Python获取豆瓣前十页的两个方法

第一种方法

import urllib.request

for i in range(0,201,20):
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0'
    }
    url = f'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&start={i}&limit=20'
#请求对象的定制
    print(url)
    request = urllib.request.Request(url=url,headers=headers)
#获取响应数据
    response = urllib.request.urlopen(request)

    content = response.read().decode('utf-8')


    with open('douban'+str(i)+'.json','w',encoding='utf-8') as fp:
        fp.write(content)

第二种方法

import urllib.request
import urllib.parse
def creat_request(page):
    base_url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&'
    data = {
        'start':'(page-1)*20',
        'limit':'20'
    }
    data = urllib.parse.urlencode(data)
    url = base_url + data
    headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0'
    }
    request = urllib.request.Request(url=url,headers=headers)
    return request

def get_content(request):
    response = urllib.request.urlopen(request)
    content = response.read().decode('utf-8')
    return content
def down_load(page,content):
    with open('douban'+str(page)+'.json','w',encoding='utf-8') as fp:
        fp.write(content)



if __name__=='__main__':
    start_page = int(input('请输入初始页码'))
    end_page = int(input('请输入结束页码'))

    for page in range(start_page,end_page+1):
        request = creat_request(page)
        content=get_content(request)
        down_load(page,content)

  • 10
    点赞
  • 10
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值