]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/funimation.py
[cleanup] Fix infodict returned fields (#8906)
[yt-dlp.git] / yt_dlp / extractor / funimation.py
CommitLineData
929ba399 1import random
8cd69fc4 2import re
929ba399
RA
3import string
4
ab4bdc91 5from .common import InfoExtractor
3d2623a8 6from ..networking.exceptions import HTTPError
ab4bdc91 7from ..utils import (
0647d925 8 ExtractorError,
f542a3d2 9 determine_ext,
f377f44d 10 int_or_none,
34921b43 11 join_nonempty,
91399b2f 12 js_to_json,
0647d925 13 make_archive_id,
8cd69fc4
J
14 orderedSet,
15 qualities,
3acf6d38 16 str_or_none,
8cd69fc4 17 traverse_obj,
3acf6d38 18 try_get,
29f63c96 19 urlencode_postdata,
ab4bdc91 20)
ab4bdc91 21
b4c299ba 22
8cd69fc4
J
23class FunimationBaseIE(InfoExtractor):
24 _NETRC_MACHINE = 'funimation'
25 _REGION = None
26 _TOKEN = None
27
28 def _get_region(self):
29 region_cookie = self._get_cookies('https://www.funimation.com').get('region')
30 region = region_cookie.value if region_cookie else self.get_param('geo_bypass_country')
31 return region or traverse_obj(
32 self._download_json(
33 'https://geo-service.prd.funimationsvc.com/geo/v1/region/check', None, fatal=False,
34 note='Checking geo-location', errnote='Unable to fetch geo-location information'),
35 'region') or 'US'
36
52efa4b3 37 def _perform_login(self, username, password):
38 if self._TOKEN:
8cd69fc4
J
39 return
40 try:
41 data = self._download_json(
42 'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
43 None, 'Logging in', data=urlencode_postdata({
44 'username': username,
45 'password': password,
46 }))
52efa4b3 47 FunimationBaseIE._TOKEN = data['token']
8cd69fc4 48 except ExtractorError as e:
3d2623a8 49 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
50 error = self._parse_json(e.cause.response.read().decode(), None)['error']
8cd69fc4
J
51 raise ExtractorError(error, expected=True)
52 raise
53
54
55class FunimationPageIE(FunimationBaseIE):
3acf6d38 56 IE_NAME = 'funimation:page'
8cd69fc4 57 _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?:(?P<lang>[^/]+)/)?(?:shows|v)/(?P<show>[^/]+)/(?P<episode>[^/?#&]+)'
3acf6d38 58
59 _TESTS = [{
60 'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
61 'info_dict': {
62 'id': '210050',
63 'ext': 'mp4',
64 'title': 'Broadcast Dub Preview',
65 # Other metadata is tested in FunimationIE
66 },
67 'params': {
68 'skip_download': 'm3u8',
69 },
70 'add_ie': ['Funimation'],
71 }, {
72 # Not available in US
73 'url': 'https://www.funimation.com/shows/hacksign/role-play/',
74 'only_matching': True,
75 }, {
76 # with lang code
77 'url': 'https://www.funimation.com/en/shows/hacksign/role-play/',
78 'only_matching': True,
79 }, {
80 'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
81 'only_matching': True,
8cd69fc4
J
82 }, {
83 'url': 'https://www.funimation.com/v/a-certain-scientific-railgun/super-powered-level-5',
84 'only_matching': True,
3acf6d38 85 }]
86
8cd69fc4
J
87 def _real_initialize(self):
88 if not self._REGION:
89 FunimationBaseIE._REGION = self._get_region()
8cd69fc4 90
3acf6d38 91 def _real_extract(self, url):
8cd69fc4
J
92 locale, show, episode = self._match_valid_url(url).group('lang', 'show', 'episode')
93
94 video_id = traverse_obj(self._download_json(
95 f'https://title-api.prd.funimationsvc.com/v1/shows/{show}/episodes/{episode}',
96 f'{show}_{episode}', query={
97 'deviceType': 'web',
98 'region': self._REGION,
99 'locale': locale or 'en'
100 }), ('videoList', ..., 'id'), get_all=False)
101
3acf6d38 102 return self.url_result(f'https://www.funimation.com/player/{video_id}', FunimationIE.ie_key(), video_id)
103
104
8cd69fc4 105class FunimationIE(FunimationBaseIE):
3acf6d38 106 _VALID_URL = r'https?://(?:www\.)?funimation\.com/player/(?P<id>\d+)'
ab4bdc91 107
b59623ef 108 _TESTS = [{
3acf6d38 109 'url': 'https://www.funimation.com/player/210051',
ab4bdc91 110 'info_dict': {
3acf6d38 111 'id': '210050',
112 'display_id': 'broadcast-dub-preview',
b59623ef 113 'ext': 'mp4',
3acf6d38 114 'title': 'Broadcast Dub Preview',
115 'thumbnail': r're:https?://.*\.(?:jpg|png)',
116 'episode': 'Broadcast Dub Preview',
117 'episode_id': '210050',
118 'season': 'Extras',
119 'season_id': '166038',
120 'season_number': 99,
121 'series': 'Attack on Titan: Junior High',
122 'description': '',
8cd69fc4 123 'duration': 155,
b59623ef 124 },
91399b2f 125 'params': {
3acf6d38 126 'skip_download': 'm3u8',
91399b2f 127 },
b091529a 128 }, {
3acf6d38 129 'note': 'player_id should be extracted with the relevent compat-opt',
130 'url': 'https://www.funimation.com/player/210051',
0b1bb1ac 131 'info_dict': {
804181dd 132 'id': '210051',
0b1bb1ac
S
133 'display_id': 'broadcast-dub-preview',
134 'ext': 'mp4',
3acf6d38 135 'title': 'Broadcast Dub Preview',
ec85ded8 136 'thumbnail': r're:https?://.*\.(?:jpg|png)',
3acf6d38 137 'episode': 'Broadcast Dub Preview',
138 'episode_id': '210050',
139 'season': 'Extras',
140 'season_id': '166038',
141 'season_number': 99,
142 'series': 'Attack on Titan: Junior High',
143 'description': '',
8cd69fc4 144 'duration': 155,
0b1bb1ac 145 },
804181dd 146 'params': {
3acf6d38 147 'skip_download': 'm3u8',
148 'compat_opts': ['seperate-video-versions'],
804181dd 149 },
b59623ef 150 }]
f542a3d2 151
3acf6d38 152 @staticmethod
153 def _get_experiences(episode):
154 for lang, lang_data in episode.get('languages', {}).items():
155 for video_data in lang_data.values():
156 for version, f in video_data.items():
157 yield lang, version.title(), f
f542a3d2 158
3acf6d38 159 def _get_episode(self, webpage, experience_id=None, episode_id=None, fatal=True):
160 ''' Extract the episode, season and show objects given either episode/experience id '''
161 show = self._parse_json(
162 self._search_regex(
163 r'show\s*=\s*({.+?})\s*;', webpage, 'show data', fatal=fatal),
164 experience_id, transform_source=js_to_json, fatal=fatal) or []
165 for season in show.get('seasons', []):
166 for episode in season.get('episodes', []):
167 if episode_id is not None:
168 if str(episode.get('episodePk')) == episode_id:
169 return episode, season, show
170 continue
171 for _, _, f in self._get_experiences(episode):
172 if f.get('experienceId') == experience_id:
173 return episode, season, show
174 if fatal:
175 raise ExtractorError('Unable to find episode information')
176 else:
177 self.report_warning('Unable to find episode information')
178 return {}, {}, {}
91399b2f 179
3acf6d38 180 def _real_extract(self, url):
181 initial_experience_id = self._match_id(url)
182 webpage = self._download_webpage(
183 url, initial_experience_id, note=f'Downloading player webpage for {initial_experience_id}')
184 episode, season, show = self._get_episode(webpage, experience_id=int(initial_experience_id))
185 episode_id = str(episode['episodePk'])
186 display_id = episode.get('slug') or episode_id
91399b2f 187
3acf6d38 188 formats, subtitles, thumbnails, duration = [], {}, [], 0
189 requested_languages, requested_versions = self._configuration_arg('language'), self._configuration_arg('version')
e919569e 190 language_preference = qualities((requested_languages or [''])[::-1])
191 source_preference = qualities((requested_versions or ['uncut', 'simulcast'])[::-1])
3acf6d38 192 only_initial_experience = 'seperate-video-versions' in self.get_param('compat_opts', [])
193
194 for lang, version, fmt in self._get_experiences(episode):
195 experience_id = str(fmt['experienceId'])
196 if (only_initial_experience and experience_id != initial_experience_id
4bb6b02f 197 or requested_languages and lang.lower() not in requested_languages
198 or requested_versions and version.lower() not in requested_versions):
3acf6d38 199 continue
200 thumbnails.append({'url': fmt.get('poster')})
201 duration = max(duration, fmt.get('duration', 0))
202 format_name = '%s %s (%s)' % (version, lang, experience_id)
203 self.extract_subtitles(
204 subtitles, experience_id, display_id=display_id, format_name=format_name,
205 episode=episode if experience_id == initial_experience_id else episode_id)
f542a3d2 206
8fa17117
RA
207 headers = {}
208 if self._TOKEN:
209 headers['Authorization'] = 'Token %s' % self._TOKEN
3acf6d38 210 page = self._download_json(
211 'https://www.funimation.com/api/showexperience/%s/' % experience_id,
212 display_id, headers=headers, expected_status=403, query={
efa944f4 213 'pinst_id': ''.join(random.choices(string.digits + string.ascii_letters, k=8)),
3acf6d38 214 }, note=f'Downloading {format_name} JSON')
215 sources = page.get('items') or []
216 if not sources:
217 error = try_get(page, lambda x: x['errors'][0], dict)
218 if error:
219 self.report_warning('%s said: Error %s - %s' % (
220 self.IE_NAME, error.get('code'), error.get('detail') or error.get('title')))
221 else:
222 self.report_warning('No sources found for format')
f542a3d2 223
3acf6d38 224 current_formats = []
225 for source in sources:
226 source_url = source.get('src')
227 source_type = source.get('videoType') or determine_ext(source_url)
228 if source_type == 'm3u8':
229 current_formats.extend(self._extract_m3u8_formats(
230 source_url, display_id, 'mp4', m3u8_id='%s-%s' % (experience_id, 'hls'), fatal=False,
231 note=f'Downloading {format_name} m3u8 information'))
232 else:
233 current_formats.append({
234 'format_id': '%s-%s' % (experience_id, source_type),
235 'url': source_url,
236 })
237 for f in current_formats:
238 # TODO: Convert language to code
e919569e 239 f.update({
240 'language': lang,
241 'format_note': version,
242 'source_preference': source_preference(version.lower()),
243 'language_preference': language_preference(lang.lower()),
244 })
3acf6d38 245 formats.extend(current_formats)
1d485a1a 246 if not formats and (requested_languages or requested_versions):
247 self.raise_no_formats(
248 'There are no video formats matching the requested languages/versions', expected=True, video_id=display_id)
3acf6d38 249 self._remove_duplicate_formats(formats)
b59623ef 250
ab4bdc91 251 return {
1e8fe57e 252 'id': episode_id,
0647d925 253 '_old_archive_ids': [make_archive_id(self, initial_experience_id)],
f542a3d2 254 'display_id': display_id,
3acf6d38 255 'duration': duration,
256 'title': episode['episodeTitle'],
257 'description': episode.get('episodeSummary'),
258 'episode': episode.get('episodeTitle'),
259 'episode_number': int_or_none(episode.get('episodeId')),
260 'episode_id': episode_id,
261 'season': season.get('seasonTitle'),
262 'season_number': int_or_none(season.get('seasonId')),
263 'season_id': str_or_none(season.get('seasonPk')),
264 'series': show.get('showTitle'),
ab4bdc91 265 'formats': formats,
3acf6d38 266 'thumbnails': thumbnails,
267 'subtitles': subtitles,
9f14daf2 268 '_format_sort_fields': ('lang', 'source'),
ab4bdc91 269 }
29f63c96 270
3acf6d38 271 def _get_subtitles(self, subtitles, experience_id, episode, display_id, format_name):
272 if isinstance(episode, str):
273 webpage = self._download_webpage(
9222c381 274 f'https://www.funimation.com/player/{experience_id}/', display_id,
3acf6d38 275 fatal=False, note=f'Downloading player webpage for {format_name}')
276 episode, _, _ = self._get_episode(webpage, episode_id=episode, fatal=False)
277
278 for _, version, f in self._get_experiences(episode):
279 for source in f.get('sources'):
280 for text_track in source.get('textTracks'):
281 if not text_track.get('src'):
282 continue
283 sub_type = text_track.get('type').upper()
284 sub_type = sub_type if sub_type != 'FULL' else None
285 current_sub = {
286 'url': text_track['src'],
34921b43 287 'name': join_nonempty(version, text_track.get('label'), sub_type, delim=' ')
3acf6d38 288 }
34921b43 289 lang = join_nonempty(text_track.get('language', 'und'),
290 version if version != 'Simulcast' else None,
291 sub_type, delim='_')
3acf6d38 292 if current_sub not in subtitles.get(lang, []):
293 subtitles.setdefault(lang, []).append(current_sub)
29f63c96 294 return subtitles
125728b0
M
295
296
8cd69fc4 297class FunimationShowIE(FunimationBaseIE):
125728b0
M
298 IE_NAME = 'funimation:show'
299 _VALID_URL = r'(?P<url>https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?P<locale>[^/]+)?/?shows/(?P<id>[^/?#&]+))/?(?:[?#]|$)'
300
301 _TESTS = [{
302 'url': 'https://www.funimation.com/en/shows/sk8-the-infinity',
303 'info_dict': {
f4f9f6d0 304 'id': '1315000',
125728b0
M
305 'title': 'SK8 the Infinity'
306 },
307 'playlist_count': 13,
308 'params': {
309 'skip_download': True,
310 },
311 }, {
312 # without lang code
313 'url': 'https://www.funimation.com/shows/ouran-high-school-host-club/',
314 'info_dict': {
f4f9f6d0 315 'id': '39643',
125728b0
M
316 'title': 'Ouran High School Host Club'
317 },
318 'playlist_count': 26,
319 'params': {
320 'skip_download': True,
321 },
322 }]
323
ad226b1d 324 def _real_initialize(self):
8cd69fc4
J
325 if not self._REGION:
326 FunimationBaseIE._REGION = self._get_region()
ad226b1d 327
125728b0 328 def _real_extract(self, url):
5ad28e7f 329 base_url, locale, display_id = self._match_valid_url(url).groups()
125728b0
M
330
331 show_info = self._download_json(
ad226b1d 332 'https://title-api.prd.funimationsvc.com/v2/shows/%s?region=%s&deviceType=web&locale=%s'
8cd69fc4
J
333 % (display_id, self._REGION, locale or 'en'), display_id)
334 items_info = self._download_json(
125728b0 335 'https://prod-api-funimationnow.dadcdigital.com/api/funimation/episodes/?limit=99999&title_id=%s'
8cd69fc4
J
336 % show_info.get('id'), display_id)
337
e6f868a6 338 vod_items = traverse_obj(items_info, ('items', ..., lambda k, _: re.match(r'(?i)mostRecent[AS]vod', k), 'item'))
125728b0
M
339
340 return {
341 '_type': 'playlist',
f4f9f6d0 342 'id': str_or_none(show_info['id']),
125728b0 343 'title': show_info['name'],
8cd69fc4 344 'entries': orderedSet(
125728b0 345 self.url_result(
3acf6d38 346 '%s/%s' % (base_url, vod_item.get('episodeSlug')), FunimationPageIE.ie_key(),
125728b0 347 vod_item.get('episodeId'), vod_item.get('episodeName'))
8cd69fc4 348 for vod_item in sorted(vod_items, key=lambda x: x.get('episodeOrder', -1))),
125728b0 349 }