最近看简书文章关注了几个专题作者,写的文章都不错,对爬虫和数据分析都写的挺好,因此想到能不能获取最新的文章推送到Ipad网易邮箱大师。邮件发送代码封装成一个函数,从廖雪峰大神那里学的
网页源码获取和解析获取文章标题和url依然是用到的requests和BeautifulSoup4 模块 也封装成一个函数。
#coding: utf-8
import sys
import requests
from bs4 import BeautifulSoup as bs
import smtplib
import datetime
from email.mime.text import MIMEText
from email.header import Header
from email.utils import parseaddr, formataddr
#系统编码置为'utf-8'
reload(sys)
sys.setdefaultencoding('utf-8')
#简书作者专题入口
rooturl='http://www.jianshu.com/notebooks/4204686/latest'
#获取网页源代码 并用bs4解析 返回soup对象
def gethtml(url):
res=requests.get(url)
res.encoding='utf-8'
html=res.text
soup=bs(html,'html.parser')
return soup
#调用gethtml()函数获取网页soup对象 对网页进行解析 参数都是url
def sendmail(url):
soup=gethtml(url)
catename = soup.select('h3.title a')[0].text
titlename = soup.select('h4.title a')[0].text
titleurl = 'http://www.jianshu.com' + soup.select('h4.title a')[0]['href']
sender = '发件人邮箱'
receiver = '收件人邮箱'
subject = 'python email test'
smtpserver = '发件人邮箱smtp服务器'
username = '发件人邮箱'
password = '发件人邮箱密码'
date=datetime.date.today()
def _format_addr(s):
name, addr = parseaddr(s)
return formataddr((
Header(name, 'utf-8').encode(),
addr.encode('utf-8') if isinstance(addr, unicode) else addr))
msg = MIMEText('''
早安!
Mr_Cxy,今天是%s!
简书作者"向右奔跑"在【%s】目录下最新发表的文章是:
%s.
文章链接:%s
''' % (date,catename,titlename,titleurl), 'plain', 'utf-8')
msg['From'] = _format_addr(u'简书App <%s>' % sender)
msg['To'] = _format_addr(u'yourself~ <%s>' % receiver)
msg['Subject'] = Header(u'简书作者最新文章', 'utf-8').encode()
smtp = smtplib.SMTP('smtp.163.com',25)
smtp.login(username, password)
smtp.sendmail(sender, receiver, msg.as_string())
smtp.quit()
print sendmail(rooturl)