etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-26 02:55:17 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'rai-update' of https://github.com/iamleot/youtube-dl into iamleot-rai-update

Browse source
This commit is contained in:
Tom-Oliver Heidel 2020-09-12 05:12:19 +02:00
commit d153de9d10
1 changed files with 49 additions and 78 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

127
youtube_dlc/extractor/rai.py
View file

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
@ -17,7 +18,6 @@
parse_duration, parse_duration,
strip_or_none, strip_or_none,
try_get, try_get,
unescapeHTML,
unified_strdate, unified_strdate,
unified_timestamp, unified_timestamp,
update_url_query, update_url_query,
@ -30,6 +30,7 @@ class RaiBaseIE(InfoExtractor):
_UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}' _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
_GEO_COUNTRIES = ['IT'] _GEO_COUNTRIES = ['IT']
_GEO_BYPASS = False _GEO_BYPASS = False
_BASE_URL = 'https://www.raiplay.it'
def _extract_relinker_info(self, relinker_url, video_id): def _extract_relinker_info(self, relinker_url, video_id):
if not re.match(r'https?://', relinker_url): if not re.match(r'https?://', relinker_url):
@ -122,41 +123,19 @@ def _extract_subtitles(url, subtitle_url):
class RaiPlayIE(RaiBaseIE): class RaiPlayIE(RaiBaseIE):
_VALID_URL = r'(?P<url>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s)\.html)' % RaiBaseIE._UUID_RE _VALID_URL = r'(?P<url>(?P<base>https?://(?:www\.)?raiplay\.it/.+?-)(?P<id>%s)(?P<ext>\.(?:html|json)))' % RaiBaseIE._UUID_RE
_TESTS = [{ _TESTS = [{
'url': 'http://www.raiplay.it/video/2016/10/La-Casa-Bianca-e06118bb-59a9-4636-b914-498e4cfd2c66.html?source=twitter',
'md5': '340aa3b7afb54bfd14a8c11786450d76',
'info_dict': {
'id': 'e06118bb-59a9-4636-b914-498e4cfd2c66',
'ext': 'mp4',
'title': 'La Casa Bianca',
'alt_title': 'S2016 - Puntata del 23/10/2016',
'description': 'md5:a09d45890850458077d1f68bb036e0a5',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Rai 3',
'creator': 'Rai 3',
'duration': 3278,
'timestamp': 1477764300,
'upload_date': '20161029',
'series': 'La Casa Bianca',
'season': '2016',
},
}, {
'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html', 'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
'md5': '8970abf8caf8aef4696e7b1f2adfc696', 'md5': '8970abf8caf8aef4696e7b1f2adfc696',
'info_dict': { 'info_dict': {
'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391', 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Report del 07/04/2014', 'title': 'Report del 07/04/2014',
'alt_title': 'S2013/14 - Puntata del 07/04/2014', 'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014 ',
'description': 'md5:f27c544694cacb46a078db84ec35d2d9', 'description': 'md5:d730c168a58f4bb35600fc2f881ec04e',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Rai 5', 'uploader': 'Rai Gulp',
'creator': 'Rai 5',
'duration': 6160, 'duration': 6160,
'series': 'Report',
'season_number': 5,
'season': '2013/14',
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -168,16 +147,15 @@ class RaiPlayIE(RaiBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
url, video_id = mobj.group('url', 'id') url, base, video_id, ext = mobj.group('url', 'base', 'id', 'ext')
media = self._download_json( media = self._download_json(
'%s?json' % url, video_id, 'Downloading video JSON') '%s%s.json' % (base, video_id), video_id, 'Downloading video JSON')
title = media['name'] title = media['name']
video = media['video'] video = media['video']
relinker_info = self._extract_relinker_info(video['contentUrl'], video_id) relinker_info = self._extract_relinker_info(video['content_url'], video_id)
self._sort_formats(relinker_info['formats']) self._sort_formats(relinker_info['formats'])
thumbnails = [] thumbnails = []
@ -185,7 +163,7 @@ def _real_extract(self, url):
for _, value in media.get('images').items(): for _, value in media.get('images').items():
if value: if value:
thumbnails.append({ thumbnails.append({
'url': value.replace('[RESOLUTION]', '600x400') 'url': urljoin(RaiBaseIE._BASE_URL, value.replace('[RESOLUTION]', '600x400'))
}) })
timestamp = unified_timestamp(try_get( timestamp = unified_timestamp(try_get(
@ -225,7 +203,7 @@ class RaiPlayLiveIE(RaiBaseIE):
'display_id': 'rainews24', 'display_id': 'rainews24',
'ext': 'mp4', 'ext': 'mp4',
'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'md5:6eca31500550f9376819f174e5644754', 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497',
'uploader': 'Rai News 24', 'uploader': 'Rai News 24',
'creator': 'Rai News 24', 'creator': 'Rai News 24',
'is_live': True, 'is_live': True,
@ -238,20 +216,32 @@ class RaiPlayLiveIE(RaiBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) media = self._download_json(
