出'
        input = raw_input()
        #     #每当输入回车一次，判断一下是否要加载新页面
        #     self.loadPage()
        #     #如果输入Q则程序结束
        if input == "Q":
            self.enable = False
            return
        #print len(story)
        print u'%s' %story[1]
    #开始方法
    def start(self):
        print u"正在读取糗事百科,按回车查看新段子，Q退出"
        #使变量为True，程序可以正常运行
        self.enable = True
       
        #先加载一页内容
        self.loadPage()
        
        #局部变量，控制当前读到了第几页
        #nowPage = 0
        while self.enable:
            if len(self.stories)>0:
                #print len(self.stories)
                #print "-------stories"
                #从全局list中获取一页的段子
                self.pageStories = self.stories[0]
                #当前读到的页数加一
                #nowPage += 1
                #将全局list中第一个元素删除，因为已经取出
                del self.stories[0]
                #print "---------------------------------"
                #print len(pageStories)
                #print nowPage
                #输出该页的段子
                self.getOneStory()
    def getAJoke(self):
        self.enable = True
        self.loadPage()
        self.pageStories = self.stories[0]
        del self.stories[0]
        len_page = len(self.pageStories)
        story = self.pageStories[random.randint(0, len_page-1)]
        self.enable = True
        return story[1]

        #print u'回车看下一个，Q退出'
        #input = raw_input()
        #     #每当输入回车一次，判断一下是否要加载新页面
        #     self.loadPage()
        #     #如果输入Q则程序结束
        #if input == "Q":
        #   self.enable = False
        #    return
        #print len(story)
        #print u'%s' %story[1]

#spider = QSBK()
#Aspider.start()
#print spider.getAJoke()

使用方法如下：

#-*- coding:utf-8 -*-


#!/usr/bin/python
__author__ = 'Leon'

'''
    Author : Leon
    Email  : yangli0534@yahoo.com
    Description: 1 grab a joke from the Internet 
                 2 email to someone on schedule 
                 3 参考了部分网友的代码 ，感谢。侵权删
'''
import smtplib
from email.MIMEMultipart import MIMEMultipart
from email.MIMEText import MIMEText
import re
import schedule
import time
import datetime
from qiushibaike import qiushibaike

def job():
    #global myRandomJoke
    global myQiuBai
    #global server
    global toaddr
    global fromaddr
    global password
    t = datetime.datetime.now()
    content = ''
    content = content+ u'笑口常开！'
    content = content+ u"It's "
    content = content+ t.strftime("%A, %d. %B %Y %I:%M%p")+'\n'
    #myRandomJoke.setContent()
    #myRandomJoke.printAJoke(2)
    #content = content + myRandomJoke.getAJoke(2)
    content = content + myQiuBai.getAJoke()
    print content
    #content = u'''你好，这是一封测试邮件，来自yangli0534@yahooc.com'''
    #content = content +t.strftime("%A, %d. %B %Y %I:%M%p")
    msg = MIMEMultipart()
    msg['From'] =fromaddr
    msg['To'] =','.join(toaddr)
    msg['Cc'] = ','.join(ccaddr)
    msg['Bcc'] = ','.join(ccaddr)
    msg['Subject'] = u"Leon send a joke to you on"+t.strftime("%A, %d. %B %Y %I:%M%p")
    
    try:
        #body = "YOUR MESSAGE HERE"
        body = content
        #msg.attach(MIMEText(content, 'plain'))
        #msg.attach(MIMEText(content, 'plain'))
        #msg.attach(MIMEText(content,format,'utf-8'))
        msg.attach(MIMEText(body.encode('gbk')))
        text = msg.as_string()
        #server = smtplib.SMTP_SSL("smtp.126.com", 25)# connect to email server
        server = smtplib.SMTP("smtp.139.com",25)# connect to email server
        server.login(fromaddr,password)
        #server.sendmail(fromaddr, toaddr, text)
        server.sendmail(fromaddr, toaddr + ccaddr, text)
        #server.sendmail(fromaddr, fromaddr,text)
        server.quit()
        print "send email successfully"
    except:
        print "failed!"

toaddr = ['1184802734@qq.com','18811007706@139.com'] # email address to send
ccaddr = ['502327976@qq.com'] # carbon copy
bccaddr = ['15210579762@139.com']#blind carbon copy
#toaddr2 = '502327976@qq.com'
fromaddr = 'china__mobile@139.com'#send address
password = "xxxxxxx"#password
#server = smtplib.SMTP('smtp.yahoo.com', 587, None, 30)
#server = smtplib.SMTP_SSL('smtp.googlemail.com', 465)
#server = smtplib.SMTP_SSL("smtp.qq.com", 465)# connect to email server

#server = smtplib.SMTP_SSL("smtp.qq.com", 465)# connect to email server
#server.login(fromaddr,password)
#myRandomJoke = randomJoke()
myQiuBai = qiushibaike() # 
job()
schedule.every(2).minutes.do(job)# send a email every 2 minutes
#notQuit = True
#print u"你好，这里是随机笑话！"
while True:
    schedule.run_pending()# 
    time.sleep(10)
    


server.quit()
quit()