xpath爬取新闻增强版

大家好，我是天空之城，今天给大家带来xpath爬取新闻增强版

import requests
import lxml
from lxml import etree

import smtplib
from email.mime.text import MIMEText
from email.header import Header


url='http://news.baidu.com/'
headers = {
      'Referer': 'http://news.baidu.com/',
      'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:46.0) Gecko/20100101 Firefox/46.0',
      'Cookie':'BAIDUID=EBEA8880C23200910DFF3E7E174D2046:FG=1; BIDUPSID=EBEA8880C23200910DFF3E7E174D2046; PSTM=1587205902; H_PS_PSSID=1443_31326_21115_31110_31591_31464_30823; LOCALGX=%u5357%u4EAC%7C%32%34%39%34%7C%u5357%u4EAC%7C%32%34%39%34; Hm_lvt_e9e114d958ea263de46e080563e254c4=1590801807; Hm_lpvt_e9e114d958ea263de46e080563e254c4=1590801807'

}


def getdata():
    res=requests.get(url,headers=headers)
    source = res.content.decode('utf-8')
    html=etree.HTML(source)
    list_all = []
    news1_title=html.xpath('//div[@class="hotnews"]/ul/li/strong/a/text()')
    news1_link=html.xpath('//div[@class="hotnews"]/ul/li/strong/a/@href')
    for title,link in zip(news1_title,news1_link):

        list_all.append(title+'\n'+link+'\n')

    news2_title=html.xpath('//div[@id="pane-news"]/ul/li/a/text()')
    news2_link = html.xpath('//div[@id="pane-news"]/ul/li/a/@href')
    for title1,link1 in zip(news2_title,news2_link):

        list_all.append(title1 + '\n' + link1 +'\n')

    return '\n\n'.join(list_all)


def send_email(list):
    mailhost = 'smtp.qq.com'
    qqmail = smtplib.SMTP()
    qqmail.connect(mailhost, 25)
    qqmail.login(account, password)
    content = '亲爱的，今天的推荐新闻是：' +'\n'+ list
    message = MIMEText(content, 'plain', 'utf-8')
    subject = '今日推荐'
    message['Subject'] = Header(subject, 'utf-8')
    try:
        qqmail.sendmail(account, receiver, message.as_string())
        print('邮件发送成功')
    except:
        print('邮件发送失败')
    qqmail.quit()


account = input('请输入你的邮箱')
password = input('请输入你的邮箱密码')
receiver = input('请输入收件人的邮箱')

mess = getdata()
send_email(mess)