pkgsrc-Changes archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

CVS commit: pkgsrc/net/youtube-dl



Module Name:    pkgsrc
Committed By:   leot
Date:           Mon Dec  9 11:45:59 UTC 2019

Modified Files:
        pkgsrc/net/youtube-dl: Makefile distinfo
Added Files:
        pkgsrc/net/youtube-dl/patches: patch-youtube__dl_extractor_rai.py

Log Message:
youtube-dl: Apply a patch to fix rai extractor

Shared upstream via:

 <https://github.com/ytdl-org/youtube-dl/pull/23040/>


To generate a diff of this commit:
cvs rdiff -u -r1.193 -r1.194 pkgsrc/net/youtube-dl/Makefile
cvs rdiff -u -r1.176 -r1.177 pkgsrc/net/youtube-dl/distinfo
cvs rdiff -u -r0 -r1.1 \
    pkgsrc/net/youtube-dl/patches/patch-youtube__dl_extractor_rai.py

Please note that diffs are not public domain; they are subject to the
copyright notices on the relevant files.

Modified files:

Index: pkgsrc/net/youtube-dl/Makefile
diff -u pkgsrc/net/youtube-dl/Makefile:1.193 pkgsrc/net/youtube-dl/Makefile:1.194
--- pkgsrc/net/youtube-dl/Makefile:1.193        Thu Nov 28 21:22:07 2019
+++ pkgsrc/net/youtube-dl/Makefile      Mon Dec  9 11:45:59 2019
@@ -1,10 +1,11 @@
-# $NetBSD: Makefile,v 1.193 2019/11/28 21:22:07 leot Exp $
+# $NetBSD: Makefile,v 1.194 2019/12/09 11:45:59 leot Exp $
 
 # XXX: VERSION_DATE can contains also an optional part that indicates
 # XXX: possible same day revisions. PKGNAME preserves that dotted part as is.
 VERSION_DATE=  2019.11.28
 DISTNAME=      youtube-dl-${VERSION_DATE}
 PKGNAME=       ${DISTNAME:S/.//:S/.//}
+PKGREVISION=   1
 CATEGORIES=    net
 MASTER_SITES=  https://youtube-dl.org/downloads/${VERSION_DATE}/
 

Index: pkgsrc/net/youtube-dl/distinfo
diff -u pkgsrc/net/youtube-dl/distinfo:1.176 pkgsrc/net/youtube-dl/distinfo:1.177
--- pkgsrc/net/youtube-dl/distinfo:1.176        Thu Nov 28 21:22:07 2019
+++ pkgsrc/net/youtube-dl/distinfo      Mon Dec  9 11:45:59 2019
@@ -1,8 +1,9 @@
-$NetBSD: distinfo,v 1.176 2019/11/28 21:22:07 leot Exp $
+$NetBSD: distinfo,v 1.177 2019/12/09 11:45:59 leot Exp $
 
 SHA1 (youtube-dl-2019.11.28.tar.gz) = c8537c966bda1e68d3b7b8f7e392ae488dbed063
 RMD160 (youtube-dl-2019.11.28.tar.gz) = 3958b538feb2d23968a96051f52487b61980b215
 SHA512 (youtube-dl-2019.11.28.tar.gz) = fd3fc9658428ecf96d681dd699db49e02f94343e5c49e370cb68a5764e8ecebc14b3ce5bc44db0a829b0d3c4fbffc96a1f8288fb24cbd21add6e9c7852b0915d
 Size (youtube-dl-2019.11.28.tar.gz) = 3148365 bytes
 SHA1 (patch-setup.py) = a67074ae7cfe5e77847c2f610337ea553eddb69b
+SHA1 (patch-youtube__dl_extractor_rai.py) = ae67a6fb599c90491fd68b72bf71821659a2eca4
 SHA1 (patch-youtube__dl_postprocessor_ffmpeg.py) = f96676170a448d9205d542a7def4beca615a1490

Added files:

Index: pkgsrc/net/youtube-dl/patches/patch-youtube__dl_extractor_rai.py
diff -u /dev/null pkgsrc/net/youtube-dl/patches/patch-youtube__dl_extractor_rai.py:1.1
--- /dev/null   Mon Dec  9 11:45:59 2019
+++ pkgsrc/net/youtube-dl/patches/patch-youtube__dl_extractor_rai.py    Mon Dec  9 11:45:59 2019
@@ -0,0 +1,212 @@
+$NetBSD: patch-youtube__dl_extractor_rai.py,v 1.1 2019/12/09 11:45:59 leot Exp $
+
+[rai] Fix extraction for recent raiplay.it updates
+
+- Introduce _BASE_URL in RaiBaseIE class so it could be reused as base for the
+  several subextractors.
+- Remove first test of RaiPlayIE, it is no longer available
+- Adjust RaiPlayIE to recent raiplay.it updates, make it extension agnostic
+  (passing possible `.json' URLs is now supported too) and update test
+  info_dict.
+- 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.
+
+This fix issue #22923, #22906 and supersedes #23006.
+
+Shared upstream via:
+
+ https://github.com/ytdl-org/youtube-dl/pull/23040
+
+--- youtube_dl/extractor/rai.py.orig
++++ youtube_dl/extractor/rai.py
+@@ -17,7 +17,6 @@
+     parse_duration,
+     strip_or_none,
+     try_get,
+-    unescapeHTML,
+     unified_strdate,
+     unified_timestamp,
+     update_url_query,
+@@ -30,6 +29,7 @@ class RaiBaseIE(InfoExtractor):
+     _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
+     _GEO_COUNTRIES = ['IT']
+     _GEO_BYPASS = False
++    _BASE_URL = 'https://www.raiplay.it'
+ 
+     def _extract_relinker_info(self, relinker_url, video_id):
+         if not re.match(r'https?://', relinker_url):
+@@ -122,41 +122,19 @@ def _extract_subtitles(url, subtitle_url):
+ 
+ 
+ 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 = [{
+-        '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$',
+-            'uploader': 'Rai 3',
+-            'creator': 'Rai 3',
+-            'duration': 3278,
+-            'timestamp': 1477764300,
+-            'upload_date': '20161029',
+-            'series': 'La Casa Bianca',
+-            'season': '2016',
+-        },
+-    }, {
+         'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
+         'md5': '8970abf8caf8aef4696e7b1f2adfc696',
+         'info_dict': {
+             'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
+             'ext': 'mp4',
+             'title': 'Report del 07/04/2014',
+-            'alt_title': 'S2013/14 - Puntata del 07/04/2014',
+-            'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
++            'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014 ',
++            'description': 'md5:d730c168a58f4bb35600fc2f881ec04e',
+             'thumbnail': r're:^https?://.*\.jpg$',
+-            'uploader': 'Rai 5',
+-            'creator': 'Rai 5',
++            'uploader': 'Rai Gulp',
+             'duration': 6160,
+-            'series': 'Report',
+-            'season_number': 5,
+-            'season': '2013/14',
+         },
+         'params': {
+             'skip_download': True,
+@@ -168,16 +146,15 @@ class RaiPlayIE(RaiBaseIE):
+ 
+     def _real_extract(self, 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(
+-            '%s?json' % url, video_id, 'Downloading video JSON')
++            '%s%s.json' % (base, video_id), video_id, 'Downloading video JSON')
+ 
+         title = media['name']
+-
+         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'])
+ 
+         thumbnails = []
+@@ -185,7 +162,7 @@ def _real_extract(self, url):
+             for _, value in media.get('images').items():
+                 if value:
+                     thumbnails.append({
+-                        'url': value.replace('[RESOLUTION]', '600x400')
++                        'url': urljoin(RaiBaseIE._BASE_URL, value.replace('[RESOLUTION]', '600x400'))
+                     })
+ 
+         timestamp = unified_timestamp(try_get(
+@@ -225,7 +202,7 @@ 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,
+@@ -238,20 +215,32 @@ class RaiPlayLiveIE(RaiBaseIE):
+     def _real_extract(self, 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(
+-            r'data-uniquename=["\']ContentItem-(%s)' % RaiBaseIE._UUID_RE,
+-            webpage, 'content id')
++        title = media['name']
++        video = media['video']
++        video_id = media['id'].replace('ContentItem-', '')
++
++        relinker_info = self._extract_relinker_info(video['content_url'], video_id)
++        self._sort_formats(relinker_info['formats'])
+ 
+-        return {
+-            '_type': 'url_transparent',
+-            'ie_key': RaiPlayIE.ie_key(),
+-            'url': 'http://www.raiplay.it/dirette/ContentItem-%s.html' % video_id,
++        info = {
+             'id': video_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):
+     _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+)'
+@@ -260,7 +249,7 @@ class RaiPlayPlaylistIE(InfoExtractor):
+         'info_dict': {
+             'id': 'nondirloalmiocapo',
+             'title': 'Non dirlo al mio capo',
+-            'description': 'md5:9f3d603b2947c1c7abb098f3b14fac86',
++            'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
+         },
+         'playlist_mincount': 12,
+     }]
+@@ -268,21 +257,25 @@ class RaiPlayPlaylistIE(InfoExtractor):
+     def _real_extract(self, 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 = media['name']
++        description = media['program_info']['description']
+ 
+-        title = self._html_search_meta(
+-            ('programma', 'nomeProgramma'), webpage, 'title')
+-        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 = []
+-        for mobj in re.finditer(
+-                r'<a\b[^>]+\bhref=(["\'])(?P<path>/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 cs in content_sets:
++            medias = self._download_json(
++                '%s/%s.json' % (urljoin(RaiBaseIE._BASE_URL, 'programmi/' + playlist_id), cs),
++                cs, 'Downloading content set JSON')
++            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)
+ 



Home | Main Index | Thread Index | Old Index