From 5122028a4bcac4ae577ef7fbd55ccad5cb34ef5e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jes=C3=BAs?= <heckyel@hyperbola.info>
Date: Mon, 18 Oct 2021 15:24:21 -0500
Subject: update from upstream

---
 hypervideo_dl/extractor/crunchyroll.py | 133 +++++++++++++++++++++++++--------
 1 file changed, 102 insertions(+), 31 deletions(-)

(limited to 'hypervideo_dl/extractor/crunchyroll.py')

diff --git a/hypervideo_dl/extractor/crunchyroll.py b/hypervideo_dl/extractor/crunchyroll.py
index bc2d1fa..511ac1b 100644
--- a/hypervideo_dl/extractor/crunchyroll.py
+++ b/hypervideo_dl/extractor/crunchyroll.py
@@ -29,6 +29,7 @@ from ..utils import (
     merge_dicts,
     remove_end,
     sanitized_Request,
+    try_get,
     urlencode_postdata,
     xpath_text,
 )
@@ -120,7 +121,7 @@ class CrunchyrollBaseIE(InfoExtractor):
 
 class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
     IE_NAME = 'crunchyroll'
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P<id>[0-9]+))(?:[/?&]|$)'
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
         'info_dict': {
@@ -412,8 +413,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         return subtitles
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('video_id')
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id')
 
         if mobj.group('prefix') == 'm':
             mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage')
@@ -428,7 +429,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             r'<div class="showmedia-trailer-notice">(.+?)</div>',
             webpage, 'trailer-notice', default='')
         if note_m:
-            raise ExtractorError(note_m)
+            raise ExtractorError(note_m, expected=True)
 
         mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
         if mobj:
@@ -458,6 +459,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         video_description = (self._parse_json(self._html_search_regex(
             r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id,
             webpage, 'description', default='{}'), video_id) or media_metadata).get('description')
+
+        thumbnails = []
+        thumbnail_url = (self._parse_json(self._html_search_regex(
+            r'<script type="application\/ld\+json">\n\s*(.+?)<\/script>',
+            webpage, 'thumbnail_url', default='{}'), video_id)).get('image')
+        if thumbnail_url:
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': 1920,
+                'height': 1080
+            })
+
         if video_description:
             video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
         video_uploader = self._html_search_regex(
@@ -473,15 +486,11 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 stream.get('url'), video_id, stream.get('format'),
                 audio_lang, hardsub_lang)
             for f in vrv_formats:
-                if not hardsub_lang:
-                    f['preference'] = 1
-                language_preference = 0
-                if audio_lang == language:
-                    language_preference += 1
-                if hardsub_lang == language:
-                    language_preference += 1
-                if language_preference:
-                    f['language_preference'] = language_preference
+                f['language_preference'] = 1 if audio_lang == language else 0
+                f['quality'] = (
+                    1 if not hardsub_lang
+                    else 0 if hardsub_lang == language
+                    else -1)
             formats.extend(vrv_formats)
         if not formats:
             available_fmts = []
@@ -571,7 +580,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                         'ext': 'flv',
                     })
                     formats.append(format_info)
-        self._sort_formats(formats, ('preference', 'language_preference', 'height', 'width', 'tbr', 'fps'))
+        self._sort_formats(formats)
 
         metadata = self._call_rpc_api(
             'VideoPlayer_GetMediaMetadata', video_id,
@@ -596,21 +605,25 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d',
             webpage, 'series', fatal=False)
 
-        season = episode = episode_number = duration = thumbnail = None
+        season = episode = episode_number = duration = None
 
         if isinstance(metadata, compat_etree_Element):
             season = xpath_text(metadata, 'series_title')
             episode = xpath_text(metadata, 'episode_title')
             episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
             duration = float_or_none(media_metadata.get('duration'), 1000)
-            thumbnail = xpath_text(metadata, 'episode_image_url')
 
         if not episode:
             episode = media_metadata.get('title')
         if not episode_number:
             episode_number = int_or_none(media_metadata.get('episode_number'))
-        if not thumbnail:
-            thumbnail = media_metadata.get('thumbnail', {}).get('url')
+        thumbnail_url = try_get(media, lambda x: x['thumbnail']['url'])
+        if thumbnail_url:
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': 640,
+                'height': 360
+            })
 
         season_number = int_or_none(self._search_regex(
             r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)',
@@ -623,7 +636,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             'title': video_title,
             'description': video_description,
             'duration': duration,
-            'thumbnail': thumbnail,
+            'thumbnails': thumbnails,
             'uploader': video_uploader,
             'series': series,
             'season': season,
@@ -637,10 +650,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
 class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
     IE_NAME = 'crunchyroll:playlist'
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:\w{1,2}/)?(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)'
 
     _TESTS = [{
-        'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
+        'url': 'https://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
         'info_dict': {
             'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
             'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
@@ -659,28 +672,86 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
         # geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14
         'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
         'only_matching': True,
+    }, {
+        'url': 'http://www.crunchyroll.com/fr/ladies-versus-butlers',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
 
         webpage = self._download_webpage(
-            self._add_skip_wall(url), show_id,
+            # https:// gives a 403, but http:// does not
+            self._add_skip_wall(url).replace('https://', 'http://'), show_id,
             headers=self.geo_verification_headers())
         title = self._html_search_meta('name', webpage, default=None)
 
-        episode_paths = re.findall(
-            r'(?s)<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"',
-            webpage)
-        entries = [
-            self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll', ep_id)
-            for ep_id, ep in episode_paths
-        ]
-        entries.reverse()
+        episode_re = r'<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"'
+        season_re = r'<a [^>]+season-dropdown[^>]+>([^<]+)'
+        paths = re.findall(f'(?s){episode_re}|{season_re}', webpage)
+
+        entries, current_season = [], None
+        for ep_id, ep, season in paths:
+            if season:
+                current_season = season
+                continue
+            entries.append(self.url_result(
+                f'http://www.crunchyroll.com{ep}', CrunchyrollIE.ie_key(), ep_id, season=current_season))
 
         return {
             '_type': 'playlist',
             'id': show_id,
             'title': title,
-            'entries': entries,
+            'entries': reversed(entries),
         }
+
+
+class CrunchyrollBetaIE(CrunchyrollBaseIE):
+    IE_NAME = 'crunchyroll:beta'
+    _VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{1,2}/)?)watch/(?P<internal_id>\w+)/(?P<id>[\w\-]+)/?(?:\?|$)'
+    _TESTS = [{
+        'url': 'https://beta.crunchyroll.com/watch/GY2P1Q98Y/to-the-future',
+        'info_dict': {
+            'id': '696363',
+            'ext': 'mp4',
+            'timestamp': 1459610100,
+            'description': 'md5:a022fbec4fbb023d43631032c91ed64b',
+            'uploader': 'Toei Animation',
+            'title': 'World Trigger Episode 73 – To the Future',
+            'upload_date': '20160402',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Unable to download XML']
+    }]
+
+    def _real_extract(self, url):
+        lang, internal_id, display_id = self._match_valid_url(url).group('lang', 'internal_id', 'id')
+        webpage = self._download_webpage(url, display_id)
+        episode_data = self._parse_json(
+            self._search_regex(r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'episode data'),
+            display_id)['content']['byId'][internal_id]
+        video_id = episode_data['external_id'].split('.')[1]
+        series_id = episode_data['episode_metadata']['series_slug_title']
+        return self.url_result(f'https://www.crunchyroll.com/{lang}{series_id}/{display_id}-{video_id}',
+                               CrunchyrollIE.ie_key(), video_id)
+
+
+class CrunchyrollBetaShowIE(CrunchyrollBaseIE):
+    IE_NAME = 'crunchyroll:playlist:beta'
+    _VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{1,2}/)?)series/\w+/(?P<id>[\w\-]+)/?(?:\?|$)'
+    _TESTS = [{
+        'url': 'https://beta.crunchyroll.com/series/GY19NQ2QR/Girl-Friend-BETA',
+        'info_dict': {
+            'id': 'girl-friend-beta',
+            'title': 'Girl Friend BETA',
+        },
+        'playlist_mincount': 10,
+    }, {
+        'url': 'https://beta.crunchyroll.com/it/series/GY19NQ2QR/Girl-Friend-BETA',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        lang, series_id = self._match_valid_url(url).group('lang', 'id')
+        return self.url_result(f'https://www.crunchyroll.com/{lang}{series_id.lower()}',
+                               CrunchyrollShowPlaylistIE.ie_key(), series_id)
-- 
cgit v1.2.3