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
|
from youtube_dl.YoutubeDL import YoutubeDL
import json
import urllib
from string import Template
import html
import youtube.common as common
from youtube.common import default_multi_get, get_thumbnail_url, video_id, URL_ORIGIN
import youtube.comments as comments
import gevent
video_height_priority = (360, 480, 240, 720, 1080)
_formats = {
'5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
'6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
'13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
'17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
'18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
'22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
'34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
'35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
# itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
'36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
'37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
'38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
'43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
'44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
'45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
'46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
'59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
'78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
# 3D videos
'82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
'83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
'84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
'85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
'100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
'101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
'102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
# Apple HTTP Live Streaming
'91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
'92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
'93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
'94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
'95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
'96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
'132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
'151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
# DASH mp4 video
'133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
'134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
'135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
'136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
'137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
'138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
'160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
'212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
'264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
'298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
'299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
'266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
# Dash mp4 audio
'139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
'140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
'141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
'256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
'258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
'325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
'328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
# Dash webm
'167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
'168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
'169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
'170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
'218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
'219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
'278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
'242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
# itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
'272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
'303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
'308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
'313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
'315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
# Dash webm audio
'171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
'172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
# Dash webm audio with opus inside
'249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
'250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
'251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
# RTMP (unnamed)
'_rtmp': {'protocol': 'rtmp'},
}
source_tag_template = Template('''
<source src="$src" type="$type">''')
with open("yt_watch_template.html", "r") as file:
yt_watch_template = Template(file.read())
# example:
#https://www.youtube.com/related_ajax?ctoken=CBQSJhILVGNxV29rOEF1YkXAAQDIAQDgAQGiAg0o____________AUAAGAAq0gEInJOqsOyB1tAaCNeMgaD4spLIKQioxdHSu8SF9JgBCLr27tnaioDpXwj1-L_R3s7r2wcIv8TnueeUo908CMXSganIrvHDJgiVuMirrqbgqYABCJDsu8PBzdGW8wEI_-WI2t-c-IlQCOK_m_KB_rP5wAEIl7S4serqnq5YCNSs55mMt8qLyQEImvutmp-x9LaCAQiVg96VpY_pqJMBCOPsgdTflsGRsQEI7ZfYleKIub0tCIrcsb7a_uu95gEIi9Gz6_bC76zEAQjo1c_W8JzlkhI%3D&continuation=CBQSJhILVGNxV29rOEF1YkXAAQDIAQDgAQGiAg0o____________AUAAGAAq0gEInJOqsOyB1tAaCNeMgaD4spLIKQioxdHSu8SF9JgBCLr27tnaioDpXwj1-L_R3s7r2wcIv8TnueeUo908CMXSganIrvHDJgiVuMirrqbgqYABCJDsu8PBzdGW8wEI_-WI2t-c-IlQCOK_m_KB_rP5wAEIl7S4serqnq5YCNSs55mMt8qLyQEImvutmp-x9LaCAQiVg96VpY_pqJMBCOPsgdTflsGRsQEI7ZfYleKIub0tCIrcsb7a_uu95gEIi9Gz6_bC76zEAQjo1c_W8JzlkhI%3D&itct=CCkQybcCIhMIg8PShInX2gIVgdvBCh15WA0ZKPgd
def get_bloated_more_related_videos(video_url, related_videos_token, id_token):
related_videos_token = urllib.parse.quote(related_videos_token)
url = "https://www.youtube.com/related_ajax?ctoken=" + related_videos_token + "&continuation=" + related_videos_token
headers = {
'Host': 'www.youtube.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)',
'Accept': '*/*',
'Accept-Language': 'en-US,en;q=0.5',
'Referer': video_url,
'X-YouTube-Client-Name': '1',
'X-YouTube-Client-Version': '2.20180418',
'X-Youtube-Identity-Token': id_token,
}
#print(url)
req = urllib.request.Request(url, headers=headers)
response = urllib.request.urlopen(req, timeout = 5)
content = response.read()
info = json.loads(content)
return info
def get_more_related_videos_info(video_url, related_videos_token, id_token):
results = []
info = get_bloated_more_related_videos(video_url, related_videos_token, id_token)
bloated_results = info[1]['response']['continuationContents']['watchNextSecondaryResultsContinuation']['results']
for bloated_result in bloated_results:
bloated_result = bloated_result['compactVideoRenderer']
results.append({
"title": bloated_result['title']['simpleText'],
"video_id": bloated_result['videoId'],
"views_text": bloated_result['viewCountText']['simpleText'],
"length_text": default_multi_get(bloated_result, 'lengthText', 'simpleText', default=''), # livestreams dont have a length
"length_text": bloated_result['lengthText']['simpleText'],
"uploader_name": bloated_result['longBylineText']['runs'][0]['text'],
"uploader_url": bloated_result['longBylineText']['runs'][0]['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
})
return results
def more_related_videos_html(video_info):
related_videos = get_related_videos(url, 1, video_info['related_videos_token'], video_info['id_token'])
related_videos_html = ""
for video in related_videos:
related_videos_html += Template(video_related_template).substitute(
video_title=html.escape(video["title"]),
views=video["views_text"],
uploader=html.escape(video["uploader_name"]),
uploader_channel_url=video["uploader_url"],
length=video["length_text"],
video_url = "/youtube.com/watch?v=" + video["video_id"],
thumbnail_url= get_thumbnail_url(video['video_id']),
)
return related_videos_html
def get_related_items_html(info):
result = ""
for item in info['related_vids']:
if 'list' in item: # playlist:
result += common.small_playlist_item_html(watch_page_related_playlist_info(item))
else:
result += common.small_video_item_html(watch_page_related_video_info(item))
return result
# json of related items retrieved directly from the watch page has different names for everything
# converts these to standard names
def watch_page_related_video_info(item):
result = {key: item[key] for key in ('id', 'title', 'author')}
result['duration'] = common.seconds_to_timestamp(item['length_seconds'])
try:
result['views'] = item['short_view_count_text']
except KeyError:
result['views'] = ''
return result
def watch_page_related_playlist_info(item):
return {
'size': item['playlist_length'] if item['playlist_length'] != "0" else "50+",
'title': item['playlist_title'],
'id': item['list'],
'first_video_id': item['video_id'],
}
def sort_formats(info):
info['formats'].sort(key=lambda x: default_multi_get(_formats, x['format_id'], 'height', default=0))
for index, format in enumerate(info['formats']):
if default_multi_get(_formats, format['format_id'], 'height', default=0) >= 360:
break
info['formats'] = info['formats'][index:] + info['formats'][0:index]
info['formats'] = [format for format in info['formats'] if format['acodec'] != 'none' and format['vcodec'] != 'none']
def formats_html(info):
result = ''
for format in info['formats']:
result += source_tag_template.substitute(
src=format['url'],
type='audio/' + format['ext'] if format['vcodec'] == "none" else 'video/' + format['ext'],
)
return result
def choose_format(info):
suitable_formats = []
with open('teste.txt', 'w', encoding='utf-8') as f:
f.write(json.dumps(info['formats']))
for format in info['formats']:
if (format["ext"] in ("mp4", "webm")
and format["acodec"] != "none"
and format["vcodec"] != "none"
and format.get("height","none") in video_height_priority):
suitable_formats.append(format)
current_best = (suitable_formats[0],video_height_priority.index(suitable_formats[0]["height"]))
for format in suitable_formats:
video_priority_index = video_height_priority.index(format["height"])
if video_priority_index < current_best[1]:
current_best = (format, video_priority_index)
return current_best[0]
more_comments_template = Template('''<a class="page-button more-comments" href="$url">More comments</a>''')
def get_watch_page(query_string):
id = urllib.parse.parse_qs(query_string)['v'][0]
tasks = (
gevent.spawn(comments.video_comments, id ),
gevent.spawn(YoutubeDL(params={'youtube_include_dash_manifest':False}).extract_info, "https://www.youtube.com/watch?v=" + id, download=False)
)
gevent.joinall(tasks)
comments_info, info = tasks[0].value, tasks[1].value
comments_html, ctoken = comments_info
if ctoken == '':
more_comments_button = ''
else:
more_comments_button = more_comments_template.substitute(url = URL_ORIGIN + '/comments?ctoken=' + ctoken)
#comments_html = comments.comments_html(video_id(url))
#info = YoutubeDL().extract_info(url, download=False)
#chosen_format = choose_format(info)
sort_formats(info)
upload_year = info["upload_date"][0:4]
upload_month = info["upload_date"][4:6]
upload_day = info["upload_date"][6:8]
upload_date = upload_month + "/" + upload_day + "/" + upload_year
related_videos_html = get_related_items_html(info)
page = yt_watch_template.substitute(
video_title=html.escape(info["title"]),
page_title=html.escape(info["title"]),
uploader=html.escape(info["uploader"]),
uploader_channel_url='/' + info["uploader_url"],
#upload_date=datetime.datetime.fromtimestamp(info["timestamp"]).strftime("%d %b %Y %H:%M:%S"),
upload_date = upload_date,
views='{:,}'.format(info["view_count"]),
likes=(lambda x: '{:,}'.format(x) if x is not None else "")(info["like_count"]),
dislikes=(lambda x: '{:,}'.format(x) if x is not None else "")(info["dislike_count"]),
description=html.escape(info["description"]),
video_sources=formats_html(info),
related = related_videos_html,
comments=comments_html,
more_comments_button = more_comments_button,
)
return page
|
