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
|
import base64
from youtube import util, yt_data_extract, local_playlist, subscriptions
from youtube import yt_app
import urllib
import json
from string import Template
import youtube.proto as proto
import html
import math
import gevent
import re
import cachetools.func
import traceback
import flask
from flask import request
headers_desktop = (
('Accept', '*/*'),
('Accept-Language', 'en-US,en;q=0.5'),
('X-YouTube-Client-Name', '1'),
('X-YouTube-Client-Version', '2.20180830'),
) + util.desktop_ua
headers_mobile = (
('Accept', '*/*'),
('Accept-Language', 'en-US,en;q=0.5'),
('X-YouTube-Client-Name', '2'),
('X-YouTube-Client-Version', '2.20180830'),
) + util.mobile_ua
real_cookie = (('Cookie', 'VISITOR_INFO1_LIVE=8XihrAcN1l4'),)
generic_cookie = (('Cookie', 'VISITOR_INFO1_LIVE=ST1Ti53r4fU'),)
# SORT:
# videos:
# Popular - 1
# Oldest - 2
# Newest - 3
# playlists:
# Oldest - 2
# Newest - 3
# Last video added - 4
# view:
# grid: 0 or 1
# list: 2
def channel_ctoken_v3(channel_id, page, sort, tab, view=1):
# page > 1 doesn't work when sorting by oldest
offset = 30*(int(page) - 1)
page_token = proto.string(61, proto.unpadded_b64encode(
proto.string(1, proto.unpadded_b64encode(proto.uint(1,offset)))
))
tab = proto.string(2, tab)
sort = proto.uint(3, int(sort))
shelf_view = proto.uint(4, 0)
view = proto.uint(6, int(view))
continuation_info = proto.string(3,
proto.percent_b64encode(tab + sort + shelf_view + view + page_token)
)
channel_id = proto.string(2, channel_id)
pointless_nest = proto.string(80226972, channel_id + continuation_info)
return base64.urlsafe_b64encode(pointless_nest).decode('ascii')
def channel_ctoken_v2(channel_id, page, sort, tab, view=1):
# see https://github.com/iv-org/invidious/issues/1319#issuecomment-671732646
# page > 1 doesn't work when sorting by oldest
offset = 30*(int(page) - 1)
schema_number = {
3: 6307666885028338688,
2: 17254859483345278706,
1: 16570086088270825023,
}[int(sort)]
page_token = proto.string(61, proto.unpadded_b64encode(
proto.string(1, proto.uint(1, schema_number) + proto.string(
2,
proto.string(1, proto.unpadded_b64encode(proto.uint(1, offset)))
))))
tab = proto.string(2, tab)
sort = proto.uint(3, int(sort))
# page = proto.string(15, str(page) )
shelf_view = proto.uint(4, 0)
view = proto.uint(6, int(view))
continuation_info = proto.string(
3,
proto.percent_b64encode(tab + sort + shelf_view + view + page_token)
)
channel_id = proto.string(2, channel_id)
pointless_nest = proto.string(80226972, channel_id + continuation_info)
return base64.urlsafe_b64encode(pointless_nest).decode('ascii')
def channel_ctoken_v1(channel_id, page, sort, tab, view=1):
tab = proto.string(2, tab)
sort = proto.uint(3, int(sort))
page = proto.string(15, str(page))
# example with shelves in videos tab: https://www.youtube.com/channel/UCNL1ZadSjHpjm4q9j2sVtOA/videos
shelf_view = proto.uint(4, 0)
view = proto.uint(6, int(view))
continuation_info = proto.string(3, proto.percent_b64encode(tab + view + sort + shelf_view + page + proto.uint(23, 0)) )
channel_id = proto.string(2, channel_id)
pointless_nest = proto.string(80226972, channel_id + continuation_info)
return base64.urlsafe_b64encode(pointless_nest).decode('ascii')
def get_channel_tab(channel_id, page="1", sort=3, tab='videos', view=1,
ctoken=None, print_status=True):
message = 'Got channel tab' if print_status else None
if not ctoken:
ctoken = channel_ctoken_v3(channel_id, page, sort, tab, view)
