充满热点的美女"宅舞"视频每天都在更新,这不得批量爬下来慢慢看~

python芊 2022-05-05 发布于湖南

展开全文

前言

嗨喽！大家好呀~这里是魔王

本次所需知识点：

requests
post请求方式
开发者工具的使用

所使用开发环境:

版本: python 3.8
编辑器: pycharm 2021.2

思路分析

第一个步骤 (找到数据来源)

代码实现:

发送请求
获取数据
解析数据
保存数据

代码

import requests     # 发送请求

headers = {    'cookie': 'SUB=_2AkMWuiaof8NxqwJRmfEcxW7kZYV1zQHEieKg5tdzJRMxHRl-yT8XqmlbtRB6PToIR8vzOUazMyBaDx1yoAhoGvmhBh2R; SUBP=0033WrSXqPxfM72-Ws9jqgMF55529P9D9WFhP5UbeyRGEMWCEO66rKKN; SINAGLOBAL=4378435525987.705.1642506657635; UOR=,,www.baidu.com; YF-V-WEIBO-G0=35846f552801987f8c1e8f7cec0e2230; _s_tentry=www.baidu.com; Apache=4202086709610.053.1651127548346; ULV=1651127548462:5:1:1:4202086709610.053.1651127548346:1647671293014; XSRF-TOKEN=-zQTQde7oNPbwv2z7IZNWn7x; WBPSESS=5Gh1MjbHbWED7wnbzL0HessirGvmylijYYvflqusiD9GEsQ6rqnU_tJ77BAIaB7ziYAGd2bn8bjGxvzctVcMOww-G_WpuVuFa86yECy9FyzCc1G6phFPW88j0AwEPWrz',    'origin': 'https://www.weibo.com',    'page-referer': '/tv/show/1034:4762666296868953',    'referer': 'https://www.weibo.com/tv/show/1034:4762666296868953?mid=4762667594547707',    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36',    'x-xsrf-token': '-zQTQde7oNPbwv2z7IZNWn7x'}
def get_next(next_cursor):
    list_data = {        'data': '{"Component_Channel_Subchannel":{"cid":"4379160563414139"}}'
    }    if next_cursor != '':
        list_data = {
            'data': '{"Component_Channel_Subchannel":{"next_cursor":'+str(next_cursor)+',"cid":"4379160563414139"}}'
        }
    # https://www.weibo.com/tv/api/component?page=/tv/channel/4379160563414111/4379160563414139
    list_url = 'https://www.weibo.com/tv/api/component?page=/tv/channel/4379160563414111/4379160563414139'
    list_json = requests.post(list_url, headers=headers, data=list_data).json()    if list_json['data']['Component_Channel_Subchannel'] == None:        return 0
    data_list = list_json['data']['Component_Channel_Subchannel']['list']
    next_cursor = list_json['data']['Component_Channel_Subchannel']['next_cursor']    for dat_ in data_list:
        oid = dat_['oid']
        data = {            'data': '{"Component_Play_Playinfo":{"oid":"'+oid+'"}}'
        }
        url = 'https://www.weibo.com/tv/api/component?page=/tv/show/' + oid
        # 1. 发送请求
        response = requests.post(url=url, data=data, headers=headers)
        # 2. 获取数据
        json_dict = response.json()
        # 3. 解析数据
        try:
            dict_urls = json_dict['data']['Component_Play_Playinfo']['urls']
            video_url = 'https:' + dict_urls[list(dict_urls.keys())[0]]
            title = json_dict['data']['Component_Play_Playinfo']['title']
            media_id = json_dict['data']['Component_Play_Playinfo']['media_id']
            title = str(media_id) + title            print(title, video_url)
            # 4. 保存数据
            # video_data = requests.get(video_url).content
            # with open(f'video/{title}.mp4', mode='wb') as f:
            #     f.write(video_data)
        except:            print('视频违规,已下架!')
    get_next(next_cursor)

get_next('')