Merge 0cca4de1ae173b4f2623ce317acfb9a1a0c15ab0 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`

youtube_dl/extractor/bokecc.py

@@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 
 class BokeCCIE(BokeCCBaseIE):
-    _IE_DESC = 'CC视频'
+    IE_DESC = 'CC视频'
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{

youtube_dl/extractor/box.py

@@ -8,13 +8,13 @@ from .common import InfoExtractor
 from ..utils import (
     determine_ext,
     parse_iso8601,
-    # try_get,
+    try_get,
     update_url_query,
 )
 
 
 class BoxIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^.]+\.)?app\.box\.com/s/(?P<shared_name>[^/]+)/file/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?P<prefix>(?:[^.]+\.)?)app\.box\.com/s/(?P<shared_name>[^/]+)(?:/file/(?P<id>\d+))?'
     _TEST = {
         'url': 'https://mlssoccer.app.box.com/s/0evd2o3e08l60lr4ygukepvnkord1o1x/file/510727257538',
         'md5': '1f81b2fd3960f38a40a3b8823e5fcd43',
@@ -30,20 +30,22 @@ class BoxIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        shared_name, file_id = re.match(self._VALID_URL, url).groups()
+        prefix, shared_name, file_id = re.match(self._VALID_URL, url).groups()
         webpage = self._download_webpage(url, file_id)
+        if not file_id:
+            file_id = re.search(r'"typedID":\s*"f_(\d+)"', webpage).group(1)
         request_token = self._parse_json(self._search_regex(
             r'Box\.config\s*=\s*({.+?});', webpage,
             'Box config'), file_id)['requestToken']
         access_token = self._download_json(
-            'https://app.box.com/app-api/enduserapp/elements/tokens', file_id,
+            'https://' + prefix + 'app.box.com/app-api/enduserapp/elements/tokens', file_id,
             'Downloading token JSON metadata',
             data=json.dumps({'fileIDs': [file_id]}).encode(), headers={
                 'Content-Type': 'application/json',
                 'X-Request-Token': request_token,
                 'X-Box-EndUser-API': 'sharedName=' + shared_name,
             })[file_id]['read']
-        shared_link = 'https://app.box.com/s/' + shared_name
+        shared_link = 'https://' + prefix + 'app.box.com/s/' + shared_name
         f = self._download_json(
             'https://api.box.com/2.0/files/' + file_id, file_id,
             'Downloading file JSON metadata', headers={
@@ -51,7 +53,7 @@ class BoxIE(InfoExtractor):
                 'BoxApi': 'shared_link=' + shared_link,
                 'X-Rep-Hints': '[dash]',  # TODO: extract `hls` formats
             }, query={
-                'fields': 'authenticated_download_url,created_at,created_by,description,extension,is_download_available,name,representations,size'
+                'fields': 'permissions,authenticated_download_url,created_at,created_by,description,extension,is_download_available,name,representations,size'
             })
         title = f['name']
 
@@ -62,20 +64,24 @@ class BoxIE(InfoExtractor):
 
         formats = []
 
-        # for entry in (try_get(f, lambda x: x['representations']['entries'], list) or []):
-        #     entry_url_template = try_get(
-        #         entry, lambda x: x['content']['url_template'])
-        #     if not entry_url_template:
-        #         continue
-        #     representation = entry.get('representation')
-        #     if representation == 'dash':
-        #         TODO: append query to every fragment URL
-        #         formats.extend(self._extract_mpd_formats(
-        #             entry_url_template.replace('{+asset_path}', 'manifest.mpd'),
-        #             file_id, query=query))
+        for entry in (try_get(f, lambda x: x['representations']['entries'], list) or []):
+            entry_url_template = try_get(
+                entry, lambda x: x['content']['url_template'])
+            if not entry_url_template:
+                continue
+            representation = entry.get('representation')
+            if representation == 'dash':
+                extracted = self._extract_mpd_formats(
+                    entry_url_template.replace('{+asset_path}', 'manifest.mpd'),
+                    file_id, query=query)
+                for extracted_format in extracted:
+                    for fragment in extracted_format['fragments']:
+                        fragment['path'] = update_url_query(fragment['path'], query)
+                formats.extend(extracted)
 
         authenticated_download_url = f.get('authenticated_download_url')
-        if authenticated_download_url and f.get('is_download_available'):
+        permissions = f.get('permissions') or {}
+        if authenticated_download_url and f.get('is_download_available') and permissions.get('can_download', True):
             formats.append({
                 'ext': f.get('extension') or determine_ext(title),
                 'filesize': f.get('size'),

youtube_dl/extractor/cloudy.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class CloudyIE(InfoExtractor):
-    _IE_DESC = 'cloudy.ec'
+    IE_DESC = 'cloudy.ec'
     _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',

youtube_dl/extractor/common.py

@@ -422,6 +422,8 @@ class InfoExtractor(object):
     _GEO_COUNTRIES = None
     _GEO_IP_BLOCKS = None
     _WORKING = True
+    # supply this in public subclasses: used in supported sites list, etc
+    # IE_DESC = 'short description of IE'
 
     def __init__(self, downloader=None):
         """Constructor. Receives an optional downloader."""

youtube_dl/extractor/itv.py

@@ -35,15 +35,6 @@ from ..utils import (
 
 class ITVBaseIE(InfoExtractor):
 
-    def _search_nextjs_data(self, webpage, video_id, **kw):
-        transform_source = kw.pop('transform_source', None)
-        fatal = kw.pop('fatal', True)
-        return self._parse_json(
-            self._search_regex(
-                r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
-                webpage, 'next.js data', group='js', fatal=fatal, **kw),
-            video_id, transform_source=transform_source, fatal=fatal)
-
     def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
         if errnote is False:
             return False
@@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
 
 class ITVIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
-    _IE_DESC = 'ITVX'
+    IE_DESC = 'ITVX'
+    _WORKING = False
+
     _TESTS = [{
         'note': 'Hub URLs redirect to ITVX',
         'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
                 'ext': determine_ext(href, 'vtt'),
             })
 
-        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
         video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
         title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
         info = self._og_extract(webpage, require_title=not title)
@@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
 
 class ITVBTCCIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
-    _IE_DESC = 'ITV articles: News, British Touring Car Championship'
+    IE_DESC = 'ITV articles: News, British Touring Car Championship'
     _TESTS = [{
         'note': 'British Touring Car Championship',
         'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

youtube_dl/extractor/senateisvp.py

@@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
         ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
         ['arch', '', 'http://ussenate-f.akamaihd.net/']
     ]
-    _IE_NAME = 'senate.gov'
+    IE_NAME = 'senate.gov'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

youtube_dl/jsinterp.py

@@ -686,6 +686,8 @@ class JSInterpreter(object):
             raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
 
     def _dump(self, obj, namespace):
+        if obj is JS_Undefined:
+            return 'undefined'
         try:
             return json.dumps(obj)
         except TypeError: