From dd9e0f58f3482204491007e06a134c69788b1c82 Mon Sep 17 00:00:00 2001 From: Leonardo Taccari Date: Fri, 20 Nov 2020 10:00:05 +0100 Subject: [PATCH] [rai] Fix extraction for recent raiplay.it updates (#27077) - Remove first test of RaiPlayIE: it is no longer available - Make RaiPlayIE extension-agnostic (passing possible `.json' URLs is now supported too) - Adjust RaiPlayLiveIE to recent raiplay.it updates. Passing it as `url_transparent' is no longer supported (there is no longer an accessible ContentItem) - Adjust RaiPlayPlaylistIE to recent raiplay.it updates and instruct it about ContentSet-s. - Update a RaiIE test and remove two tests that are no longer availables Thanks to @remitamine for the review! --- youtube_dl/extractor/rai.py | 126 +++++++++++++++--------------------- 1 file changed, 52 insertions(+), 74 deletions(-) diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index bee2d53f5..dae7800d2 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -17,7 +17,6 @@ from ..utils import ( int_or_none, parse_duration, strip_or_none, - unescapeHTML, unified_strdate, unified_timestamp, update_url_query, @@ -122,27 +121,8 @@ class RaiBaseIE(InfoExtractor): class RaiPlayIE(RaiBaseIE): - _VALID_URL = r'(?Phttps?://(?:www\.)?raiplay\.it/.+?-(?P%s)\.html)' % RaiBaseIE._UUID_RE + _VALID_URL = r'(?Phttps?://(?:www\.)?raiplay\.it/.+?-)(?P%s)\.(?:html|json)' % RaiBaseIE._UUID_RE _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$', - 'uploader': 'Rai 3', - 'creator': 'Rai 3', - 'duration': 3278, - 'timestamp': 1477764300, - 'upload_date': '20161029', - 'series': 'La Casa Bianca', - 'season': '2016', - }, - 'skip': 'This content is not available', - }, { 'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html', 'md5': '8970abf8caf8aef4696e7b1f2adfc696', 'info_dict': { @@ -166,10 +146,11 @@ class RaiPlayIE(RaiBaseIE): }] def _real_extract(self, url): - url, video_id = re.match(self._VALID_URL, url).groups() + mobj = re.match(self._VALID_URL, url) + base, video_id, = mobj.group('base', 'id') media = self._download_json( - url.replace('.html', '.json'), video_id, 'Downloading video JSON') + '%s%s.json' % (base, video_id), video_id, 'Downloading video JSON') title = media['name'] @@ -219,7 +200,7 @@ class RaiPlayIE(RaiBaseIE): class RaiPlayLiveIE(RaiBaseIE): - _VALID_URL = r'https?://(?:www\.)?raiplay\.it/dirette/(?P[^/?#&]+)' + _VALID_URL = r'(?Phttps?://(?:www\.)?raiplay\.it/dirette/(?P[^/?#&]+))' _TEST = { 'url': 'http://www.raiplay.it/dirette/rainews24', 'info_dict': { @@ -227,7 +208,7 @@ class RaiPlayLiveIE(RaiBaseIE): 'display_id': 'rainews24', 'ext': 'mp4', 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'description': 'md5:6eca31500550f9376819f174e5644754', + 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497', 'uploader': 'Rai News 24', 'creator': 'Rai News 24', 'is_live': True, @@ -238,53 +219,75 @@ class RaiPlayLiveIE(RaiBaseIE): } def _real_extract(self, url): - display_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + base, display_id, = mobj.group('base', 'id') - webpage = self._download_webpage(url, display_id) + media = self._download_json( + '%s.json' % base, + display_id, 'Downloading channel JSON') - video_id = self._search_regex( - r'data-uniquename=["\']ContentItem-(%s)' % RaiBaseIE._UUID_RE, - webpage, 'content id') + title = media['name'] + video = media['video'] + video_id = media['id'].replace('ContentItem-', '') - return { - '_type': 'url_transparent', - 'ie_key': RaiPlayIE.ie_key(), - 'url': 'http://www.raiplay.it/dirette/ContentItem-%s.html' % video_id, + relinker_info = self._extract_relinker_info(video['content_url'], video_id) + self._sort_formats(relinker_info['formats']) + + info = { 'id': video_id, 'display_id': display_id, + 'title': self._live_title(title) if relinker_info.get( + 'is_live') else title, + 'description': media.get('description'), + 'uploader': strip_or_none(media.get('channel')), + 'creator': strip_or_none(media.get('editor')), } + info.update(relinker_info) + return info + class RaiPlayPlaylistIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P[^/?#&]+)' + _VALID_URL = r'(?Phttps?://(?:www\.)?raiplay\.it/programmi/(?P[^/?#&]+))' _TESTS = [{ 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/', 'info_dict': { 'id': 'nondirloalmiocapo', 'title': 'Non dirlo al mio capo', - 'description': 'md5:9f3d603b2947c1c7abb098f3b14fac86', + 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b', }, 'playlist_mincount': 12, }] def _real_extract(self, url): - playlist_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + base, playlist_id, = mobj.group('base', 'id') - webpage = self._download_webpage(url, playlist_id) + media = self._download_json( + '%s.json' % base, + playlist_id, 'Downloading program JSON') - title = self._html_search_meta( - ('programma', 'nomeProgramma'), webpage, 'title') - description = unescapeHTML(self._html_search_meta( - ('description', 'og:description'), webpage, 'description')) + title = media.get('name') + description = None + if media.get('program_info') and media['program_info'].get('description'): + description = media['program_info']['description'] entries = [] - for mobj in re.finditer( - r']+\bhref=(["\'])(?P/raiplay/video/.+?)\1', - webpage): - video_url = urljoin(url, mobj.group('path')) - entries.append(self.url_result( - video_url, ie=RaiPlayIE.ie_key(), - video_id=RaiPlayIE._match_id(video_url))) + for b in media.get('blocks', []): + for s in b.get('sets', []): + cs = s.get('id') + if not cs: + continue + medias = self._download_json( + '%s/%s.json' % (base, cs), + cs, 'Downloading content set JSON', fatal=False) + if not medias: + continue + for m in medias['items']: + video_url = urljoin(url, m['path_id']) + 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) @@ -329,19 +332,6 @@ class RaiIE(RaiBaseIE): 'duration': 2214, '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', - }, - 'skip': 'This content is not available', }, { # initEdizione('ContentItem-...' 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined', @@ -353,18 +343,6 @@ class RaiIE(RaiBaseIE): 'upload_date': '20170401', }, '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, - }, - 'skip': 'This content is available only in Italy', }, { # HLS live stream with ContentItem in og:url 'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',