Merge f295f4f6e4e7a49ba562a993859c10de1f978ae8 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/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/cnnturk.py

@@ -0,0 +1,99 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class CNNTurkIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                https?://
+                    (?:www\.)?cnnturk\.com/
+                    (?:
+                        tv-cnn-turk/programlar/|
+                        video/|
+                        turkiye/|
+                        dunya/|
+                        ekonomi/
+                    )
+                    (?:[^/]+/)*
+                    (?P<id>[^/?#&]+)
+                '''
+    _TESTS = [{
+        'url': 'https://www.cnnturk.com/tv-cnn-turk/programlar/dort-bir-taraf/dort-bir-taraf-43',
+        'md5': 'ea49375a769545afdb8d63d4efb46f8b',
+        'info_dict': {
+            'id': 'dort-bir-taraf-43',
+            'ext': 'mp4',
+            'title': 'Dört Bir Taraf',
+            'description': r're:Altan Öymen, Nazlı Ilıcak, Enver Aysever ve .{116}$',
+            'thumbnail': 'https://image.cnnturk.com/i/cnnturk/75/1200x675/542174c1cecfbe19c07cacea.jpg',
+            'upload_date': '20120601',
+        }
+    }, {
+        'url': 'https://www.cnnturk.com/tv-cnn-turk/programlar/tarafsiz-bolge/mahalle-baskisi-anayasa-tartismasi',
+        'md5': 'c3999fbe0fb3366b36cb2ea56d692697',
+        'info_dict': {
+            'id': 'mahalle-baskisi-anayasa-tartismasi',
+            'ext': 'mp4',
+            'title': 'MAHALLE BASKISI - ANAYASA TARTIŞMASI',
+            'description': r're:MAHALLE BASKISI ,  ANAYASA TARTIŞMASI .{96}$',
+            'thumbnail': 'https://image.cnnturk.com/i/cnnturk/75/1200x675/63530cb4bf773b1104bb482d.jpg',
+            'upload_date': '20120330',
+        }
+    }, {
+        'url': 'https://www.cnnturk.com/tv-cnn-turk/programlar/edip-akbayram-enver-aysever-in-sorularini-yanitladi-aykiri-sorular-09-07-2012',
+        'md5': '36814483fe64d450f35c985d5a2d2d18',
+        'info_dict': {
+            'id': 'edip-akbayram-enver-aysever-in-sorularini-yanitladi-aykiri-sorular-09-07-2012',
+            'ext': 'mp4',
+            'title': 'Edip Akbayram, Enver Aysever’in sorularını yanıtladı - Aykırı Sorular (09.07.2012)',
+            'description': 'Anadolu Pop Müziğinin önde gelen isimlerinden .{94}$',
+            'thumbnail': 'https://image.cnnturk.com/i/cnnturk/75/1200x675/54353b6dcecfbe1578205c80.jpg',
+            'upload_date': '20120710',
+        }
+    }, {
+        'url': 'https://www.cnnturk.com/tv-cnn-turk/programlar/aykiri-sorular/ilber-ortayli-enver-ayseverin-sorularini-yanitladi-aykiri-sorular-16-06-2014',
+        'md5': '36814483fe64d450f35c985d5a2d2d18',
+        'info_dict': {
+            'id': 'ilber-ortayli-enver-ayseverin-sorularini-yanitladi-aykiri-sorular-16-06-2014',
+            'ext': 'm3u8',
+            'title': 'İlber Ortaylı Enver Aysever\'in sorularını yanıtladı: Aykırı Sorular - 16.06.2014',
+            'description': 'Aykırı Sorular, Tarihçi Prof. Dr. İlber Ortaylıyı .{109}',
+            'thumbnail': 'https://image.cnnturk.com/i/cnnturk/75/1200x675/54353e78cecfbe15782068ae.jpg',
+            'upload_date': '20140617',
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        # Video info is a JSON object inside a script tag
+        video_info = self._parse_json(
+            self._search_regex(
+                r'({"Ancestors":.+?\);)', webpage, 'stream')[:-2],
+            video_id)
+
+        video_url = video_info['MediaFiles'][0]['Path']
+        if not video_url.startswith("http"):
+            video_url = 'https://cnnvod.duhnet.tv/' + video_url
+        extension = 'mp4' if video_url.endswith('mp4') else 'm3u8'
+        formats = [{
+            'url': video_url,
+            'ext': extension,
+            'language': 'tr',
+        }]
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'release_date': video_info['published_date'],
+            'upload_date': video_info['created_date'],
+            'formats': formats,
+        }

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/extractors.py

@@ -247,6 +247,7 @@ from .cnn import (
     CNNBlogsIE,
     CNNArticleIE,
 )
+from .cnnturk import CNNTurkIE
 from .coub import CoubIE
 from .comedycentral import (
     ComedyCentralIE,

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: