抖音爬虫

Posted 2021-02-06 snackpython

import requests
import time
import re
import json
import pandas as pd
headers= {‘user-agent‘: ‘mobile‘}
def douyin_Spyder(id,url2):
    data=requests.get(‘http://aweme.snssdk.com/aweme/v1/user/?user_id={}&retry_type=retry_http&iid=59238161664&device_id=62578609382&ac=wifi&channel=aweGW&aid=1128&app_name=aweme&version_code=230&version_name=2.3.0&device_platform=android&ssmix=a&device_type=CHM-TL00H&device_brand=Honor&language=zh&os_api=19&os_version=4.4.4&uuid=745270478576539&openudid=589e358ee90e53&manifest_version_code=230&resolution=720*1280&dpi=320&update_version_code=2302&_rticket=1548395034447&ts={}&as=a1659a843a314c425a4355&cp=a518ca55a1a04624e1gkoo&mas=0141e7dcb9b69675674bffb55a194f1c3facaccc2c86ac4c2cc62c‘.format(id,time.time()),headers=headers)
    data2 = requests.get(url2,headers=headers)
    data2=requests.get(url2,headers=headers)
    content=data.content.decode(‘utf-8‘)
    dict_json = json.loads(content)
    print(‘******主页数据******‘)
    print(‘粉丝数:‘,dict_json[‘user‘][‘follower_count‘])
    print(‘获赞数:‘, dict_json[‘user‘][‘total_favorited‘])
    content2 = data2.content.decode(‘utf-8‘)
    dict_json2 = json.loads(content2)
    aweme_list=dict_json2[‘aweme_list‘]
    print(‘******视频区数据******‘)
    comment_count_list=[]
    digg_count_list = []
    share_count_list = []
    play_list = []
    forward_count_list = []
    id=[]
    desc=[]
    for i,key  in enumerate(aweme_list):
        # print(‘>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>‘)
        # print(‘标题：‘,key[‘desc‘])
        # print(‘ID:‘,key[‘aweme_id‘])
        video=key[‘video‘][‘play_addr‘][‘url_list‘][1]
        print(‘视频地址：‘,key[‘video‘][‘play_addr‘][‘url_list‘][1])
        res = requests.get(video, headers=headers)
        with open(r‘C:/Users/Administrator/Desktop/B站视频/迪丽热巴‘+str(i)+‘.mp4‘, ‘wb‘) as f:
            f.write(res.content)
        # print(‘分享地址：‘,key[‘share_url‘])
        # print(‘评论数：‘,key[‘statistics‘][‘comment_count‘])
        # print(‘点赞数：‘, key[‘statistics‘][‘digg_count‘])
        # print(‘转发量：‘, key[‘statistics‘][‘share_count‘])
        # print(‘forward_count：‘, key[‘statistics‘][‘forward_count‘])
        comment_count_list .append(key[‘statistics‘][‘comment_count‘])
        digg_count_list.append(key[‘statistics‘][‘digg_count‘])
        share_count_list .append(key[‘statistics‘][‘share_count‘])
        forward_count_list.append( key[‘statistics‘][‘forward_count‘])
        play_list.append(key[‘share_url‘])
        id.append(key[‘aweme_id‘])
        desc.append(key[‘desc‘])
    df = pd.DataFrame({‘ID‘: id, ‘标题‘: desc,‘链接地址‘:play_list,‘评论数‘:comment_count_list,‘点赞数‘:digg_count_list,‘转发量‘:share_count_list})
    df=df.set_index(‘ID‘)
    tim=time.strftime(‘%Y-%m-%d‘,time.localtime(time.time()))
    df.to_excel(‘C:/Users/Administrator/Desktop/‘+str(tim)+‘-7.xlsx‘)


if __name__ == ‘__main__‘:
    url2=input(‘url:‘)
    douyin_Spyder(79302973596,url2)