requests爬虫实践：TOP250电影数据

# -*- coding: utf-8 -*-
"""
Created on Mon Oct 28 21:10:15 2019

@author: asus
"""


"""
requests爬虫实践：TOP250电影数据
"""
#import save_data#自己编写的保存列表文件模块
import requests
from bs4 import BeautifulSoup

def get_movies():
    headers = {
        'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36',
        'Host':'movie.douban.com'
        }
    movies_list = []
    for i in range(0,10):
        link = 'https://movie.douban.com/top250?start=' + str(i * 25) + '&filter='
        r = requests.get(link,headers = headers,timeout = 10)
        print(str(i + 1),"页响应状态码 ：",r.status_code)
        
        soup = BeautifulSoup(r.text,"lxml")
        div_list = soup.find_all('div',class_ = 'hd')
        for each in div_list:
            movie = each.a.span.text.strip()
            movies_list.append(movie)
    
    return movies_list
        
        

movies = get_movies()
print(movies)


#filename = r'C:\Users\asus\Desktop\豆瓣电影TOP250.txt'
#save_data.text_save(filename,movies)