28、周末看电影（每周五自动从top250中随机选取三部电影，并将下载链接发到邮箱里）

 

练习介绍

 

在第3关的一个课后练习里，我们爬取了指定电影的下载链接；在第6关的一个课后练习里，我们存储了豆瓣TOP250的榜单信息。

 

现在，我们完善这个程序，每周五在存储的榜单中，随机抽三部电影，然后去爬取这三部电影的下载链接，并把链接的结果发送到邮箱。

 

这样一来，我们就可以选择一部电影在周末欣赏啦。

 

import requests
import time
import schedule
import smtplib
import numpy
from urllib.request import quote
from bs4 import BeautifulSoup
from email.mime.text import MIMEText
from email.header import Header

def fun_top250_3():

    movie_names = []

    for i in numpy.random.randint(0,249,3):
        res = requests.get('https://movie.douban.com/top250?start={}'.format(i))
        soup = BeautifulSoup(res.text,'html.parser')
        item = soup.find('div',class_='item').find('span').text
        movie_names.append(item)

    return movie_names

def fun_download_url():

    movie_names = fun_top250_3()

    movie_names_urls = ''

    for i in movie_names:
        key_word = quote(i,encoding='gbk')
        res = requests.get('http://s.ygdy8.com/plus/so.php?typeid=1&keyword={}'.format(key_word))
        res.encoding='gbk'
        soup = BeautifulSoup(res.text,'html.parser')
        check_none = soup.find('div',class_='co_content8').find('table')

        if check_none:
            item = soup.find('td',width='55%').find('b').find('a')
            res = requests.get('https://www.ygdy8.com'+item['href'])
            res.encoding='gbk'
            soup = BeautifulSoup(res.text,'html.parser')
            item = soup.find('td',style='WORD-WRAP: break-word').find('a').text
            movie_names_urls += '电影名：{}	下载链接：{}
'.format(i,item)
        else:
            movie_names_urls += '电影名：{}	下载链接：没有找到
'.format(i)

    return movie_names_urls

def fun_sendmail():

    movie_names_urls = fun_download_url()

    mail_user = 'www1707@xxx.cn'
    mail_pwd  = 'yyy'
    receiver  = 'user01@xxx.cn'
    subject   = time.strftime('%Y{}%W{}%S').format('年 第','周 推荐电影')
    content   = movie_names_urls

    alimail = smtplib.SMTP()
    alimail.connect('smtp.qiye.aliyun.com',25)
    alimail.login(mail_user,mail_pwd)

    message = MIMEText(content,'plain','utf-8')
    message['Subject'] = Header(subject,'utf-8')
    message['From']    = Header(mail_user,'utf-8')
    message['To']      = Header(receiver,'utf-8')

    alimail.sendmail(mail_user,receiver,message.as_string())
    alimail.quit()

    print(movie_names_urls)

#schedule.every().friday.do(fun_sendmail())
schedule.every(10).seconds.do(fun_sendmail)

while True:
    schedule.run_pending()
    time.sleep(1)

老师的答案

import requests,csv,random,smtplib,schedule,time
from bs4 import BeautifulSoup
from urllib.request import quote
from email.mime.text import MIMEText
from email.header import Header

def get_movielist():
    csv_file=open('movieTop.csv', 'w', newline='',encoding='utf-8')
    writer = csv.writer(csv_file)
    for x in range(10):
        url = 'https://movie.douban.com/top250?start=' + str(x*25) + '&filter='
        res = requests.get(url)
        bs = BeautifulSoup(res.text, 'html.parser')
        bs = bs.find('ol', class_="grid_view")
        for titles in bs.find_all('li'):
            title = titles.find('span', class_="title").text
            list1 = [title]
            writer.writerow(list1)
    csv_file.close()

def get_randommovie():
    movielist=[]
    csv_file=open('movieTop.csv','r',newline='',encoding='utf-8')
    reader=csv.reader(csv_file)
    for row in reader:
        movielist.append(row[0])
    three_movies=random.sample(movielist,3)
    contents=''
    for movie in three_movies:
        gbkmovie = movie.encode('gbk')
        urlsearch = 'http://s.ygdy8.com/plus/so.php?typeid=1&keyword='+quote(gbkmovie)
        res = requests.get(urlsearch)
        res.encoding='gbk'
        soup_movie = BeautifulSoup(res.text,'html.parser')
        urlpart=soup_movie.find(class_="co_content8").find_all('table')
        if urlpart:
            urlpart=urlpart[0].find('a')['href']
            urlmovie='https://www.ygdy8.com/'+urlpart
            res1=requests.get(urlmovie)
            res1.encoding='gbk'
            soup_movie1=BeautifulSoup(res1.text,'html.parser')
            urldownload=soup_movie1.find('div',id="Zoom").find('span').find('table').find('a')['href']
            content=movie+'
'+urldownload+'

'
            print(content)
            contents=contents+content
        else:
            content='没有'+movie+'的下载链接'
            print(content)
    return contents

def send_movielink(contents):
    mailhost='smtp.qq.com'
    qqmail = smtplib.SMTP()
    qqmail.connect(mailhost,25)
    account = '×××××××××@qq.com' # 因为是自己发给自己，所以邮箱账号、密码都可以提前设置好，当然，也可以发给别人啦
    password = '×××××××××××××××' # 因为是自己发给自己，所以邮箱账号、密码都可以提前设置好，当然，也可以发给别人啦。
    qqmail.login(account,password)
    receiver='×××××××××@qq.com'  # 因为是自己发给自己，所以邮箱账号、密码都可以提前设置好，当然，也可以发给别人啦。
    message = MIMEText(contents, 'plain', 'utf-8')
    subject = '电影链接'
    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()

def job():
    get_movielist()
    contents=get_randommovie()
    send_movielink(contents)

schedule.every().friday.at("18:00").do(job)while True:
    schedule.run_pending()
    time.sleep(1)