爬取豆瓣电影排行榜

运用到的库有：

time库

requests库

bs4库

不懂的可以在下方留言交流

#!D:\Anaconda\Python 3.7.0
# -*- coding: utf-8 -*-
# @author:LiuQing

import requests
from bs4 import BeautifulSoup
import time


time.perf_counter()
def get_url(url):   #获取url链接
    kv = {'user-agent': 'Mozilla/5.0'}
    response = requests.get(url, headers=kv, timeout=30)
    response.encoding = response.apparent_encoding
    return response.text

def get_info(txt):  #解析网页
    soup = BeautifulSoup(txt, 'html.parser')
    items = soup.find_all('div', class_='item')
    for item in items:
        #1.获取排名
        rank = item.find_all('div', class_='pic')[0].text.strip('\n')
        #2.获取评分人数
        value = item.find_all('span')[-2].text
        #3.获取标题
        title = item.find('span', class_='title').text
        #4.获取分数
        score = item.find('span', class_='rating_num').text
        #5.获取演员
        actor = item.find_all('p')[0].text.strip()
        #6.获取url
        url = item.a.get('href')
        print(f'{rank},{value},{score},{title},{actor},{url}')

def main():
    print("{}{}{}{}{}{}".format('排名','评分人数','标题','分数','演员','url'))
    #遍历url
    for i in range(0, 250, 25):
        html = f'https://movie.douban.com/top250?start={i}&filter='
        txt=get_url(html)
        get_info(txt)
    print(f'程序共运行{time.perf_counter()}')
if __name__ == '__main__':
    main()