Merge 8edbee2a507a4337d99b5a1b9b73d4c6721dddd5 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

@@ -833,6 +833,7 @@ from .nintendo import NintendoIE
 from .njpwworld import NJPWWorldIE
 from .nobelprize import NobelPrizeIE
 from .nonktube import NonkTubeIE
+from .noodledude import NoodleDudeIE
 from .noovo import NoovoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE

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/noodledude.py

@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+import re
+import json
+
+class NoodleDudeIE(InfoExtractor):
+    IE_NAME = 'NoodleDude'
+    _VALID_URL = r'https?://(www\.)?noodledude\.io/videos/(?P<id>[0-9a-zA-Z_-]+)'
+    _TEST = {
+        'url': 'https://www.noodledude.io/videos/kawaii-vs-goth',
+        'md5': '9d3465ea49d16860a531035517ea8aec',
+        'info_dict': {
+            'id': 'kawaii-vs-goth',
+            'ext': 'mp4',
+            'title': 'Kawaii VS Goth',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:f16fef1f758a4dc38041bd6648b9d3b2',
+            # TODO more properties, either as:
+            # * A value
+            # * MD5 checksum; start the string with md5:
+            # * A regular expression; start the string with re:
+            # * Any Python type (for example int or float)
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id, headers={'Referer': 'https://www.noodledude.io/'})
+
+        #with open('webpage.tmp', 'w') as f:
+            #f.write(webpage)
+
+        # TODO more code goes here, for example ...
+        title = self._html_search_regex(r'<h1 id="video-title".*?>(.+?)</h1>', webpage, 'title')
+        description = self._html_search_meta('description', webpage, 'decription')
+
+        print('Title:', title)
+        print('Description:', description)
+
+        iframe_url = self._search_regex(r'<iframe\s*src="(.+?)"', webpage, 'iframe_url', flags=re.MULTILINE)
+        #print('iframe: ', iframe_url)
+
+        iframe_data = self._download_webpage(iframe_url, video_id, headers={'Referer': 'https://www.noodledude.io/'}) 
+        #with open('iframe.tmp', 'w') as f:
+            #f.write(iframe_data)
+
+        m3u8_url = self._search_regex(r'<source.*?src="(.+?)"', iframe_data, 'm3u8_url')
+        print('M3U8:', m3u8_url)
+
+        poster_url = self._search_regex(r'<video.*?data-poster="(.+?)"', iframe_data, 'poster_url')
+        print('Poster:', poster_url)
+
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', headers={'Referer': 'https://iframe.mediadelivery.net/'})
+        print('Formats:', json.dumps(formats))
+        for f in formats:
+            f.setdefault('http_headers', {})['Referer'] = 'https://iframe.mediadelivery.net/'
+
+        return {
+            'id': video_id,
+            'url': url,
+            'title': title,
+            'description': description,
+            'formats': formats,
+            'thumbnail': poster_url
+            #'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
+            # TODO more properties (see youtube_dl/extractor/common.py)
+        }

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: