Merge 2730e55b36d299e17beacc4aaa8fa9441932c8aa 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

@@ -810,6 +810,10 @@ from .nhk import (
     NhkVodIE,
     NhkVodProgramIE,
 )
+from .nhkRadio import (
+    NhkRadioIE,
+    NhkRadioProgramIE
+)
 from .nhl import NHLIE
 from .nick import (
     NickIE,

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/nhkRadio.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+from __future__ import unicode_literals
+from .common import InfoExtractor
+from ..utils import ExtractorError, parse_iso8601
+from ..compat import compat_HTTPError
+import re
+
+
+class NhkRadioBase(InfoExtractor):
+    def _get_json_meta(self, program_id, corner_id):
+        program_corner_id = program_id + "_" + corner_id
+        try:
+            data = self._download_json(
+                "https://www.nhk.or.jp/radioondemand/json/"
+                + program_id
+                + "/bangumi_"
+                + program_corner_id
+                + ".json",
+                program_corner_id,
+            )
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
+                raise ExtractorError("The invalid url", expected=True)
+        return data
+
+    def _extract_program(self, info, program_corner_id):
+        id = program_corner_id + "_" + info.get("headline_id")
+        file = info.get("file_list")[0]
+        formats = self._extract_m3u8_formats(file.get("file_name", None), id, "m4a", entry_protocol="m3u8_native", m3u8_id="hls")
+        self._sort_formats(formats)
+        return {
+            "id": id,
+            "title": file.get("file_title"),
+            "formats": formats,
+            "timestamp": parse_iso8601(file.get("close_time")),
+        }
+
+
+class NhkRadioIE(NhkRadioBase):
+    _VALID_URL = r"https?://www\.nhk\.or\.jp/radio/player/ondemand\.html\?p=(?P<program_id>\d+)_(?P<corner_id>\d+)_(?P<headline_id>\d+)"
+
+    _TESTS = [
+        {
+            "url": "https://www.nhk.or.jp/radio/player/ondemand.html?p=4812_01_2898188",
+            "info_dict": {
+                "id": "4812_01_2898188",
+                "ext": "m4a",
+                "title": "世界へ発信！ニュースで英語術　＃２０９▽“首相長男から接待”　総務省１１人を処分",
+                "upload_date": str,
+                "timestamp": int,
+            },
+        },
+        {
+            "url": "https://www.nhk.or.jp/radio/player/ondemand.html?p=0444_01_2890944",
+            "info_dict": {
+                "ext": "m4a",
+                "id": "0444_01_2890944",
+                "title": "歌謡スクランブル　春色コレクション（３）　▽尾崎亜美",
+                "upload_date": str,
+                "timestamp": int,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        program_id, corner_id, headline_id = re.match(self._VALID_URL, url).groups()
+        program_corner_id = program_id + "_" + corner_id
+        data = self._download_json(
+            "https://www.nhk.or.jp/radioondemand/json/"
+            + program_id
+            + "/bangumi_"
+            + program_corner_id
+            + ".json",
+            program_corner_id,
+        )
+        for detail in data["main"]["detail_list"]:
+            if headline_id == detail.get("headline_id"):
+                return self._extract_program(detail, program_corner_id)
+        raise ExtractorError("The program not found", expected=True)
+
+
+class NhkRadioProgramIE(NhkRadioBase):
+    _VALID_URL = r"https?://www\.nhk\.or\.jp/radio/ondemand/detail\.html\?p=(?P<program_id>\d+)_(?P<corner_id>\d+)"
+
+    _TESTS = [
+        {
+            "url": "https://www.nhk.or.jp/radio/ondemand/detail.html?p=0164_01",
+            "info_dict": {"title": "青春アドベンチャー", "id": "0164_01"},
+            "playlist_mincount": 5,
+        },
+        {
+            "url": "https://www.nhk.or.jp/radio/ondemand/detail.html?p=0455_01",
+            "info_dict": {"id": "0455_01", "title": "弾き語りフォーユー"},
+            "playlist_mincount": 5,
+        },
+    ]
+
+    def _real_extract(self, url):
+        program_id, corner_id = re.match(self._VALID_URL, url).groups()
+        data = self._get_json_meta(program_id, corner_id)
+        entries = []
+        for detail in data["main"]["detail_list"]:
+            entries.append(self._extract_program(detail, program_id + "_" + corner_id))
+        return self.playlist_result(
+            entries, program_id + "_" + corner_id, data["main"]["program_name"]
+        )

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: