這是我在CSDN的第一篇博客，假期剛自學Python，嘗試爬取了一下豆瓣top250.
希望可以有大佬指點
感謝

            
              import requests
from bs4 import BeautifulSoup


def gethtml(url):
    try:
        kv = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36'}

        r=requests.get(url,headers=kv,timeout=30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        
        return r.text
    except:
        print("fault")
    

def jiexi(list1,list2,list3,html):
    soup=BeautifulSoup(html,"html.parser")
    div_list=soup.find_all('div', class_='hd')
    div_list1=soup.find_all('div',class_='bd')
    div_list2=soup.find_all('div',class_='star')
    for each in div_list:
        movie=each.a.span.text
        list1.append(movie)
    for each in div_list1:
        yy=each.p.text.strip()
        if len(yy)>2:
            list2.append(yy)

    for each in div_list2:
        fen=each.contents
        list3.append((fen[3]).text)

    
    

def printlist(list1,list2,list3):
    print("豆瓣排名電影")
    print(len(list1))
    for i in range(len(list1)):
        print("排名"+str(i+1))
        print("名字："+list1[i])
        print("詳情："+list2[i])    
        print("評分："+list3[i])
        print("--------------------------------------------------------------------------")

def main():
    url0="https://movie.douban.com/top250?start="
    
    list1=[]
    list2=[]
    list3=[]

    for i in range(4):    #4是爬取的頁數
        try:

            url=url0+str(i*25)
            html=gethtml(url)
            jiexi(list1,list2,list3,html)
        except:
            continue
    printlist(list1,list2,list3)
        

main()