Compare commits

..

2 Commits

Author SHA1 Message Date
Remita Amine
3ded751985 [generic] comment a test covered now by AmericasTestKitchenIE 2020-12-07 15:27:13 +01:00
Remita Amine
6956db3606 [tvplay:home] Fix extraction(closes #21153) 2020-12-07 15:12:54 +01:00
2 changed files with 52 additions and 72 deletions

View File

@ -2117,23 +2117,23 @@ class GenericIE(InfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
}, },
{ # {
# Zype embed # # Zype embed
'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites', # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
'info_dict': { # 'info_dict': {
'id': '5b400b834b32992a310622b9', # 'id': '5b400b834b32992a310622b9',
'ext': 'mp4', # 'ext': 'mp4',
'title': 'Smoky Barbecue Favorites', # 'title': 'Smoky Barbecue Favorites',
'thumbnail': r're:^https?://.*\.jpe?g', # 'thumbnail': r're:^https?://.*\.jpe?g',
'description': 'md5:5ff01e76316bd8d46508af26dc86023b', # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
'upload_date': '20170909', # 'upload_date': '20170909',
'timestamp': 1504915200, # 'timestamp': 1504915200,
}, # },
'add_ie': [ZypeIE.ie_key()], # 'add_ie': [ZypeIE.ie_key()],
'params': { # 'params': {
'skip_download': True, # 'skip_download': True,
}, # },
}, # },
{ {
# videojs embed # videojs embed
'url': 'https://video.sibnet.ru/shell.php?videoid=3422904', 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',

View File

@ -12,11 +12,13 @@ from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
parse_duration,
parse_iso8601, parse_iso8601,
qualities, qualities,
try_get, try_get,
update_url_query, update_url_query,
url_or_none, url_or_none,
urljoin,
) )
@ -414,7 +416,7 @@ class ViafreeIE(InfoExtractor):
class TVPlayHomeIE(InfoExtractor): class TVPlayHomeIE(InfoExtractor):
_VALID_URL = r'https?://tvplay\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/[^/]+/[^/?#&]+-(?P<id>\d+)' _VALID_URL = r'https?://(?:tv3?)?play\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/(?:[^/]+/)*[^/?#&]+-(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/', 'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
'info_dict': { 'info_dict': {
@ -433,80 +435,58 @@ class TVPlayHomeIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
'add_ie': [TVPlayIE.ie_key()],
}, { }, {
'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/', 'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/', 'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://play.tv3.lt/aferistai-10047125',
'only_matching': True,
}, {
'url': 'https://tv3play.skaties.lv/vinas-melo-labak-10280317',
'only_matching': True,
}, {
'url': 'https://play.tv3.ee/cool-d-ga-mehhikosse-10044354',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) asset = self._download_json(
urljoin(url, '/sb/public/asset/' + video_id), video_id)
video_id = self._search_regex( m3u8_url = asset['movie']['contentUrl']
r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id') video_id = asset['assetId']
asset_title = asset['title']
if len(video_id) < 8: title = asset_title['title']
return self.url_result(
'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
m3u8_url = self._search_regex(
r'data-file\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'm3u8 url', group='url')
formats = self._extract_m3u8_formats( formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
m3u8_id='hls')
self._sort_formats(formats) self._sort_formats(formats)
title = self._search_regex( thumbnails = None
r'data-title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, image_url = asset.get('imageUrl')
'title', default=None, group='value') or self._html_search_meta( if image_url:
'title', webpage, default=None) or self._og_search_title( thumbnails = [{
webpage) 'url': urljoin(url, image_url),
'ext': 'jpg',
}]
description = self._html_search_meta( metadata = asset.get('metadata') or {}
'description', webpage,
default=None) or self._og_search_description(webpage)
thumbnail = self._search_regex(
r'data-image\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'thumbnail', default=None, group='url') or self._html_search_meta(
'thumbnail', webpage, default=None) or self._og_search_thumbnail(
webpage)
duration = int_or_none(self._search_regex(
r'data-duration\s*=\s*["\'](\d+)', webpage, 'duration',
fatal=False))
season = self._search_regex(
(r'data-series-title\s*=\s*(["\'])[^/]+/(?P<value>(?:(?!\1).)+)\1',
r'\bseason\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
'season', default=None, group='value')
season_number = int_or_none(self._search_regex(
r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number',
default=None))
episode = self._search_regex(
(r'\bepisode\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
r'data-subtitle\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
'episode', default=None, group='value')
episode_number = int_or_none(self._search_regex(
r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number',
default=None))
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': description, 'description': asset_title.get('summaryLong') or asset_title.get('summaryShort'),
'thumbnail': thumbnail, 'thumbnails': thumbnails,
'duration': duration, 'duration': parse_duration(asset_title.get('runTime')),
'season': season, 'series': asset.get('tvSeriesTitle'),
'season_number': season_number, 'season': asset.get('tvSeasonTitle'),
'episode': episode, 'season_number': int_or_none(metadata.get('seasonNumber')),
'episode_number': episode_number, 'episode': asset_title.get('titleBrief'),
'episode_number': int_or_none(metadata.get('episodeNumber')),
'formats': formats, 'formats': formats,
} }