-# coding: utf-8
-from __future__ import unicode_literals
-
import itertools
+import random
import re
from .common import InfoExtractor
from ..utils import (
+ ExtractorError,
clean_html,
determine_ext,
- ExtractorError,
- get_element_by_attribute,
- orderedSet,
+ dict_get,
+ int_or_none,
+ js_to_json,
+ str_or_none,
+ strip_or_none,
+ traverse_obj,
+ try_get,
+ url_or_none,
)
class TVPIE(InfoExtractor):
IE_NAME = 'tvp'
IE_DESC = 'Telewizja Polska'
- _VALID_URL = r'https?://[^/]+\.tvp\.(?:pl|info)/(?:video/(?:[^,\s]*,)*|(?:(?!\d+/)[^/]+/)*)(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:[^/]+\.)?(?:tvp(?:parlament)?\.(?:pl|info)|tvpworld\.com|swipeto\.pl)/(?:(?!\d+/)[^/]+/)*(?P<id>\d+)(?:[/?#]|$)'
_TESTS = [{
- 'url': 'https://vod.tvp.pl/video/czas-honoru,i-seria-odc-13,194536',
- 'md5': 'a21eb0aa862f25414430f15fdfb9e76c',
+ # TVPlayer 2 in js wrapper
+ 'url': 'https://swipeto.pl/64095316/uliczny-foxtrot-wypozyczalnia-kaset-kto-pamieta-dvdvideo',
'info_dict': {
- 'id': '194536',
+ 'id': '64095316',
'ext': 'mp4',
- 'title': 'Czas honoru, odc. 13 – Władek',
- 'description': 'md5:437f48b93558370b031740546b696e24',
+ 'title': 'Uliczny Foxtrot — Wypożyczalnia kaset. Kto pamięta DVD-Video?',
+ 'age_limit': 0,
+ '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
+ 'url': 'https://www.tvp.pl/polska-press-video-uploader/wideo/62042351',
+ 'info_dict': {
+ 'id': '62042351',
+ 'ext': 'mp4',
+ 'title': 'Wideo',
+ 'description': 'Wideo Kamera',
+ 'duration': 24,
+ 'age_limit': 0,
+ 'thumbnail': r're:https://.+',
+ },
+ }, {
+ # TVPlayer 2 in iframe
+ 'url': 'https://wiadomosci.tvp.pl/50725617/dzieci-na-sprzedaz-dla-homoseksualistow',
+ 'info_dict': {
+ 'id': '50725617',
+ 'ext': 'mp4',
+ 'title': 'Dzieci na sprzedaż dla homoseksualistów',
+ 'description': 'md5:7d318eef04e55ddd9f87a8488ac7d590',
+ 'age_limit': 12,
+ 'duration': 259,
+ 'thumbnail': r're:https://.+',
},
}, {
- 'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',
- 'md5': 'b0005b542e5b4de643a9690326ab1257',
+ # TVPlayer 2 in client-side rendered website (regional; window.__newsData)
+ 'url': 'https://warszawa.tvp.pl/25804446/studio-yayo',
'info_dict': {
- 'id': '17916176',
+ 'id': '25804446',
'ext': 'mp4',
- 'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
- 'description': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
+ 'title': 'Studio Yayo',
+ 'upload_date': '20160616',
+ 'timestamp': 1466075700,
+ 'age_limit': 0,
+ 'duration': 20,
+ 'thumbnail': r're:https://.+',
},
+ 'skip': 'Geo-blocked outside PL',
}, {
- # page id is not the same as video id(#7799)
- 'url': 'https://wiadomosci.tvp.pl/33908820/28092017-1930',
- 'md5': '84cd3c8aec4840046e5ab712416b73d0',
+ # TVPlayer 2 in client-side rendered website (tvp.info; window.__videoData)
+ 'url': 'https://www.tvp.info/52880236/09042021-0800',
'info_dict': {
- 'id': '33908820',
+ 'id': '52880236',
'ext': 'mp4',
- 'title': 'Wiadomości, 28.09.2017, 19:30',
- 'description': 'Wydanie główne codziennego serwisu informacyjnego.'
