Merge a4ae6b45202a92ff5e60e5bbd77d1712f251fa0f 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/googledrive.py

@@ -1,6 +1,7 @@
 from __future__ import unicode_literals
 
 import re
+# from venv import create
 
 from .common import InfoExtractor
 from ..compat import compat_parse_qs
@@ -12,6 +13,7 @@ from ..utils import (
     lowercase_escape,
     try_get,
     update_url_query,
+    unified_strdate,
 )
 
 
@@ -28,6 +30,7 @@ class GoogleDriveIE(InfoExtractor):
                             )
                             (?P<id>[a-zA-Z0-9_-]{28,})
                     '''
+    _API_KEY = "AIzaSyCGrlNJSIw19pjonNQOqMIyS2Xai9g0YT0"
     _TESTS = [{
         'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
         'md5': '5c602afbbf2c1db91831f5d82f678554',
@@ -161,12 +164,25 @@ class GoogleDriveIE(InfoExtractor):
         return self._get_captions_by_type(
             video_id, subtitles_id, 'automatic_captions', origin_lang_code)
 
+    def _call_api(self, video_id):
+        # Call Google Drive API
+        json_data = self._download_json('https://www.googleapis.com/drive/v3/files/%s?fields=createdTime,modifiedTime,owners&key=%s' % (video_id, self._API_KEY), video_id)
+        return json_data
+
+    # USING URL: https://drive.google.com/file/d/1lVFQrzYKnJDd045Gc9xv1W4YA9zKPX7r/view?usp=sharing
+    # API KEY: AIzaSyCGrlNJSIw19pjonNQOqMIyS2Xai9g0YT0
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_info = compat_parse_qs(self._download_webpage(
             'https://drive.google.com/get_video_info',
             video_id, query={'docid': video_id}))
 
+        json_data = self._call_api(video_id)
+        createdTime = unified_strdate(json_data['createdTime'])
+        modifiedTime = unified_strdate(json_data['modifiedTime'])
+
+        owner_lst = [owner['displayName'] for owner in json_data['owners']]
+
         def get_value(key):
             return try_get(video_info, lambda x: x[key][0])
 
@@ -271,6 +287,9 @@ class GoogleDriveIE(InfoExtractor):
             'title': title,
             'thumbnail': 'https://drive.google.com/thumbnail?id=' + video_id,
             'duration': int_or_none(get_value('length_seconds')),
+            'created_date': createdTime,
+            'modified_date': modifiedTime,
+            'owners': owner_lst,
             'formats': formats,
             'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
             'automatic_captions': self.extract_automatic_captions(

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/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: