Merge 8a0905798e1716100ed3c39b397df3a4012a2f90 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

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

docs/supportedsites.md

@@ -482,6 +482,7 @@
  - **lynda**: lynda.com videos
  - **lynda:course**: lynda.com online courses
  - **m6**
+ - **MacProVideo.com**
  - **mailru**: Видео@Mail.Ru
  - **mailru:music**: Музыка@Mail.Ru
  - **mailru:music:search**: Музыка@Mail.Ru

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

@@ -652,6 +652,10 @@ from .lynda import (
     LyndaCourseIE
 )
 from .m6 import M6IE
+from .macprovideo import (
+    MacProVideoIE,
+    MacProVideoCourseIE
+)
 from .mailru import (
     MailRuIE,
     MailRuMusicIE,

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/macprovideo.py

@@ -0,0 +1,86 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from youtube_dl.utils import try_get, str_or_none
+
+from .common import InfoExtractor
+
+
+class MacProVideoBaseIE(InfoExtractor):
+    def _get_video_info(self, data):
+        meta = data.get('ned_programmanifest')
+        video_id = str_or_none(meta.get('fk_videoMediaID'))
+
+        formats = self._extract_m3u8_formats(
+            data['video_medium']['mediaURL'], video_id, 'mp4', m3u8_id='hls', fatal=False)
+        self._sort_formats(formats)
+
+        description = try_get(data, lambda x: x['ned_programmanifest_description']['description'])
+        thumbnail = try_get(data, lambda x: x['thumbnail_medium']['mediaURL'])
+
+        return {
+            'id': video_id,
+            'title': meta.get('vid_title'),
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': meta.get('vid_duration'),
+            'formats': formats
+        }
+
+
+class MacProVideoIE(MacProVideoBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?macprovideo\.com/video/(?P<course>[0-9a-zA-Z-]+)/(?P<num>[0-9]+)-[0-9a-zA-Z-]+'
+    _TEST = {
+        'url': 'https://www.macprovideo.com/video/apple-logic-pro-102-recording-and-editing-audio/1-1-transducers-and-converters',
+        'md5': 'md5:608d7c8cf9f31202cbd269273df62aaf',
+        'info_dict': {
+            'id': '319676',
+            'ext': 'mp4',
+            'title': '1. Transducers and Converters',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:c16dc8a42252e2be44225f129c591c3d',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+            'format': 'bestvideo'
+        },
+    }
+
+    def _real_extract(self, url):
+        course, num = re.match(self._VALID_URL, url).groups()
+        num = int(num) - 1
+        data = self._download_json('https://www.macprovideo.com/ajax/videos/' + course,
+                                   None)['data']['videos'][num]
+        return self._get_video_info(data)
+
+
+class MacProVideoCourseIE(MacProVideoBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?macprovideo\.com/course/(?P<id>[0-9a-zA-Z-]+)'
+    _TEST = {
+        'url': 'https://www.macprovideo.com/course/apple-logic-pro-102-recording-and-editing-audio',
+        'md5': 'md5:608d7c8cf9f31202cbd269273df62aaf',
+        'info_dict': {
+            'id': '319676',
+            'ext': 'mp4',
+            'title': '1. Transducers and Converters',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:c16dc8a42252e2be44225f129c591c3d',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+            'format': 'bestvideo'
+        },
+    }
+
+    def _real_extract(self, url):
+        course_id = self._match_id(url)
+        videos = self._download_json('https://www.macprovideo.com/ajax/videos/' + course_id, None)['data']['videos']
+        title = try_get(videos, lambda x: x[0]['tutorial']['tu_title'])
+
+        return self.playlist_result(
+            [self._get_video_info(data) for data in videos],
+            playlist_id=course_id, playlist_title=title)

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: