Merge f7a7601f27951db481cd23c3bc8491d6bf86524b 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

@@ -1566,6 +1566,7 @@ from .wdr import (
     WDRElefantIE,
     WDRMobileIE,
 )
+from .webarchive import WebArchiveIE
 from .webcaster import (
     WebcasterIE,
     WebcasterFeedIE,

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/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/extractor/webarchive.py

@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class WebArchiveIE(InfoExtractor):
+    _VALID_URL = r'https?:\/\/(?:www\.)?web\.archive\.org\/web\/([0-9]+)\/https?:\/\/(?:www\.)?youtube\.com\/watch\?v=(?P<id>[0-9A-Za-z_-]{1,11})$'
+    _TEST = {
+        'url': 'https://web.archive.org/web/20150415002341/https://www.youtube.com/watch?v=aYAGB11YrSs',
+        'md5': 'ec44dc1177ae37189a8606d4ca1113ae',
+        'info_dict': {
+            'url': 'https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/aYAGB11YrSs',
+            'id': 'aYAGB11YrSs',
+            'ext': 'mp4',
+            'title': 'Team Fortress 2 - Sandviches!',
+            'author': 'Zeurel',
+        }
+    }
+
+    def _real_extract(self, url):
+        # Get video ID and page
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        # Extract title and author
+        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title').strip()
+        author = self._html_search_regex(r'"author":"([a-zA-Z0-9]+)"', webpage, 'author').strip()
+
+        # Parse title
+        if title.endswith(' - YouTube'):
+            title = title[:-10]
+
+        # Use link translator mentioned in https://github.com/ytdl-org/youtube-dl/issues/13655
+        link_stub = "https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/"
+
+        # Extract hash from url
+        hash_idx = url.find("watch?v=") + len("watch?v=")
+        youtube_hash = url[hash_idx:]
+
+        # If there's an ampersand, cut off before it
+        ampersand = youtube_hash.find('&')
+        if ampersand != -1:
+            youtube_hash = youtube_hash[:ampersand]
+
+        # Recreate the fixed pattern url and return
+        reconstructed_url = link_stub + youtube_hash
+        return {
+            'url': reconstructed_url,
+            'id': video_id,
+            'title': title,
+            'author': author,
+            'ext': "mp4"
+        }

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: