Merge 94c633d58a598334beb49bf2871de125839d4861 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/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

@@ -961,6 +961,7 @@ from .pluralsight import (
     PluralsightIE,
     PluralsightCourseIE,
 )
+from .podchaser import PodchaserIE
 from .podomatic import PodomaticIE
 from .pokemon import PokemonIE
 from .polskieradio 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/podchaser.py

@@ -0,0 +1,114 @@
+# coding: utf-8
+from __future__ import unicode_literals
+import json
+import re
+from ..utils import float_or_none, try_get, str_to_int, unified_timestamp, merge_dicts
+from ..compat import compat_str
+from .common import InfoExtractor
+
+
+class PodchaserIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?podchaser\.com/
+        (?:
+            (?:podcasts/[\w-]+-(?P<podcast_id>[\d]+)))
+        (?:/episodes/[\w\-]+-
+            (?P<id>[\d]+))?'''
+
+    _TESTS = [{
+        'url': 'https://www.podchaser.com/podcasts/cum-town-36924/episodes/ep-285-freeze-me-off-104365585',
+        'info_dict': {
+            'id': '104365585',
+            'title': "Ep. 285 – freeze me off",
+            'description': 'cam ahn',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'ext': 'mp3',
+            'categories': ['Comedy'],
+            'tags': ['comedy', 'dark humor'],
+            'series': 'Cum Town',
+            'duration': 3708,
+            'timestamp': 1636531259,
+            'upload_date': '20211110'
+        }
+    }, {
+        'url': 'https://www.podchaser.com/podcasts/the-bone-zone-28853',
+        'info_dict': {
+            'id': '28853',
+            'title': 'The Bone Zone',
+            'description': 'Podcast by The Bone Zone',
+        },
+        'playlist_count': 275
+    }, {
+        'url': 'https://www.podchaser.com/podcasts/sean-carrolls-mindscape-scienc-699349/episodes',
+        'info_dict': {
+            'id': '699349',
+            'title': "Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas",
+            'description': 'md5:2cbd8f4749891a84dc8235342e0b5ff1'
+        },
+        'playlist_mincount': 199
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        audio_id, podcast_id = mobj.group('id'), mobj.group('podcast_id')
+
+        # If one episode
+        if audio_id:
+            episodes = [self._download_json("https://api.podchaser.com/episodes/%s" % audio_id, audio_id)]
+
+        # Else get every episode available
+        else:
+            total_episode_count = self._download_json(
+                "https://api.podchaser.com/list/episode", podcast_id,
+                headers={'Content-Type': 'application/json;charset=utf-8'},
+                data=json.dumps({
+                    "filters": {"podcast_id": podcast_id}
+                }).encode()).get('total')
+            episodes = []
+            print(total_episode_count)
+            for i in range(total_episode_count // 100 + 1):
+                curr_episodes_data = self._download_json(
+                    "https://api.podchaser.com/list/episode", podcast_id,
+                    headers={'Content-Type': 'application/json;charset=utf-8'},
+                    data=json.dumps({
+                        "start": i * 100,
+                        "count": (i + 1) * 100,
+                        "sort_order": "SORT_ORDER_RECENT",
+                        "filters": {
+                            "podcast_id": podcast_id
+                        }, "options": {}
+                    }).encode())
+                curr_episodes = curr_episodes_data.get('entities') or []
+                if len(curr_episodes) + len(episodes) <= total_episode_count:
+                    episodes.extend(curr_episodes)
+
+        podcast_data = merge_dicts(
+            self._download_json("https://api.podchaser.com/podcasts/%s" % podcast_id, audio_id or podcast_id) or {},
+            episodes[0].get('podcast') or {} if episodes else {})
+
+        entries = [{
+            'id': compat_str(episode.get('id')),
+            'title': episode.get('title'),
+            'description': episode.get('description'),
+            'url': episode.get('audio_url'),
+            'thumbnail': episode.get('image_url'),
+            'duration': str_to_int(episode.get('length')),
+            'timestamp': unified_timestamp(episode.get('air_date')),
+            'rating': float_or_none(episode.get('rating')),
+            'categories': [
+                x.get('text') for x in
+                podcast_data.get('categories')
+                or try_get(podcast_data, lambda x: x['summary']['categories'], list) or []],
+            'tags': [tag.get('text') for tag in podcast_data.get('tags') or []],
+            'series': podcast_data.get('title'),
+        } for episode in episodes]
+
+        if len(entries) > 1:
+            # Return playlist
+            return self.playlist_result(
+                entries, playlist_id=compat_str(podcast_data.get('id')),
+                playlist_title=podcast_data.get('title'),
+                playlist_description=podcast_data.get('description'))
+
+        # Return episode
+        return entries[0]

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: