mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-25 04:35:52 +01:00
[ITV] Fix extractor, add subtitles and thumbnails (#913)
Original PR: https://github.com/ytdl-org/youtube-dl/pull/28955 (see also https://github.com/ytdl-org/youtube-dl/issues/28906#issuecomment-831008270) Closes #861, https://github.com/ytdl-org/youtube-dl/issues/28906, https://github.com/ytdl-org/youtube-dl/issues/29337, https://github.com/ytdl-org/youtube-dl/issues/29190, https://github.com/ytdl-org/youtube-dl/issues/28939, https://github.com/ytdl-org/youtube-dl/issues/29620 Authored-by: coletdjnz, sleaux-meaux, Vangelis66
This commit is contained in:
parent
f60990ddfc
commit
ea706726d6
@ -5,10 +5,14 @@
|
|||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from .brightcove import BrightcoveNewIE
|
from .brightcove import BrightcoveNewIE
|
||||||
|
|
||||||
|
from ..compat import compat_str
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
|
base_url,
|
||||||
clean_html,
|
clean_html,
|
||||||
determine_ext,
|
determine_ext,
|
||||||
extract_attributes,
|
extract_attributes,
|
||||||
|
ExtractorError,
|
||||||
get_element_by_class,
|
get_element_by_class,
|
||||||
JSON_LD_RE,
|
JSON_LD_RE,
|
||||||
merge_dicts,
|
merge_dicts,
|
||||||
@ -16,6 +20,8 @@
|
|||||||
smuggle_url,
|
smuggle_url,
|
||||||
try_get,
|
try_get,
|
||||||
url_or_none,
|
url_or_none,
|
||||||
|
url_basename,
|
||||||
|
urljoin,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@ -23,15 +29,32 @@ class ITVIE(InfoExtractor):
|
|||||||
_VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
|
_VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
|
||||||
_GEO_COUNTRIES = ['GB']
|
_GEO_COUNTRIES = ['GB']
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://www.itv.com/hub/liar/2a4547a0012',
|
'url': 'https://www.itv.com/hub/plebs/2a1873a0002',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '2a4547a0012',
|
'id': '2a1873a0002',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Liar - Series 2 - Episode 6',
|
'title': 'Plebs - The Orgy',
|
||||||
'description': 'md5:d0f91536569dec79ea184f0a44cca089',
|
'description': 'md5:4d7159af53ebd5b36e8b3ec82a41fdb4',
|
||||||
'series': 'Liar',
|
'series': 'Plebs',
|
||||||
'season_number': 2,
|
'season_number': 1,
|
||||||
'episode_number': 6,
|
'episode_number': 1,
|
||||||
|
'thumbnail': r're:https?://hubimages\.itv\.com/episode/2_1873_0002'
|
||||||
|
},
|
||||||
|
'params': {
|
||||||
|
# m3u8 download
|
||||||
|
'skip_download': True,
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.itv.com/hub/the-jonathan-ross-show/2a1166a0209',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '2a1166a0209',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'The Jonathan Ross Show - Series 17 - Episode 8',
|
||||||
|
'description': 'md5:3023dcdd375db1bc9967186cdb3f1399',
|
||||||
|
'series': 'The Jonathan Ross Show',
|
||||||
|
'episode_number': 8,
|
||||||
|
'season_number': 17,
|
||||||
|
'thumbnail': r're:https?://hubimages\.itv\.com/episode/2_1873_0002'
|
||||||
},
|
},
|
||||||
'params': {
|
'params': {
|
||||||
# m3u8 download
|
# m3u8 download
|
||||||
@ -51,22 +74,16 @@ class ITVIE(InfoExtractor):
|
|||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _generate_api_headers(self, hmac):
|
||||||
video_id = self._match_id(url)
|
return merge_dicts({
|
||||||
webpage = self._download_webpage(url, video_id)
|
|
||||||
params = extract_attributes(self._search_regex(
|
|
||||||
r'(?s)(<[^>]+id="video"[^>]*>)', webpage, 'params'))
|
|
||||||
|
|
||||||
ios_playlist_url = params.get('data-video-playlist') or params['data-video-id']
|
|
||||||
hmac = params['data-video-hmac']
|
|
||||||
headers = self.geo_verification_headers()
|
|
||||||
headers.update({
|
|
||||||
'Accept': 'application/vnd.itv.vod.playlist.v2+json',
|
'Accept': 'application/vnd.itv.vod.playlist.v2+json',
|
||||||
'Content-Type': 'application/json',
|
'Content-Type': 'application/json',
|
||||||
'hmac': hmac.upper(),
|
'hmac': hmac.upper(),
|
||||||
})
|
}, self.geo_verification_headers())
|
||||||
ios_playlist = self._download_json(
|
|
||||||
ios_playlist_url, video_id, data=json.dumps({
|
def _call_api(self, video_id, playlist_url, headers, platform_tag, featureset, fatal=True):
|
||||||
|
return self._download_json(
|
||||||
|
playlist_url, video_id, data=json.dumps({
|
||||||
'user': {
|
'user': {
|
||||||
'itvUserId': '',
|
'itvUserId': '',
|
||||||
'entitlements': [],
|
'entitlements': [],
|
||||||
@ -87,15 +104,56 @@ def _real_extract(self, url):
|
|||||||
},
|
},
|
||||||
'variantAvailability': {
|
'variantAvailability': {
|
||||||
'featureset': {
|
'featureset': {
|
||||||
'min': ['hls', 'aes', 'outband-webvtt'],
|
'min': featureset,
|
||||||
'max': ['hls', 'aes', 'outband-webvtt']
|
'max': featureset
|
||||||
},
|
},
|
||||||
'platformTag': 'dotcom'
|
'platformTag': platform_tag
|
||||||
}
|
}
|
||||||
}).encode(), headers=headers)
|
}).encode(), headers=headers, fatal=fatal)
|
||||||
video_data = ios_playlist['Playlist']['Video']
|
|
||||||
ios_base_url = video_data.get('Base')
|
|
||||||
|
|
||||||
|
def _get_subtitles(self, video_id, variants, ios_playlist_url, headers, *args, **kwargs):
|
||||||
|
subtitles = {}
|
||||||
|
platform_tag_subs, featureset_subs = next(
|
||||||
|
((platform_tag, featureset)
|
||||||
|
for platform_tag, featuresets in variants.items() for featureset in featuresets
|
||||||
|
if try_get(featureset, lambda x: x[2]) == 'outband-webvtt'),
|
||||||
|
(None, None))
|
||||||
|
if platform_tag_subs or featureset_subs:
|
||||||
|
subs_playlist = self._call_api(
|
||||||
|
video_id, ios_playlist_url, headers, platform_tag_subs, featureset_subs, fatal=False)
|
||||||
|
subs = try_get(subs_playlist, lambda x: x['Playlist']['Video']['Subtitles'], list) or []
|
||||||
|
for sub in subs:
|
||||||
|
if not isinstance(sub, dict):
|
||||||
|
continue
|
||||||
|
href = url_or_none(sub.get('Href'))
|
||||||
|
if not href:
|
||||||
|
continue
|
||||||
|
subtitles.setdefault('en', []).append({'url': href})
|
||||||
|
return subtitles
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
video_id = self._match_id(url)
|
||||||
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
params = extract_attributes(self._search_regex(
|
||||||
|
r'(?s)(<[^>]+id="video"[^>]*>)', webpage, 'params'))
|
||||||
|
variants = self._parse_json(
|
||||||
|
try_get(params, lambda x: x['data-video-variants'], compat_str) or '{}',
|
||||||
|
video_id, fatal=False)
|
||||||
|
platform_tag_video, featureset_video = next(
|
||||||
|
((platform_tag, featureset)
|
||||||
|
for platform_tag, featuresets in variants.items() for featureset in featuresets
|
||||||
|
if try_get(featureset, lambda x: x[:2]) == ['hls', 'aes']),
|
||||||
|
(None, None))
|
||||||
|
if not platform_tag_video or not featureset_video:
|
||||||
|
raise ExtractorError('No downloads available', expected=True, video_id=video_id)
|
||||||
|
|
||||||
|
ios_playlist_url = params.get('data-video-playlist') or params['data-video-id']
|
||||||
|
headers = self._generate_api_headers(params['data-video-hmac'])
|
||||||
|
ios_playlist = self._call_api(
|
||||||
|
video_id, ios_playlist_url, headers, platform_tag_video, featureset_video)
|
||||||
|
|
||||||
|
video_data = try_get(ios_playlist, lambda x: x['Playlist']['Video'], dict) or {}
|
||||||
|
ios_base_url = video_data.get('Base')
|
||||||
formats = []
|
formats = []
|
||||||
for media_file in (video_data.get('MediaFiles') or []):
|
for media_file in (video_data.get('MediaFiles') or []):
|
||||||
href = media_file.get('Href')
|
href = media_file.get('Href')
|
||||||
@ -113,20 +171,6 @@ def _real_extract(self, url):
|
|||||||
'url': href,
|
'url': href,
|
||||||
})
|
})
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
subtitles = {}
|
|
||||||
subs = video_data.get('Subtitles') or []
|
|
||||||
for sub in subs:
|
|
||||||
if not isinstance(sub, dict):
|
|
||||||
continue
|
|
||||||
href = url_or_none(sub.get('Href'))
|
|
||||||
if not href:
|
|
||||||
continue
|
|
||||||
subtitles.setdefault('en', []).append({
|
|
||||||
'url': href,
|
|
||||||
'ext': determine_ext(href, 'vtt'),
|
|
||||||
})
|
|
||||||
|
|
||||||
info = self._search_json_ld(webpage, video_id, default={})
|
info = self._search_json_ld(webpage, video_id, default={})
|
||||||
if not info:
|
if not info:
|
||||||
json_ld = self._parse_json(self._search_regex(
|
json_ld = self._parse_json(self._search_regex(
|
||||||
@ -140,13 +184,33 @@ def _real_extract(self, url):
|
|||||||
info = self._json_ld(item, video_id, fatal=False) or {}
|
info = self._json_ld(item, video_id, fatal=False) or {}
|
||||||
break
|
break
|
||||||
|
|
||||||
|
thumbnails = []
|
||||||
|
thumbnail_url = try_get(params, lambda x: x['data-video-posterframe'], compat_str)
|
||||||
|
if thumbnail_url:
|
||||||
|
thumbnails.extend([{
|
||||||
|
'url': thumbnail_url.format(width=1920, height=1080, quality=100, blur=0, bg='false'),
|
||||||
|
'width': 1920,
|
||||||
|
'height': 1080,
|
||||||
|
}, {
|
||||||
|
'url': urljoin(base_url(thumbnail_url), url_basename(thumbnail_url)),
|
||||||
|
'preference': -2
|
||||||
|
}])
|
||||||
|
|
||||||
|
thumbnail_url = self._html_search_meta(['og:image', 'twitter:image'], webpage, default=None)
|
||||||
|
if thumbnail_url:
|
||||||
|
thumbnails.append({
|
||||||
|
'url': thumbnail_url,
|
||||||
|
})
|
||||||
|
self._remove_duplicate_formats(thumbnails)
|
||||||
|
|
||||||
return merge_dicts({
|
return merge_dicts({
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
|
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
'subtitles': subtitles,
|
'subtitles': self.extract_subtitles(video_id, variants, ios_playlist_url, headers),
|
||||||
'duration': parse_duration(video_data.get('Duration')),
|
'duration': parse_duration(video_data.get('Duration')),
|
||||||
'description': clean_html(get_element_by_class('episode-info__synopsis', webpage)),
|
'description': clean_html(get_element_by_class('episode-info__synopsis', webpage)),
|
||||||
|
'thumbnails': thumbnails
|
||||||
}, info)
|
}, info)
|
||||||
|
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user