forked from niu12503/douyin
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathTikTok.py
1129 lines (945 loc) · 48.8 KB
/
TikTok.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
#!/usr/bin/env python
# -*- encoding: utf-8 -*-
'''
@Description:TikTok.py
@Date :2023/01/27 19:36:18
@Author :imgyh
@version :1.0
@Github :https://github.com/imgyh
@Mail :[email protected]
-------------------------------------------------
Change Log : 2023/02/11 修改接口
-------------------------------------------------
'''
import re
import requests
import json
import time
import os
import copy
from tqdm import tqdm
from concurrent.futures import ThreadPoolExecutor, wait, ALL_COMPLETED
# rich 进度条
# from functools import partial
# from urllib.request import urlopen
# import signal
# from threading import Event
# from rich.progress import (
# BarColumn,
# DownloadColumn,
# Progress,
# TaskID,
# TextColumn,
# TimeRemainingColumn,
# TransferSpeedColumn
# )
from TikTokUtils import Utils
from TikTokUrls import Urls
from TikTokResult import Result
class TikTok(object):
def __init__(self):
self.urls = Urls()
self.utils = Utils()
self.result = Result()
self.headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36',
'referer': 'https://www.douyin.com/',
'Cookie': f"msToken={self.utils.generate_random_str(107)}; ttwid={self.utils.getttwid()}; odin_tt=324fb4ea4a89c0c05827e18a1ed9cf9bf8a17f7705fcc793fec935b637867e2a5a9b8168c885554d029919117a18ba69; passport_csrf_token=f61602fc63757ae0e4fd9d6bdcee4810;"
}
# 用于设置重复请求某个接口的最大时间
self.timeout = 10
# rich 进度条
# self.progress = Progress(
# TextColumn("[bold blue]{task.fields[filename]}", justify="left"),
# BarColumn(bar_width=20),
# "[progress.percentage]{task.percentage:>3.1f}%",
# "•",
# DownloadColumn(),
# "•",
# TransferSpeedColumn(),
# "•",
# TimeRemainingColumn(),
# )
# self.done_event = Event()
# signal.signal(signal.SIGINT, self.handle_sigint)
# 从分享链接中提取网址
def getShareLink(self, string):
# findall() 查找匹配正则表达式的字符串
return re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', string)[0]
# 得到 作品id 或者 用户id
# 传入 url 支持 https://www.iesdouyin.com 与 https://v.douyin.com
def getKey(self, url):
key = None
key_type = None
try:
r = requests.get(url=url, headers=self.headers)
except Exception as e:
print('[ 错误 ]:输入链接有误！\r')
return key_type, key
# 抖音把图集更新为note
# 作品 第一步解析出来的链接是share/video/{aweme_id}
# https://www.iesdouyin.com/share/video/7037827546599263488/?region=CN&mid=6939809470193126152&u_code=j8a5173b&did=MS4wLjABAAAA1DICF9-A9M_CiGqAJZdsnig5TInVeIyPdc2QQdGrq58xUgD2w6BqCHovtqdIDs2i&iid=MS4wLjABAAAAomGWi4n2T0H9Ab9x96cUZoJXaILk4qXOJlJMZFiK6b_aJbuHkjN_f0mBzfy91DX1&with_sec_did=1&titleType=title&schema_type=37&from_ssr=1&utm_source=copy&utm_campaign=client_share&utm_medium=android&app=aweme
# 用户 第一步解析出来的链接是share/user/{sec_uid}
# https://www.iesdouyin.com/share/user/MS4wLjABAAAA06y3Ctu8QmuefqvUSU7vr0c_ZQnCqB0eaglgkelLTek?did=MS4wLjABAAAA1DICF9-A9M_CiGqAJZdsnig5TInVeIyPdc2QQdGrq58xUgD2w6BqCHovtqdIDs2i&iid=MS4wLjABAAAAomGWi4n2T0H9Ab9x96cUZoJXaILk4qXOJlJMZFiK6b_aJbuHkjN_f0mBzfy91DX1&with_sec_did=1&sec_uid=MS4wLjABAAAA06y3Ctu8QmuefqvUSU7vr0c_ZQnCqB0eaglgkelLTek&from_ssr=1&u_code=j8a5173b×tamp=1674540164&ecom_share_track_params=%7B%22is_ec_shopping%22%3A%221%22%2C%22secuid%22%3A%22MS4wLjABAAAA-jD2lukp--I21BF8VQsmYUqJDbj3FmU-kGQTHl2y1Cw%22%2C%22enter_from%22%3A%22others_homepage%22%2C%22share_previous_page%22%3A%22others_homepage%22%7D&utm_source=copy&utm_campaign=client_share&utm_medium=android&app=aweme
# 合集
# https://www.douyin.com/collection/7093490319085307918
urlstr = str(r.request.path_url)
if "/user/" in urlstr:
# 获取用户 sec_uid
if '?' in r.request.path_url:
for one in re.finditer(r'user\/([\d\D]*)([?])', str(r.request.path_url)):
key = one.group(1)
else:
for one in re.finditer(r'user\/([\d\D]*)', str(r.request.path_url)):
key = one.group(1)
key_type = "user"
elif "/video/" in urlstr:
# 获取作品 aweme_id
key = re.findall('video/(\d+)?', urlstr)[0]
key_type = "aweme"
elif "/note/" in urlstr:
# 获取note aweme_id
key = re.findall('note/(\d+)?', urlstr)[0]
key_type = "aweme"
elif "/mix/detail/" in urlstr:
# 获取合集 id
key = re.findall('/mix/detail/(\d+)?', urlstr)[0]
key_type = "mix"
elif "/collection/" in urlstr:
# 获取合集 id
key = re.findall('/collection/(\d+)?', urlstr)[0]
key_type = "mix"
elif "/music/" in urlstr:
# 获取原声 id
key = re.findall('music/(\d+)?', urlstr)[0]
key_type = "music"
elif "/webcast/reflow/" in urlstr:
key1 = re.findall('reflow/(\d+)?', urlstr)[0]
url = self.urls.LIVE2 + self.utils.getXbogus(
f'live_id=1&room_id={key1}&app_id=1128')
res = requests.get(url, headers=self.headers)
resjson = json.loads(res.text)
key = resjson['data']['room']['owner']['web_rid']
key_type = "live"
elif "live.douyin.com" in r.url:
key = r.url.replace('https://live.douyin.com/', '')
key_type = "live"
if key is None or key_type is None:
print('[ 错误 ]:输入链接有误！无法获取 id\r')
return key_type, key
return key_type, key
def getAwemeInfoApi(self, aweme_id):
if aweme_id is None:
return None
start = time.time() # 开始时间
while True:
try:
jx_url = self.urls.POST_DETAIL + self.utils.getXbogus(
url=f'aweme_id={aweme_id}&aid=1128&version_name=23.5.0&device_platform=android&os_version=2333')
raw = requests.get(url=jx_url, headers=self.headers).text
datadict = json.loads(raw)
if datadict is not None and datadict["status_code"] == 0:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
return None
# 清空self.awemeDict
self.result.clearDict(self.result.awemeDict)
# 默认为视频
awemeType = 0
try:
if datadict['aweme_detail']["images"] is not None:
awemeType = 1
except Exception as e:
pass
# 转换成我们自己的格式
self.result.dataConvert(awemeType, self.result.awemeDict, datadict['aweme_detail'])
return self.result.awemeDict, datadict
# 传入 aweme_id
# 返回 数据 字典
def getAwemeInfo(self, aweme_id):
print('[ 提示 ]:正在请求的作品 id = %s\r' % aweme_id)
if aweme_id is None:
return None
start = time.time() # 开始时间
while True:
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
try:
# 单作品接口返回 'aweme_detail'
# 主页作品接口返回 'aweme_list'->['aweme_detail']
jx_url = self.urls.POST_DETAIL + self.utils.getXbogus(
url=f'aweme_id={aweme_id}&aid=1128&version_name=23.5.0&device_platform=android&os_version=2333')
raw = requests.get(url=jx_url, headers=self.headers).text
datadict = json.loads(raw)
if datadict is not None and datadict["status_code"] == 0:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
# raise RuntimeError("重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
return {},{}
# print("[ 警告 ]:接口未返回数据, 正在重新请求!\r")
# 清空self.awemeDict
self.result.clearDict(self.result.awemeDict)
# 默认为视频
awemeType = 0
try:
# datadict['aweme_detail']["images"] 不为 None 说明是图集
if datadict['aweme_detail']["images"] is not None:
awemeType = 1
except Exception as e:
print("[ 警告 ]:接口中未找到 images\r")
# 转换成我们自己的格式
self.result.dataConvert(awemeType, self.result.awemeDict, datadict['aweme_detail'])
return self.result.awemeDict, datadict
def getUserInfoApi(self, sec_uid, mode="post", count=35, max_cursor=0):
if sec_uid is None:
return None
awemeList = []
start = time.time() # 开始时间
while True:
try:
if mode == "post":
url = self.urls.USER_POST + self.utils.getXbogus(
url=f'device_platform=webapp&aid=6383&os_version=10&version_name=17.4.0&sec_user_id={sec_uid}&count={count}&max_cursor={max_cursor}')
elif mode == "like":
url = self.urls.USER_FAVORITE_A + self.utils.getXbogus(
url=f'sec_user_id={sec_uid}&count={count}&max_cursor={max_cursor}&aid=1128&version_name=23.5.0&device_platform=android&os_version=2333')
else:
return None
res = requests.get(url=url, headers=self.headers)
datadict = json.loads(res.text)
if datadict is not None and datadict["status_code"] == 0:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
return None
for aweme in datadict["aweme_list"]:
# 清空self.awemeDict
self.result.clearDict(self.result.awemeDict)
# 默认为视频
awemeType = 0
try:
if aweme["images"] is not None:
awemeType = 1
except Exception as e:
pass
# 转换成我们自己的格式
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
if self.result.awemeDict is not None and self.result.awemeDict != {}:
awemeList.append(copy.deepcopy(self.result.awemeDict))
return awemeList, datadict, datadict["max_cursor"], datadict["has_more"]
# 传入 url 支持 https://www.iesdouyin.com 与 https://v.douyin.com
# mode : post | like 模式选择 like为用户点赞 post为用户发布
def getUserInfo(self, sec_uid, mode="post", count=35, number=0):
print('[ 提示 ]:正在请求的用户 id = %s\r\n' % sec_uid)
if sec_uid is None:
return None
if number <= 0:
numflag = False
else:
numflag = True
max_cursor = 0
awemeList = []
print("[ 提示 ]:正在获取所有作品数据请稍后...\r")
print("[ 提示 ]:会进行多次请求，等待时间较长...\r\n")
times = 0
while True:
times = times + 1
print("[ 提示 ]:正在对 [主页] 进行第 " + str(times) + " 次请求...\r")
start = time.time() # 开始时间
while True:
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
try:
if mode == "post":
url = self.urls.USER_POST + self.utils.getXbogus(
url=f'device_platform=webapp&aid=6383&os_version=10&version_name=17.4.0&sec_user_id={sec_uid}&count={count}&max_cursor={max_cursor}')
elif mode == "like":
url = self.urls.USER_FAVORITE_A + self.utils.getXbogus(
url=f'sec_user_id={sec_uid}&count={count}&max_cursor={max_cursor}&aid=1128&version_name=23.5.0&device_platform=android&os_version=2333')
else:
print("[ 错误 ]:模式选择错误, 仅支持post、like、mix, 请检查后重新运行!\r")
return None
res = requests.get(url=url, headers=self.headers)
datadict = json.loads(res.text)
print('[ 提示 ]:本次请求返回 ' + str(len(datadict["aweme_list"])) + ' 条数据\r')
# print('[ 提示 ]:开始对 ' + str(len(datadict["aweme_list"])) + ' 条数据请求作品详情\r\n')
if datadict is not None and datadict["status_code"] == 0:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
# raise RuntimeError("重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
return awemeList
# print("[ 警告 ]:接口未返回数据, 正在重新请求!\r")
for aweme in datadict["aweme_list"]:
# 获取 aweme_id
# aweme_id = aweme["aweme_id"]
# 深拷贝 dict 不然list里面全是同样的数据
# datanew, dataraw = self.getAwemeInfo(aweme_id)
# 清空self.awemeDict
self.result.clearDict(self.result.awemeDict)
# 默认为视频
awemeType = 0
try:
if aweme["images"] is not None:
awemeType = 1
except Exception as e:
print("[ 警告 ]:接口中未找到 images\r")
# 转换成我们自己的格式
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
if self.result.awemeDict is not None and self.result.awemeDict != {}:
awemeList.append(copy.deepcopy(self.result.awemeDict))
if numflag:
number-=1
if number==0:
break
if numflag and number==0:
print("\r\n[ 提示 ]: [主页] 下指定数量作品数据获取完成...\r\n")
break
# 更新 max_cursor
max_cursor = datadict["max_cursor"]
# 退出条件
if datadict["has_more"] == 0 or datadict["has_more"] == False:
print("\r\n[ 提示 ]: [主页] 下所有作品数据获取完成...\r\n")
break
else:
print("\r\n[ 提示 ]:[主页] 第 " + str(times) + " 次请求成功...\r\n")
return awemeList
def getLiveInfoApi(self, web_rid: str):
start = time.time() # 开始时间
while True:
try:
live_api = self.urls.LIVE + self.utils.getXbogus(
url=f'aid=6383&device_platform=web&web_rid={web_rid}')
response = requests.get(live_api, headers=self.headers)
live_json = json.loads(response.text)
if live_json != {} and live_json['status_code'] == 0:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
return None
# 清空字典
self.result.clearDict(self.result.liveDict)
# 类型
self.result.liveDict["awemeType"] = 2
# 是否在播
self.result.liveDict["status"] = live_json['data']['data'][0]['status']
if self.result.liveDict["status"] == 4:
return self.result.liveDict, live_json
# 直播标题
self.result.liveDict["title"] = live_json['data']['data'][0]['title']
# 直播cover
self.result.liveDict["cover"] = live_json['data']['data'][0]['cover']['url_list'][0]
# 头像
self.result.liveDict["avatar"] = live_json['data']['data'][0]['owner']['avatar_thumb']['url_list'][0].replace("100x100", "1080x1080")
# 观看人数
self.result.liveDict["user_count"] = live_json['data']['data'][0]['user_count_str']
# 昵称
self.result.liveDict["nickname"] = live_json['data']['data'][0]['owner']['nickname']
# sec_uid
self.result.liveDict["sec_uid"] = live_json['data']['data'][0]['owner']['sec_uid']
# 直播间观看状态
self.result.liveDict["display_long"] = live_json['data']['data'][0]['room_view_stats']['display_long']
# 推流
self.result.liveDict["flv_pull_url"] = live_json['data']['data'][0]['stream_url']['flv_pull_url']
try:
# 分区
self.result.liveDict["partition"] = live_json['data']['partition_road_map']['partition']['title']
self.result.liveDict["sub_partition"] = live_json['data']['partition_road_map']['sub_partition']['partition'][
'title']
except Exception as e:
self.result.liveDict["partition"] = '无'
self.result.liveDict["sub_partition"] = '无'
flv = []
for i, f in enumerate(self.result.liveDict["flv_pull_url"].keys()):
flv.append(f)
self.result.liveDict["flv_pull_url0"] = self.result.liveDict["flv_pull_url"][flv[0]].replace("http://", "https://")
return self.result.liveDict, live_json
def getLiveInfo(self, web_rid: str):
print('[ 提示 ]:正在请求的直播间 id = %s\r\n' % web_rid)
# web_rid = live_url.replace('https://live.douyin.com/', '')
start = time.time() # 开始时间
while True:
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
try:
live_api = self.urls.LIVE + self.utils.getXbogus(
url=f'aid=6383&device_platform=web&web_rid={web_rid}')
response = requests.get(live_api, headers=self.headers)
live_json = json.loads(response.text)
if live_json != {} and live_json['status_code'] == 0:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
# raise RuntimeError("重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
return {}
# 清空字典
self.result.clearDict(self.result.liveDict)
# 类型
self.result.liveDict["awemeType"] = 2
# 是否在播
self.result.liveDict["status"] = live_json['data']['data'][0]['status']
if self.result.liveDict["status"] == 4:
print('[ 📺 ]:当前直播已结束，正在退出')
return self.result.liveDict
# 直播标题
self.result.liveDict["title"] = live_json['data']['data'][0]['title']
# 直播cover
self.result.liveDict["cover"] = live_json['data']['data'][0]['cover']['url_list'][0]
# 头像
self.result.liveDict["avatar"] = live_json['data']['data'][0]['owner']['avatar_thumb']['url_list'][0].replace("100x100", "1080x1080")
# 观看人数
self.result.liveDict["user_count"] = live_json['data']['data'][0]['user_count_str']
# 昵称
self.result.liveDict["nickname"] = live_json['data']['data'][0]['owner']['nickname']
# sec_uid
self.result.liveDict["sec_uid"] = live_json['data']['data'][0]['owner']['sec_uid']
# 直播间观看状态
self.result.liveDict["display_long"] = live_json['data']['data'][0]['room_view_stats']['display_long']
# 推流
self.result.liveDict["flv_pull_url"] = live_json['data']['data'][0]['stream_url']['flv_pull_url']
try:
# 分区
self.result.liveDict["partition"] = live_json['data']['partition_road_map']['partition']['title']
self.result.liveDict["sub_partition"] = live_json['data']['partition_road_map']['sub_partition']['partition'][
'title']
except Exception as e:
self.result.liveDict["partition"] = '无'
self.result.liveDict["sub_partition"] = '无'
info = '[ 💻 ]:直播间：%s 当前%s 主播：%s 分区：%s-%s\r' % (
self.result.liveDict["title"], self.result.liveDict["display_long"], self.result.liveDict["nickname"],
self.result.liveDict["partition"], self.result.liveDict["sub_partition"])
print(info)
flv = []
print('[ 🎦 ]:直播间清晰度')
for i, f in enumerate(self.result.liveDict["flv_pull_url"].keys()):
print('[ %s ]: %s' % (i, f))
flv.append(f)
rate = int(input('[ 🎬 ]输入数字选择推流清晰度：'))
self.result.liveDict["flv_pull_url0"] = self.result.liveDict["flv_pull_url"][flv[rate]].replace("http://", "https://")
# 显示清晰度列表
print('[ %s ]:%s' % (flv[rate], self.result.liveDict["flv_pull_url"][flv[rate]]))
print('[ 📺 ]:复制链接使用下载工具下载')
return self.result.liveDict
def getMixInfoApi(self, mix_id: str, count=35, cursor=0):
if mix_id is None:
return None
awemeList = []
start = time.time() # 开始时间
while True:
try:
url = self.urls.USER_MIX + self.utils.getXbogus(
url=f'device_platform=webapp&aid=6383&os_version=10&version_name=17.4.0&mix_id={mix_id}&cursor={cursor}&count={count}')
res = requests.get(url=url, headers=self.headers)
datadict = json.loads(res.text)
if datadict is not None:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
return None
for aweme in datadict["aweme_list"]:
# 清空self.awemeDict
self.result.clearDict(self.result.awemeDict)
# 默认为视频
awemeType = 0
try:
if aweme["images"] is not None:
awemeType = 1
except Exception as e:
pass
# 转换成我们自己的格式
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
if self.result.awemeDict is not None and self.result.awemeDict != {}:
awemeList.append(copy.deepcopy(self.result.awemeDict))
return awemeList, datadict, datadict["cursor"], datadict["has_more"]
def getMixInfo(self, mix_id: str, count=35, number=0):
print('[ 提示 ]:正在请求的合集 id = %s\r\n' % mix_id)
if mix_id is None:
return None
if number <= 0:
numflag = False
else:
numflag = True
cursor = 0
awemeList = []
print("[ 提示 ]:正在获取合集下的所有作品数据请稍后...\r")
print("[ 提示 ]:会进行多次请求，等待时间较长...\r\n")
times = 0
while True:
times = times + 1
print("[ 提示 ]:正在对 [合集] 进行第 " + str(times) + " 次请求...\r")
start = time.time() # 开始时间
while True:
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
try:
url = self.urls.USER_MIX + self.utils.getXbogus(
url=f'device_platform=webapp&aid=6383&os_version=10&version_name=17.4.0&mix_id={mix_id}&cursor={cursor}&count={count}')
res = requests.get(url=url, headers=self.headers)
datadict = json.loads(res.text)
print('[ 提示 ]:本次请求返回 ' + str(len(datadict["aweme_list"])) + ' 条数据\r')
# print('[ 提示 ]:开始对 ' + str(len(datadict["aweme_list"])) + ' 条数据请求作品详情\r\n')
if datadict is not None:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
# raise RuntimeError("重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
return awemeList
# print("[ 警告 ]:接口未返回数据, 正在重新请求!\r")
for aweme in datadict["aweme_list"]:
# 获取 aweme_id
# aweme_id = aweme["aweme_id"]
# 深拷贝 dict 不然list里面全是同样的数据
# datanew, dataraw = self.getAwemeInfo(aweme_id)
# 清空self.awemeDict
self.result.clearDict(self.result.awemeDict)
# 默认为视频
awemeType = 0
try:
if aweme["images"] is not None:
awemeType = 1
except Exception as e:
print("[ 警告 ]:接口中未找到 images\r")
# 转换成我们自己的格式
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
if self.result.awemeDict is not None and self.result.awemeDict != {}:
awemeList.append(copy.deepcopy(self.result.awemeDict))
if numflag:
number -= 1
if number == 0:
break
if numflag and number == 0:
print("\r\n[ 提示 ]:[合集] 下指定数量作品数据获取完成...\r\n")
break
# 更新 max_cursor
cursor = datadict["cursor"]
# 退出条件
if datadict["has_more"] == 0 or datadict["has_more"] == False:
print("\r\n[ 提示 ]:[合集] 下所有作品数据获取完成...\r\n")
break
else:
print("\r\n[ 提示 ]:[合集] 第 " + str(times) + " 次请求成功...\r\n")
return awemeList
def getUserAllMixInfoApi(self, sec_uid, count=35, cursor=0):
if sec_uid is None:
return None
mixIdlist = []
start = time.time() # 开始时间
while True:
try:
url = self.urls.USER_MIX_LIST + self.utils.getXbogus(
url=f'device_platform=webapp&aid=6383&os_version=10&version_name=17.4.0&sec_user_id={sec_uid}&count={count}&cursor={cursor}')
res = requests.get(url=url, headers=self.headers)
datadict = json.loads(res.text)
if datadict is not None and datadict["status_code"] == 0:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
return None
for mix in datadict["mix_infos"]:
mixIdNameDict={}
mixIdNameDict["https://www.douyin.com/collection/" + mix["mix_id"]] = mix["mix_name"]
mixIdlist.append(mixIdNameDict)
return mixIdlist, datadict, datadict["cursor"], datadict["has_more"]
def getUserAllMixInfo(self, sec_uid, count=35, number=0):
print('[ 提示 ]:正在请求的用户 id = %s\r\n' % sec_uid)
if sec_uid is None:
return None
if number <= 0:
numflag = False
else:
numflag = True
cursor = 0
mixIdNameDict = {}
print("[ 提示 ]:正在获取主页下所有合集 id 数据请稍后...\r")
print("[ 提示 ]:会进行多次请求，等待时间较长...\r\n")
times = 0
while True:
times = times + 1
print("[ 提示 ]:正在对 [合集列表] 进行第 " + str(times) + " 次请求...\r")
start = time.time() # 开始时间
while True:
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
try:
url = self.urls.USER_MIX_LIST + self.utils.getXbogus(
url=f'device_platform=webapp&aid=6383&os_version=10&version_name=17.4.0&sec_user_id={sec_uid}&count={count}&cursor={cursor}')
res = requests.get(url=url, headers=self.headers)
datadict = json.loads(res.text)
print('[ 提示 ]:本次请求返回 ' + str(len(datadict["mix_infos"])) + ' 条数据\r')
# print('[ 提示 ]:开始对 ' + str(len(datadict["mix_infos"])) + ' 条数据请求作品详情\r\n')
if datadict is not None and datadict["status_code"] == 0:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
# raise RuntimeError("重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
return mixIdNameDict
# print("[ 警告 ]:接口未返回数据, 正在重新请求!\r")
for mix in datadict["mix_infos"]:
mixIdNameDict[mix["mix_id"]] = mix["mix_name"]
if numflag:
number -= 1
if number == 0:
break
if numflag and number == 0:
print("\r\n[ 提示 ]:[合集列表] 下指定数量合集数据获取完成...\r\n")
break
# 更新 max_cursor
cursor = datadict["cursor"]
# 退出条件
if datadict["has_more"] == 0 or datadict["has_more"] == False:
print("[ 提示 ]:[合集列表] 下所有合集 id 数据获取完成...\r\n")
break
else:
print("\r\n[ 提示 ]:[合集列表] 第 " + str(times) + " 次请求成功...\r\n")
return mixIdNameDict
def getMusicInfoApi(self, music_id: str, count=35, cursor=0):
if music_id is None:
return None
awemeList = []
start = time.time() # 开始时间
while True:
try:
url = self.urls.MUSIC + self.utils.getXbogus(
url=f'device_platform=webapp&aid=6383&os_version=10&version_name=17.4.0&music_id={music_id}&cursor={cursor}&count={count}')
res = requests.get(url=url, headers=self.headers)
datadict = json.loads(res.text)
if datadict is not None and datadict["status_code"] == 0:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
return None
for aweme in datadict["aweme_list"]:
# 清空self.awemeDict
self.result.clearDict(self.result.awemeDict)
# 默认为视频
awemeType = 0
try:
if aweme["images"] is not None:
awemeType = 1
except Exception as e:
pass
# 转换成我们自己的格式
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
if self.result.awemeDict is not None and self.result.awemeDict != {}:
awemeList.append(copy.deepcopy(self.result.awemeDict))
return awemeList, datadict, datadict["cursor"], datadict["has_more"]
def getMusicInfo(self, music_id: str, count=35, number=0):
print('[ 提示 ]:正在请求的音乐集合 id = %s\r\n' % music_id)
if music_id is None:
return None
if number <= 0:
numflag = False
else:
numflag = True
cursor = 0
awemeList = []
print("[ 提示 ]:正在获取音乐集合下的所有作品数据请稍后...\r")
print("[ 提示 ]:会进行多次请求，等待时间较长...\r\n")
times = 0
while True:
times = times + 1
print("[ 提示 ]:正在对 [音乐集合] 进行第 " + str(times) + " 次请求...\r")
start = time.time() # 开始时间
while True:
# 接口不稳定, 有时服务器不返回数据, 需要重新获取
try:
url = self.urls.MUSIC + self.utils.getXbogus(
url=f'device_platform=webapp&aid=6383&os_version=10&version_name=17.4.0&music_id={music_id}&cursor={cursor}&count={count}')
res = requests.get(url=url, headers=self.headers)
datadict = json.loads(res.text)
print('[ 提示 ]:本次请求返回 ' + str(len(datadict["aweme_list"])) + ' 条数据\r')
# print('[ 提示 ]:开始对 ' + str(len(datadict["aweme_list"])) + ' 条数据请求作品详情\r\n')
if datadict is not None and datadict["status_code"] == 0:
break
except Exception as e:
end = time.time() # 结束时间
if end - start > self.timeout:
# raise RuntimeError("重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
print("[ 提示 ]:重复请求该接口" + str(self.timeout) + "s, 仍然未获取到数据")
return awemeList
# print("[ 警告 ]:接口未返回数据, 正在重新请求!\r")
for aweme in datadict["aweme_list"]:
# 获取 aweme_id
# aweme_id = aweme["aweme_id"]
# 深拷贝 dict 不然list里面全是同样的数据
# datanew, dataraw = self.getAwemeInfo(aweme_id)
# 清空self.awemeDict
self.result.clearDict(self.result.awemeDict)
# 默认为视频
awemeType = 0
try:
if aweme["images"] is not None:
awemeType = 1
except Exception as e:
print("[ 警告 ]:接口中未找到 images\r")
# 转换成我们自己的格式
self.result.dataConvert(awemeType, self.result.awemeDict, aweme)
if self.result.awemeDict is not None and self.result.awemeDict != {}:
awemeList.append(copy.deepcopy(self.result.awemeDict))
if numflag:
number -= 1
if number == 0:
break
if numflag and number == 0:
print("\r\n[ 提示 ]:[音乐集合] 下指定数量作品数据获取完成...\r\n")
break
# 更新 cursor
cursor = datadict["cursor"]
# 退出条件
if datadict["has_more"] == 0 or datadict["has_more"] == False:
print("\r\n[ 提示 ]:[音乐集合] 下所有作品数据获取完成...\r\n")
break
else:
print("\r\n[ 提示 ]:[音乐集合] 第 " + str(times) + " 次请求成功...\r\n")
return awemeList
# rich 进度条
# https://github.com/textualize/rich/blob/master/examples/downloader.py
# def handle_sigint(self, signum, frame):
# self.done_event.set()
#
# def copy_url(self, task_id: TaskID, url: str, path: str) -> None:
# """Copy data from a url to a local file."""
# # self.progress.console.log(f"Requesting {url}")
# response = urlopen(url)
# try:
# # This will break if the response doesn't contain content length
# self.progress.update(task_id, total=int(response.info()["Content-length"]))
# with open(path, "wb") as dest_file:
# self.progress.start_task(task_id)
# for data in iter(partial(response.read, 32768), b""):
# dest_file.write(data)
# self.progress.update(task_id, advance=len(data))
# if self.done_event.is_set():
# return
# except Exception as e:
# # 下载异常 删除原来下载的文件, 可能未下成功
# if os.path.exists(path):
# os.remove(path)
# print("[ 错误 ]:下载出错\r")
# 来自 https://blog.csdn.net/weixin_43347550/article/details/105248223
def progressBarDownload(self, url, filepath, desc):
response = requests.get(url, stream=True, headers=self.headers)
chunk_size = 1024 # 每次下载的数据大小
content_size = int(response.headers['content-length']) # 下载文件总大小
try:
if response.status_code == 200: # 判断是否响应成功
# print('[开始下载]:文件大小:{size:.2f} MB'.format(
# size=content_size / chunk_size / 1024)) # 开始下载，显示下载文件大小
with open(filepath, 'wb') as file, tqdm(total=content_size,
unit="iB",
desc=desc,
unit_scale=True,
unit_divisor=1024,
) as bar: # 显示进度条
for data in response.iter_content(chunk_size=chunk_size):
size = file.write(data)
bar.update(size)
except Exception as e:
# 下载异常 删除原来下载的文件, 可能未下成功
if os.path.exists(filepath):
os.remove(filepath)
print("[ 错误 ]:下载出错\r")
def awemeDownload(self, awemeDict: dict, music=True, cover=True, avatar=True, resjson=True, savePath=os.getcwd()):
if awemeDict is None:
return
if not os.path.exists(savePath):
os.mkdir(savePath)
try:
# 使用作品 创建时间+描述 当文件夹
file_name = awemeDict["create_time"] + "_" + self.utils.replaceStr(awemeDict["desc"])
aweme_path = os.path.join(savePath, file_name)
if not os.path.exists(aweme_path):
os.mkdir(aweme_path)
# 保存获取到的字典信息
# print("[ 提示 ]:正在保存获取到的信息到 result.json\r\n")
if resjson:
try:
with open(os.path.join(aweme_path, "result.json"), "w", encoding='utf-8') as f:
f.write(json.dumps(awemeDict, ensure_ascii=False, indent=2))
f.close()
except Exception as e:
print("[ 错误 ]:保存 result.json 失败... 作品名: " + file_name +"\r\n")
desc = file_name[:30]
# 下载 视频
if awemeDict["awemeType"] == 0:
# print("[ 提示 ]:正在下载视频...\r")
video_path = os.path.join(aweme_path, file_name + ".mp4")
if os.path.exists(video_path):
# print("[ 提示 ]:视频已存在为您跳过...\r\n")
pass
else:
try:
url = awemeDict["video"]["play_addr"]["url_list"]
if url != "":
self.isdwownload = False
# task_id = self.progress.add_task("download", filename="[ 视频 ]:" + desc, start=False)
# self.alltask.append(self.pool.submit(self.copy_url, task_id, url, video_path))
self.alltask.append(
self.pool.submit(self.progressBarDownload, url, video_path, "[ 视频 ]:" + desc))
except Exception as e:
print("[ 警告 ]:视频下载失败,请重试... 作品名: " + file_name +"\r\n")
# 下载 图集
if awemeDict["awemeType"] == 1:
# print("[ 提示 ]:正在下载图集...\r")
for ind, image in enumerate(awemeDict["images"]):
image_path = os.path.join(aweme_path, "image" + str(ind) + ".jpeg")
if os.path.exists(image_path):
# print("[ 提示 ]:图片已存在为您跳过...\r\n")
pass
else:
try:
url = image["url_list"][0]
if url != "":
self.isdwownload = False
# task_id = self.progress.add_task("download", filename="[ 图集 ]:" + desc, start=False)
# self.alltask.append(self.pool.submit(self.copy_url, task_id, url, image_path))
self.alltask.append(
self.pool.submit(self.progressBarDownload, url, image_path, "[ 图集 ]:" + desc))
except Exception as e:
print("[ 警告 ]:图片下载失败,请重试... 作品名: " + file_name +"\r\n")
# 下载 音乐
if music:
# print("[ 提示 ]:正在下载音乐...\r")
music_name = self.utils.replaceStr(awemeDict["music"]["title"])
music_path = os.path.join(aweme_path, music_name + ".mp3")
if os.path.exists(music_path):
# print("[ 提示 ]:音乐已存在为您跳过...\r\n")
pass
else:
try:
url = awemeDict["music"]["play_url"]["url_list"][0]
if url != "":
self.isdwownload = False
# task_id = self.progress.add_task("download", filename="[ 原声 ]:" + desc, start=False)
# self.alltask.append(self.pool.submit(self.copy_url, task_id, url, music_path))
self.alltask.append(
self.pool.submit(self.progressBarDownload, url, music_path, "[ 原声 ]:" + desc))
except Exception as e: