Task05 爬虫入门与综合应用

import requests
import random
from bs4 import BeautifulSoup
import smtplib  # 发送邮件模块
from email.mime.text import MIMEText  # 定义邮件内容
from email.header import Header  # 定义邮件标题

smtpserver = 'smtp.qq.com'

# 发送邮箱用户名密码
user = ''
password = ''

# 发送和接收邮箱
sender = ''
receive = ''

user_agent = [
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
"Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)"]

def main():
    print('正在爬取数据')
    url = 'https://36kr.com/newsflashes'
    headers = {'User-Agent': random.choice(user_agent)}
    response = requests.get(url, headers=headers)
    response=response.content.decode('utf-8', 'ignore')
    soup = BeautifulSoup(response, 'lxml')
    news = soup.find_all('a', class_='item-title')  
    news_list=[]
    for i in news:
        title=i.get_text()
        href='https://36kr.com'+i['href']
        news_list.append(title+'
'+href) info='

'.join(news_list) print('正在发送信息') send_email(info) def send_email(content): # 通过QQ邮箱发送 title='36kr快讯' subject = title msg = MIMEText(content, 'html', 'utf-8') msg['Subject'] = Header(subject, 'utf-8') msg['From'] = sender msg['To'] = receive # SSL协议端口号要使用465 smtp = smtplib.SMTP_SSL(smtpserver, 465) # 这里是服务器端口! # HELO 向服务器标识用户身份 smtp.helo(smtpserver) # 服务器返回结果确认 smtp.ehlo(smtpserver) # 登录邮箱服务器用户名和密码 smtp.login(user, password) smtp.sendmail(sender, receive, msg.as_string()) smtp.quit() if __name__ == '__main__': main()

你可能感兴趣的:(Task05 爬虫入门与综合应用)