python爬取豆瓣电影内容

python爬取豆瓣电影内容

import urllib.parse
import urllib.request
"""
下载前N页豆瓣数据

"""

def create_request(page):
    "定制请求对象"
    bese_url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&'

    data = {
        'start':(page-1)*20,
        'limit':20
    }

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
    }

    data = urllib.parse.urlencode(data)
    url = bese_url + data

    request = urllib.request.Request(url=url, headers=headers)
    return request

def get_content(request):
    "获取响应内容"
    response = urllib.request.urlopen(request)
    content = response.read().decode('utf-8')
    return content

def down_load(page, content):
    "下载响应内容"
    with open('douban_' + str(page) + '.json', 'w', encoding='utf-8') as fp:
        fp.write(content)




if __name__ == '__main__':
    start_page = int(input("请输入起始页码"))
    end_page = int(input("请输入结束页码"))
    for page in range(start_page, end_page):
        request = create_request(page)
        content = get_content(request)
        down_load(page, content)