爬虫day02：request请求库爬取豆瓣电影信息

 

import requests
import re
def get_page(url):
    response = requests.get(url)
    #print(response.text)
    return response

def parse_index(html):
    """''''''
    ''''''"""
    movie_list = re.findall(
        '<div class="item">.*?<em class="">(.*?)</em>.*?<a href="(.*?)">.*?<span class="title">(.*?)</span>.*?导演: (.*?)主演: (.*?)<br>(.*?)</p>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价</span>.*?<span class="inq">(.*?)</span>',
        html,
        re.S)
    return movie_list

def save_data(movie):
    top, m_url, name, daoyan, actor, year_type, \
    point, commit, desc = movie
    year_type = year_type.strip('\n')
    data = f'''
                电影名称:{top}
                电影url:{m_url}
                电影导演:{name}
                电影主演:{daoyan}
                电影年份:{actor}
                电影类型:{year_type}
                电影评分:{point}
                电影评论:{commit}
                电影简介:{desc}
                '''
    print(data)
    with open('douban_top250.txt','a',encoding='utf-8') as f:
        f.write(data)

    print(f'电影:{name} 写入成功')

if __name__=='__main__':
    #拼接所有主页
    num = 0
    for line in range(10):
        url = f'https://movie.douban.com/top250?start={num}&filter='
        num += 25
        print(url)

        index_res = get_page(url)

        movie_list = parse_index(index_res.text)

        for movie in movie_list:
            # print(movie)

            # 3.保存数据
            save_data(movie)