抖音搜索视频采集

13955925361

这次给大家分享抖音搜索数据采集，注意是在视频区，我的cookies如果过期了要换自己网页上的，
使用方法也是一如既往的简单，输入想搜索的关键词即可，获得全部视频并命名保存在文件夹内。

[Python] 纯文本查看 复制代码

?

001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169

import requests import  os   ##请注意，务必使用自己电脑上搜索网页产生的cookies cookies = {     'device_web_cpu_core': '32',     'device_web_memory_size': '8',     'architecture': 'amd64',     'csrf_session_id': 'ad3faf6a949237d5af255894374b89ff',     'webcast_leading_last_show_time': '1706274219677',     'webcast_leading_total_show_times': '1',     'webcast_local_quality': 'origin',     'passport_fe_beating_status': 'true',     'ttwid': '1%7Cj0AB1Pl_aVbAjGwE4P9_3H5KBw7ZA0yqZ-wsbk--sK0%7C1740372914%7Cd386f650da113d88512b6460bfa04f26f0c825f7a53abb7c264b3f2c2974215c',     'x-web-secsdk-uid': 'af66562d-005d-4f16-8e4a-271cf2c137f3',     'hevc_supported': 'true',     'fpk1': 'U2FsdGVkX19skYOCWrK0wT5e5n6BV8l93DWMmAaH5s98G0h9oYVdqy8gL8FY7f6M2B0NpCTlg/GdPMi86+ev7g==',     'fpk2': '9258db5fffd4f17a8703a19e760af505',     'odin_tt': '712ca6a9cffa424266aae08ebe4d32d1e6c0f535013ff0be84d2f1634a07b1cbc45f3cd7a22e3c7df641ef637068418fb780411c8aeffcfd47de0e943823d780f9fcabdb4129bbf4d935be3ac9a836ce',     'UIFID': '3af258ad659545d9553f15cf32bb8a88df248991ebb865c20b5fa6f7dab6eb54e8d56c91612405705c23ef3169c754057359a8de37c8fd82c06b56053b9959d15d41fa3acf61ab30ac9b68a4d6560f5b522876f27befff69f38fe90a10431891784e6f60feb4a69d5369417c250b3fe1dc3cce6465b0755720c4b3ecd50009900a9692dd076221d8ed878bc103da6bf910d0cfd5b168c5fcac47ba2732e629e1',     'dy_swidth': '1707',     'dy_sheight': '960',     's_v_web_id': 'verify_m9a3id25_jv982Snw_4Egf_42Zu_9Osa_L79yf6GHm4Kv',     'is_dash_user': '1',     'volume_info': '%7B%22isUserMute%22%3Afalse%2C%22isMute%22%3Atrue%2C%22volume%22%3A0.201%7D',     'xgplayer_user_id': '818224755114',     'passport_csrf_token': '7ea9d1cb10eb7b782cfee69890eea146',     'passport_csrf_token_default': '7ea9d1cb10eb7b782cfee69890eea146',     'FORCE_LOGIN': '%7B%22videoConsumedRemainSeconds%22%3A180%7D',     '__security_mc_1_s_sdk_crypt_sdk': 'e581bcff-4b0c-821a',     '__security_mc_1_s_sdk_cert_key': 'd7b521c3-4836-8a84',     '__security_mc_1_s_sdk_sign_data_key_web_protect': '14766a15-43d8-acf4',     'bd_ticket_guard_client_web_domain': '2',     'SearchMultiColumnLandingAbVer': '1',     'SEARCH_RESULT_LIST_TYPE': '%22multi%22',     'xgplayer_device_id': '76706908427',     'stream_recommend_feed_params': '%22%7B%5C%22cookie_enabled%5C%22%3Atrue%2C%5C%22screen_width%5C%22%3A1707%2C%5C%22screen_height%5C%22%3A960%2C%5C%22browser_online%5C%22%3Atrue%2C%5C%22cpu_core_num%5C%22%3A32%2C%5C%22device_memory%5C%22%3A8%2C%5C%22downlink%5C%22%3A10%2C%5C%22effective_type%5C%22%3A%5C%224g%5C%22%2C%5C%22round_trip_time%5C%22%3A50%7D%22',     'strategyABtestKey': '%221744218661.635%22',     'SearchColumnSwitchLog': '%5B%7B%22date%22%3A%222025-04-09%22%2C%22latestColumnType%22%3A%22multi%22%7D%2C%7B%22date%22%3A%222025-04-10%22%2C%22latestColumnType%22%3A%22multi%22%7D%5D',     'download_guide': '%223%2F20250410%2F0%22',     'home_can_add_dy_2_desktop': '%221%22',     'biz_trace_id': '10a3bd37',     'bd_ticket_guard_client_data': 