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
|
from .podcasts import parse_episode, parse_podcast
from .songs import *
def parse_mixed_content(rows):
items = []
for row in rows:
if DESCRIPTION_SHELF[0] in row:
results = nav(row, DESCRIPTION_SHELF)
title = nav(results, ["header", *RUN_TEXT])
contents = nav(results, DESCRIPTION)
else:
results = next(iter(row.values()))
if "contents" not in results:
continue
title = nav(results, [*CAROUSEL_TITLE, "text"])
contents = []
for result in results["contents"]:
data = nav(result, [MTRIR], True)
content = None
if data:
page_type = nav(data, TITLE + NAVIGATION_BROWSE + PAGE_TYPE, True)
if page_type is None: # song or watch_playlist
if nav(data, NAVIGATION_WATCH_PLAYLIST_ID, True) is not None:
content = parse_watch_playlist(data)
else:
content = parse_song(data)
elif page_type == "MUSIC_PAGE_TYPE_ALBUM":
content = parse_album(data)
elif page_type == "MUSIC_PAGE_TYPE_ARTIST":
content = parse_related_artist(data)
elif page_type == "MUSIC_PAGE_TYPE_PLAYLIST":
content = parse_playlist(data)
elif page_type == "MUSIC_PAGE_TYPE_PODCAST_SHOW_DETAIL_PAGE":
content = parse_podcast(data)
elif data := nav(result, [MRLIR], True):
content = parse_song_flat(data)
elif data := nav(result, [MMRIR], True):
content = parse_episode(data)
else:
continue
contents.append(content)
items.append({"title": title, "contents": contents})
return items
def parse_content_list(results, parse_func, key=MTRIR):
contents = []
for result in results:
contents.append(parse_func(result[key]))
return contents
def parse_album(result):
album = {
"title": nav(result, TITLE_TEXT),
"type": nav(result, SUBTITLE),
"artists": [parse_id_name(x) for x in nav(result, ["subtitle", "runs"]) if "navigationEndpoint" in x],
"browseId": nav(result, TITLE + NAVIGATION_BROWSE_ID),
"audioPlaylistId": nav(result, THUMBNAIL_OVERLAY, True),
"thumbnails": nav(result, THUMBNAIL_RENDERER),
"isExplicit": nav(result, SUBTITLE_BADGE_LABEL, True) is not None,
}
if (year := nav(result, SUBTITLE2, True)) and year.isnumeric():
album["year"] = year
return album
def parse_single(result):
return {
"title": nav(result, TITLE_TEXT),
"year": nav(result, SUBTITLE, True),
"browseId": nav(result, TITLE + NAVIGATION_BROWSE_ID),
"thumbnails": nav(result, THUMBNAIL_RENDERER),
}
def parse_song(result):
song = {
"title": nav(result, TITLE_TEXT),
"videoId": nav(result, NAVIGATION_VIDEO_ID),
"playlistId": nav(result, NAVIGATION_PLAYLIST_ID, True),
"thumbnails": nav(result, THUMBNAIL_RENDERER),
}
song.update(parse_song_runs(nav(result, SUBTITLE_RUNS)))
return song
def parse_song_flat(data):
columns = [get_flex_column_item(data, i) for i in range(0, len(data["flexColumns"]))]
song = {
"title": nav(columns[0], TEXT_RUN_TEXT),
"videoId": nav(columns[0], TEXT_RUN + NAVIGATION_VIDEO_ID, True),
"artists": parse_song_artists(data, 1),
"thumbnails": nav(data, THUMBNAILS),
"isExplicit": nav(data, BADGE_LABEL, True) is not None,
}
if len(columns) > 2 and columns[2] is not None and "navigationEndpoint" in nav(columns[2], TEXT_RUN):
song["album"] = {
"name": nav(columns[2], TEXT_RUN_TEXT),
"id": nav(columns[2], TEXT_RUN + NAVIGATION_BROWSE_ID),
}
else:
song["views"] = nav(columns[1], ["text", "runs", -1, "text"]).split(" ")[0]
return song
def parse_video(result):
runs = nav(result, SUBTITLE_RUNS)
artists_len = get_dot_separator_index(runs)
videoId = nav(result, NAVIGATION_VIDEO_ID, True)
if not videoId:
videoId = next(
id for entry in nav(result, MENU_ITEMS) if nav(entry, MENU_SERVICE + QUEUE_VIDEO_ID, True)
)
return {
"title": nav(result, TITLE_TEXT),
"videoId": videoId,
"artists": parse_song_artists_runs(runs[:artists_len]),
"playlistId": nav(result, NAVIGATION_PLAYLIST_ID, True),
"thumbnails": nav(result, THUMBNAIL_RENDERER, True),
"views": runs[-1]["text"].split(" ")[0],
}
def parse_playlist(data):
playlist = {
"title": nav(data, TITLE_TEXT),
"playlistId": nav(data, TITLE + NAVIGATION_BROWSE_ID)[2:],
"thumbnails": nav(data, THUMBNAIL_RENDERER),
}
subtitle = data["subtitle"]
if "runs" in subtitle:
playlist["description"] = "".join([run["text"] for run in subtitle["runs"]])
if len(subtitle["runs"]) == 3 and re.search(r"\d+ ", nav(data, SUBTITLE2)):
playlist["count"] = nav(data, SUBTITLE2).split(" ")[0]
playlist["author"] = parse_song_artists_runs(subtitle["runs"][:1])
return playlist
def parse_related_artist(data):
subscribers = nav(data, SUBTITLE, True)
if subscribers:
subscribers = subscribers.split(" ")[0]
return {
"title": nav(data, TITLE_TEXT),
"browseId": nav(data, TITLE + NAVIGATION_BROWSE_ID),
"subscribers": subscribers,
"thumbnails": nav(data, THUMBNAIL_RENDERER),
}
def parse_watch_playlist(data):
return {
"title": nav(data, TITLE_TEXT),
"playlistId": nav(data, NAVIGATION_WATCH_PLAYLIST_ID),
"thumbnails": nav(data, THUMBNAIL_RENDERER),
}
|
