Merge dadf80a9293a40e5a8bc52bc1c48b7b272ce4ff9 into 4e714f9df1ed2cccd51df60d45ff5504abe827b7

* 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

@@ -1079,7 +1079,10 @@ from .rutube import (
     RutubePlaylistIE,
 )
 from .rutv import RUTVIE
-from .ruutu import RuutuIE
+from .ruutu import (
+    RuutuIE,
+    HSfiIE,
+)
 from .ruv import RuvIE
 from .s4c import (
     S4CIE,

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/ruutu.py

@@ -8,11 +8,13 @@ from ..utils import (
     ExtractorError,
     find_xpath_attr,
     int_or_none,
+    try_get,
     unified_strdate,
     url_or_none,
     xpath_attr,
     xpath_text,
 )
+from ..compat import compat_str
 
 
 class RuutuIE(InfoExtractor):
@@ -36,6 +38,7 @@ class RuutuIE(InfoExtractor):
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'duration': 114,
                 'age_limit': 0,
+                'upload_date': '20150508',
             },
         },
         {
@@ -49,6 +52,7 @@ class RuutuIE(InfoExtractor):
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'duration': 40,
                 'age_limit': 0,
+                'upload_date': '20150507',
             },
         },
         {
@@ -61,6 +65,7 @@ class RuutuIE(InfoExtractor):
                 'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe',
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'age_limit': 0,
+                'upload_date': '20151012',
             },
         },
         # Episode where <SourceFile> is "NOT-USED", but has other
@@ -80,6 +85,7 @@ class RuutuIE(InfoExtractor):
                 'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52',
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'age_limit': 0,
+                'upload_date': '20190320',
             },
             'expected_warnings': [
                 'HTTP Error 502: Bad Gateway',
@@ -225,3 +231,51 @@ class RuutuIE(InfoExtractor):
             'categories': themes.split(',') if themes else [],
             'formats': formats,
         }
+
+
+class HSfiIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hs\.fi/[^/]+/art-(?P<id>\d+).html'
+    _TESTS = [
+        {
+            'url': 'https://www.hs.fi/politiikka/art-2000007761258.html',
+            'md5': '63231668b42cbfcbed99f0b8cda76954',
+            'info_dict': {
+                'id': '3773692',
+                'ext': 'mp4',
+                'title': 'Ministeri Kiuru esittelee hallituksen päivitetyt toimenpiteet koronaepidemian hillintään (25.1.21)',
+                'thumbnail': r're:^https?://.+\.jpg$',
+                'duration': 607,
+                'age_limit': 0,
+                'upload_date': '20210125',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        art_id = self._match_id(url)
+        webpage = self._download_webpage(url, art_id)
+        json_s = self._html_search_regex(
+            r'<script id="__NEXT_DATA__" type="application/json">(.+?)</script>', webpage, 'json')
+        jdict = self._parse_json(json_s, art_id)
+        main_id = try_get(
+            jdict,
+            lambda x: x["props"]["pageProps"]["page"]["assetData"]["mainVideo"]["sourceId"],
+            compat_str)
+        slist = try_get(
+            jdict,
+            lambda x: x["props"]["pageProps"]["page"]["assetData"]["splitBody"],
+            list)
+        video_ids = list(set(dd["video"]["sourceId"] for dd in slist
+                         if type(dd) == dict
+                             and dd.get("type", "") == "video"
+                             and "video" in dd.keys()
+                             and "sourceId" in dd["video"].keys()))
+        # TODO: return playlist?
+        if main_id is not None:
+            video_id = main_id
+        elif video_ids:
+            video_id = video_ids[0]
+        else:
+            raise ExtractorError("No video found on this page", expected=True)
+
+        return self.url_result("http://www.ruutu.fi/video/%s" % video_id)

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',