Merge a712000b9b18c0530168e5549199c61560db99b3 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/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/dumpert.py

@@ -3,13 +3,14 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     int_or_none,
     qualities,
 )
 
 
 class DumpertIE(InfoExtractor):
-    _VALID_URL = r'(?P<protocol>https?)://(?:(?:www|legacy)\.)?dumpert\.nl/(?:mediabase|embed|item)/(?P<id>[0-9]+[/_][0-9a-zA-Z]+)'
+    _VALID_URL = r'(?P<protocol>https?)://(?:(?:www|legacy)\.)?dumpert\.nl(?:/(?:mediabase|embed|item)/|(?:/toppers|/latest)?/?\?selectedId=)(?P<id>[0-9]+[/_][0-9a-zA-Z]+)'
     _TESTS = [{
         'url': 'https://www.dumpert.nl/item/6646981_951bc60f',
         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
@@ -29,6 +30,25 @@ class DumpertIE(InfoExtractor):
     }, {
         'url': 'http://legacy.dumpert.nl/embed/6675421/dc440fe7',
         'only_matching': True,
+    }, {
+        'url': 'https://www.dumpert.nl/item/100031688_b317a185',
+        'md5': '34a0c10c91d281141b959b27ee862b8f',
+        'info_dict': {
+            'id': '100031688/b317a185',
+            'ext': 'mp4',
+            'title': 'Epic schijnbeweging',
+            'description': '<p>Die zag je niet eh</p>',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
+        },
+    }, {
+        'url': 'https://www.dumpert.nl/toppers?selectedId=100031688_b317a185',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.dumpert.nl/latest?selectedId=100031688_b317a185',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.dumpert.nl/?selectedId=100031688_b317a185',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -39,17 +59,24 @@ class DumpertIE(InfoExtractor):
         title = item['title']
         media = next(m for m in item['media'] if m.get('mediatype') == 'VIDEO')
 
-        quality = qualities(['flv', 'mobile', 'tablet', '720p'])
+        quality = qualities(['flv', 'mobile', 'tablet', '720p', '1080p'])
         formats = []
         for variant in media.get('variants', []):
             uri = variant.get('uri')
             if not uri:
                 continue
             version = variant.get('version')
+            preference = quality(version)
+            ext = determine_ext(uri)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    uri, video_id, ext='mp4', entry_protocol='m3u8_native',
+                    preference=preference))
+            else:
                 formats.append({
                     'url': uri,
                     'format_id': version,
-                'quality': quality(version),
+                    'preference': preference,
                 })
         self._sort_formats(formats)
 

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',