-
Notifications
You must be signed in to change notification settings - Fork 429
/
spider.py
2232 lines (1958 loc) · 108 KB
/
spider.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# -*- encoding: utf-8 -*-
"""
Author: Hmily
GitHub: https://github.com/ihmily
Date: 2023-07-15 23:15:00
Update: 2024-06-26 12:21:00
Copyright (c) 2023 by Hmily, All Rights Reserved.
Function: Get live stream data.
"""
import gzip
import hashlib
import random
import string
import time
import urllib.parse
import urllib.error
from urllib.request import Request
from typing import Union, Dict, Any, Tuple, List
import requests
import ssl
import re
import json
import execjs
import urllib.request
from utils import (
trace_error_decorator,
update_config, dict_to_cookie_str
)
from logger import script_path
import http.cookiejar
from web_rid import get_sec_user_id
no_proxy_handler = urllib.request.ProxyHandler({})
opener = urllib.request.build_opener(no_proxy_handler)
ssl_context = ssl.create_default_context()
ssl_context.check_hostname = False
ssl_context.verify_mode = ssl.CERT_NONE
def get_req(
url: str,
proxy_addr: Union[str, None] = None,
headers: Union[dict, None] = None,
data: Union[dict, bytes, None] = None,
json_data: Union[dict, list, None] = None,
timeout: int = 20,
abroad: bool = False,
content_conding: str = 'utf-8',
redirect_url: bool = False,
) -> Union[str, Any]:
if headers is None:
headers = {}
try:
if proxy_addr:
proxies = {
'http': proxy_addr,
'https': proxy_addr
}
if data or json_data:
response = requests.post(url, data=data, json=json_data, headers=headers, proxies=proxies,
timeout=timeout)
else:
response = requests.get(url, headers=headers, proxies=proxies, timeout=timeout)
if redirect_url:
return response.url
resp_str = response.text
else:
if data and not isinstance(data, bytes):
data = urllib.parse.urlencode(data).encode(content_conding)
if json_data and isinstance(json_data, (dict, list)):
data = json.dumps(json_data).encode(content_conding)
req = urllib.request.Request(url, data=data, headers=headers)
try:
if abroad:
response = urllib.request.urlopen(req, timeout=timeout)
else:
response = opener.open(req, timeout=timeout)
if redirect_url:
return response.url
content_encoding = response.info().get('Content-Encoding')
try:
if content_encoding == 'gzip':
with gzip.open(response, 'rt', encoding=content_conding) as gzipped:
resp_str = gzipped.read()
else:
resp_str = response.read().decode(content_conding)
finally:
response.close()
except urllib.error.HTTPError as e:
if e.code == 400:
resp_str = e.read().decode(content_conding)
else:
raise
except urllib.error.URLError as e:
print("URL Error:", e)
raise
except Exception as e:
print("An error occurred:", e)
raise
except Exception as e:
resp_str = str(e)
return resp_str
def get_params(url: str, params: str) -> Union[str, None]:
parsed_url = urllib.parse.urlparse(url)
query_params = urllib.parse.parse_qs(parsed_url.query)
if params in query_params:
return query_params[params][0]
def generate_random_string(length):
characters = string.ascii_uppercase + string.digits
random_string = ''.join(random.choices(characters, k=length))
return random_string
def jsonp_to_json(jsonp_str: str) -> Union[dict, None]:
pattern = r'(\w+)\((.*)\);?$'
match = re.search(pattern, jsonp_str)
if match:
_, json_str = match.groups()
json_obj = json.loads(json_str)
return json_obj
else:
raise Exception("No JSON data found in JSONP response.")
def replace_url(file_path: str, old: str, new: str) -> None:
with open(file_path, 'r', encoding='utf-8-sig') as f:
content = f.read()
if old in content:
with open(file_path, 'w', encoding='utf-8-sig') as f:
f.write(content.replace(old, new))
def get_play_url_list(m3u8: str, proxy: Union[str, None] = None, header: Union[dict, None] = None,
abroad: bool = False) -> List[str]:
resp = get_req(url=m3u8, proxy_addr=proxy, headers=header, abroad=abroad)
play_url_list = []
for i in resp.split('\n'):
if i.startswith('https://'):
play_url_list.append(i.strip())
if not play_url_list:
for i in resp.split('\n'):
if i.strip().endswith('m3u8'):
play_url_list.append(i.strip())
bandwidth_pattern = re.compile(r'BANDWIDTH=(\d+)')
bandwidth_list = bandwidth_pattern.findall(resp)
url_to_bandwidth = {url: int(bandwidth) for bandwidth, url in zip(bandwidth_list, play_url_list)}
play_url_list = sorted(play_url_list, key=lambda url: url_to_bandwidth[url], reverse=True)
return play_url_list
@trace_error_decorator
def get_douyin_app_stream_data(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Referer': 'https://live.douyin.com/',
'Cookie': 'ttwid=1%7CB1qls3GdnZhUov9o2NxOMxxYS2ff6OSvEWbv0ytbES4%7C1680522049%7C280d802d6d478e3e78d0c807f7c487e7ffec0ae4e5fdd6a0fe74c3c6af149511; my_rd=1; passport_csrf_token=3ab34460fa656183fccfb904b16ff742; passport_csrf_token_default=3ab34460fa656183fccfb904b16ff742; d_ticket=9f562383ac0547d0b561904513229d76c9c21; n_mh=hvnJEQ4Q5eiH74-84kTFUyv4VK8xtSrpRZG1AhCeFNI; store-region=cn-fj; store-region-src=uid; LOGIN_STATUS=1; __security_server_data_status=1; FORCE_LOGIN=%7B%22videoConsumedRemainSeconds%22%3A180%7D; pwa2=%223%7C0%7C3%7C0%22; download_guide=%223%2F20230729%2F0%22; volume_info=%7B%22isUserMute%22%3Afalse%2C%22isMute%22%3Afalse%2C%22volume%22%3A0.6%7D; strategyABtestKey=%221690824679.923%22; stream_recommend_feed_params=%22%7B%5C%22cookie_enabled%5C%22%3Atrue%2C%5C%22screen_width%5C%22%3A1536%2C%5C%22screen_height%5C%22%3A864%2C%5C%22browser_online%5C%22%3Atrue%2C%5C%22cpu_core_num%5C%22%3A8%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%3A150%7D%22; VIDEO_FILTER_MEMO_SELECT=%7B%22expireTime%22%3A1691443863751%2C%22type%22%3Anull%7D; home_can_add_dy_2_desktop=%221%22; __live_version__=%221.1.1.2169%22; device_web_cpu_core=8; device_web_memory_size=8; xgplayer_user_id=346045893336; csrf_session_id=2e00356b5cd8544d17a0e66484946f28; odin_tt=724eb4dd23bc6ffaed9a1571ac4c757ef597768a70c75fef695b95845b7ffcd8b1524278c2ac31c2587996d058e03414595f0a4e856c53bd0d5e5f56dc6d82e24004dc77773e6b83ced6f80f1bb70627; __ac_nonce=064caded4009deafd8b89; __ac_signature=_02B4Z6wo00f01HLUuwwAAIDBh6tRkVLvBQBy9L-AAHiHf7; ttcid=2e9619ebbb8449eaa3d5a42d8ce88ec835; webcast_leading_last_show_time=1691016922379; webcast_leading_total_show_times=1; webcast_local_quality=sd; live_can_add_dy_2_desktop=%221%22; msToken=1JDHnVPw_9yTvzIrwb7cQj8dCMNOoesXbA_IooV8cezcOdpe4pzusZE7NB7tZn9TBXPr0ylxmv-KMs5rqbNUBHP4P7VBFUu0ZAht_BEylqrLpzgt3y5ne_38hXDOX8o=; msToken=jV_yeN1IQKUd9PlNtpL7k5vthGKcHo0dEh_QPUQhr8G3cuYv-Jbb4NnIxGDmhVOkZOCSihNpA2kvYtHiTW25XNNX_yrsv5FN8O6zm3qmCIXcEe0LywLn7oBO2gITEeg=; tt_scid=mYfqpfbDjqXrIGJuQ7q-DlQJfUSG51qG.KUdzztuGP83OjuVLXnQHjsz-BRHRJu4e986'
}
if cookies:
headers['Cookie'] = cookies
def get_app_data():
room_id, sec_uid = get_sec_user_id(url=url, proxy_addr=proxy_addr)
api2 = f'https://webcast.amemv.com/webcast/room/reflow/info/?verifyFp=verify_lxj5zv70_7szNlAB7_pxNY_48Vh_ALKF_GA1Uf3yteoOY&type_id=0&live_id=1&room_id={room_id}&sec_user_id={sec_uid}&version_code=99.99.99&app_id=1128'
json_str2 = get_req(url=api2, proxy_addr=proxy_addr, headers=headers)
json_data2 = json.loads(json_str2)['data']
room_data2 = json_data2['room']
room_data2['anchor_name'] = room_data2['owner']['nickname']
return room_data2
try:
web_rid = url.split('?')[0].split('live.douyin.com/')
if len(web_rid) > 1:
web_rid = web_rid[1]
api = f'https://live.douyin.com/webcast/room/web/enter/?aid=6383&app_name=douyin_web&live_id=1&device_platform=web&language=zh-CN&browser_language=zh-CN&browser_platform=Win32&browser_name=Chrome&browser_version=116.0.0.0&web_rid={web_rid}'
json_str = get_req(url=api, proxy_addr=proxy_addr, headers=headers)
json_data = json.loads(json_str)['data']
room_data = json_data['data'][0]
room_data['anchor_name'] = json_data['user']['nickname']
else:
room_data = get_app_data()
if 'stream_url' not in room_data:
raise RuntimeError('该直播类型或玩法电脑端暂未支持，请使用app端分享链接进行录制')
live_core_sdk_data = room_data['stream_url']['live_core_sdk_data']
if room_data['status'] == 2:
if live_core_sdk_data:
json_str = live_core_sdk_data['pull_data']['stream_data']
json_data = json.loads(json_str)
if 'origin' in json_data['data']:
origin_url_list = json_data['data']['origin']['main']
origin_m3u8 = {'ORIGIN': origin_url_list["hls"]}
origin_flv = {'ORIGIN': origin_url_list["flv"]}
hls_pull_url_map = room_data['stream_url']['hls_pull_url_map']
flv_pull_url = room_data['stream_url']['flv_pull_url']
room_data['stream_url']['hls_pull_url_map'] = {**origin_m3u8, **hls_pull_url_map}
room_data['stream_url']['flv_pull_url'] = {**origin_flv, **flv_pull_url}
except Exception as e:
print(f"错误信息: {e} 发生错误的行数: {e.__traceback__.tb_lineno}")
room_data = {'anchor_name': ""}
return room_data
@trace_error_decorator
def get_douyin_stream_data(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Referer': 'https://live.douyin.com/',
'Cookie': 'ttwid=1%7CB1qls3GdnZhUov9o2NxOMxxYS2ff6OSvEWbv0ytbES4%7C1680522049%7C280d802d6d478e3e78d0c807f7c487e7ffec0ae4e5fdd6a0fe74c3c6af149511; my_rd=1; passport_csrf_token=3ab34460fa656183fccfb904b16ff742; passport_csrf_token_default=3ab34460fa656183fccfb904b16ff742; d_ticket=9f562383ac0547d0b561904513229d76c9c21; n_mh=hvnJEQ4Q5eiH74-84kTFUyv4VK8xtSrpRZG1AhCeFNI; store-region=cn-fj; store-region-src=uid; LOGIN_STATUS=1; __security_server_data_status=1; FORCE_LOGIN=%7B%22videoConsumedRemainSeconds%22%3A180%7D; pwa2=%223%7C0%7C3%7C0%22; download_guide=%223%2F20230729%2F0%22; volume_info=%7B%22isUserMute%22%3Afalse%2C%22isMute%22%3Afalse%2C%22volume%22%3A0.6%7D; strategyABtestKey=%221690824679.923%22; stream_recommend_feed_params=%22%7B%5C%22cookie_enabled%5C%22%3Atrue%2C%5C%22screen_width%5C%22%3A1536%2C%5C%22screen_height%5C%22%3A864%2C%5C%22browser_online%5C%22%3Atrue%2C%5C%22cpu_core_num%5C%22%3A8%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%3A150%7D%22; VIDEO_FILTER_MEMO_SELECT=%7B%22expireTime%22%3A1691443863751%2C%22type%22%3Anull%7D; home_can_add_dy_2_desktop=%221%22; __live_version__=%221.1.1.2169%22; device_web_cpu_core=8; device_web_memory_size=8; xgplayer_user_id=346045893336; csrf_session_id=2e00356b5cd8544d17a0e66484946f28; odin_tt=724eb4dd23bc6ffaed9a1571ac4c757ef597768a70c75fef695b95845b7ffcd8b1524278c2ac31c2587996d058e03414595f0a4e856c53bd0d5e5f56dc6d82e24004dc77773e6b83ced6f80f1bb70627; __ac_nonce=064caded4009deafd8b89; __ac_signature=_02B4Z6wo00f01HLUuwwAAIDBh6tRkVLvBQBy9L-AAHiHf7; ttcid=2e9619ebbb8449eaa3d5a42d8ce88ec835; webcast_leading_last_show_time=1691016922379; webcast_leading_total_show_times=1; webcast_local_quality=sd; live_can_add_dy_2_desktop=%221%22; msToken=1JDHnVPw_9yTvzIrwb7cQj8dCMNOoesXbA_IooV8cezcOdpe4pzusZE7NB7tZn9TBXPr0ylxmv-KMs5rqbNUBHP4P7VBFUu0ZAht_BEylqrLpzgt3y5ne_38hXDOX8o=; msToken=jV_yeN1IQKUd9PlNtpL7k5vthGKcHo0dEh_QPUQhr8G3cuYv-Jbb4NnIxGDmhVOkZOCSihNpA2kvYtHiTW25XNNX_yrsv5FN8O6zm3qmCIXcEe0LywLn7oBO2gITEeg=; tt_scid=mYfqpfbDjqXrIGJuQ7q-DlQJfUSG51qG.KUdzztuGP83OjuVLXnQHjsz-BRHRJu4e986'
}
if cookies:
headers['Cookie'] = cookies
try:
origin_url_list = None
html_str = get_req(url=url, proxy_addr=proxy_addr, headers=headers)
match_json_str = re.search(r'(\{\\"state\\":.*?)]\\n"]\)', html_str)
if not match_json_str:
match_json_str = re.search(r'(\{\\"common\\":.*?)]\\n"]\)</script><div hidden', html_str)
json_str = match_json_str.group(1)
cleaned_string = json_str.replace('\\', '').replace(r'u0026', r'&')
room_store = re.search('"roomStore":(.*?),"linkmicStore"', cleaned_string, re.S).group(1)
anchor_name = re.search('"nickname":"(.*?)","avatar_thumb', room_store, re.S).group(1)
room_store = room_store.split(',"has_commerce_goods"')[0] + '}}}'
json_data = json.loads(room_store)['roomInfo']['room']
json_data['anchor_name'] = anchor_name
if 'status' in json_data and json_data['status'] == 4:
return json_data
match_json_str2 = re.search(r'"(\{\\"common\\":.*?)"]\)</script><script nonce=', html_str)
if match_json_str2:
json_str = match_json_str2.group(1).replace('\\', '').replace('"{', '{').replace('}"', '}').replace('u0026', '&')
json_data2 = json.loads(json_str)
if 'origin' in json_data2['data']:
origin_url_list = json_data2['data']['origin']['main']
else:
match_json_str3 = re.search('"origin":\{"main":(.*?),"dash"',html_str.replace('\\', '').replace('u0026', '&'), re.S)
if match_json_str3:
origin_url_list = json.loads(match_json_str3.group(1) + '}')
if origin_url_list:
origin_m3u8 = {'ORIGIN': origin_url_list["hls"]}
origin_flv = {'ORIGIN': origin_url_list["flv"]}
hls_pull_url_map = json_data['stream_url']['hls_pull_url_map']
flv_pull_url = json_data['stream_url']['flv_pull_url']
json_data['stream_url']['hls_pull_url_map'] = {**origin_m3u8, **hls_pull_url_map}
json_data['stream_url']['flv_pull_url'] = {**origin_flv, **flv_pull_url}
return json_data
except Exception as e:
print(f'第一次获取数据失败：{url} 准备切换解析方法{e}')
return get_douyin_app_stream_data(url=url, proxy_addr=proxy_addr, cookies=cookies)
@trace_error_decorator
def get_tiktok_stream_data(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.79',
'Cookie': 'ttwid=1%7CM-rF193sJugKuNz2RGNt-rh6pAAR9IMceUSzlDnPCNI%7C1683274418%7Cf726d4947f2fc37fecc7aeb0cdaee52892244d04efde6f8a8edd2bb168263269; tiktok_webapp_theme=light; tt_chain_token=VWkygAWDlm1cFg/k8whmOg==; passport_csrf_token=6e422c5a7991f8cec7033a8082921510; passport_csrf_token_default=6e422c5a7991f8cec7033a8082921510; d_ticket=f8c267d4af4523c97be1ccb355e9991e2ae06; odin_tt=320b5f386cdc23f347be018e588873db7f7aea4ea5d1813681c3fbc018ea025dde957b94f74146dbc0e3612426b865ccb95ec8abe4ee36cca65f15dbffec0deff7b0e69e8ea536d46e0f82a4fc37d211; cmpl_token=AgQQAPNSF-RO0rT04baWtZ0T_jUjl4fVP4PZYM2QPw; uid_tt=319b558dbba684bb1557206c92089cd113a875526a89aee30595925d804b81c7; uid_tt_ss=319b558dbba684bb1557206c92089cd113a875526a89aee30595925d804b81c7; sid_tt=ad5e736f4bedb2f6d42ccd849e706b1d; sessionid=ad5e736f4bedb2f6d42ccd849e706b1d; sessionid_ss=ad5e736f4bedb2f6d42ccd849e706b1d; store-idc=useast5; store-country-code=us; store-country-code-src=uid; tt-target-idc=useast5; tt-target-idc-sign=qXNk0bb1pDQ0FbCNF120Pl9WWMLZg9Edv5PkfyCbS4lIk5ieW5tfLP7XWROnN0mEaSlc5hg6Oji1pF-yz_3ZXnUiNMrA9wNMPvI6D9IFKKVmq555aQzwPIGHv0aQC5dNRgKo5Z5LBkgxUMWEojTKclq2_L8lBciw0IGdhFm_XyVJtbqbBKKgybGDLzK8ZyxF4Jl_cYRXaDlshZjc38JdS6wruDueRSHe7YvNbjxCnApEFUv-OwJANSPU_4rvcqpVhq3JI2VCCfw-cs_4MFIPCDOKisk5EhAo2JlHh3VF7_CLuv80FXg_7ZqQ2pJeMOog294rqxwbbQhl3ATvjQV_JsWyUsMd9zwqecpylrPvtySI2u1qfoggx1owLrrUynee1R48QlanLQnTNW_z1WpmZBgVJqgEGLwFoVOmRzJuFFNj8vIqdjM2nDSdWqX8_wX3wplohkzkPSFPfZgjzGnQX28krhgTytLt7BXYty5dpfGtsdb11WOFHM6MZ9R9uLVB; sid_guard=ad5e736f4bedb2f6d42ccd849e706b1d%7C1690990657%7C15525213%7CMon%2C+29-Jan-2024+08%3A11%3A10+GMT; sid_ucp_v1=1.0.0-KGM3YzgwYjZhODgyYWI1NjIwNTA0NjBmOWUxMGRhMjIzYTI2YjMxNDUKGAiqiJ30keKD5WQQwfCppgYYsws4AkDsBxAEGgd1c2Vhc3Q1IiBhZDVlNzM2ZjRiZWRiMmY2ZDQyY2NkODQ5ZTcwNmIxZA; ssid_ucp_v1=1.0.0-KGM3YzgwYjZhODgyYWI1NjIwNTA0NjBmOWUxMGRhMjIzYTI2YjMxNDUKGAiqiJ30keKD5WQQwfCppgYYsws4AkDsBxAEGgd1c2Vhc3Q1IiBhZDVlNzM2ZjRiZWRiMmY2ZDQyY2NkODQ5ZTcwNmIxZA; tt_csrf_token=dD0EIH8q-pe3qDQsCyyD1jLN6KizJDRjOEyk; __tea_cache_tokens_1988={%22_type_%22:%22default%22%2C%22user_unique_id%22:%227229608516049831425%22%2C%22timestamp%22:1683274422659}; ttwid=1%7CM-rF193sJugKuNz2RGNt-rh6pAAR9IMceUSzlDnPCNI%7C1694002151%7Cd89b77afc809b1a610661a9d1c2784d80ebef9efdd166f06de0d28e27f7e4efe; msToken=KfJAVZ7r9D_QVeQlYAUZzDFbc1Yx-nZz6GF33eOxgd8KlqvTg1lF9bMXW7gFV-qW4MCgUwnBIhbiwU9kdaSpgHJCk-PABsHCtTO5J3qC4oCTsrXQ1_E0XtbqiE4OVLZ_jdF1EYWgKNPT2SnwGkQ=; msToken=KfJAVZ7r9D_QVeQlYAUZzDFbc1Yx-nZz6GF33eOxgd8KlqvTg1lF9bMXW7gFV-qW4MCgUwnBIhbiwU9kdaSpgHJCk-PABsHCtTO5J3qC4oCTsrXQ1_E0XtbqiE4OVLZ_jdF1EYWgKNPT2SnwGkQ='
}
if cookies:
headers['Cookie'] = cookies
for i in range(3):
html_str = get_req(url=url, proxy_addr=proxy_addr, headers=headers, abroad=True)
time.sleep(1)
if 'We regret to inform you that we have discontinued operating TikTok' in html_str:
msg = re.search('<p>\n\s+(We regret to inform you that we have discontinu.*?)\.\n\s+</p>', html_str)
raise ConnectionError(
f'你的代理节点地区网络被禁止访问TikTok，请切换其他地区的节点访问 {msg.group(1) if msg else ""}')
if 'UNEXPECTED_EOF_WHILE_READING' not in html_str:
try:
json_str = re.findall(
'<script id="SIGI_STATE" type="application/json">(.*?)</script>',
html_str, re.S)[0]
except Exception:
raise ConnectionError("请检查你的网络是否可以正常访问TikTok网站")
json_data = json.loads(json_str)
return json_data
@trace_error_decorator
def get_kuaishou_stream_data(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
}
if cookies:
headers['Cookie'] = cookies
try:
html_str = get_req(url=url, proxy_addr=proxy_addr, headers=headers)
except Exception as e:
print(f"Failed to fetch data from {url}.{e}")
return {"type": 1, "is_live": False}
try:
json_str = re.search('<script>window.__INITIAL_STATE__=(.*?);\(function\(\)\{var s;', html_str).group(1)
play_list = re.findall('(\{"liveStream".*?),"gameInfo', json_str)[0] + "}"
play_list = json.loads(play_list)
except (AttributeError, IndexError, json.JSONDecodeError) as e:
print(f"Failed to parse JSON data from {url}. Error: {e}")
return {"type": 1, "is_live": False}
result = {"type": 2, "is_live": False}
if 'errorType' in play_list or 'liveStream' not in play_list:
error_msg = play_list.get('errorType', {}).get('title', '') + play_list.get('errorType', {}).get('content', '')
print(f'失败地址：{url} 错误信息: {error_msg}')
return result
if not play_list.get('liveStream'):
print("IP banned. Please change device or network.")
return result
anchor_name = play_list['author'].get('name', '')
result.update({"anchor_name": anchor_name})
if play_list['liveStream'].get("playUrls"):
play_url_list = play_list['liveStream']['playUrls'][0]['adaptationSet']['representation']
result.update({"flv_url_list": play_url_list, "is_live": True})
return result
@trace_error_decorator
def get_kuaishou_stream_data2(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Linux; Android 11; SAMSUNG SM-G973U) AppleWebKit/537.36 (KHTML, like Gecko) SamsungBrowser/14.2 Chrome/87.0.4280.141 Mobile Safari/537.36',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Referer': "https://www.kuaishou.com/short-video/3x224rwabjmuc9y?fid=1712760877&cc=share_copylink&followRefer=151&shareMethod=TOKEN&docId=9&kpn=KUAISHOU&subBiz=BROWSE_SLIDE_PHOTO&photoId=3x224rwabjmuc9y&shareId=17144298796566&shareToken=X-6FTMeYTsY97qYL&shareResourceType=PHOTO_OTHER&userId=3xtnuitaz2982eg&shareType=1&et=1_i/2000048330179867715_h3052&shareMode=APP&originShareId=17144298796566&appType=21&shareObjectId=5230086626478274600&shareUrlOpened=0×tamp=1663833792288&utm_source=app_share&utm_medium=app_share&utm_campaign=app_share&location=app_share",
'content-type': 'application/json',
'Cookie': 'did=web_e988652e11b545469633396abe85a89f; didv=1796004001000',
}
if cookies:
headers['Cookie'] = cookies
try:
eid = url.split('/u/')[1].strip()
data = {"source": 5, "eid": eid, "shareMethod": "card", "clientType": "WEB_OUTSIDE_SHARE_H5"}
app_api = 'https://livev.m.chenzhongtech.com/rest/k/live/byUser?kpn=GAME_ZONE&captchaToken='
json_str = get_req(url=app_api, proxy_addr=proxy_addr, headers=headers, data=data)
json_data = json.loads(json_str)
live_stream = json_data['liveStream']
anchor_name = live_stream['user']['user_name']
result = {
"type": 2,
"anchor_name": anchor_name,
"is_live": False,
}
live_status = live_stream['living']
if live_status:
result['is_live'] = True
backup_m3u8_url = live_stream['hlsPlayUrl']
backup_flv_url = live_stream['playUrls'][0]['url']
if 'multiResolutionHlsPlayUrls' in live_stream:
m3u8_url_list = live_stream['multiResolutionHlsPlayUrls'][0]['urls']
result['m3u8_url_list'] = m3u8_url_list
if 'multiResolutionPlayUrls' in live_stream:
flv_url_list = live_stream['multiResolutionPlayUrls'][0]['urls']
result['flv_url_list'] = flv_url_list
result['backup'] = {'m3u8_url': backup_m3u8_url, 'flv_url': backup_flv_url}
if result['anchor_name']:
return result
except Exception as e:
print(f'{e},失败地址：{url} 准备切换为备用方案重新解析 ')
return get_kuaishou_stream_data(url, cookies=cookies, proxy_addr=proxy_addr)
@trace_error_decorator
def get_huya_stream_data(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:123.0) Gecko/20100101 Firefox/123.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Cookie': 'huya_ua=webh5&0.1.0&websocket; game_did=zXyXVqV1NF4ZeNWg7QaOFbpIEWqcsrxkoVy; alphaValue=0.80; isInLiveRoom=; guid=0a7df378828609654d01a205a305fb52; __yamid_tt1=0.8936157401010706; __yamid_new=CA715E8BC9400001E5A313E028F618DE; udb_guiddata=4657813d32ce43d381ea8ff8d416a3c2; udb_deviceid=w_756598227007868928; sdid=0UnHUgv0_qmfD4KAKlwzhqQB32nywGZJYLZl_9RLv0Lbi5CGYYNiBGLrvNZVszz4FEo_unffNsxk9BdvXKO_PkvC5cOwCJ13goOiNYGClLirWVkn9LtfFJw_Qo4kgKr8OZHDqNnuwg612sGyflFn1draukOt03gk2m3pwGbiKsB143MJhMxcI458jIjiX0MYq; Hm_lvt_51700b6c722f5bb4cf39906a596ea41f=1708583696; SoundValue=0.50; sdidtest=0UnHUgv0_qmfD4KAKlwzhqQB32nywGZJYLZl_9RLv0Lbi5CGYYNiBGLrvNZVszz4FEo_unffNsxk9BdvXKO_PkvC5cOwCJ13goOiNYGClLirWVkn9LtfFJw_Qo4kgKr8OZHDqNnuwg612sGyflFn1draukOt03gk2m3pwGbiKsB143MJhMxcI458jIjiX0MYq; sdidshorttest=test; __yasmid=0.8936157401010706; _yasids=__rootsid^%^3DCAA3838C53600001F4EE863017406250; huyawap_rep_cnt=4; udb_passdata=3; huya_web_rep_cnt=89; huya_flash_rep_cnt=20; Hm_lpvt_51700b6c722f5bb4cf39906a596ea41f=1709548534; _rep_cnt=3; PHPSESSID=r0klm0vccf08q1das65bnd8co1; guid=0a7df378828609654d01a205a305fb52; huya_hd_rep_cnt=8',
}
if cookies:
headers['Cookie'] = cookies
html_str = get_req(url=url, proxy_addr=proxy_addr, headers=headers)
json_str = re.findall('stream: (\{"data".*?),"iWebDefaultBitRate"', html_str)[0]
json_data = json.loads(json_str + '}')
return json_data
def md5(data):
return hashlib.md5(data.encode('utf-8')).hexdigest()
def get_token_js(rid: str, did: str, proxy_addr: Union[str, None] = None) -> Union[list, Dict[str, Any]]:
"""
通过PC网页端的接口获取完整直播源。
:param proxy_addr:
:param did:
:param rid:
:param cdn: 主线路ws-h5、备用线路tct-h5
:param rate: 1流畅；2高清；3超清；4蓝光4M；0蓝光8M或10M
"""
url = f'https://www.douyu.com/{rid}'
html_str = get_req(url=url, proxy_addr=proxy_addr)
result = re.search(r'(vdwdae325w_64we[\s\S]*function ub98484234[\s\S]*?)function', html_str).group(1)
func_ub9 = re.sub(r'eval.*?;}', 'strc;}', result)
js = execjs.compile(func_ub9)
res = js.call('ub98484234')
t10 = str(int(time.time()))
v = re.search(r'v=(\d+)', res).group(1)
rb = md5(rid + did + t10 + v)
func_sign = re.sub(r'return rt;}\);?', 'return rt;}', res)
func_sign = func_sign.replace('(function (', 'function sign(')
func_sign = func_sign.replace('CryptoJS.MD5(cb).toString()', '"' + rb + '"')
js = execjs.compile(func_sign)
params = js.call('sign', rid, did, t10)
params_list = re.findall('=(.*?)(?=&|$)', params)
return params_list
@trace_error_decorator
def get_douyu_info_data(url: str, proxy_addr: Union[str, None] = None) -> Dict[str, Any]:
match_rid = re.search('rid=(.*?)(?=&|$)', url)
if match_rid:
rid = match_rid.group(1)
else:
rid = re.search('douyu.com/(.*?)(?=\?|$)', url).group(1)
headers = {
'referer': 'https://www.douyu.com/7644887?dyshid=0-40f7c4a06aae9dc5bede316000031701&dyshci=181',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36 Edg/121.0.0.0',
}
url2 = f'https://www.douyu.com/betard/{rid}'
json_str = get_req(url=url2, proxy_addr=proxy_addr, headers=headers)
json_data = json.loads(json_str)
result = {
"anchor_name": json_data['room']['nickname'],
"is_live": False
}
if json_data['room']['videoLoop'] == 0 and json_data['room']['show_status'] == 1:
result["is_live"] = True
result["room_id"] = json_data['room']['room_id']
return result
@trace_error_decorator
def get_douyu_stream_data(rid: str, rate: str = '-1', proxy_addr: Union[str, None] = None,
cookies: Union[str, None] = None) -> Dict[str, Any]:
did = '10000000000000000000000000003306'
params_list = get_token_js(rid, did, proxy_addr=proxy_addr)
headers = {
'User-Agent': 'Mozilla/5.0 (Linux; Android 11; SAMSUNG SM-G973U) AppleWebKit/537.36 (KHTML, like Gecko) SamsungBrowser/14.2 Chrome/87.0.4280.141 Mobile Safari/537.36',
'Referer': 'https://m.douyu.com/3125893?rid=3125893&dyshid=0-96003918aa5365bc6dcb4933000316p1&dyshci=181',
'Cookie': 'dy_did=413b835d2ae00270f0c69f6400031601; acf_did=413b835d2ae00270f0c69f6400031601; Hm_lvt_e99aee90ec1b2106afe7ec3b199020a7=1692068308,1694003758; m_did=96003918aa5365bc6dcb4933000316p1; dy_teen_mode=%7B%22uid%22%3A%22472647365%22%2C%22status%22%3A0%2C%22birthday%22%3A%22%22%2C%22password%22%3A%22%22%7D; PHPSESSID=td59qi2fu2gepngb8mlehbeme3; acf_auth=94fc9s%2FeNj%2BKlpU%2Br8tZC3Jo9sZ0wz9ClcHQ1akL2Nhb6ZyCmfjVWSlR3LFFPuePWHRAMo0dt9vPSCoezkFPOeNy4mYcdVOM1a8CbW0ZAee4ipyNB%2Bflr58; dy_auth=bec5yzM8bUFYe%2FnVAjmUAljyrsX%2FcwRW%2FyMHaoArYb5qi8FS9tWR%2B96iCzSnmAryLOjB3Qbeu%2BBD42clnI7CR9vNAo9mva5HyyL41HGsbksx1tEYFOEwxSI; wan_auth37wan=5fd69ed5b27fGM%2FGoswWwDo%2BL%2FRMtnEa4Ix9a%2FsH26qF0sR4iddKMqfnPIhgfHZUqkAk%2FA1d8TX%2B6F7SNp7l6buIxAVf3t9YxmSso8bvHY0%2Fa6RUiv8; acf_uid=472647365; acf_username=472647365; acf_nickname=%E7%94%A8%E6%88%B776576662; acf_own_room=0; acf_groupid=1; acf_phonestatus=1; acf_avatar=https%3A%2F%2Fapic.douyucdn.cn%2Fupload%2Favatar%2Fdefault%2F24_; acf_ct=0; acf_ltkid=25305099; acf_biz=1; acf_stk=90754f8ed18f0c24; Hm_lpvt_e99aee90ec1b2106afe7ec3b199020a7=1694003778'
}
if cookies:
headers['Cookie'] = cookies
data = {
'v': params_list[0],
'did': params_list[1],
'tt': params_list[2],
'sign': params_list[3], # 10分钟有效期
'ver': '22011191',
'rid': rid,
'rate': rate, # 0蓝光、3超清、2高清、-1默认
}
# app_api = 'https://m.douyu.com/hgapi/livenc/room/getStreamUrl'
app_api = f'https://www.douyu.com/lapi/live/getH5Play/{rid}'
json_str = get_req(url=app_api, proxy_addr=proxy_addr, headers=headers, data=data)
json_data = json.loads(json_str)
return json_data
@trace_error_decorator
def get_yy_stream_data(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Referer': 'https://www.yy.com/',
'Cookie': 'hd_newui=0.2103068903976506; hdjs_session_id=0.4929014850884579; hdjs_session_time=1694004002636; hiido_ui=0.923076230899782'
}
if cookies:
headers['Cookie'] = cookies
html_str = get_req(url=url, proxy_addr=proxy_addr, headers=headers)
anchor_name = re.search('nick: "(.*?)",\n\s+logo', html_str).group(1)
cid = re.search('sid : "(.*?)",\n\s+ssid', html_str, re.S).group(1)
data = '{"head":{"seq":1701869217590,"appidstr":"0","bidstr":"121","cidstr":"' + cid + '","sidstr":"' + cid + '","uid64":0,"client_type":108,"client_ver":"5.17.0","stream_sys_ver":1,"app":"yylive_web","playersdk_ver":"5.17.0","thundersdk_ver":"0","streamsdk_ver":"5.17.0"},"client_attribute":{"client":"web","model":"web0","cpu":"","graphics_card":"","os":"chrome","osversion":"0","vsdk_version":"","app_identify":"","app_version":"","business":"","width":"1920","height":"1080","scale":"","client_type":8,"h265":0},"avp_parameter":{"version":1,"client_type":8,"service_type":0,"imsi":0,"send_time":1701869217,"line_seq":-1,"gear":4,"ssl":1,"stream_format":0}}'
data_bytes = data.encode('utf-8')
url2 = f'https://stream-manager.yy.com/v3/channel/streams?uid=0&cid={cid}&sid={cid}&appid=0&sequence=1701869217590&encode=json'
json_str = get_req(url=url2, data=data_bytes, proxy_addr=proxy_addr, headers=headers)
json_data = json.loads(json_str)
json_data['anchor_name'] = anchor_name
return json_data
@trace_error_decorator
def get_bilibili_stream_data(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:127.0) Gecko/20100101 Firefox/127.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
}
if cookies:
headers['Cookie'] = cookies
def get_data_from_api(link: str) -> Dict[str, Any]:
room_id = link.split('?')[0].rsplit('/', maxsplit=1)[1]
api = f'https://api.live.bilibili.com/xlive/web-room/v2/index/getRoomPlayInfo?room_id={room_id}&no_playurl=0&mask=1&qn=0&platform=web&protocol=0,1&format=0,1,2&codec=0,1,2&dolby=5&panorama=1'
json_str = get_req(url=api, proxy_addr=proxy_addr, headers=headers)
return json.loads(json_str)
try:
html_str = get_req(url=url, proxy_addr=proxy_addr, headers=headers)
json_str = re.search('<script>window.__NEPTUNE_IS_MY_WAIFU__=(.*?)</script><script>', html_str, re.S)
if json_str:
json_str = json_str.group(1)
json_data = json.loads(json_str)
json_data['anchor_name'] = json_data['roomInfoRes']['data']['anchor_info']['base_info']['uname']
json_data['stream_data'] = json_data['roomInitRes']['data']
else:
json_data = get_data_from_api(url)
json_data['anchor_name'] = f"房间号{json_data['data']['room_id']}的直播"
json_data['stream_data'] = json_data['data']
return json_data
except Exception as e:
print(e)
return {"anchor_name": '', "is_live": False}
@trace_error_decorator
def get_xhs_stream_url(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:122.0) Gecko/20100101 Firefox/122.0',
'Accept': 'application/json, text/plain, */*',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Referer': 'https://www.redelight.cn/hina/livestream/569077534207413574/1707413727088?share_source=&share_source_id=null&source=share_out_of_app&host_id=58bafe4282ec39085a56ece9&xhsshare=WeixinSession&appuid=5f3f478a00000000010005b3&apptime=1707413727',
}
if cookies:
headers['Cookie'] = cookies
if 'xhslink.com' in url:
url = get_req(url, proxy_addr=proxy_addr, headers=headers, redirect_url=True)
appuid = re.search('host_id=(.*?)(?=&|$)', url).group(1)
else:
appuid = re.search('appuid=(.*?)(?=&|$)', url).group(1)
room_id = re.search('/livestream/(.*?)(?=/|\?)', url).group(1)
app_api = f'https://www.xiaohongshu.com/api/sns/red/live/app/v1/ecology/outside/share_info?room_id={room_id}'
# app_api = f'https://www.redelight.cn/api/sns/red/live/app/v1/ecology/outside/share_info?room_id={room_id}'
json_str = get_req(url=app_api, proxy_addr=proxy_addr, headers=headers)
json_data = json.loads(json_str)
anchor_name = json_data['data']['host_info']['nickname']
live_status = json_data['data']['room']['status']
result = {
"anchor_name": anchor_name,
"is_live": False,
}
# 这个判断不准确，无论是否在直播status都为0,暂无法判断
if live_status == 0:
flv_url = f'http://live-play.xhscdn.com/live/{room_id}.flv?uid={appuid}'
result['flv_url'] = flv_url
result['is_live'] = True
result['record_url'] = flv_url
return result
@trace_error_decorator
def get_bigo_stream_url(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/119.0',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Referer': 'https://www.bigo.tv/',
}
if cookies:
headers['Cookie'] = cookies
room_id = re.search('www.bigo.tv/cn/(\w+)', url).group(1)
data = {'siteId': room_id} # roomId
url2 = 'https://ta.bigo.tv/official_website/studio/getInternalStudioInfo'
json_str = get_req(url=url2, proxy_addr=proxy_addr, headers=headers, data=data)
json_data = json.loads(json_str)
anchor_name = json_data['data']['nick_name']
live_status = json_data['data']['alive']
result = {
"anchor_name": anchor_name,
"is_live": False,
}
if live_status == 1:
m3u8_url = json_data['data']['hls_src']
result['m3u8_url'] = m3u8_url
result['is_live'] = True
result['record_url'] = m3u8_url
elif result['anchor_name'] == '':
html_str = get_req(url=url, proxy_addr=proxy_addr, headers=headers)
result['anchor_name'] = re.search('<title>(.*?)</title>', html_str, re.S).group(1)
return result
@trace_error_decorator
def get_blued_stream_url(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Linux; Android 11; SAMSUNG SM-G973U) AppleWebKit/537.36 (KHTML, like Gecko) SamsungBrowser/14.2 Chrome/87.0.4280.141 Mobile Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
}
if cookies:
headers['Cookie'] = cookies
html_str = get_req(url=url, proxy_addr=proxy_addr, headers=headers)
json_str = re.search('decodeURIComponent\(\"(.*?)\"\)\),window\.Promise', html_str, re.S).group(1)
json_str = urllib.parse.unquote(json_str)
json_data = json.loads(json_str)
anchor_name = json_data['userInfo']['name']
live_status = json_data['userInfo']['onLive']
result = {
"anchor_name": anchor_name,
"is_live": False,
}
if live_status:
m3u8_url = "http:" + json_data['liveInfo']['liveUrl']
result['m3u8_url'] = m3u8_url
result['is_live'] = True
result['record_url'] = m3u8_url
return result
@trace_error_decorator
def login_afreecatv(username: str, password: str, proxy_addr: Union[str, None] = None) -> Union[str, None]:
if len(username) < 6 or len(password) < 10:
raise RuntimeError('AfreecaTV登录失败！请在config.ini配置文件中填写正确的AfreecaTV平台的账号和密码')
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:122.0) Gecko/20100101 Firefox/122.0',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Referer': 'https://login.afreecatv.com/afreeca/login.php?szFrom=full&request_uri=https%3A%2F%2Fwww.afreecatv.com%2F',
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
}
data = {
'szWork': 'login',
'szType': 'json',
'szUid': username,
'szPassword': password,
'isSaveId': 'true',
'szScriptVar': 'oLoginRet',
'szAction': '',
'isLoginRetain': 'Y',
}
url = 'https://login.afreecatv.com/app/LoginAction.php?callback=jQuery17208926278503069585_1707311376418'
try:
if proxy_addr:
proxies = {
'http': proxy_addr,
'https': proxy_addr
}
response = requests.post(url, data=data, headers=headers, proxies=proxies, timeout=20)
cookie_dict = response.cookies.get_dict()
else:
data = urllib.parse.urlencode(data).encode('utf-8')
cookie_jar = http.cookiejar.CookieJar()
login_opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cookie_jar))
req = Request(url, data=data, headers=headers)
_ = login_opener.open(req, timeout=20)
cookie_dict = {cookie.name: cookie.value for cookie in cookie_jar}
cookie = dict_to_cookie_str(cookie_dict)
return cookie
except Exception:
raise Exception('AfreecaTV登录失败,请检查配置文件中的账号密码是否正确')
@trace_error_decorator
def get_afreecatv_cdn_url(broad_no: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/119.0',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Referer': 'https://play.afreecatv.com/oul282/249469582',
'Content-Type': 'application/x-www-form-urlencoded',
}
if cookies:
headers['Cookie'] = cookies
params = {
'return_type': 'gcp_cdn',
'use_cors': 'false',
'cors_origin_url': 'play.afreecatv.com',
'broad_key': f'{broad_no}-common-master-hls',
'time': '8361.086329376785',
}
url2 = 'http://livestream-manager.afreecatv.com/broad_stream_assign.html?' + urllib.parse.urlencode(params)
json_str = get_req(url=url2, proxy_addr=proxy_addr, headers=headers, abroad=True)
json_data = json.loads(json_str)
return json_data
@trace_error_decorator
def get_afreecatv_tk(url: str, rtype: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Union[str, tuple, None]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:122.0) Gecko/20100101 Firefox/122.0',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Referer': 'https://play.afreecatv.com/secretx/250989857',
'Content-Type': 'application/x-www-form-urlencoded',
}
if cookies:
headers['Cookie'] = cookies
split_url = url.split('/')
bj_id = split_url[3] if len(split_url) < 6 else split_url[5]
room_password = get_params(url, "pwd")
if not room_password:
room_password = ''
data = {
'bid': bj_id,
'bno': '',
'type': rtype,
'pwd': room_password,
'player_type': 'html5',
'stream_type': 'common',
'quality': 'master',
'mode': 'landing',
'from_api': '0',
}
url2 = f'https://live.afreecatv.com/afreeca/player_live_api.php?bjid={bj_id}'
json_str = get_req(url=url2, proxy_addr=proxy_addr, headers=headers, data=data, abroad=True)
json_data = json.loads(json_str)
if rtype == 'aid':
token = json_data["CHANNEL"]["AID"]
return token
else:
bj_name = json_data['CHANNEL']['BJNICK']
bj_id = json_data['CHANNEL']['BJID']
return f"{bj_name}-{bj_id}", json_data['CHANNEL']['BNO']
@trace_error_decorator
def get_afreecatv_stream_data(
url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None,
username: Union[str, None] = None, password: Union[str, None] = None
) -> Dict[str, Any]:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/119.0',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Referer': 'https://m.afreecatv.com/',
'Content-Type': 'application/x-www-form-urlencoded',
}
if cookies:
headers['Cookie'] = cookies
split_url = url.split('/')
bj_id = split_url[3] if len(split_url) < 6 else split_url[5]
data = {
'bj_id': bj_id,
'broad_no': '',
'agent': 'web',
'confirm_adult': 'true',
'player_type': 'webm',
'mode': 'live',
}
url2 = 'http://api.m.afreecatv.com/broad/a/watch'
json_str = get_req(url=url2, proxy_addr=proxy_addr, headers=headers, data=data, abroad=True)
json_data = json.loads(json_str)
if 'user_nick' in json_data['data']:
anchor_name = json_data['data']['user_nick']
if "bj_id" in json_data['data']:
anchor_name = f"{anchor_name}-{json_data['data']['bj_id']}"
else:
anchor_name = ''
result = {
"anchor_name": '' if anchor_name is None else anchor_name,
"is_live": False,
}
def get_url_list(m3u8: str) -> List[str]:
resp = get_req(url=m3u8, proxy_addr=proxy_addr, headers=headers, abroad=True)
play_url_list = []
url_prefix = m3u8.rsplit('/', maxsplit=1)[0] + '/'
for i in resp.split('\n'):
if i.startswith('auth_playlist'):
play_url_list.append(url_prefix + i.strip())
bandwidth_pattern = re.compile(r'BANDWIDTH=(\d+)')
bandwidth_list = bandwidth_pattern.findall(resp)
url_to_bandwidth = {url: int(bandwidth) for bandwidth, url in zip(bandwidth_list, play_url_list)}
play_url_list = sorted(play_url_list, key=lambda url: url_to_bandwidth[url], reverse=True)
return play_url_list
if not anchor_name:
def handle_login():
cookie = login_afreecatv(username, password, proxy_addr=proxy_addr)
if 'PdboxBbs=' in cookie:
print('AfreecaTV平台登录成功！开始获取直播数据...')
return cookie
def fetch_data(cookie):
aid_token = get_afreecatv_tk(url, rtype='aid', proxy_addr=proxy_addr, cookies=cookie)
anchor_name, broad_no = get_afreecatv_tk(url, rtype='info', proxy_addr=proxy_addr, cookies=cookie)
view_url = get_afreecatv_cdn_url(broad_no, proxy_addr=proxy_addr)['view_url']
m3u8_url = view_url + '?aid=' + aid_token
result['anchor_name'] = anchor_name
result['m3u8_url'] = m3u8_url
result['is_live'] = True
result['play_url_list'] = get_url_list(m3u8_url)
return result
if json_data['data']['code'] == -3001:
print("AfreecaTV直播获取失败[直播刚结束]:", json_data['data']['message'])
return result
elif json_data['data']['code'] == -3002:
print("AfreecaTV直播获取失败[未登录]: 19+", json_data['data']['message'])
print("正在尝试使用您的账号和密码登录AfreecaTV直播平台，请确保已配置")
new_cookie = handle_login()
if new_cookie and len(new_cookie) > 0:
update_config('./config/config.ini', 'Cookie', 'afreecatv_cookie', new_cookie)
return fetch_data(new_cookie)
raise RuntimeError('AfreecaTV登录失败，请检查账号和密码是否正确')
elif json_data['data']['code'] == -3004:
# print("AfreecaTV直播获取失败[未认证]:", json_data['data']['message'])
if cookies and len(cookies) > 0:
return fetch_data(cookies)
else:
raise RuntimeError('AfreecaTV登录失败，请检查账号和密码是否正确')
elif json_data['data']['code'] == -6001:
print(f"错误信息：{json_data['data']['message']}请检查输入的直播间地址是否正确")
return result
if json_data['result'] == 1 and anchor_name:
broad_no = json_data['data']['broad_no']
hls_authentication_key = json_data['data']['hls_authentication_key']
view_url = get_afreecatv_cdn_url(broad_no, proxy_addr=proxy_addr)['view_url']
m3u8_url = view_url + '?aid=' + hls_authentication_key
result['m3u8_url'] = m3u8_url
result['is_live'] = True
result['play_url_list'] = get_url_list(m3u8_url)
return result
@trace_error_decorator
def get_netease_stream_data(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
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',
'referer': 'https://cc.163.com/',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.58',
}
if cookies:
headers['Cookie'] = cookies
url = url + '/' if url[-1] != '/' else url
html_str = get_req(url=url, proxy_addr=proxy_addr, headers=headers)
json_str = re.search('<script id="__NEXT_DATA__" .* crossorigin="anonymous">(.*?)</script></body>',
html_str, re.S).group(1)
json_data = json.loads(json_str)
room_data = json_data['props']['pageProps']['roomInfoInitData']
live_data = room_data['live']
result = {"is_live": False}
if 'quickplay' not in live_data:
result["anchor_name"] = room_data['nickname']
else:
result["anchor_name"] = live_data['nickname']
result["stream_list"] = live_data['quickplay']
result["is_live"] = True
return result
@trace_error_decorator
def get_qiandurebo_stream_data(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
'referer': 'https://qiandurebo.com/web/index.php',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.58',
}
if cookies:
headers['Cookie'] = cookies
html_str = get_req(url=url, proxy_addr=proxy_addr, headers=headers)
data = re.search('var user = (.*?)\r\n\s+user\.play_url', html_str, re.S).group(1)
anchor_name = re.findall('"zb_nickname": "(.*?)",\r\n', data)
result = {"anchor_name": "", "is_live": False}
if len(anchor_name) > 0:
result['anchor_name'] = anchor_name[0]
play_url = re.findall('"play_url": "(.*?)",\r\n', data)
if len(play_url) > 0 and 'common-text-center" style="display:block' not in html_str:
result['anchor_name'] = anchor_name[0]
result['flv_url'] = play_url[0]
result['is_live'] = True
result['record_url'] = play_url[0]
return result
@trace_error_decorator
def get_pandatv_stream_data(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
headers = {
'referer': 'https://www.pandalive.co.kr/',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.58',
}
if cookies:
headers['Cookie'] = cookies
user_id = url.split('?')[0].rsplit('/', maxsplit=1)[1]
url2 = 'https://api.pandalive.co.kr/v1/live/play'
data = {
'userId': user_id,
'info': 'media fanGrade',
}
room_password = get_params(url, "pwd")
if not room_password:
room_password = ''
data2 = {
'action': 'watch',
'userId': user_id,
'password': room_password,
'shareLinkType': '',
}
result = {"anchor_name": "", "is_live": False}
json_str = get_req('https://api.pandalive.co.kr/v1/member/bj',
proxy_addr=proxy_addr, headers=headers, data=data, abroad=True)
json_data = json.loads(json_str)
anchor_id = json_data['bjInfo']['id']
anchor_name = f"{json_data['bjInfo']['nick']}-{anchor_id}"
result['anchor_name'] = anchor_name
live_status = 'media' in json_data
if live_status:
json_str = get_req(url2, proxy_addr=proxy_addr, headers=headers, data=data2, abroad=True)
json_data = json.loads(json_str)
if 'errorData' in json_data:
if json_data['errorData']['code'] == 'needAdult':
raise RuntimeError(f'{url} 直播间需要登录后成人才可观看，请你在配置文件中正确填写登录后的cookie')
else:
raise RuntimeError(json_data['errorData']['code'], json_data['message'])
play_url = json_data['PlayList']['hls'][0]['url']
result['m3u8_url'] = play_url
result['is_live'] = True
result['play_url_list'] = get_play_url_list(m3u8=play_url, proxy=proxy_addr, header=headers, abroad=True)
return result
@trace_error_decorator
def get_maoerfm_stream_url(url: str, proxy_addr: Union[str, None] = None, cookies: Union[str, None] = None) -> \
Dict[str, Any]:
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',
'referer': 'https://fm.missevan.com/live/868895007',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.58',