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
|
from youtube import util
import html
import json
# videos (all of type str):
# id
# title
# url
# author
# author_url
# thumbnail
# description
# published
# duration
# likes
# dislikes
# views
# playlist_index
# playlists:
# id
# title
# url
# author
# author_url
# thumbnail
# description
# updated
# size
# first_video_id
def get_plain_text(node):
try:
return node['simpleText']
except KeyError:
return ''.join(text_run['text'] for text_run in node['runs'])
def format_text_runs(runs):
if isinstance(runs, str):
return runs
result = ''
for text_run in runs:
if text_run.get("bold", False):
result += "<b>" + html.escape(text_run["text"]) + "</b>"
elif text_run.get('italics', False):
result += "<i>" + html.escape(text_run["text"]) + "</i>"
else:
result += html.escape(text_run["text"])
return result
def get_url(node):
try:
return node['runs'][0]['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url']
except KeyError:
return node['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url']
def get_text(node):
if node == {}:
return ''
try:
return node['simpleText']
except KeyError:
pass
try:
return node['runs'][0]['text']
except IndexError: # empty text runs
return ''
except KeyError:
print(node)
raise
def get_formatted_text(node):
try:
return node['runs']
except KeyError:
return node['simpleText']
def get_badges(node):
badges = []
for badge_node in node:
badge = badge_node['metadataBadgeRenderer']['label']
if badge.lower() != 'new':
badges.append(badge)
return badges
def get_thumbnail(node):
try:
return node['thumbnails'][0]['url'] # polymer format
except KeyError:
return node['url'] # ajax format
dispatch = {
# polymer format
'title': ('title', get_text),
'publishedTimeText': ('published', get_text),
'videoId': ('id', lambda node: node),
'descriptionSnippet': ('description', get_formatted_text),
'lengthText': ('duration', get_text),
'thumbnail': ('thumbnail', get_thumbnail),
'thumbnails': ('thumbnail', lambda node: node[0]['thumbnails'][0]['url']),
'viewCountText': ('views', get_text),
'numVideosText': ('size', lambda node: get_text(node).split(' ')[0]), # the format is "324 videos"
'videoCountText': ('size', get_text),
'playlistId': ('id', lambda node: node),
'descriptionText': ('description', get_formatted_text),
'subscriberCountText': ('subscriber_count', get_text),
'channelId': ('id', lambda node: node),
'badges': ('badges', get_badges),
# ajax format
'view_count_text': ('views', get_text),
'num_videos_text': ('size', lambda node: get_text(node).split(' ')[0]),
'owner_text': ('author', get_text),
'owner_endpoint': ('author_url', lambda node: node['url']),
'description': ('description', get_formatted_text),
'index': ('playlist_index', get_text),
'short_byline': ('author', get_text),
'length': ('duration', get_text),
'video_id': ('id', lambda node: node),
}
def ajax_info(item_json):
try:
info = {}
for key, node in item_json.items():
try:
simple_key, function = dispatch[key]
except KeyError:
continue
info[simple_key] = function(node)
return info
except KeyError:
print(item_json)
raise
def prefix_urls(item):
try:
item['thumbnail'] = '/' + item['thumbnail'].lstrip('/')
except KeyError:
pass
try:
item['author_url'] = util.URL_ORIGIN + item['author_url']
except KeyError:
pass
def add_extra_html_info(item):
if item['type'] == 'video':
item['url'] = util.URL_ORIGIN + '/watch?v=' + item['id']
video_info = {}
for key in ('id', 'title', 'author', 'duration'):
try:
video_info[key] = item[key]
except KeyError:
video_info[key] = ''
item['video_info'] = json.dumps(video_info)
elif item['type'] == 'playlist':
item['url'] = util.URL_ORIGIN + '/playlist?list=' + item['id']
elif item['type'] == 'channel':
item['url'] = util.URL_ORIGIN + "/channel/" + item['id']
def renderer_info(renderer, additional_info={}):
type = list(renderer.keys())[0]
renderer = renderer[type]
info = {}
if type == 'itemSectionRenderer':
return renderer_info(renderer['contents'][0], additional_info)
if type in ('movieRenderer', 'clarificationRenderer'):
info['type'] = 'unsupported'
return info
info.update(additional_info)
if type.startswith('compact') or (type.startswith('playlist') and type != 'playlistRenderer'):
info['item_size'] = 'small'
else:
info['item_size'] = 'medium'
if type in ('compactVideoRenderer', 'videoRenderer', 'playlistVideoRenderer', 'gridVideoRenderer'):
info['type'] = 'video'
elif type in ('playlistRenderer', 'compactPlaylistRenderer', 'gridPlaylistRenderer',
'radioRenderer', 'compactRadioRenderer', 'gridRadioRenderer',
'showRenderer', 'compactShowRenderer', 'gridShowRenderer'):
info['type'] = 'playlist'
elif type == 'channelRenderer':
info['type'] = 'channel'
elif type == 'playlistHeaderRenderer':
info['type'] = 'playlist_metadata'
else:
info['type'] = 'unsupported'
return info
try:
if 'viewCountText' in renderer: # prefer this one as it contains all the digits
info['views'] = get_text(renderer['viewCountText'])
elif 'shortViewCountText' in renderer:
info['views'] = get_text(renderer['shortViewCountText'])
if 'ownerText' in renderer:
info['author'] = renderer['ownerText']['runs'][0]['text']
info['author_url'] = renderer['ownerText']['runs'][0]['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url']
try:
overlays = renderer['thumbnailOverlays']
except KeyError:
pass
else:
for overlay in overlays:
if 'thumbnailOverlayTimeStatusRenderer' in overlay:
info['duration'] = get_text(overlay['thumbnailOverlayTimeStatusRenderer']['text'])
# show renderers don't have videoCountText
elif 'thumbnailOverlayBottomPanelRenderer' in overlay:
info['size'] = get_text(overlay['thumbnailOverlayBottomPanelRenderer']['text'])
# show renderers don't have playlistId, have to dig into the url to get it
try:
info['id'] = renderer['navigationEndpoint']['watchEndpoint']['playlistId']
except KeyError:
pass
for key, node in renderer.items():
if key in ('longBylineText', 'shortBylineText'):
info['author'] = get_text(node)
try:
info['author_url'] = get_url(node)
except KeyError:
pass
# show renderers don't have thumbnail key at top level, dig into thumbnailRenderer
elif key == 'thumbnailRenderer' and 'showCustomThumbnailRenderer' in node:
info['thumbnail'] = node['showCustomThumbnailRenderer']['thumbnail']['thumbnails'][0]['url']
else:
try:
simple_key, function = dispatch[key]
except KeyError:
continue
info[simple_key] = function(node)
if info['type'] == 'video' and 'duration' not in info:
info['duration'] = 'Live'
return info
except KeyError:
print(renderer)
raise
def parse_info_prepare_for_html(renderer, additional_info={}):
item = renderer_info(renderer, additional_info)
prefix_urls(item)
add_extra_html_info(item)
return item
|
