（一）古诗爬取

访问古诗文网站名句主页（https://so.gushiwen.cn/mingjus/），爬取里面的名句和出处（包括链接）保存到一个文本文件poems.txt中去。每个名句占用一行，内容格式如下：
编号(从1开始，占3位做对齐)：名句–出处(全诗链接)
空两格（诗句的译文注释和赏析）

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
from bs4 import BeautifulSoup as BS
import requests
#变量
rank=0
temp_line2=''
fs = open("诗词.txt",'w',encoding='utf-8')
soup=BS(requests.get("https://so.gushiwen.cn/mingjus/").content.decode("utf-8"),"lxml")
content=soup.select('body > div.main3 > div.left > div.sons > div.cont')
for i in content:
    #诗词出处、网址
    str=i.find_all('a')
    url='https://so.gushiwen.cn'+i.find('a')['href'];
    temp_soup=BS(requests.get(url).content.decode("utf-8"),"lxml")
    # 诗词翻译内容
    temp_content=temp_soup.select('#sonsyuanwen > div.cont > div.contson')
    for x in temp_content:
        temp_line1 = x.text.split('\n')
        for z in temp_line1:
            temp_line2+="  "+z+'\n'
    line2=temp_line2[:-1]
    temp_line2=''
    poem=str[0].text
    if(len(str)==1):
        poet="没有出处"
    else: poet = "出自"+str[1].text 
    rank+=1
    line1=f"{rank}："+poem+"--"+poet+'('+url+')'
    fs.write('{0:>3}'.format(line1))
    fs.write(line2)
fs.close()

（二）显示影片基本信息

访问豆瓣电影Top250（https://movie.douban.com/top250?start=0），
获取每部电影的中文片名、排名、评分及其对应的链接，按照“排名-中文片名-评分-链接”的格式显示在屏幕上。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
from bs4 import BeautifulSoup as BS
import requests

rank=0
fs = open("豆瓣.txt",'w',encoding='utf-8')
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36"
}
for page in range(0,251,25):
    soup=BS(requests.get(f"https://movie.douban.com/top250?start={page}&filter=",headers=headers).content.decode("utf-8"),"lxml")
    content=soup.select('#content > div > div.article > ol > li > div > div.info ')
    for i in content:
        rank=rank+1
        name=i.select('.title')
        star=i.select('.rating_num')
        url=i.find('a')['href']
        print("排名:"+str(rank)+"-《"+name[0].text+"》-评分:"+star[0].text+"-链接:"+url)
        fs.write("排名:"+str(rank)+"-《"+name[0].text+"》-评分:"+star[0].text+"-链接:"+url+'\n')
fs.close()

（三）存储影片详细信息

访问豆瓣电影Top250（https://movie.douban.com/top250?start=0）
在问题1的基础上，获取每部电影的导演、编剧、主演、类型、上映时间、片长、评分人数以及剧情简介等信息，并将获取到的信息保存至本地文件中。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
from bs4 import BeautifulSoup as BS
import requests

fs = open("豆瓣.txt",'w',encoding='utf-8')
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36"
}
for page in range(0,250,25):
    soup=BS(requests.get(f"https://movie.douban.com/top250?start={page}&filter=",headers=headers).content.decode("utf-8"),"lxml")
    content=soup.select('#content > div > div.article > ol > li > div > div.info ')
    for i in content:
        # 电影
        name="电影:"+i.select('.title')[0].text
        url=i.find('a')['href']
        sp=BS(requests.get(url,headers=headers).content.decode("utf-8"),"lxml")
        # 导演、主演、类型、上映时间
        mainer=i.find('p')
        mainer=mainer.text.strip()
        # # 编剧
        writers=sp.select('#info > span') 
        writers=writers[1].text
        # # 片长
        all_time=sp.select('span[property="v:runtime"]')
        all_time="时长:"+all_time[0].text
        # 评分人数
        number=i.find_all('span')
        number="评分人数:"+number[-2].text
        # 简介
        brief=sp.select('span[property="v:summary"]')
        brief="简介:"+brief[0].text
        all=name+"\n"+mainer+"\n"+writers+"\n"+all_time+"\n"+number+"\n"+brief+"\n"
        fs.write(all+'\n\n')
fs.close()

（四）访问热搜榜并发送邮件

访问微博热搜榜（https://s.weibo.com/top/summary）
获取微博热搜榜前50条热搜名称、链接及其实时热度，并将获取到的数据通过邮件的形式，每20秒发送一次到个人邮箱中。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
import requests
from bs4 import BeautifulSoup as BS
import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
import time

def get_line():
    headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36",
    'Cookie':'4210214103(保密了)'
    }
    url = 'https://s.weibo.com/top/summary'
    soup=BS(requests.get(url,headers=headers).content.decode('utf-8'),'lxml')
    tips=soup.select('#pl_top_realtimehot > table > tbody > tr > td.td-02 > a')
    hot=soup.select('#pl_top_realtimehot > table > tbody > tr > td.td-02 > span')
    x=soup.select('#pl_top_realtimehot > table > tbody > tr > td.td-02 > a')
    line='\n'
    for i in range(1,51):
        line+=f"Top{i}:"+tips[i].text+" 热度:"+hot[i].text+"\n地址:https://s.weibo.com"+x[i].get('href')+'\n\n'
    return line
def send_email(line):
    sender_email = "941521358@qq.com" 
    receiver_email = "ldyertop@qq.com"
    password = "4210214103（保密了）"  
    message = MIMEMultipart()
    message['From'] = sender_email
    message['To'] = receiver_email
    message['Subject'] = "Ldyer的微博热搜"
    message.attach(MIMEText(line, 'plain'))
    with smtplib.SMTP_SSL('smtp.qq.com', 465) as server:
        server.login(sender_email, password)
        server.sendmail(sender_email, receiver_email, message.as_string())
while True:
    send_email(get_line())
    print("邮件已发送")
time.sleep(20)