+ 'title': '09.04.2021, 08:00',
+ 'age_limit': 0,
+ 'thumbnail': r're:https://.+',
},
- 'skip': 'HTTP Error 404: Not Found',
+ 'skip': 'Geo-blocked outside PL',
+ }, {
+ # client-side rendered (regional) program (playlist) page
+ 'url': 'https://opole.tvp.pl/9660819/rozmowa-dnia',
+ 'info_dict': {
+ 'id': '9660819',
+ 'description': 'Od poniedziałku do piątku o 18:55',
+ 'title': 'Rozmowa dnia',
+ },
+ 'playlist_mincount': 1800,
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ # ABC-specific video embeding
+ # moved to https://bajkowakraina.tvp.pl/wideo/50981130,teleranek,51027049,zubr,51116450
+ 'url': 'https://abc.tvp.pl/48636269/zubry-odc-124',
+ 'info_dict': {
+ 'id': '48320456',
+ 'ext': 'mp4',
+ 'title': 'Teleranek, Żubr',
+ },
+ 'skip': 'unavailable',
+ }, {
+ # yet another vue page
+ 'url': 'https://jp2.tvp.pl/46925618/filmy',
+ 'info_dict': {
+ 'id': '46925618',
+ 'title': 'Filmy',
+ },
+ 'playlist_mincount': 19,
}, {
'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',
'only_matching': True,
}, {
'url': 'http://www.tvp.info/25511919/trwa-rewolucja-wladza-zdecydowala-sie-na-pogwalcenie-konstytucji',
'only_matching': True,
+ }, {
+ 'url': 'https://tvp.info/49193823/teczowe-flagi-na-pomnikach-prokuratura-wszczela-postepowanie-wieszwiecej',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.tvpparlament.pl/retransmisje-vod/inne/wizyta-premiera-mateusza-morawieckiego-w-firmie-berotu-sp-z-oo/48857277',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://tvpworld.com/48583640/tescos-polish-business-bought-by-danish-chain-netto',
+ 'only_matching': True,
}]
+ def _parse_vue_website_data(self, webpage, page_id):
+ website_data = self._search_regex([
+ # website - regiony, tvp.info
+ # directory - jp2.tvp.pl
+ r'window\.__(?:website|directory)Data\s*=\s*({(?:.|\s)+?});',
+ ], webpage, 'website data')
+ if not website_data:
+ return None
+ return self._parse_json(website_data, page_id, transform_source=js_to_json)
+
+ def _extract_vue_video(self, video_data, page_id=None):
+ if isinstance(video_data, str):
+ video_data = self._parse_json(video_data, page_id, transform_source=js_to_json)
+ thumbnails = []
+ image = video_data.get('image')
+ if image:
+ for thumb in (image if isinstance(image, list) else [image]):
+ thmb_url = str_or_none(thumb.get('url'))
+ if thmb_url:
+ thumbnails.append({
+ 'url': thmb_url,
+ })
+ is_website = video_data.get('type') == 'website'
+ if is_website:
+ url = video_data['url']
+ else:
+ url = 'tvp:' + str_or_none(video_data.get('_id') or page_id)
+ return {
+ '_type': 'url_transparent',
+ 'id': str_or_none(video_data.get('_id') or page_id),
+ 'url': url,
+ 'ie_key': (TVPIE if is_website else TVPEmbedIE).ie_key(),
+ 'title': str_or_none(video_data.get('title')),
+ 'description': str_or_none(video_data.get('lead')),
+ 'timestamp': int_or_none(video_data.get('release_date_long')),
+ 'duration': int_or_none(video_data.get('duration')),
+ 'thumbnails': thumbnails,
+ }
+
+ def _handle_vuejs_page(self, url, webpage, page_id):
+ # vue client-side rendered sites (all regional pages + tvp.info)
+ video_data = self._search_regex([
+ r'window\.__(?:news|video)Data\s*=\s*({(?:.|\s)+?})\s*;',
+ ], webpage, 'video data', default=None)
+ if video_data:
+ return self._extract_vue_video(video_data, page_id=page_id)
+ # paged playlists
+ website_data = self._parse_vue_website_data(webpage, page_id)
+ if website_data:
+ entries = self._vuejs_entries(url, website_data, page_id)
+
+ return {
+ '_type': 'playlist',
+ 'id': page_id,
+ 'title': str_or_none(website_data.get('title')),
+ 'description': str_or_none(website_data.get('lead')),
+ 'entries': entries,
+ }
+ raise ExtractorError('Could not extract video/website data')
+
+ def _vuejs_entries(self, url, website_data, page_id):
+
+ def extract_videos(wd):
+ if wd.get('latestVideo'):
+ yield self._extract_vue_video(wd['latestVideo'])
+ for video in wd.get('videos') or []:
+ yield self._extract_vue_video(video)
+ for video in wd.get('items') or []:
+ yield self._extract_vue_video(video)
+
+ yield from extract_videos(website_data)
+
+ if website_data.get('items_total_count') > website_data.get('items_per_page'):
+ for page in itertools.count(2):
+ page_website_data = self._parse_vue_website_data(
+ self._download_webpage(url, page_id, note=f'Downloading page #{page}',
+ query={'page': page}),
+ page_id)
+ if not page_website_data.get('videos') and not page_website_data.get('items'):
+ break
+ yield from extract_videos(page_website_data)
+
def _real_extract(self, url):
page_id = self._match_id(url)
- webpage = self._download_webpage(url, page_id)
+ webpage, urlh = self._download_webpage_handle(url, page_id)
+
+ # The URL may redirect to a VOD
+ # example: https://vod.tvp.pl/48463890/wadowickie-spotkania-z-janem-pawlem-ii
+ for ie_cls in (TVPVODSeriesIE, TVPVODVideoIE):
+ if ie_cls.suitable(urlh.url):
+ return self.url_result(urlh.url, ie=ie_cls.ie_key(), video_id=page_id)
+
+ if re.search(
+ r'window\.__(?:video|news|website|directory)Data\s*=',
+ webpage):
+ return self._handle_vuejs_page(url, webpage, page_id)
+
+ # classic server-side rendered sites
video_id = self._search_regex([
+ r'<iframe[^>]+src="[^"]*?embed\.php\?(?:[^&]+&)*ID=(\d+)',
r'<iframe[^>]+src="[^"]*?object_id=(\d+)',
r"object_id\s*:\s*'(\d+)'",
- r'data-video-id="(\d+)"'], webpage, 'video id', default=page_id)
+ r'data-video-id="(\d+)"',
+
+ # abc.tvp.pl - somehow there are more than one video IDs that seem to be the same video?
+ # the first one is referenced to as "copyid", and seems to be unused by the website
+ r'<script>\s*tvpabc\.video\.init\(\s*\d+,\s*(\d+)\s*\)\s*</script>',
+ ], webpage, 'video id', default=page_id)
return {
'_type': 'url_transparent',
'url': 'tvp:' + video_id,
'description': self._og_search_description(
- webpage, default=None) or self._html_search_meta(
- 'description', webpage, default=None),
+ webpage, default=None) or (self._html_search_meta(
+ 'description', webpage, default=None)
+ if '//s.tvp.pl/files/portal/v' in webpage else None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'ie_key': 'TVPEmbed',
}
+class TVPStreamIE(InfoExtractor):
+ IE_NAME = 'tvp:stream'
+ _VALID_URL = r'(?:tvpstream:|https?://(?:tvpstream\.vod|stream)\.tvp\.pl/(?:\?(?:[^&]+[&;])*channel_id=)?)(?P<id>\d*)'
+ _TESTS = [{
+ 'url': 'https://stream.tvp.pl/?channel_id=56969941',
+ 'only_matching': True,
+ }, {
+ # untestable as "video" id changes many times across a day
+ 'url': 'https://tvpstream.vod.tvp.pl/?channel_id=1455',
+ 'only_matching': True,
+ }, {
+ 'url': 'tvpstream:39821455',
+ 'only_matching': True,
+ }, {
+ # the default stream when you provide no channel_id, most probably TVP Info
+ 'url': 'tvpstream:',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://tvpstream.vod.tvp.pl/',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ channel_id = self._match_id(url)
+ channel_url = self._proto_relative_url(f'//stream.tvp.pl/?channel_id={channel_id}' or 'default')
+ webpage = self._download_webpage(channel_url, channel_id or 'default', 'Downloading channel webpage')
+ channels = self._search_json(
+ r'window\.__channels\s*=', webpage, 'channel list', channel_id,
+ contains_pattern=r'\[\s*{(?s:.+)}\s*]')
+ channel = traverse_obj(channels, (lambda _, v: channel_id == str(v['id'])), get_all=False) if channel_id else channels[0]
+ audition = traverse_obj(channel, ('items', lambda _, v: v['is_live'] is True), get_all=False)
+ return {
+ '_type': 'url_transparent',
+ 'id': channel_id or channel['id'],
+ 'url': 'tvp:{}'.format(audition['video_id']),
+ 'title': audition.get('title'),
+ 'alt_title': channel.get('title'),
+ 'is_live': True,
+ 'ie_key': 'TVPEmbed',
+ }
+
+
class TVPEmbedIE(InfoExtractor):
IE_NAME = 'tvp:embed'
IE_DESC = 'Telewizja Polska'
+ _GEO_BYPASS = False
_VALID_URL = r'''(?x)
(?:
tvp:
|https?://
(?:[^/]+\.)?
- (?:tvp(?:parlament)?\.pl|tvp\.info|polandin\.com)/
+ (?:tvp(?:parlament)?\.pl|tvp\.info|tvpworld\.com|swipeto\.pl)/
(?:sess/
(?:tvplayer\.php\?.*?object_id
|TVPlayer2/(?:embed|api)\.php\?.*[Ii][Dd])
=)
(?P<id>\d+)
'''
+ _EMBED_REGEX = [rf'(?x)<iframe[^>]+?src=(["\'])(?P<url>{_VALID_URL[4:]})']
_TESTS = [{
'url': 'tvp:194536',
'title': 'Czas honoru, odc. 13 – Władek',
'description': 'md5:76649d2014f65c99477be17f23a4dead',
'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&autoplay=false',
'id': '51247504',
'ext': 'mp4',
'title': 'Razmova 091220',
+ 'duration': 876,
+ 'age_limit': 0,
+ 'thumbnail': r're:https://.+',
},
}, {
# TVPlayer2 embed URL
'only_matching': True,
}]
- @staticmethod
- def _extract_urls(webpage, **kw):
- return [m.group('embed') for m in re.finditer(
- r'(?x)<iframe[^>]+?src=(["\'])(?P<embed>%s)' % TVPEmbedIE._VALID_URL[4:],
- webpage)]
-
def _real_extract(self, url):
video_id = self._match_id(url)
))
webpage = self._download_webpage(
- ('https://www.tvp.pl/sess/TVPlayer2/api.php?id=%s'
- + '&@method=getTvpConfig&@callback=%s') % (video_id, callback), video_id)
+ f'https://www.tvp.pl/sess/TVPlayer2/api.php?id={video_id}&@method=getTvpConfig&@callback={callback}', video_id)
# stripping JSONP padding
datastr = webpage[15 + len(callback):-3]
if datastr.startswith('null,'):
- error = self._parse_json(datastr[5:], video_id)
- raise ExtractorError(error[0]['desc'])
+ error = self._parse_json(datastr[5:], video_id, fatal=False)
+ 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']
info = content['info']
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 = []
for file in content['files']:
- video_url = file.get('url')
+ video_url = url_or_none(file.get('url'))
if not video_url:
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))
- elif video_url.endswith('.mpd'):
+ elif ext == 'mpd':
if is_live:
# doesn't work with either ffmpeg or native downloader
continue
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))
elif video_url.endswith('.ism/manifest'):
formats.extend(self._extract_ism_formats(video_url, video_id, ism_id='mss', fatal=False))
else:
- # mp4, wmv or something
- quality = file.get('quality', {})
formats.append({
'format_id': 'direct',
'url': video_url,
- 'ext': determine_ext(video_url, file['type']),
- 'fps': int_or_none(quality.get('fps')),
- 'tbr': int_or_none(quality.get('bitrate')),
- 'width': int_or_none(quality.get('width')),
- 'height': int_or_none(quality.get('height')),
+ 'ext': ext or file.get('type'),
+ 'fps': int_or_none(traverse_obj(file, ('quality', 'fps'))),
+ 'tbr': int_or_none(traverse_obj(file, ('quality', 'bitrate')), scale=1000),
+ 'width': int_or_none(traverse_obj(file, ('quality', 'width'))),
+ 'height': int_or_none(traverse_obj(file, ('quality', 'height'))),
})
- self._sort_formats(formats)
-
title = dict_get(info, ('subtitle', 'title', 'seoTitle'))
description = dict_get(info, ('description', 'seoDescription'))
thumbnails = []
# vod.tvp.pl
if info.get('vortalName') == 'vod':
info_dict.update({
