爬虫实战2(动态页面)

import pandas as pd
import requests
import json
data=[]
cookies = {
    'bid': 'VU-910l63_o',
    'ap_v': '0,6.0',
    '__utma': '30149280.1187284749.1715913689.1715913689.1715913689.1',
    '__utmb': '30149280.0.10.1715913689',
    '__utmc': '30149280',
    '__utmz': '30149280.1715913689.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)',
}

headers = {
    'Accept': 'application/json, text/plain, */*',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
    'Connection': 'keep-alive',
    # Requests sorts cookies= alphabetically
    # 'Cookie': 'bid=VU-910l63_o; ap_v=0,6.0; __utma=30149280.1187284749.1715913689.1715913689.1715913689.1; __utmb=30149280.0.10.1715913689; __utmc=30149280; __utmz=30149280.1715913689.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)',
    'Origin': 'https://movie.douban.com',
    'Referer': 'https://movie.douban.com/explore',
    'Sec-Fetch-Dest': 'empty',
    'Sec-Fetch-Mode': 'cors',
    'Sec-Fetch-Site': 'same-site',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 Edg/124.0.0.0',
    'sec-ch-ua': '"Chromium";v="124", "Microsoft Edge";v="124", "Not-A.Brand";v="99"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Windows"',
}

params = {
    'refresh': '0',
    'start': '0',
    'count': '20',
    'selected_categories': '{}',
    'uncollect': 'false',
    'sort': 'T',
    'tags': '',
}

r= requests.get('https://m.douban.com/rexxar/api/v2/movie/recommend', params=params, cookies=cookies, headers=headers)
res=json.loads(r.text)
for i in res['items']:
    title=i['title']
    year=i['year']
    info=i['card_subtitle']
    rating=i['rating']['value']
    dict={
        '标题':title,'上映年份':year,'简介':info,'评分':rating
    }
    data.append(dict)
    df=pd.DataFrame(data)
    df.to_excel('豆瓣电影.xlsx')

运用到下方三个网址
https://movie.douban.com/explore//豆瓣网
https://www.lddgo.net/convert/curl-to-code//在线curl命令转换码
http://www.esjson.com/jsonviewer.html//JSON在线可视化视图|(ES JSON在线工具)

复制源代码转换
---------------------------------------------------------------------------------------------------------------------------------

将运行结果json代码复制

将代码转换

  • 11
    点赞
  • 12
    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