20210825 python 通过搜索关键词查询新闻，并通过邮件发送

# @Time:2021-8-24 10:26
import requests
import re
import smtplib
from email.mime.text import MIMEText
from email.utils import formataddr
from email.header import Header
import datetime


def baidu(company):
    proxies = {
        "http": "http://192.168.1.101:3256",
        #"https": "http://192.168.1.101:3256",
    }
    #proxies = random.choice(proxies)

    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'}
    url = 'https://www.baidu.com/s?tn=news&rtt=1&bsst=1&cl=2&wd=' + company  # 把链接中rtt参数换成4即是按时间排序，默认为1按焦点排序，
    ##问题：可以看看第二页搜索页，网页链接的代码规律；
    ##区别在于第一页什么都没加，第二页最后加了"pn=10",第三页加了"pn=20",因为每一页有10个新闻
    res = requests.get(url, headers=headers, proxies=proxies).text  # 加上headers用来告诉网站这是通过一个浏览器进行的访问
    #print(res)
    p_href = '<h3 class="news-title_1YtI1"><a href="(.*?)"'
    href = re.findall(p_href, res, re.S) #re.S自动考虑源代码换行，爬取新闻链接，一次性会爬取出10个网页链接，每个都存在这个叫"href"的链表里
    p_title = '<h3 class="news-title_1YtI1">.*?>(.*?)</a>'
    title = re.findall(p_title, res, re.S) ##爬取出新闻标题
    p_date = '<span class="c-color-gray2 c-font-normal">(.*?)</span>'
    date = re.findall(p_date, res) ##爬取新闻发布日期
    p_source = '<span class="c-color-gray c-font-normal c-gap-right">(.*?)</span>'
    source = re.findall(p_source, res) ##爬取新闻来源
    #

    news = []
    #for i in range(len(title)):  # range(len(title)),这里因为知道len(title) = 10，所以也可以写成for i in range(10)
    for i in range(5):
        title[i] = title[i].strip()  # strip()函数用来取消字符串两端的换行或者空格，不过这里好像不太需要了
        title[i] = re.sub('<.*?>', '', title[i])  # 核心，用re.sub()函数来替换不重要的内容
        # time.sleep(2)# 不要爬太快，爬太快会被百度反爬
        print(str(i + 1) + '.' + title[i], source[i], date[i])
        print(href[i])

        news.extend(str(i + 1)+ '.' +title[i][0:]+ ' '+date[i]+'\n')
        news.extend(href[i][0:]+'\n')
    return news


def send_news():
    date = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')  # 获取当前日期时间
    # 输入Email地址和口令:
    mail_user_name = 'miya'
    mail_user = 'm******@163.com'
    mail_pass = 'C*******KG'
    # 输入收件人地址:
    receivers = ["3*****3@qq.com","m*****@163.com"]
    # 输入SMTP服务器地址:
    smtp_server = 'smtp.163.com'

    companys = ['CWDM','DWDM','CCWDM','AWG','FWDM']
    #companys = ['芯片','5G市场','波分复用器','800G光模块','平面波导']
    #companys = ['光模块', '收发器', '8寸晶圆', 'WDM']
    for i in companys:  # 这个i只是个代号，可以换成其他内容
        news_list = baidu(i)
        #输入要发送的内容:
        # news_list = get_news()
        # print(news_list)
        msg_header = '今日行业新闻收集统计 - miya'
        news ="今日新闻收集:"+"\n"+ date +"\n"
        for i in range(0,len(news_list)):
            news = news + news_list[i]
        print(news)

        msg = MIMEText(news, 'plain', 'utf-8')
        msg['From'] = formataddr([mail_user_name, mail_user])
        server = smtplib.SMTP_SSL(smtp_server)
        msg['Subject'] = Header(msg_header, 'utf-8')
        # SMTP协议默认端口是25
        #server.set_debuglevel(1)
        server.login(mail_user, mail_pass)
        try:
            for item in receivers:
                server.sendmail(mail_user, [item], msg.as_string())
            print("Success: 已成功发送邮件!")
            server.quit()
        except smtplib.SMTPException:
            print("Error: 无法发送邮件")

if __name__ == '__main__':
    send_news()