'%s.json' % urljoin(RaiBaseIE._BASE_URL, 'dirette/' + display_id),
display_id, 'Downloading channel JSON')
video_id = self._search_regex( title = media['name']
r'data-uniquename=["\']ContentItem-(%s)' % RaiBaseIE._UUID_RE, video = media['video']
webpage, 'content id') video_id = media['id'].replace('ContentItem-', '')
return { relinker_info = self._extract_relinker_info(video['content_url'], video_id)
'_type': 'url_transparent', self._sort_formats(relinker_info['formats'])
'ie_key': RaiPlayIE.ie_key(),
'url': 'http://www.raiplay.it/dirette/ContentItem-%s.html' % video_id, info = {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'title': self._live_title(title) if relinker_info.get(
'is_live') else title,
'alt_title': media.get('subtitle'),
'description': media.get('description'),
'uploader': strip_or_none(media.get('channel')),
'creator': strip_or_none(media.get('editor')),
'duration': parse_duration(video.get('duration')),
} }
info.update(relinker_info)
return info
class RaiPlayPlaylistIE(InfoExtractor): class RaiPlayPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+)'
@ -260,7 +250,7 @@ class RaiPlayPlaylistIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': 'nondirloalmiocapo', 'id': 'nondirloalmiocapo',
'title': 'Non dirlo al mio capo', 'title': 'Non dirlo al mio capo',
'description': 'md5:9f3d603b2947c1c7abb098f3b14fac86', 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
}, },
'playlist_mincount': 12, 'playlist_mincount': 12,
}] }]
@ -268,21 +258,25 @@ class RaiPlayPlaylistIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
playlist_id = self._match_id(url) playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id) media = self._download_json(
'%s.json' % urljoin(RaiBaseIE._BASE_URL, 'programmi/' + playlist_id),
playlist_id, 'Downloading program JSON')
title = self._html_search_meta( title = media['name']
('programma', 'nomeProgramma'), webpage, 'title') description = media['program_info']['description']
description = unescapeHTML(self._html_search_meta(
('description', 'og:description'), webpage, 'description')) content_sets = [s['id'] for b in media['blocks'] for s in b['sets']]
entries = [] entries = []
for mobj in re.finditer( for cs in content_sets:
r'<a\b[^>]+\bhref=(["\'])(?P<path>/raiplay/video/.+?)\1', medias = self._download_json(
webpage): '%s/%s.json' % (urljoin(RaiBaseIE._BASE_URL, 'programmi/' + playlist_id), cs),
video_url = urljoin(url, mobj.group('path')) cs, 'Downloading content set JSON')
entries.append(self.url_result( for m in medias['items']:
video_url, ie=RaiPlayIE.ie_key(), video_url = urljoin(url, m['path_id'])
video_id=RaiPlayIE._match_id(video_url))) entries.append(self.url_result(
video_url, ie=RaiPlayIE.ie_key(),
video_id=RaiPlayIE._match_id(video_url)))
return self.playlist_result(entries, playlist_id, title, description) return self.playlist_result(entries, playlist_id, title, description)
@ -316,7 +310,7 @@ class RaiIE(RaiBaseIE):
}, { }, {
# with ContentItem in og:url # with ContentItem in og:url
'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html', 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
'md5': '11959b4e44fa74de47011b5799490adf', 'md5': '6865dd00cf0bbf5772fdd89d59bd768a',
'info_dict': { 'info_dict': {
'id': 'efb17665-691c-45d5-a60c-5301333cbb0c', 'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
'ext': 'mp4', 'ext': 'mp4',
@ -326,18 +320,6 @@ class RaiIE(RaiBaseIE):
'duration': 2214, 'duration': 2214,
'upload_date': '20161103', 'upload_date': '20161103',
} }
}, {
# drawMediaRaiTV(...)
'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
'md5': '2dd727e61114e1ee9c47f0da6914e178',
'info_dict': {
'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
'ext': 'mp4',
'title': 'Il pacco',
'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20141221',
},
}, { }, {
# initEdizione('ContentItem-...' # initEdizione('ContentItem-...'
'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined', 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
@ -349,17 +331,6 @@ class RaiIE(RaiBaseIE):
'upload_date': '20170401', 'upload_date': '20170401',
}, },
'skip': 'Changes daily', 'skip': 'Changes daily',
}, {
# HDS live stream with only relinker URL
'url': 'http://www.rai.tv/dl/RaiTV/dirette/PublishingBlock-1912dbbf-3f96-44c3-b4cf-523681fbacbc.html?channel=EuroNews',
'info_dict': {
'id': '1912dbbf-3f96-44c3-b4cf-523681fbacbc',
'ext': 'flv',
'title': 'EuroNews',
},
'params': {
'skip_download': True,
},
}, { }, {
# HLS live stream with ContentItem in og:url # HLS live stream with ContentItem in og:url
'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html', 'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',