Merge f43daa36fa3f9946302eadc1567084dd29cffd2b 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

@@ -736,6 +736,7 @@ from .mtv import (
     MTVJapanIE,
 )
 from .muenchentv import MuenchenTVIE
+from .murrtube import MurrtubeIE, MurrtubeUserIE
 from .mwave import MwaveIE, MwaveMeetGreetIE
 from .mychannels import MyChannelsIE
 from .myspace import MySpaceIE, MySpaceAlbumIE

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/murrtube.py

@@ -0,0 +1,218 @@
+# coding: utf-8
+from __future__ import unicode_literals
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    try_get,
+    unified_strdate,
+)
+
+
+class MurrtubeIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                        (?:
+                            murrtube:|
+                            https?://murrtube\.net/videos/(?:[a-z0-9\-]+)\-
+                        )
+                        (?P<id>[a-f0-9]{8}\-[a-f0-9]{4}\-[a-f0-9]{4}\-[a-f0-9]{4}\-[a-f0-9]{12})
+                    '''
+    _TEST = {
+        'url': 'https://murrtube.net/videos/inferno-x-skyler-148b6f2a-fdcc-4902-affe-9c0f41aaaca0',
+        'md5': '169f494812d9a90914b42978e73aa690',
+        'info_dict': {
+            'id': '148b6f2a-fdcc-4902-affe-9c0f41aaaca0',
+            'ext': 'mp4',
+            'title': 'Inferno X Skyler',
+            'description': 'Humping a very good slutty sheppy (roomate)',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 284,
+            'uploader': 'Inferno Wolf',
+            'upload_date': '20200502',
+            'age_limit': 18,
+        }
+    }
+
+    def _download_gql(self, video_id, op, note=None, fatal=True):
+        result = self._download_json(
+            "https://murrtube.net/graphql",
+            video_id,
+            note,
+            data=json.dumps(op).encode(),
+            headers={
+                'Content-Type': "application/json",
+            },
+            fatal=fatal,
+        )
+        return result['data']
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        data = self._download_gql(video_id, {
+            "operationName": "Medium",
+            "variables": {
+                "id": video_id,
+            },
+            "query": """query Medium($id: ID!) {
+  medium(id: $id) {
+    id
+    slug
+    title
+    description
+    key
+    duration
+    commentsCount
+    likesCount
+    liked
+    viewsCount
+    publishedAt
+    thumbnailKey
+    smallThumbnailKey
+    tagList
+    user {
+      id
+      slug
+      name
+      avatar
+      __typename
+    }
+    __typename
+  }
+}"""})
+        meta = data['medium']
+
+        storage_url = 'https://storage.murrtube.net/murrtube/'
+        format_url = storage_url + meta['key']
+        thumbnail = storage_url + meta['thumbnailKey']
+
+        formats = []
+        if determine_ext(format_url) == 'm3u8':
+            formats.extend(self._extract_m3u8_formats(
+                format_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                preference=1, fatal=False))
+        else:
+            formats.append({
+                'url': format_url,
+            })
+
+        return {
+            'id': video_id,
+            'title': meta['title'],
+            'description': meta.get('description'),
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'duration': int(meta['duration']),
+            'uploader': try_get(meta, lambda x: x['user']['name']),
+            'upload_date': unified_strdate(meta.get('publishedAt')),
+            'view_count': int_or_none(meta.get('viewsCount')),
+            'like_count': int_or_none(meta.get('likesCount')),
+            'comment_count': int_or_none(meta.get('commentsCount')),
+            'tags': meta.get('tagList', []),
+            'age_limit': 18,
+        }
+
+
+class MurrtubeUserIE(MurrtubeIE):
+    IE_DESC = 'Murrtube user profile'
+    _VALID_URL = r'https?://murrtube\.net/(?P<id>[^/]+)/?$'
+    _TEST = {
+        'url': 'https://murrtube.net/stormy',
+        'info_dict': {
+            'id': 'stormy',
+            'age_limit': 18,
+        },
+        'playlist_mincount': 28,
+    }
+
+    def _real_extract(self, url):
+        username = self._match_id(url)
+        data = self._download_gql(username, {
+            "operationName": "User",
+            "variables": {
+                "id": username,
+            },
+            "query": """query User($id: ID!) {
+  user(id: $id) {
+    id
+    public
+    chatEnabled
+    slug
+    name
+    avatar
+    banner
+    bio
+    website
+    followed
+    following
+    mediaCount
+    followersCount
+    followingCount
+    likesCount
+    blocked
+    __typename
+  }
+}"""},
+            "Downloading user info")
+        user = data['user']
+
+        page_size = 10
+        num_pages = int(user['mediaCount']) // page_size + 1
+        entries = []
+
+        for page in range(num_pages):
+            data = self._download_gql(username, {
+                "operationName": "Media",
+                "variables": {
+                    "limit": page_size,
+                    "offset": page * page_size,
+                    "sort": "latest",
+                    "userId": user['id'],
+                },
+                "query": """query Media($q: String, $sort: String, $userId: ID, $offset: Int!, $limit: Int!) {
+  media(q: $q, sort: $sort, userId: $userId, offset: $offset, limit: $limit) {
+    id
+    slug
+    title
+    description
+    previewKey
+    thumbnailKey
+    smallThumbnailKey
+    publishedAt
+    duration
+    commentsCount
+    likesCount
+    viewsCount
+    tagList
+    visibility
+    restriction
+    user {
+      id
+      slug
+      name
+      avatar
+      __typename
+    }
+    __typename
+  }
+  users(q: $q, fillWithFollowing: false, offset: 0, limit: 2) {
+    id
+    slug
+    name
+    avatar
+    mediaCount
+    __typename
+  }
+}"""},
+                "Downloading page {0}".format(page + 1))
+            media = data['media']
+
+            for entry in media:
+                entries.append(self.url_result(
+                    'murrtube:{0}'.format(entry['id']),
+                    MurrtubeIE.ie_key()))
+
+        playlist = self.playlist_result(entries, username)
+        playlist['age_limit'] = 18
+        return playlist

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: