[extractor/tvp] Update extractors (#5346)

Closes #5328
Authored by: selfisekai
This commit is contained in:
lauren 2022-11-06 19:10:06 +01:00 committed by GitHub
parent 8c188d5d09
commit 728f4b5c2e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 161 additions and 76 deletions

View File

@ -1964,7 +1964,8 @@
TVPEmbedIE, TVPEmbedIE,
TVPIE, TVPIE,
TVPStreamIE, TVPStreamIE,
TVPWebsiteIE, TVPVODSeriesIE,
TVPVODVideoIE,
) )
from .tvplay import ( from .tvplay import (
TVPlayIE, TVPlayIE,

View File

@ -4,40 +4,51 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
clean_html,
determine_ext, determine_ext,
dict_get, dict_get,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
js_to_json, js_to_json,
orderedSet,
str_or_none, str_or_none,
strip_or_none,
traverse_obj,
try_get, try_get,
url_or_none,
) )
class TVPIE(InfoExtractor): class TVPIE(InfoExtractor):
IE_NAME = 'tvp' IE_NAME = 'tvp'
IE_DESC = 'Telewizja Polska' IE_DESC = 'Telewizja Polska'
_VALID_URL = r'https?://(?:[^/]+\.)?(?:tvp(?:parlament)?\.(?:pl|info)|polandin\.com)/(?:video/(?:[^,\s]*,)*|(?:(?!\d+/)[^/]+/)*)(?P<id>\d+)' _VALID_URL = r'https?://(?:[^/]+\.)?(?:tvp(?:parlament)?\.(?:pl|info)|tvpworld\.com|swipeto\.pl)/(?:(?!\d+/)[^/]+/)*(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
# TVPlayer 2 in js wrapper # TVPlayer 2 in js wrapper
'url': 'https://vod.tvp.pl/video/czas-honoru,i-seria-odc-13,194536', 'url': 'https://swipeto.pl/64095316/uliczny-foxtrot-wypozyczalnia-kaset-kto-pamieta-dvdvideo',
'info_dict': { 'info_dict': {
'id': '194536', 'id': '64095316',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Czas honoru, odc. 13 Władek', 'title': 'Uliczny Foxtrot — Wypożyczalnia kaset. Kto pamięta DVD-Video?',
'description': 'md5:437f48b93558370b031740546b696e24', 'age_limit': 0,
'age_limit': 12, 'duration': 374,
'thumbnail': r're:https://.+',
}, },
'expected_warnings': [
'Failed to download ISM manifest: HTTP Error 404: Not Found',
'Failed to download m3u8 information: HTTP Error 404: Not Found',
],
}, { }, {
# TVPlayer legacy # TVPlayer legacy
'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176', 'url': 'https://www.tvp.pl/polska-press-video-uploader/wideo/62042351',
'info_dict': { 'info_dict': {
'id': '17916176', 'id': '62042351',
'ext': 'mp4', 'ext': 'mp4',
'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata', 'title': 'Wideo',
'description': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata', 'description': 'Wideo Kamera',
'duration': 24,
'age_limit': 0,
'thumbnail': r're:https://.+',
}, },
}, { }, {
# TVPlayer 2 in iframe # TVPlayer 2 in iframe
@ -48,6 +59,8 @@ class TVPIE(InfoExtractor):
'title': 'Dzieci na sprzedaż dla homoseksualistów', 'title': 'Dzieci na sprzedaż dla homoseksualistów',
'description': 'md5:7d318eef04e55ddd9f87a8488ac7d590', 'description': 'md5:7d318eef04e55ddd9f87a8488ac7d590',
'age_limit': 12, 'age_limit': 12,
'duration': 259,
'thumbnail': r're:https://.+',
}, },
}, { }, {
# TVPlayer 2 in client-side rendered website (regional; window.__newsData) # TVPlayer 2 in client-side rendered website (regional; window.__newsData)
@ -58,7 +71,11 @@ class TVPIE(InfoExtractor):
'title': 'Studio Yayo', 'title': 'Studio Yayo',
'upload_date': '20160616', 'upload_date': '20160616',
'timestamp': 1466075700, 'timestamp': 1466075700,
} 'age_limit': 0,
'duration': 20,
'thumbnail': r're:https://.+',
},
'skip': 'Geo-blocked outside PL',
}, { }, {
# TVPlayer 2 in client-side rendered website (tvp.info; window.__videoData) # TVPlayer 2 in client-side rendered website (tvp.info; window.__videoData)
'url': 'https://www.tvp.info/52880236/09042021-0800', 'url': 'https://www.tvp.info/52880236/09042021-0800',
@ -66,7 +83,10 @@ class TVPIE(InfoExtractor):
'id': '52880236', 'id': '52880236',
'ext': 'mp4', 'ext': 'mp4',
'title': '09.04.2021, 08:00', 'title': '09.04.2021, 08:00',
'age_limit': 0,
'thumbnail': r're:https://.+',
}, },
'skip': 'Geo-blocked outside PL',
}, { }, {
# client-side rendered (regional) program (playlist) page # client-side rendered (regional) program (playlist) page
'url': 'https://opole.tvp.pl/9660819/rozmowa-dnia', 'url': 'https://opole.tvp.pl/9660819/rozmowa-dnia',
@ -122,7 +142,7 @@ class TVPIE(InfoExtractor):
'url': 'https://www.tvpparlament.pl/retransmisje-vod/inne/wizyta-premiera-mateusza-morawieckiego-w-firmie-berotu-sp-z-oo/48857277', 'url': 'https://www.tvpparlament.pl/retransmisje-vod/inne/wizyta-premiera-mateusza-morawieckiego-w-firmie-berotu-sp-z-oo/48857277',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://polandin.com/47942651/pln-10-billion-in-subsidies-transferred-to-companies-pm', 'url': 'https://tvpworld.com/48583640/tescos-polish-business-bought-by-danish-chain-netto',
'only_matching': True, 'only_matching': True,
}] }]
@ -151,16 +171,13 @@ def _extract_vue_video(self, video_data, page_id=None):
is_website = video_data.get('type') == 'website' is_website = video_data.get('type') == 'website'
if is_website: if is_website:
url = video_data['url'] url = video_data['url']
fucked_up_url_parts = re.match(r'https?://vod\.tvp\.pl/(\d+)/([^/?#]+)', url)
if fucked_up_url_parts:
url = f'https://vod.tvp.pl/website/{fucked_up_url_parts.group(2)},{fucked_up_url_parts.group(1)}'
else: else:
url = 'tvp:' + str_or_none(video_data.get('_id') or page_id) url = 'tvp:' + str_or_none(video_data.get('_id') or page_id)
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',
'id': str_or_none(video_data.get('_id') or page_id), 'id': str_or_none(video_data.get('_id') or page_id),
'url': url, 'url': url,
'ie_key': 'TVPEmbed' if not is_website else 'TVPWebsite', 'ie_key': (TVPIE if is_website else TVPEmbedIE).ie_key(),
'title': str_or_none(video_data.get('title')), 'title': str_or_none(video_data.get('title')),
'description': str_or_none(video_data.get('lead')), 'description': str_or_none(video_data.get('lead')),
'timestamp': int_or_none(video_data.get('release_date_long')), 'timestamp': int_or_none(video_data.get('release_date_long')),
@ -217,8 +234,9 @@ def _real_extract(self, url):
# The URL may redirect to a VOD # The URL may redirect to a VOD
# example: https://vod.tvp.pl/48463890/wadowickie-spotkania-z-janem-pawlem-ii # example: https://vod.tvp.pl/48463890/wadowickie-spotkania-z-janem-pawlem-ii
if TVPWebsiteIE.suitable(urlh.url): for ie_cls in (TVPVODSeriesIE, TVPVODVideoIE):
return self.url_result(urlh.url, ie=TVPWebsiteIE.ie_key(), video_id=page_id) if ie_cls.suitable(urlh.url):
return self.url_result(urlh.url, ie=ie_cls.ie_key(), video_id=page_id)
if re.search( if re.search(
r'window\.__(?:video|news|website|directory)Data\s*=', r'window\.__(?:video|news|website|directory)Data\s*=',
@ -297,12 +315,13 @@ def _real_extract(self, url):
class TVPEmbedIE(InfoExtractor): class TVPEmbedIE(InfoExtractor):
IE_NAME = 'tvp:embed' IE_NAME = 'tvp:embed'
IE_DESC = 'Telewizja Polska' IE_DESC = 'Telewizja Polska'
_GEO_BYPASS = False
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
(?: (?:
tvp: tvp:
|https?:// |https?://
(?:[^/]+\.)? (?:[^/]+\.)?
(?:tvp(?:parlament)?\.pl|tvp\.info|polandin\.com)/ (?:tvp(?:parlament)?\.pl|tvp\.info|tvpworld\.com|swipeto\.pl)/
(?:sess/ (?:sess/
(?:tvplayer\.php\?.*?object_id (?:tvplayer\.php\?.*?object_id
|TVPlayer2/(?:embed|api)\.php\?.*[Ii][Dd]) |TVPlayer2/(?:embed|api)\.php\?.*[Ii][Dd])
@ -320,6 +339,12 @@ class TVPEmbedIE(InfoExtractor):
'title': 'Czas honoru, odc. 13 Władek', 'title': 'Czas honoru, odc. 13 Władek',
'description': 'md5:76649d2014f65c99477be17f23a4dead', 'description': 'md5:76649d2014f65c99477be17f23a4dead',
'age_limit': 12, 'age_limit': 12,
'duration': 2652,
'series': 'Czas honoru',
'episode': 'Episode 13',
'episode_number': 13,
'season': 'sezon 1',
'thumbnail': r're:https://.+',
}, },
}, { }, {
'url': 'https://www.tvp.pl/sess/tvplayer.php?object_id=51247504&amp;autoplay=false', 'url': 'https://www.tvp.pl/sess/tvplayer.php?object_id=51247504&amp;autoplay=false',
@ -327,6 +352,9 @@ class TVPEmbedIE(InfoExtractor):
'id': '51247504', 'id': '51247504',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Razmova 091220', 'title': 'Razmova 091220',
'duration': 876,
'age_limit': 0,
'thumbnail': r're:https://.+',
}, },
}, { }, {
# TVPlayer2 embed URL # TVPlayer2 embed URL
@ -361,40 +389,48 @@ def _real_extract(self, url):
# stripping JSONP padding # stripping JSONP padding
datastr = webpage[15 + len(callback):-3] datastr = webpage[15 + len(callback):-3]
if datastr.startswith('null,'): if datastr.startswith('null,'):
error = self._parse_json(datastr[5:], video_id) error = self._parse_json(datastr[5:], video_id, fatal=False)
raise ExtractorError(error[0]['desc']) error_desc = traverse_obj(error, (0, 'desc'))
if error_desc == 'Obiekt wymaga płatności':
raise ExtractorError('Video requires payment and log-in, but log-in is not implemented')
raise ExtractorError(error_desc or 'unexpected JSON error')
content = self._parse_json(datastr, video_id)['content'] content = self._parse_json(datastr, video_id)['content']
info = content['info'] info = content['info']
is_live = try_get(info, lambda x: x['isLive'], bool) is_live = try_get(info, lambda x: x['isLive'], bool)
if info.get('isGeoBlocked'):
# actual country list is not provided, we just assume it's always available in PL
self.raise_geo_restricted(countries=['PL'])
formats = [] formats = []
for file in content['files']: for file in content['files']:
video_url = file.get('url') video_url = url_or_none(file.get('url'))
if not video_url: if not video_url:
continue continue
if video_url.endswith('.m3u8'): ext = determine_ext(video_url, None)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False, live=is_live)) formats.extend(self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False, live=is_live))
elif video_url.endswith('.mpd'): elif ext == 'mpd':
if is_live: if is_live:
# doesn't work with either ffmpeg or native downloader # doesn't work with either ffmpeg or native downloader
continue continue
formats.extend(self._extract_mpd_formats(video_url, video_id, mpd_id='dash', fatal=False)) formats.extend(self._extract_mpd_formats(video_url, video_id, mpd_id='dash', fatal=False))
elif video_url.endswith('.f4m'): elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(video_url, video_id, f4m_id='hds', fatal=False)) formats.extend(self._extract_f4m_formats(video_url, video_id, f4m_id='hds', fatal=False))
elif video_url.endswith('.ism/manifest'): elif video_url.endswith('.ism/manifest'):
formats.extend(self._extract_ism_formats(video_url, video_id, ism_id='mss', fatal=False)) formats.extend(self._extract_ism_formats(video_url, video_id, ism_id='mss', fatal=False))
else: else:
# mp4, wmv or something
quality = file.get('quality', {})
formats.append({ formats.append({
'format_id': 'direct', 'format_id': 'direct',
'url': video_url, 'url': video_url,
'ext': determine_ext(video_url, file['type']), 'ext': ext or file.get('type'),
'fps': int_or_none(quality.get('fps')), 'fps': int_or_none(traverse_obj(file, ('quality', 'fps'))),
'tbr': int_or_none(quality.get('bitrate')), 'tbr': int_or_none(traverse_obj(file, ('quality', 'bitrate')), scale=1000),
'width': int_or_none(quality.get('width')), 'width': int_or_none(traverse_obj(file, ('quality', 'width'))),
'height': int_or_none(quality.get('height')), 'height': int_or_none(traverse_obj(file, ('quality', 'height'))),
}) })
self._sort_formats(formats) self._sort_formats(formats)
@ -449,57 +485,105 @@ def _real_extract(self, url):
return info_dict return info_dict
class TVPWebsiteIE(InfoExtractor): class TVPVODBaseIE(InfoExtractor):
IE_NAME = 'tvp:series' _API_BASE_URL = 'https://vod.tvp.pl/api/products'
_VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)'
def _call_api(self, resource, video_id, **kwargs):
return self._download_json(
f'{self._API_BASE_URL}/{resource}', video_id,
query={'lang': 'pl', 'platform': 'BROWSER'}, **kwargs)
def _parse_video(self, video):
return {
'_type': 'url',
'url': 'tvp:' + video['externalUid'],
'ie_key': TVPEmbedIE.ie_key(),
'title': video.get('title'),
'description': traverse_obj(video, ('lead', 'description')),
'age_limit': int_or_none(video.get('rating')),
'duration': int_or_none(video.get('duration')),
}
class TVPVODVideoIE(TVPVODBaseIE):
IE_NAME = 'tvp:vod'
_VALID_URL = r'https?://vod\.tvp\.pl/[a-z\d-]+,\d+/[a-z\d-]+(?<!-odcinki)(?:-odcinki,\d+/odcinek-\d+,S\d+E\d+)?,(?P<id>\d+)(?:\?[^#]+)?(?:#.+)?$'
_TESTS = [{ _TESTS = [{
# series 'url': 'https://vod.tvp.pl/dla-dzieci,24/laboratorium-alchemika-odcinki,309338/odcinek-24,S01E24,311357',
'url': 'https://vod.tvp.pl/website/wspaniale-stulecie,17069012/video',
'info_dict': { 'info_dict': {
'id': '17069012', 'id': '60468609',
},
'playlist_count': 312,
}, {
# film
'url': 'https://vod.tvp.pl/website/krzysztof-krawczyk-cale-moje-zycie,51374466',
'info_dict': {
'id': '51374509',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Krzysztof Krawczyk całe moje życie, Krzysztof Krawczyk całe moje życie', 'title': 'Laboratorium alchemika, Tusze termiczne. Jak zobaczyć niewidoczne. Odcinek 24',
'description': 'md5:2e80823f00f5fc263555482f76f8fa42', 'description': 'md5:1d4098d3e537092ccbac1abf49b7cd4c',
'age_limit': 12, 'duration': 300,
'episode_number': 24,
'episode': 'Episode 24',
'age_limit': 0,
'series': 'Laboratorium alchemika',
'thumbnail': 're:https://.+',
}, },
'params': {
'skip_download': True,
},
'add_ie': ['TVPEmbed'],
}, { }, {
'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312', 'url': 'https://vod.tvp.pl/filmy-dokumentalne,163/ukrainski-sluga-narodu,339667',
'info_dict': {
'id': '51640077',
'ext': 'mp4',
'title': 'Ukraiński sługa narodu, Ukraiński sługa narodu',
'series': 'Ukraiński sługa narodu',
'description': 'md5:b7940c0a8e439b0c81653a986f544ef3',
'age_limit': 12,
'episode': 'Episode 0',
'episode_number': 0,
'duration': 3051,
'thumbnail': 're:https://.+',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self._parse_video(self._call_api(f'vods/{video_id}', video_id))
class TVPVODSeriesIE(TVPVODBaseIE):
IE_NAME = 'tvp:vod:series'
_VALID_URL = r'https?://vod\.tvp\.pl/[a-z\d-]+,\d+/[a-z\d-]+-odcinki,(?P<id>\d+)(?:\?[^#]+)?(?:#.+)?$'
_TESTS = [{
'url': 'https://vod.tvp.pl/seriale,18/ranczo-odcinki,316445',
'info_dict': {
'id': '316445',
'title': 'Ranczo',
'age_limit': 12,
'categories': ['seriale'],
},
'playlist_count': 129,
}, {
'url': 'https://vod.tvp.pl/programy,88/rolnik-szuka-zony-odcinki,284514',
'only_matching': True,
}, {
'url': 'https://vod.tvp.pl/dla-dzieci,24/laboratorium-alchemika-odcinki,309338',
'only_matching': True, 'only_matching': True,
}] }]
def _entries(self, display_id, playlist_id): def _entries(self, seasons, playlist_id):
url = 'https://vod.tvp.pl/website/%s,%s/video' % (display_id, playlist_id) for season in seasons:
for page_num in itertools.count(1): episodes = self._call_api(
page = self._download_webpage( f'vods/serials/{playlist_id}/seasons/{season["id"]}/episodes', playlist_id,
url, display_id, 'Downloading page %d' % page_num, note=f'Downloading episode list for {season["title"]}')
query={'page': page_num}) yield from map(self._parse_video, episodes)
video_ids = orderedSet(re.findall(
r'<a[^>]+\bhref=["\']/video/%s,[^,]+,(\d+)' % display_id,
page))
if not video_ids:
break
for video_id in video_ids:
yield self.url_result(
'tvp:%s' % video_id, ie=TVPEmbedIE.ie_key(),
video_id=video_id)
def _real_extract(self, url): def _real_extract(self, url):
mobj = self._match_valid_url(url) playlist_id = self._match_id(url)
display_id, playlist_id = mobj.group('display_id', 'id') metadata = self._call_api(
f'vods/serials/{playlist_id}', playlist_id,
note='Downloading serial metadata')
seasons = self._call_api(
f'vods/serials/{playlist_id}/seasons', playlist_id,
note='Downloading season list')
return self.playlist_result( return self.playlist_result(
self._entries(display_id, playlist_id), playlist_id) self._entries(seasons, playlist_id), playlist_id, strip_or_none(metadata.get('title')),
clean_html(traverse_obj(metadata, ('description', 'lead'), expected_type=strip_or_none)),
categories=[traverse_obj(metadata, ('mainCategory', 'name'))],
age_limit=int_or_none(metadata.get('rating')),
)