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