- 'title': '%s, %s' % (info.get('title'), info.get('subtitle')),
+ 'title': '{}, {}'.format(info.get('title'), info.get('subtitle')),
'series': info.get('title'),
'season': info.get('season'),
'episode_number': info.get('episode'),
return info_dict
-class TVPWebsiteIE(InfoExtractor):
- IE_NAME = 'tvp:series'
- _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)'
+class TVPVODBaseIE(InfoExtractor):
+ _API_BASE_URL = 'https://vod.tvp.pl/api/products'
+
+ def _call_api(self, resource, video_id, query={}, **kwargs):
+ is_valid = lambda x: 200 <= x < 300
+ document, urlh = self._download_json_handle(
+ f'{self._API_BASE_URL}/{resource}', video_id,
+ query={'lang': 'pl', 'platform': 'BROWSER', **query},
+ expected_status=lambda x: is_valid(x) or 400 <= x < 500, **kwargs)
+ if is_valid(urlh.status):
+ return document
+ raise ExtractorError(f'Woronicza said: {document.get("code")} (HTTP {urlh.status})')
+
+ def _parse_video(self, video, with_url=True):
+ info_dict = traverse_obj(video, {
+ 'id': ('id', {str_or_none}),
+ 'title': 'title',
+ 'age_limit': ('rating', {int_or_none}),
+ 'duration': ('duration', {int_or_none}),
+ 'episode_number': ('number', {int_or_none}),
+ 'series': ('season', 'serial', 'title', {str_or_none}),
+ 'thumbnails': ('images', ..., ..., {'url': ('url', {url_or_none})}),
+ })
+ info_dict['description'] = clean_html(dict_get(video, ('lead', 'description')))
+ if with_url:
+ info_dict.update({
+ '_type': 'url',
+ 'url': video['webUrl'],
+ 'ie_key': TVPVODVideoIE.ie_key(),
+ })
+ return info_dict
+
+
+class TVPVODVideoIE(TVPVODBaseIE):
+ IE_NAME = 'tvp:vod'
+ _VALID_URL = r'https?://vod\.tvp\.pl/(?P<category>[a-z\d-]+,\d+)/[a-z\d-]+(?<!-odcinki)(?:-odcinki,\d+/odcinek-\d+,S\d+E\d+)?,(?P<id>\d+)/?(?:[?#]|$)'
_TESTS = [{
- # series
- 'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312/video',
+ 'url': 'https://vod.tvp.pl/dla-dzieci,24/laboratorium-alchemika-odcinki,309338/odcinek-24,S01E24,311357',
'info_dict': {
- 'id': '38678312',
+ 'id': '311357',
+ 'ext': 'mp4',
+ 'title': 'Tusze termiczne. Jak zobaczyć niewidoczne. Odcinek 24',
+ 'description': 'md5:1d4098d3e537092ccbac1abf49b7cd4c',
+ 'duration': 300,
+ 'episode_number': 24,
+ 'episode': 'Episode 24',
+ 'age_limit': 0,
+ 'series': 'Laboratorium alchemika',
+ 'thumbnail': 're:https?://.+',
},
- 'playlist_count': 115,
+ 'params': {'skip_download': 'm3u8'},
}, {
- # film
- 'url': 'https://vod.tvp.pl/website/gloria,35139666',
+ 'url': 'https://vod.tvp.pl/filmy-dokumentalne,163/ukrainski-sluga-narodu,339667',
'info_dict': {
- 'id': '36637049',
+ 'id': '339667',
'ext': 'mp4',
- 'title': 'Gloria, Gloria',
+ 'title': 'Ukraiński sługa narodu',
+ 'description': 'md5:b7940c0a8e439b0c81653a986f544ef3',
+ 'age_limit': 12,
+ 'duration': 3051,
+ 'thumbnail': 're:https?://.+',
+ 'subtitles': 'count:2',
},
- 'params': {
- 'skip_download': True,
+ 'params': {'skip_download': 'm3u8'},
+ }, {
+ 'note': 'embed fails with "payment required"',
+ 'url': 'https://vod.tvp.pl/seriale,18/polowanie-na-cmy-odcinki,390116/odcinek-7,S01E07,398869',
+ 'info_dict': {
+ 'id': '398869',
+ 'ext': 'mp4',
+ 'title': 'odc. 7',
+ 'description': 'md5:dd2bb33f023dc5c2fbaddfbe4cb5dba0',
+ 'duration': 2750,
+ 'age_limit': 16,
+ 'series': 'Polowanie na ćmy',
+ 'episode_number': 7,
+ 'episode': 'Episode 7',
+ 'thumbnail': 're:https?://.+',
},
- 'add_ie': ['TVPEmbed'],
+ 'params': {'skip_download': 'm3u8'},
}, {
- 'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312',
- 'only_matching': True,
+ 'url': 'https://vod.tvp.pl/live,1/tvp-world,399731',
+ 'info_dict': {
+ 'id': '399731',
+ 'ext': 'mp4',
+ 'title': r're:TVP WORLD \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+ 'live_status': 'is_live',
+ 'thumbnail': 're:https?://.+',
+ },
}]
- def _entries(self, display_id, playlist_id):
- url = 'https://vod.tvp.pl/website/%s,%s/video' % (display_id, playlist_id)
- for page_num in itertools.count(1):
- page = self._download_webpage(
- url, display_id, 'Downloading page %d' % page_num,
- query={'page': page_num})
+ def _real_extract(self, url):
+ category, video_id = self._match_valid_url(url).group('category', 'id')
+
+ is_live = category == 'live,1'
+ entity = 'lives' if is_live else 'vods'
+ info_dict = self._parse_video(self._call_api(f'{entity}/{video_id}', video_id), with_url=False)
+
+ playlist = self._call_api(f'{video_id}/videos/playlist', video_id, query={'videoType': 'MOVIE'})
+
+ info_dict['formats'] = []
+ for manifest_url in traverse_obj(playlist, ('sources', 'HLS', ..., 'src')):
+ info_dict['formats'].extend(self._extract_m3u8_formats(manifest_url, video_id, fatal=False))
+ for manifest_url in traverse_obj(playlist, ('sources', 'DASH', ..., 'src')):
+ info_dict['formats'].extend(self._extract_mpd_formats(manifest_url, video_id, fatal=False))
+
+ info_dict['subtitles'] = {}
+ for sub in playlist.get('subtitles') or []:
+ info_dict['subtitles'].setdefault(sub.get('language') or 'und', []).append({
+ 'url': sub['url'],
+ 'ext': 'ttml',
+ })
+
+ info_dict['is_live'] = is_live
+
+ return info_dict
- video_ids = orderedSet(re.findall(
- r'<a[^>]+\bhref=["\']/video/%s,[^,]+,(\d+)' % display_id,
- page))
- if not video_ids:
- break
+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': 130,
+ }, {
+ '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,
+ }]
- for video_id in video_ids:
- yield self.url_result(
- 'tvp:%s' % video_id, ie=TVPEmbedIE.ie_key(),
- video_id=video_id)
+ def _entries(self, seasons, playlist_id):
+ for season in seasons:
+ episodes = self._call_api(
+ f'vods/serials/{playlist_id}/seasons/{season["id"]}/episodes', playlist_id,
+ note=f'Downloading episode list for {season["title"]}')
+ yield from map(self._parse_video, episodes)
def _real_extract(self, url):
- mobj = self._match_valid_url(url)
- display_id, playlist_id = mobj.group('display_id', 'id')
+ playlist_id = self._match_id(url)
+ 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(
- 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')),
+ )
projects / yt-dlp.git / blobdiff