requests+beautifulsoup爬取猫眼电影Top1

Requests库+正则表达式爬取猫眼Top100里的正则表达式编写有的时候过于繁琐，而beautifulsoup可以较好的解决这一麻烦。

import requests
from bs4 import BeautifulSoup
import pandas as pd
import numpy as np

results = []
def get_one_page(offset):
    url = 'https://maoyan.com/board/4?offset='+str(offset)
    response = requests.get(url)
    soup = BeautifulSoup(response.content,'lxml')
    top =soup.find(name='dl',class_="board-wrapper")
    for data  in top.find_all('dd'):
        rank = data.find('i').get_text()
        title = data.find('p',class_="name").get_text()
        actors = data.find('p',class_="star").get_text().strip()[3:]
        time = data.find('p',class_='releasetime').get_text().strip()[5:]
        score = data.find('p',class_="score").get_text()
        result_list = [int(rank),title,actors,time,float(score)]
        results.append(result_list)
        
def main():           
    for i in range(10):
        get_one_page(i*10)
    pd.DataFrame(results,columns=['rank','title','actors','time','score']).to_excel('top100.xlsx',index=False)
    
main()

结果部分如图：