Merge 43fe4b597f502273cce97c9d1a181f1847288c84 into 4e714f9df1ed2cccd51df60d45ff5504abe827b7

* 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/ciscolive.py

@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import itertools
-
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
@@ -10,6 +8,7 @@ from ..compat import (
 )
 from ..utils import (
     clean_html,
+    ExtractorError,
     float_or_none,
     int_or_none,
     try_get,
@@ -21,12 +20,13 @@ class CiscoLiveBaseIE(InfoExtractor):
     # These appear to be constant across all Cisco Live presentations
     # and are not tied to any user session or event
     RAINFOCUS_API_URL = 'https://events.rainfocus.com/api/%s'
-    RAINFOCUS_API_PROFILE_ID = 'Na3vqYdAlJFSxhYTYQGuMbpafMqftalz'
-    RAINFOCUS_WIDGET_ID = 'n6l4Lo05R8fiy3RpUBm447dZN8uNWoye'
+    RAINFOCUS_API_PROFILE_ID = ''  # if blank will be fetched at runtime from site javascript
+    RAINFOCUS_WIDGET_ID = ''  # if blank will be fetched at runtime from site javascript
+    RAINFOCUS_TOKENS_URL = 'https://cdn-events.rainfocus.com/pages/cisco/clondemand/catalog.js'
     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5647924234001/SyK2FdqjM_default/index.html?videoId=%s'
 
     HEADERS = {
-        'Origin': 'https://ciscolive.cisco.com',
+        'Origin': 'https://ciscolive.com',
         'rfApiProfileId': RAINFOCUS_API_PROFILE_ID,
         'rfWidgetId': RAINFOCUS_WIDGET_ID,
     }
@@ -34,9 +34,25 @@ class CiscoLiveBaseIE(InfoExtractor):
     def _call_api(self, ep, rf_id, query, referrer, note=None):
         headers = self.HEADERS.copy()
         headers['Referer'] = referrer
-        return self._download_json(
+        if not self.RAINFOCUS_API_PROFILE_ID or not self.RAINFOCUS_WIDGET_ID:
+            rf_token_js = self._download_webpage(self.RAINFOCUS_TOKENS_URL, 'catalog.js', headers=headers)
+            for token in ('apiToken', 'widgetId'):
+                if token not in rf_token_js:
+                    raise ExtractorError(
+                        'Unable to fetch ' + token, expected=True)
+            api_token = self._html_search_regex(
+                r'''apiToken:\s+["'](\w+)''', rf_token_js, 'apiToken')
+            widget_id = self._html_search_regex(
+                r'''widgetId:\s+["'](\w+)''', rf_token_js, 'widgetId')
+            headers['rfApiProfileId'] = api_token
+            headers['rfWidgetId'] = widget_id
+        rf_result = self._download_json(
             self.RAINFOCUS_API_URL % ep, rf_id, note=note,
             data=urlencode_postdata(query), headers=headers)
+        if int(rf_result['responseCode']) != 0:
+            raise ExtractorError(
+                'Rainfocus %s api returned a non success responseCode: %s. api keys might be invalid' % (ep, rf_result['responseCode']), expected=True)
+        return rf_result
 
     def _parse_rf_item(self, rf_item):
         event_name = rf_item.get('eventName')
@@ -67,17 +83,16 @@ class CiscoLiveBaseIE(InfoExtractor):
 class CiscoLiveSessionIE(CiscoLiveBaseIE):
     _VALID_URL = r'https?://(?:www\.)?ciscolive(?:\.cisco)?\.com/[^#]*#/session/(?P<id>[^/?&]+)'
     _TESTS = [{
-        'url': 'https://ciscolive.cisco.com/on-demand-library/?#/session/1423353499155001FoSs',
-        'md5': 'c98acf395ed9c9f766941c70f5352e22',
+        'url': 'https://www.ciscolive.com/on-demand/on-demand-library.html?search=#/session/16360600004400017rMx',
+        'md5': 'e0f5b0b2927b586ebff619294fec6926',
         'info_dict': {
-            'id': '5803694304001',
+            'id': '6128601216001',
             'ext': 'mp4',
-            'title': '13 Smart Automations to Monitor Your Cisco IOS Network',
-            'description': 'md5:ec4a436019e09a918dec17714803f7cc',
-            'timestamp': 1530305395,
-            'upload_date': '20180629',
+            'title': 'A Deeper Dive into the Telco Cloud Architecture Evolution to support 5G and MEC - BRKSPG-1565',
+            'description': 'md5:04bc54ec8ede2bbd9d21264bfaf16cb3',
+            'timestamp': 1580474594,
+            'upload_date': '20200131',
             'uploader_id': '5647924234001',
-            'location': '16B Mezz.',
         },
     }, {
         'url': 'https://www.ciscolive.com/global/on-demand-library.html?search.event=ciscoliveemea2019#/session/15361595531500013WOU',
@@ -85,6 +100,9 @@ class CiscoLiveSessionIE(CiscoLiveBaseIE):
     }, {
         'url': 'https://www.ciscolive.com/global/on-demand-library.html?#/session/1490051371645001kNaS',
         'only_matching': True,
+    }, {
+        'url': 'https://www.ciscolive.com/on-demand/on-demand-library.html?#/session/16360600774720017Iby',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -94,16 +112,15 @@ class CiscoLiveSessionIE(CiscoLiveBaseIE):
 
 
 class CiscoLiveSearchIE(CiscoLiveBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?ciscolive(?:\.cisco)?\.com/(?:global/)?on-demand-library(?:\.html|/)'
+    _VALID_URL = r'https?://(?:www\.)?ciscolive(?:\.cisco)?\.com/(?:global/|on-demand/)?on-demand-library(?:\.html|/)'
     _TESTS = [{
-        'url': 'https://ciscolive.cisco.com/on-demand-library/?search.event=ciscoliveus2018&search.technicallevel=scpsSkillLevel_aintroductory&search.focus=scpsSessionFocus_designAndDeployment#/',
+        'url': 'https://www.ciscolive.com/on-demand/on-demand-library.html?search.technology=1614262524988009b6j9&search.technicallevel=scpsSkillLevel_bintermediate#/',
         'info_dict': {
             'title': 'Search query',
         },
-        'playlist_count': 5,
+        'playlist_count': 6,
     }, {
-        'url': 'https://ciscolive.cisco.com/on-demand-library/?search.technology=scpsTechnology_applicationDevelopment&search.technology=scpsTechnology_ipv6&search.focus=scpsSessionFocus_troubleshootingTroubleshooting#/',
-        'only_matching': True,
+        'url': 'https://www.ciscolive.com/on-demand/on-demand-library.html?search.technology=scpsTechnology_automation&search.technicallevel=scpsSkillLevel_cadvanced#/',
     }, {
         'url': 'https://www.ciscolive.com/global/on-demand-library.html?search.technicallevel=scpsSkillLevel_aintroductory&search.event=ciscoliveemea2019&search.technology=scpsTechnology_dataCenter&search.focus=scpsSessionFocus_bestPractices#/',
         'only_matching': True,
@@ -118,31 +135,25 @@ class CiscoLiveSearchIE(CiscoLiveBaseIE):
         return int_or_none(try_get(rf_item, lambda x: x['videos'][0]['url'])) is not None
 
     def _entries(self, query, url):
-        query['size'] = 50
-        query['from'] = 0
-        for page_num in itertools.count(1):
-            results = self._call_api(
-                'search', None, query, url,
-                'Downloading search JSON page %d' % page_num)
-            sl = try_get(results, lambda x: x['sectionList'][0], dict)
-            if sl:
-                results = sl
-            items = results.get('items')
-            if not items or not isinstance(items, list):
-                break
-            for item in items:
-                if not isinstance(item, dict):
-                    continue
-                if not self._check_bc_id_exists(item):
-                    continue
-                yield self._parse_rf_item(item)
-            size = int_or_none(results.get('size'))
-            if size is not None:
-                query['size'] = size
-            total = int_or_none(results.get('total'))
-            if total is not None and query['from'] + query['size'] > total:
-                break
-            query['from'] += query['size']
+        results = self._call_api(
+            'search', None, query, url,
+            'Downloading search JSON')
+        if int(results['totalSearchItems']) == 0:
+            raise ExtractorError(
+                'Search api returned no items (if matches are expected rfApiProfileId may be invalid)',
+                expected=True)
+        sl = try_get(results, lambda x: x['sectionList'], list)
+        if sl is not None:
+            for s in sl:
+                items = s.get('items')
+                if not items or not isinstance(items, list):
+                    break
+                for item in items:
+                    if not isinstance(item, dict):
+                        continue
+                    if not self._check_bc_id_exists(item):
+                        continue
+                    yield self._parse_rf_item(item)
 
     def _real_extract(self, url):
         query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)

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',