'eyJiZC10aWNrZXQtZ3VhcmQtdmVyc2lvbiI6MiwiYmQtdGlja2V0LWd1YXJkLWl0ZXJhdGlvbi12ZXJzaW9uIjoxLCJiZC10aWNrZXQtZ3VhcmQtcmVlLXB1YmxpYy1rZXkiOiJCTVJjNHh5RnVOdTFtR0JmV3Z3ZEhaZkp1MUVFVjVWdjJiWHBZNTZ2OHY4YzhJN2VBRkVlZ0VoK1NGY1I5MTFBNWpVcndWeExwcjVVeG5HbG11MUJIZ0E9IiwiYmQtdGlja2V0LWd1YXJkLXdlYi12ZXJzaW9uIjoyfQ%3D%3D',     'gulu_source_res': 'eyJwX2luIjoiOWVjNWI1NGQzNWVlMDQ1YzJlZjdlOGUwZDI0NmQ5NTE2MzVmZTQ5YWRiNTA1Njg3ZjFkM2MyMzJhOTc2MzEzOSJ9',     'xg_device_score': '7.8003162307251666',     'sdk_source_info': '7e276470716a68645a606960273f276364697660272927676c715a6d6069756077273f276364697660272927666d776a68605a607d71606b766c6a6b5a7666776c7571273f275e58272927666a6b766a69605a696c6061273f27636469766027292762696a6764695a7364776c6467696076273f275e5827292771273f2732313d313c30313d3731313234272927676c715a75776a716a666a69273f2763646976602778',     'bit_env': 'RZd5QHG5wBOkX44_tiN7wJ9iXIgwJevXDML38TE3gv7gyTJ5UTUCF_MfgTiqqplcoxoake1d3johbioUxEmlByKaBFBP0sgypqhkd81i9ZH8CddJoFJQatNaJAkEjbNwksTCAk4iTf444nVBPct_lPDuUU1cjwJY4cyEzNXk3xxpMcUzSIp3vlbVEMjTAttSkak9pZNq2sRSJJRgKkebRSDc8QbXqMLoPM1Mpzyrsjl1FTO-baAPjiKeCegJIlvuL04_6eHfLyCisGAtWBtfsAWp-YzTE6dYU0fDTQtUUuaXKJRwsN7uwmRLlfeY0gW2OlQMRKKacp_gTRDzU8YftSiFuEPQKn1wjMzUQnVqvHYKwvxK3ZoE3DzRQ0_E-Mli_rlyGA3_aeoLcQr0dDyfY-7z-ihW_vfJDD2UoUd7NByv-8F-wa619S5IZ_tfraeQAQvVH9_Sp7rfelM2stqrZLW58rqQL7IhjeMyDl3JbZ8pmJ7JrsZBY5QkPOC05fHRp5keyjgT-9X1usg4ZJFhMjCJhly-myvIk22yKr1hgE0%3D',     'passport_auth_mix_state': 'gf0d1y95s4d4v9cl601scq3cjbvxy9hwo34tnnf2itqhwwok',     'stream_player_status_params': '%22%7B%5C%22is_auto_play%5C%22%3A0%2C%5C%22is_full_screen%5C%22%3A0%2C%5C%22is_full_webscreen%5C%22%3A0%2C%5C%22is_mute%5C%22%3A1%2C%5C%22is_speed%5C%22%3A1%2C%5C%22is_visible%5C%22%3A1%7D%22',     'IsDouyinActive': 'true', }       class Spider(object):     os_path = os.getcwd() + '/抖音搜索视频/'     if not os.path.exists(os_path):         os.mkdir(os_path)     def __init__(self):         self.url= 'https://www.douyin.com/aweme/v1/web/search/item/'         self.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',             'cache-control': 'no-cache',             'pragma': 'no-cache',             'priority': 'u=1, i',             'referer': 'https://www.douyin.com/root/search/%E5%BC%A0%E4%BC%9F?type=video',             'sec-ch-ua': '"Microsoft Edge";v="135", "Not-A.Brand";v="8", "Chromium";v="135"',             'sec-ch-ua-mobile': '?0',             'sec-ch-ua-platform': '"Windows"',             'sec-fetch-dest': 'empty',             'sec-fetch-mode': 'cors',             'sec-fetch-site': 'same-origin',             'uifid': '3af258ad659545d9553f15cf32bb8a88df248991ebb865c20b5fa6f7dab6eb54e8d56c91612405705c23ef3169c754057359a8de37c8fd82c06b56053b9959d15d41fa3acf61ab30ac9b68a4d6560f5b522876f27befff69f38fe90a10431891784e6f60feb4a69d5369417c250b3fe1dc3cce6465b0755720c4b3ecd50009900a9692dd076221d8ed878bc103da6bf910d0cfd5b168c5fcac47ba2732e629e1',             'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36 Edg/135.0.0.0',         }         self.key = str(input('请输入您想采集的内容： '))         def parse_start_url(self, page_number):             params = (             ('device_platform', 'webapp'),             ('aid', '6383'),             ('channel', 'channel_pc_web'),             ('search_channel', 'aweme_video_web'),             ('enable_history', '1'),             ('keyword', self.key),             ('search_source', 'normal_search'),             ('query_correct_type', '1'),             ('is_filter_search', '0'),             ('from_group_id', ''),             ('offset', page_number),             ('count', '10'),             ('need_filter_settings', '1'),             ('list_type', 'multi'),             ('update_version_code', '170400'),             ('pc_client_type', '1'),             ('pc_libra_divert', 'Windows'),             ('support_h265', '1'),             ('support_dash', '1'),             ('version_code', '170400'),             ('version_name', '17.4.0'),             ('cookie_enabled', 'true'),             ('screen_width', '1707'),             ('screen_height', '960'),             ('browser_language', 'zh-CN'),             ('browser_platform', 'Win32'),             ('browser_name', 'Edge'),             ('browser_version', '135.0.0.0'),             ('browser_online', 'true'),             ('engine_name', 'Blink'),             ('engine_version', '135.0.0.0'),             ('os_name', 'Windows'),             ('os_version', '10'),             ('cpu_core_num', '32'),             ('device_memory', '8'),             ('platform', 'PC'),             ('downlink', '10'),             ('effective_type', '4g'),             ('round_trip_time', '50'),             ('webid', '7474844642175010344'),             ('uifid',              '3af258ad659545d9553f15cf32bb8a88df248991ebb865c20b5fa6f7dab6eb54e8d56c91612405705c23ef3169c754057359a8de37c8fd82c06b56053b9959d15d41fa3acf61ab30ac9b68a4d6560f5b522876f27befff69f38fe90a10431891784e6f60feb4a69d5369417c250b3fe1dc3cce6465b0755720c4b3ecd50009900a9692dd076221d8ed878bc103da6bf910d0cfd5b168c5fcac47ba2732e629e1'),)           # ('msToken',         #  'yJ3OCyQmLkA3aYgRBx4gEVXtArb0A68nWhwJneWw-OOjdFLqZGeNcovnGg9P8_fAqKJGiYCZ761Fl8QV84CMjju1_LSCbefoH_DcswS2-3B0cUcRc6uX5SJdzU5NlvT3w5T3DcMnBlttd9yzIlgvj7F76SmQ0kY20KxpALs7e8UVBrReUA=='),         #     ('a_bogus',         #      'mJsRgtWjxd/VPdFbmcTGt-3lrAgANP8yKpTdWCPT9NFEGwtcE8PIpxSXJxuPm7WR4mBkioNH4d-AafdcQTX0Z99kqmpkSwUSe42IVUfoMqiIbtwkLrfhSL8zqwBSUbwil/nWiIW5Us0EIEI5INAmApIGC5zLQmg2SqZCp2Y9JDSWps6TVn/1Ca26'),         # )   (         # 'msToken'和'a_bogus'动态变化，但是输入了一次，后面可以不管，没怎么做校验，我是直接给注释掉了。           response = requests.get(self.url, headers=self.headers, params=params,cookies=cookies).json()        # print(response)         self.save_data(response)         def save_data(self,response):         for data in response['data']:             name=data['aweme_info']['desc']             if not name:                 name=data['aweme_info']['aweme_id']             for char in '<>:"/\\|?*\n':                 name = name.replace(char, '_')             mp4_url=data['aweme_info']['video']['play_addr']['url_list'][-1]             print(name,mp4_url)             self.save_video(name,mp4_url)       def save_video(self,name,mp4_url):         video_data = requests.get(mp4_url, headers=self.headers).content         with open(self.os_path + name + '.mp4', 'wb') as f:             f.write(video_data)             print(f"视频 ：{name} - - - 下载完成",'\n\n')     if __name__ == '__main__':     spider = Spider()   page_number = 0 while True:     spider.parse_start_url(page_number)     page_number +=10 else:     print(f'已下载{page_number}个视频')     ##spider.parse_start_url(page_number)函数接口 page_number为视频个数，从0开始，每页+10， # 便于中途报错重新爬取，直接  FOR 循环输入大于page_number即可，是10的整数倍，这就是全部爬取了。

wari01

不知道有木有大神做好成品

zzZzzZ124213123

zxhlh 发表于 2025-5-14 10:51
来个成品可以吗？感谢

[Python] 纯文本查看 复制代码

?

001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135

import requests import  os import time   def string_to_dict(cookie_string):     cookie_dict = {}     for cookie in cookie_string.split(';'):         if '=' in cookie:             key, value = cookie.strip().split('=', 1)             cookie_dict[key] = value     return cookie_dict ##请注意，务必使用自己电脑上搜索网页产生的cookies cookie_str = 'UIFID_TEMP=9813fed978a3c771be2b666bdcfa929d1334ed722b7c12524b489df48e588a5c51cb117a18fa5735b4a61dbc57f41dfe5b73b2fdf0e28ff9931f9e523880ce37ed1447cd909e4869637c2adef01c068d; fpk1=U2FsdGVkX1+tFweCK8NMTa4xF84b75AAt0tPzCi5lS/09031IV8EDhEJ5AIx1SdEmiVT9pTMWza7XYZiLdbX6g==; fpk2=0a4ec5943b80707adbc82b48683207dd; UIFID=9813fed978a3c771be2b666bdcfa929d1334ed722b7c12524b489df48e588a5c25cfe601d9a654bcdf603de3057a5ca0e42c655d3730a355c58a5acf3e8567593342557d2bc1e7c4581fc67f55491c54407b25ecddf2ab6b67adf6cad934d3c8c4857a0e790b505bdeaacee778eca9e6cb649d7394bb142724e0e1b544f1b060e17a38a3ab2259409372d999225e429542bcb903565408618e8fc0d2c50c5500; hevc_supported=true; xgplayer_device_id=14451711088; xgplayer_user_id=277492132112; SEARCH_RESULT_LIST_TYPE=%22single%22; is_dash_user=1; passport_csrf_token=f5c2a1a860aca5b614d19eb832404b8d; passport_csrf_token_default=f5c2a1a860aca5b614d19eb832404b8d; __security_mc_1_s_sdk_crypt_sdk=2a3419f7-4a28-9bca; bd_ticket_guard_client_web_domain=2; volume_info=%7B%22isUserMute%22%3Afalse%2C%22isMute%22%3Afalse%2C%22volume%22%3A1%7D; s_v_web_id=verify_ma1zdq2m_T58IKTlX_JSyp_4aiD_ASnw_P6zqSHe9CDaA; ttwid=1%7C9J-wbAEBpW1RbU_nrLYSAiTl9ShIyGjygHrlsF-rVio%7C1745939026%7Cc57869d5101670dce1fe34bc9fb4e3632d6a2160f0059810dd915b8f513ea2a6; passport_mfa_token=Cjd6%2Bwrz7RHQuLwuVbMpeJ0xd8Peerc1iMheAUOfq%2BzFgJ48xO4qDeQtMHigHPD3UGTVC31CZFAWGkoKPAAAAAAAAAAAAABO7%2BpfTPg%2BXOZXCB76%2B3eZlgH0CEI9Anla5F4rtgu9yMKnul4nGXGbIOj9KIN94n%2BNfBD4hvANGPax0WwgAiIBA%2Bd22eo%3D; d_ticket=1aefd782c7eac07793b6028676b2011c99105; passport_assist_user=CkGWKuT-Nt6Y-Hxc_VNFM33kHrke1s_-ftti6qnE4YbNimlcOw8DHxQiDSynPbIp7JYqOPXyYxazzBzyVSyiOhHkCBpKCjwqhVj9z6sweHl7zu4u_MmNZdUHBQ2wWH-IfdcGOCKl_eYMq9Wpf1IojNJ6H74pzawMkqw5emrPV2iMUJYQtobwDRiJr9ZUIAEiAQMNlH0J; n_mh=40vgplZPesxOieWeAud-o_mn_8l6Lg33PWrWzo10Rno; passport_auth_status=0a5f27eee16474ad6fe858963787654b%2C; passport_auth_status_ss=0a5f27eee16474ad6fe858963787654b%2C; sid_guard=d638a6c2f1639b58a0a7d53fa66ea9e6%7C1745939405%7C5184000%7CSat%2C+28-Jun-2025+15%3A10%3A05+GMT; uid_tt=f44a2e5049b95d3f0bd4ff608d9cafc7; uid_tt_ss=f44a2e5049b95d3f0bd4ff608d9cafc7; sid_tt=d638a6c2f1639b58a0a7d53fa66ea9e6; sessionid=d638a6c2f1639b58a0a7d53fa66ea9e6; sessionid_ss=d638a6c2f1639b58a0a7d53fa66ea9e6; is_staff_user=false; sid_ucp_v1=1.0.0-KDdlMDJhOTg2ZmI5NmM5MmQ1MmM3OTg2Mjk0ZTVmNDg2MGU1N2E4OGYKIQiuztCx2435BRDN18PABhjvMSAMMJPH7ZYGOAJA8QdIBBoCaGwiIGQ2MzhhNmMyZjE2MzliNThhMGE3ZDUzZmE2NmVhOWU2; ssid_ucp_v1=1.0.0-KDdlMDJhOTg2ZmI5NmM5MmQ1MmM3OTg2Mjk0ZTVmNDg2MGU1N2E4OGYKIQiuztCx2435BRDN18PABhjvMSAMMJPH7ZYGOAJA8QdIBBoCaGwiIGQ2MzhhNmMyZjE2MzliNThhMGE3ZDUzZmE2NmVhOWU2; login_time=1745939404074; SelfTabRedDotControl=%5B%5D; _bd_ticket_crypt_cookie=379b54ed005dab727dcab14c1d6d32ef; __security_mc_1_s_sdk_sign_data_key_web_protect=068970f3-4a9e-b45b; __security_mc_1_s_sdk_cert_key=0b34d9e3-493f-af14; __security_server_data_status=1; __ac_signature=_02B4Z6wo00f01pp45XgAAIDDiJWtRtq4KPqaWOHAAM6ZVwPvKnx.a-0hkPj74RO7nFTOOydWBG5KS0P5sIpHd9phrR7YhGXdyR.O-dC7dGbFzx7okwxoidJ.4ycY9RnoEp5h9uvJ.7lSKZne80; publish_badge_show_info=%220%2C0%2C0%2C1746606382125%22; download_guide=%223%2F20250508%2F0%22; csrf_session_id=7c0e798ff1522cdbef32df6e26638d9b; IsDouyinActive=true; bd_ticket_guard_client_data=eyJiZC10aWNrZXQtZ3VhcmQtdmVyc2lvbiI6MiwiYmQtdGlja2V0LWd1YXJkLWl0ZXJhdGlvbi12ZXJzaW9uIjoxLCJiZC10aWNrZXQtZ3VhcmQtcmVlLXB1YmxpYy1rZXkiOiJCTFNyZEZkZ3JlbVdneS9lUk9BZkhoVEZ4a1FPSlhPT0szVnFGK29pSGs1d2RHYTNheThvK2lxSERKV2U3cHV0SnVKaXB4dnltWEpwcldTeGZrTy9sWVk9IiwiYmQtdGlja2V0LWd1YXJkLXdlYi12ZXJzaW9uIjoyfQ%3D%3D; home_can_add_dy_2_desktop=%221%22; passport_fe_beating_status=true; odin_tt=952beaa801083cb75ef1c2b2859fa58b2e870e9bc2c03e31ee2ac84a6fc6008e223f70f242b544ce07b1de9c0316b56e6cf7f31e9a6e940e4526dff5736a1b0a; __ac_nonce=068228ea3003830f08b71' cookies = string_to_dict(cookie_str) print(cookies)   class Spider(object):     os_path = os.path.dirname(os.path.abspath(__file__)) + '/抖音搜索视频/'     if not os.path.exists(os_path):         os.mkdir(os_path)     def __init__(self):         self.url= 'https://www.douyin.com/aweme/v1/web/search/item/'         self.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',             'cache-control': 'no-cache',             'pragma': 'no-cache',             'priority': 'u=1, i',             'referer': 'https://www.douyin.com/root/search/%E5%BC%A0%E4%BC%9F?type=video',             'sec-ch-ua': '"Microsoft Edge";v="135", "Not-A.Brand";v="8", "Chromium";v="135"',             'sec-ch-ua-mobile': '?0',             'sec-ch-ua-platform': '"Windows"',             'sec-fetch-dest': 'empty',             'sec-fetch-mode': 'cors',             'sec-fetch-site': 'same-origin',             'uifid': '3af258ad659545d9553f15cf32bb8a88df248991ebb865c20b5fa6f7dab6eb54e8d56c91612405705c23ef3169c754057359a8de37c8fd82c06b56053b9959d15d41fa3acf61ab30ac9b68a4d6560f5b522876f27befff69f38fe90a10431891784e6f60feb4a69d5369417c250b3fe1dc3cce6465b0755720c4b3ecd50009900a9692dd076221d8ed878bc103da6bf910d0cfd5b168c5fcac47ba2732e629e1',             'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36 Edg/135.0.0.0',             'Cookie': f'{cookie_str}'         }         self.key = str(input('请输入您想采集的内容： '))           def parse_start_url(self, page_number):               params = (             ('device_platform', 'webapp'),             ('aid', '6383'),             ('channel', 'channel_pc_web'),             ('search_channel', 'aweme_video_web'),             ('enable_history', '1'),             ('keyword', self.key),             ('search_source', 'normal_search'),             ('query_correct_type', '1'),             ('is_filter_search', '1'), #-----------------------------------             ('sort_type', '1'),             ('publish_time', '0'),             ('from_group_id', ''),             ('offset', page_number),             ('count', '10'),             ('need_filter_settings', '1'),             ('list_type', 'multi'),             ('update_version_code', '170400'),             ('pc_client_type', '1'),             ('pc_libra_divert', 'Windows'),             ('support_h265', '1'),             ('support_dash', '1'),             ('version_code', '170400'),             ('version_name', '17.4.0'),             ('cookie_enabled', 'true'),             ('screen_width', '1707'),             ('screen_height', '960'),             ('browser_language', 'zh-CN'),             ('browser_platform', 'Win32'),             ('browser_name', 'Edge'),             ('browser_version', '135.0.0.0'),             ('browser_online', 'true'),             ('engine_name', 'Blink'),             ('engine_version', '135.0.0.0'),             ('os_name', 'Windows'),             ('os_version', '10'),             ('cpu_core_num', '32'),             ('device_memory', '8'),             ('platform', 'PC'),             ('downlink', '10'),             ('effective_type', '4g'),             ('round_trip_time', '50'),             ('webid', '7474844642175010344'),             ('uifid',              '3af258ad659545d9553f15cf32bb8a88df248991ebb865c20b5fa6f7dab6eb54e8d56c91612405705c23ef3169c754057359a8de37c8fd82c06b56053b9959d15d41fa3acf61ab30ac9b68a4d6560f5b522876f27befff69f38fe90a10431891784e6f60feb4a69d5369417c250b3fe1dc3cce6465b0755720c4b3ecd50009900a9692dd076221d8ed878bc103da6bf910d0cfd5b168c5fcac47ba2732e629e1'),#)            ('msToken',           'yJ3OCyQmLkA3aYgRBx4gEVXtArb0A68nWhwJneWw-OOjdFLqZGeNcovnGg9P8_fAqKJGiYCZ761Fl8QV84CMjju1_LSCbefoH_DcswS2-3B0cUcRc6uX5SJdzU5NlvT3w5T3DcMnBlttd9yzIlgvj7F76SmQ0kY20KxpALs7e8UVBrReUA=='),              ('a_bogus',               'mJsRgtWjxd/VPdFbmcTGt-3lrAgANP8yKpTdWCPT9NFEGwtcE8PIpxSXJxuPm7WR4mBkioNH4d-AafdcQTX0Z99kqmpkSwUSe42IVUfoMqiIbtwkLrfhSL8zqwBSUbwil/nWiIW5Us0EIEI5INAmApIGC5zLQmg2SqZCp2Y9JDSWps6TVn/1Ca26'),          )           # 'msToken'和'a_bogus'动态变化，但是输入了一次，后面可以不管，没怎么做校验，我是直接给注释掉了。            response = requests.get(self.url, headers=self.headers, params=params,cookies=cookies).json()         # print(response)         self.save_data(response)           def save_data(self,response):         for data in response['data']:             name=data['aweme_info']['desc']             if not name:                 name=data['aweme_info']['aweme_id']             for char in '<>:"/\\|?*\n':                 name = name.replace(char, '_')             mp4_url=data['aweme_info']['video']['play_addr']['url_list'][-1]             print(name,mp4_url)             self.save_video(name,mp4_url)        def save_video(self,name,mp4_url):         video_data = requests.get(mp4_url, headers=self.headers).content         with open(self.os_path + name + '.mp4', 'wb') as f:             f.write(video_data)             #time.sleep(1)             print(f"视频 ：{name} - - - 下载完成",'\n\n')       if __name__ == '__main__':     spider = Spider()    page_number = 60 while True:     spider.parse_start_url(page_number)     page_number +=10 else:     print(f'已下载{page_number}个视频')       ##spider.parse_start_url(page_number)函数接口 page_number为视频个数，从0开始，每页+10， # 便于中途报错重新爬取，直接  FOR 循环输入大于page_number即可，是10的整数倍，这就是全部爬取了。

Kanchow

可以用这个好工具下载学习资料了

caivi

感谢分享，试下效果

xiaoniaoyou325

Kanchow 发表于 2025-4-10 22:16
可以用这个好工具下载学习资料了

真的可以吗？什么原理，任何平台都能用吗

jtui6999

感恩分享   

havealook

感谢分享！

hqyt888

大佬牛逼..

xyt210819

感谢大佬分享！

zjtzjt

感谢分享，搜搜好看的小姐姐