ctoken = ctoken.replace('=', '%3D')
# Not sure what the purpose of the key is or whether it will change
# For now it seems to be constant for the API endpoint, not dependent
# on the browsing session or channel
key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
url = 'https://www.youtube.com/youtubei/v1/browse?key=' + key
data = {
'context': {
'client': {
'hl': 'en',
'gl': 'US',
'clientName': 'WEB',
'clientVersion': '2.20180830',
},
},
'continuation': ctoken,
}
content_type_header = (('Content-Type', 'application/json'),)
content = util.fetch_url(
url, headers_desktop + content_type_header,
data=json.dumps(data), debug_name='channel_tab', report_text=message)
return content
# cache entries expire after 30 minutes
@cachetools.func.ttl_cache(maxsize=128, ttl=30*60)
def get_number_of_videos_channel(channel_id):
if channel_id is None:
return 1000
# Uploads playlist
playlist_id = 'UU' + channel_id[2:]
url = 'https://m.youtube.com/playlist?list=' + playlist_id + '&pbj=1'
try:
response = util.fetch_url(url, headers_mobile,
debug_name='number_of_videos', report_text='Got number of videos')
except urllib.error.HTTPError as e:
traceback.print_exc()
print("Couldn't retrieve number of videos")
return 1000
response = response.decode('utf-8')
# match = re.search(r'"numVideosText":\s*{\s*"runs":\s*\[{"text":\s*"([\d,]*) videos"', response)
match = re.search(r'"numVideosText".*?([,\d]+)', response)
if match:
return int(match.group(1).replace(',',''))
else:
return 0
channel_id_re = re.compile(r'videos\.xml\?channel_id=([a-zA-Z0-9_-]{24})"')
@cachetools.func.lru_cache(maxsize=128)
def get_channel_id(base_url):
# method that gives the smallest possible response at ~4 kb
# needs to be as fast as possible
base_url = base_url.replace('https://www', 'https://m') # avoid redirect
response = util.fetch_url(
base_url + '/about?pbj=1', headers_mobile,
debug_name='get_channel_id', report_text='Got channel id').decode('utf-8')
match = channel_id_re.search(response)
if match:
return match.group(1)
return None
def get_number_of_videos_general(base_url):
return get_number_of_videos_channel(get_channel_id(base_url))
def get_channel_search_json(channel_id, query, page):
offset = proto.unpadded_b64encode(proto.uint(3, (page-1)*30))
params = proto.string(2, 'search') + proto.string(15, offset)
params = proto.percent_b64encode(params)
ctoken = proto.string(2, channel_id) + proto.string(3, params) + proto.string(11, query)
ctoken = base64.urlsafe_b64encode(proto.nested(80226972, ctoken)).decode('ascii')
key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
url = 'https://www.youtube.com/youtubei/v1/browse?key=' + key
data = {
'context': {
'client': {
'hl': 'en',
'gl': 'US',
'clientName': 'WEB',
'clientVersion': '2.20180830',
},
},
'continuation': ctoken,
}
content_type_header = (('Content-Type', 'application/json'),)
polymer_json = util.fetch_url(
url, headers_desktop + content_type_header,
data=json.dumps(data), debug_name='channel_search')
return polymer_json
def post_process_channel_info(info):
info['avatar'] = util.prefix_url(info['avatar'])
info['channel_url'] = util.prefix_url(info['channel_url'])
for item in info['items']:
util.prefix_urls(item)
util.add_extra_html_info(item)
def get_channel_first_page(base_url=None, channel_id=None):
if channel_id:
base_url = 'https://www.youtube.com/channel/' + channel_id
return util.fetch_url(base_url + '/videos?pbj=1&view=0', headers_desktop,
debug_name='gen_channel_videos')
playlist_sort_codes = {'2': "da", '3': "dd", '4': "lad"}
# youtube.com/[channel_id]/[tab]
# youtube.com/user/[username]/[tab]
# youtube.com/c/[custom]/[tab]
# youtube.com/[custom]/[tab]
def get_channel_page_general_url(base_url, tab, request, channel_id=None):
page_number = int(request.args.get('page', 1))
sort = request.args.get('sort', '3')
view = request.args.get('view', '1')
query = request.args.get('query', '')
ctoken = request.args.get('ctoken', '')
default_params = (page_number == 1 and sort == '3' and view == '1')
if tab == 'videos' and channel_id and not default_params:
tasks = (
gevent.spawn(get_number_of_videos_channel, channel_id),
gevent.spawn(get_channel_tab, channel_id, page_number, sort,
'videos', view, ctoken)
)
gevent.joinall(tasks)
util.check_gevent_exceptions(*tasks)
number_of_videos, polymer_json = tasks[0].value, tasks[1].value
elif tab == 'videos':
if channel_id:
num_videos_call = (get_number_of_videos_channel, channel_id)
else:
num_videos_call = (get_number_of_videos_general, base_url)
tasks = (
gevent.spawn(*num_videos_call),
gevent.spawn(get_channel_first_page, base_url=base_url),
)
gevent.joinall(tasks)
util.check_gevent_exceptions(*tasks)
number_of_videos, polymer_json = tasks[0].value, tasks[1].value
elif tab == 'about':
polymer_json = util.fetch_url(base_url + '/about?pbj=1', headers_desktop, debug_name='gen_channel_about')
elif tab == 'playlists':
polymer_json = util.fetch_url(base_url+ '/playlists?pbj=1&view=1&sort=' + playlist_sort_codes[sort], headers_desktop, debug_name='gen_channel_playlists')
elif tab == 'search' and channel_id:
polymer_json = get_channel_search_json(channel_id, query, page_number)
elif tab == 'search':
url = base_url + '/search?pbj=1&query=' + urllib.parse.quote(query, safe='')
polymer_json = util.fetch_url(url, headers_desktop, debug_name='gen_channel_search')
else:
flask.abort(404, 'Unknown channel tab: ' + tab)
info = yt_data_extract.extract_channel_info(json.loads(polymer_json), tab)
if info['error'] is not None:
return flask.render_template('error.html', error_message=info['error'])
post_process_channel_info(info)
if tab == 'videos':
info['number_of_videos'] = number_of_videos
info['number_of_pages'] = math.ceil(number_of_videos/30)
info['header_playlist_names'] = local_playlist.get_playlist_names()
if tab in ('videos', 'playlists'):
info['current_sort'] = sort
elif tab == 'search':
info['search_box_value'] = query
info['header_playlist_names'] = local_playlist.get_playlist_names()
info['page_number'] = page_number
info['subscribed'] = subscriptions.is_subscribed(info['channel_id'])
return flask.render_template(
'channel.html',
parameters_dictionary=request.args,
**info
)
@yt_app.route('/channel/<channel_id>/')
@yt_app.route('/channel/<channel_id>/<tab>')
def get_channel_page(channel_id, tab='videos'):
return get_channel_page_general_url('https://www.youtube.com/channel/' + channel_id, tab, request, channel_id)
@yt_app.route('/user/<username>/')
@yt_app.route('/user/<username>/<tab>')
def get_user_page(username, tab='videos'):
return get_channel_page_general_url('https://www.youtube.com/user/' + username, tab, request)
@yt_app.route('/c/<custom>/')
@yt_app.route('/c/<custom>/<tab>')
def get_custom_c_page(custom, tab='videos'):
return get_channel_page_general_url('https://www.youtube.com/c/' + custom, tab, request)
@yt_app.route('/<custom>')
@yt_app.route('/<custom>/<tab>')
def get_toplevel_custom_page(custom, tab='videos'):
return get_channel_page_general_url('https://www.youtube.com/' + custom, tab, request)
|
