[youtube] Add support for invidious.nixnet.xyz and yt.elukerio.org (#22223)

[youtube-dl] / youtube_dl / extractor / vlive.py

diff --git a/youtube_dl/extractor/vlive.py b/youtube_dl/extractor/vlive.py
index 78436c45cb9f4a301f416107274a2f3eabc92cf7..c3429f723ddec36cb89dfc9f329f766f45b953e1 100644 (file)
--- a/youtube_dl/extractor/vlive.py
+++ b/youtube_dl/extractor/vlive.py
@@ -54,8 +54,8 @@ class VLiveIE(InfoExtractor):
         'info_dict': {
             'id': '129100',
             'ext': 'mp4',
-            'title': "[V LIVE] [BTS+] Run BTS! 2019 - EP.71 :: Behind the scene",
-            'creator': "BTS+",
+            'title': '[V LIVE] [BTS+] Run BTS! 2019 - EP.71 :: Behind the scene',
+            'creator': 'BTS+',
             'view_count': int,
             'subtitles': 'mincount:10',
         },
@@ -79,16 +79,12 @@ class VLiveIE(InfoExtractor):
                 'https://www.vlive.tv/auth/loginInfo', None,
                 note='Downloading login info',
                 headers={'Referer': 'https://www.vlive.tv/home'})
-
-            return try_get(login_info,
-                           lambda x: x['message']['login'], bool) or False
-
-        if is_logged_in():
-            return
+            return try_get(
+                login_info, lambda x: x['message']['login'], bool) or False
 
         LOGIN_URL = 'https://www.vlive.tv/auth/email/login'
-        self._request_webpage(LOGIN_URL, None,
-                              note='Downloading login cookies')
+        self._request_webpage(
+            LOGIN_URL, None, note='Downloading login cookies')
 
         self._download_webpage(
             LOGIN_URL, None, note='Logging in',
@@ -144,7 +140,7 @@ class VLiveIE(InfoExtractor):
     def _get_common_fields(self, webpage):
         title = self._og_search_title(webpage)
         creator = self._html_search_regex(
-            r'<div[^>]+class="info_area"[^>]*>\s*(?:<em[^>]*>.*</em\s*>\s*)?<a\s+[^>]*>([^<]+)',
+            r'<div[^>]+class="info_area"[^>]*>\s*(?:<em[^>]*>.*?</em\s*>\s*)?<a\s+[^>]*>([^<]+)',
             webpage, 'creator', fatal=False)
         thumbnail = self._og_search_thumbnail(webpage)
         return {
@@ -183,9 +179,10 @@ class VLiveIE(InfoExtractor):
         if '' in (long_video_id, key):
             init_page = self._download_init_page(video_id)
             video_info = self._parse_json(self._search_regex(
-                r'(?s)oVideoStatus\s*=\s*({.*})', init_page, 'video info'),
+                (r'(?s)oVideoStatus\s*=\s*({.+?})\s*</script',
+                 r'(?s)oVideoStatus\s*=\s*({.+})'), init_page, 'video info'),
                 video_id)
-            if video_info['status'] == 'NEED_CHANNEL_PLUS':
+            if video_info.get('status') == 'NEED_CHANNEL_PLUS':
                 self.raise_login_required(
                     'This video is only available for CH+ subscribers')
             long_video_id, key = video_info['vid'], video_info['inkey']
@@ -335,26 +332,45 @@ class VLiveChannelIE(InfoExtractor):
 class VLivePlaylistIE(InfoExtractor):
     IE_NAME = 'vlive:playlist'
     _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<video_id>[0-9]+)/playlist/(?P<id>[0-9]+)'
-    _TEST = {
+    _VIDEO_URL_TEMPLATE = 'http://www.vlive.tv/video/%s'
+    _TESTS = [{
+        # regular working playlist
+        'url': 'https://www.vlive.tv/video/117956/playlist/117963',
+        'info_dict': {
+            'id': '117963',
+            'title': '아이돌룸(IDOL ROOM) 41회 - (여자)아이들'
+        },
+        'playlist_mincount': 10
+    }, {
+        # playlist with no playlistVideoSeqs
         'url': 'http://www.vlive.tv/video/22867/playlist/22912',
         'info_dict': {
-            'id': '22912',
-            'title': 'Valentine Day Message from TWICE'
+            'id': '22867',
+            'ext': 'mp4',
+            'title': '[V LIVE] Valentine Day Message from MINA',
+            'creator': 'TWICE',
+            'view_count': int
         },
-        'playlist_mincount': 9
-    }
+        'params': {
+            'skip_download': True,
+        }
+    }]
+
+    def _build_video_result(self, video_id, message):
+        self.to_screen(message)
+        return self.url_result(
+            self._VIDEO_URL_TEMPLATE % video_id,
+            ie=VLiveIE.ie_key(), video_id=video_id)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id, playlist_id = mobj.group('video_id', 'id')
 
-        VIDEO_URL_TEMPLATE = 'http://www.vlive.tv/video/%s'
         if self._downloader.params.get('noplaylist'):
-            self.to_screen(
-                'Downloading just video %s because of --no-playlist' % video_id)
-            return self.url_result(
-                VIDEO_URL_TEMPLATE % video_id,
-                ie=VLiveIE.ie_key(), video_id=video_id)
+            return self._build_video_result(
+                video_id,
+                'Downloading just video %s because of --no-playlist'
+                % video_id)
 
         self.to_screen(
             'Downloading playlist %s - add --no-playlist to just download video'
@@ -364,15 +380,21 @@ class VLivePlaylistIE(InfoExtractor):
             'http://www.vlive.tv/video/%s/playlist/%s'
             % (video_id, playlist_id), playlist_id)
 
-        item_ids = self._parse_json(
-            self._search_regex(
-                r'playlistVideoSeqs\s*=\s*(\[[^]]+\])', webpage,
-                'playlist video seqs'),
-            playlist_id)
+        raw_item_ids = self._search_regex(
+            r'playlistVideoSeqs\s*=\s*(\[[^]]+\])', webpage,
+            'playlist video seqs', default=None, fatal=False)
+
+        if not raw_item_ids:
+            return self._build_video_result(
+                video_id,
+                'Downloading just video %s because no playlist was found'
+                % video_id)
+
+        item_ids = self._parse_json(raw_item_ids, playlist_id)
 
         entries = [
             self.url_result(
-                VIDEO_URL_TEMPLATE % item_id, ie=VLiveIE.ie_key(),
+                self._VIDEO_URL_TEMPLATE % item_id, ie=VLiveIE.ie_key(),
                 video_id=compat_str(item_id))
             for item_id in item_ids]