因为一直有看hjTV的爱好,也正好在csdn上看到类似的博客,于是想做一个检查网站更新并且发邮件提醒的爬虫。
思路来源参考:https://blog.csdn.net/qq_37457202/article/details/106537627
邮件发送部分参考:http://www.yiibai.com/python/python_sending_email.htm
代码部分
import requests
from lxml import etree
import os
Url = "https://www.hanjutv.com/"
header = {
"User-Agent":"XXX"}
Host = requests.get(Url,headers=header)
Host.encoding='utf-8'
data_total = etree.HTML(Host.text)
link_total = []
#获取更新剧集部分
for link in data_total.xpath('//div[@class ="mod-main bd"]//li/a/@href')[:13]:
link_total.append(Url+link)
contents = '' #将多个不同剧集的更新内容合到一封邮件中
#发送邮件
import smtplib
from email.header import Header
from email.mime.text import MIMEText
#第三方 SMTP 服务
mail_host = "smtp.163.com" # SMTP服务器
mail_user = "XXX" # 用户名
mail_pass = "XXX" # 授权密码,非登录密码
se