Merge 0f0a0b92892803f9f5c8402444dfb5dbb4e2e640 into 4e714f9df1ed2cccd51df60d45ff5504abe827b7

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

README.md

@@ -1,5 +1,8 @@
-[![Build Status](https://github.com/ytdl-org/youtube-dl/workflows/CI/badge.svg)](https://github.com/ytdl-org/youtube-dl/actions?query=workflow%3ACI)
+# In this fork
 
+This fork adds an extractor for recording lectures from a https://livestream.kuleuven.be/ stream.
+
+# youtube-dl
 
 youtube-dl - download videos from youtube.com or other video platforms
 
@@ -238,6 +241,8 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                          url,ffmpeg,httpie,wget
     --external-downloader-args ARGS      Give these arguments to the external
                                          downloader
+    --ffmpeg-out-override ARGS           Give these arguments to the ffmpeg
+                                         instead of `-c copy`
 
 ## Filesystem Options:
     -a, --batch-file FILE                File containing URLs to download ('-'

docs/supportedsites.md

@@ -433,6 +433,7 @@
  - **KonserthusetPlay**
  - **KrasView**: Красвью
  - **Ku6**
+ - **KULLive**
  - **KUSI**
  - **kuwo:album**: 酷我音乐 - 专辑
  - **kuwo:category**: 酷我音乐 - 分类

youtube_dl/__init__.py

@@ -312,6 +312,9 @@ def _real_main(argv=None):
     postprocessor_args = None
     if opts.postprocessor_args:
         postprocessor_args = compat_shlex_split(opts.postprocessor_args)
+    ffmpeg_out_override = None
+    if opts.ffmpeg_out_override:
+        ffmpeg_out_override = compat_shlex_split(opts.ffmpeg_out_override)
     match_filter = (
         None if opts.match_filter is None
         else match_filter_func(opts.match_filter))
@@ -429,6 +432,7 @@ def _real_main(argv=None):
         'hls_prefer_native': opts.hls_prefer_native,
         'hls_use_mpegts': opts.hls_use_mpegts,
         'external_downloader_args': external_downloader_args,
+        'ffmpeg_out_override': ffmpeg_out_override,
         'postprocessor_args': postprocessor_args,
         'cn_verification_proxy': opts.cn_verification_proxy,
         'geo_verification_proxy': opts.geo_verification_proxy,

youtube_dl/downloader/external.py

@@ -469,7 +469,10 @@ class FFmpegFD(ExternalFD):
             elif isinstance(conn, compat_str):
                 args += ['-rtmp_conn', conn]
 
-        args += ['-i', url, '-c', 'copy']
+        args += ['-i', url]
+
+        ffmpeg_out_override = self.params.get('ffmpeg_out_override')
+        args += ffmpeg_out_override if ffmpeg_out_override else ['-c', 'copy']
 
         if self.params.get('test', False):
             args += ['-fs', compat_str(self._TEST_FILE_SIZE)]

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

@@ -576,6 +576,7 @@ from .konserthusetplay import KonserthusetPlayIE
 from .krasview import KrasViewIE
 from .kth import KTHIE
 from .ku6 import Ku6IE
+from .kuleuven_live import KULLiveIE
 from .kusi import KUSIIE
 from .kuwo import (
     KuwoIE,

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/kuleuven_live.py

@@ -0,0 +1,29 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class KULLiveIE(InfoExtractor):
+    _VALID_URL = r'(?:(?:https?://(?:www\.)?livestream.kuleuven\.be/\?pin=)|kulive:)(?P<id>[0-9]+)'
+
+    def _real_extract(self, url):
+        pin = self._match_id(url)
+
+        json_res = self._download_json(
+            "https://icts-p-toledo-streaming-video-live-backend.cloud.icts.kuleuven.be/api/viewers/" + pin,
+            pin,
+            'Requesting stream URL',
+            errnote='The stream with pin %s does not exist or has not started yet' % pin,
+            fatal=True)
+
+        m3u8_url = json_res['streamUrl']
+
+        formats = self._extract_m3u8_formats(m3u8_url, pin, 'mp4')
+
+        return {
+            'id': pin,
+            'title': 'kul-stream',
+            'is_live': True,
+            'formats': formats,
+        }

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/options.py

@@ -523,6 +523,10 @@ def parseOpts(overrideArguments=None):
         '--external-downloader-args',
         dest='external_downloader_args', metavar='ARGS',
         help='Give these arguments to the external downloader')
+    downloader.add_option(
+        '--ffmpeg-out-override',
+        dest='ffmpeg_out_override', metavar='ARGS',
+        help='Give these arguments to the ffmpeg instead of `-c copy`')
 
     workarounds = optparse.OptionGroup(parser, 'Workarounds')
     workarounds.add_option(