Merge e29f8e8707b3c37eb10d9e2944d76550d43d297a 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/extractors.py

@@ -1534,6 +1534,7 @@ from .voxmedia import (
     VoxMediaVolumeIE,
     VoxMediaIE,
 )
+from .voe import VOEIE
 from .vrt import VRTIE
 from .vrak import VrakIE
 from .vrv import (

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/extractor/voe.py

@@ -0,0 +1,75 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_base64_b64decode
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    url_or_none,
+)
+
+
+class VOEIE(InfoExtractor):
+    IE_NAME = 'voe'
+    IE_DESC = 'VOE.SX'
+    _VALID_URL = r'https?://voe\.sx(?P<path>/(e/)?(?P<id>[a-z0-9]+))'
+    _TESTS = [{
+        'url': 'https://voe.sx/e/ng7ja5n5n2y8',
+        'info_dict': {
+            'id': 'ng7ja5n5n2y8',
+            'title': 'md5:8dd774de9b73851151d80ef6baaea7f1',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'ext': 'm3u8',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id, video_path = self._match_valid_url(url).group('id', 'path')
+
+        webpage = self._download_webpage(
+            'https://voe.sx/e/%s' % video_id, video_id)
+
+        player_url = self._search_regex(
+            r'''("|')(?P<url>https://(?!voe\.sx/)[^/]+%s)\1\s*;''' % (video_path,),
+            webpage, 'redirect', group='url', default=None)
+        if player_url:
+            webpage = self._download_webpage(
+                player_url, video_id, note='Redirecting to player page')
+
+        sources = self._search_json(
+            r'\bsources\s*=', webpage, 'sources', video_id, transform_source=js_to_json)
+
+        title = self._search_regex(
+            r'<title>(?:Watch\s+)?(?P<title>.+?)(?:-\s+VOE\s+\|.+)?</title>',
+            webpage, 'title', group='title')
+
+        formats = []
+        for fmt in ('mp4', 'hls'):
+            if fmt not in sources:
+                continue
+            sources[fmt] = url_or_none(sources[fmt]) or url_or_none(compat_base64_b64decode(sources[fmt]).decode('utf-8'))
+            f_url = sources.get('hls')
+        if f_url:
+            formats.extend(self._extract_m3u8_formats(
+                f_url, video_id, entry_protocol='m3u8_native', fatal=False))
+        f_url = sources.get('mp4')
+        if f_url:
+            formats.append({
+                'url': f_url,
+                'ext': 'mp4',
+                'height': int_or_none(sources.get('video_height')),
+            })
+
+        self._sort_formats(formats)
+
+        thumbnail = url_or_none(self._search_regex(
+            r'''(?:VOEPlayer\s*\.\s*|data-)poster\s*=\s*("|')(?P<thumbnail>(?:(?!\1)\S)+)\1''',
+            webpage, 'thumbnail', group='thumbnail', default=None))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }