自己跟著視訊學習的第一個爬蟲小程式，裡面有許多不太清楚的地方，不如怎麼找到具體的電影名字的，那麼多級關係，怎麼以下就找到的是那個div呢？

諸如此類的，有許多，不過先做起來再說吧，後續再取去弄懂。

import requests
import bs4
import re

def open_url(url):
    #使用代理
    # proxies={'http':"127.0.0.1:1080",'https':'127.0.0.1:1080'}
    headers={"user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) \
    Chrome/86.0.4240.198 Safari/537.36 QIHU 360EE"}
    headers1={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0'}
    #res=requests.get(url,headers=headers,proxies=proxies)
    res=requests.get(url,headers=headers1)

    return res
def find_movies(res):
    soup=bs4.BeautifulSoup(res.text,'html.parser')

    #電影名
    movies=[]
    targets=soup.find_all('div',class_="hd")
    for each in targets:
        movies.append(each.a.span.text)

    #評分
    ranks=[]
    targets=soup.find_all('span',class_='rating_num')
    for each in targets:
        ranks.append('評分：{}'.format(each.text))

    #資料
    messages=[]
    targets=soup.find_all("div",class_='bd')
    for each in targets:
        try:
            messages.append(each.p.text.split('\n')[1].strip()+each.p.text.split('\n')[2].strip())
        except:
            continue
    result=[]
    length=len(movies)
    for i in range(length):
        result.append(movies[i]+ranks[i]+messages[i]+'\n')
    return result

#找出一共有多少個頁面
def find_depth(res):
    soup=bs4.BeautifulSoup(res.text,'html.parser')
    depth=soup.find('span',class_='next').previous_sibling.previous_sibling.text

    return int(depth)

def main():
    host="https://movie.douban.com/top250"
    res=open_url(host)
    depth=find_depth(res)

    result=[]
    for i in range(depth):
        url=host+'/?start='+str(25*i)
        res=open_url(url)
        result.extend(find_movies(res))
    with open("豆瓣TOP250電影.txt","w",encoding='utf-8') as f:
        for each in result:
            f.write(each)

if __name__=="__main__":
    main()