[youtube] Improve _VALID_URL (refs #28193)

Co-authored-by: Sergey M <dstftw@gmail.com>

youtube_dl/extractor/dplay.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
@@ -10,11 +11,13 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    strip_or_none,
     unified_timestamp,
 )
 
 
 class DPlayIE(InfoExtractor):
+    _PATH_REGEX = r'/(?P<id>[^/]+/[^/?#]+)'
     _VALID_URL = r'''(?x)https?://
         (?P<domain>
             (?:www\.)?(?P<host>d
@@ -24,7 +27,7 @@ class DPlayIE(InfoExtractor):
                 )
             )|
             (?P<subdomain_country>es|it)\.dplay\.com
-        )/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
+        )/[^/]+''' + _PATH_REGEX
 
     _TESTS = [{
         # non geo restricted, via secure api, unsigned download hls URL
@@ -151,21 +154,47 @@ class DPlayIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _process_errors(self, e, geo_countries):
+        info = self._parse_json(e.cause.read().decode('utf-8'), None)
+        error = info['errors'][0]
+        error_code = error.get('code')
+        if error_code == 'access.denied.geoblocked':
+            self.raise_geo_restricted(countries=geo_countries)
+        elif error_code in ('access.denied.missingpackage', 'invalid.token'):
+            raise ExtractorError(
+                'This video is only available for registered users. You may want to use --cookies.', expected=True)
+        raise ExtractorError(info['errors'][0]['detail'], expected=True)
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers['Authorization'] = 'Bearer ' + self._download_json(
+            disco_base + 'token', display_id, 'Downloading token',
+            query={
+                'realm': realm,
+            })['data']['attributes']['token']
+
+    def _download_video_playback_info(self, disco_base, video_id, headers):
+        streaming = self._download_json(
+            disco_base + 'playback/videoPlaybackInfo/' + video_id,
+            video_id, headers=headers)['data']['attributes']['streaming']
+        streaming_list = []
+        for format_id, format_dict in streaming.items():
+            streaming_list.append({
+                'type': format_id,
+                'url': format_dict.get('url'),
+            })
+        return streaming_list
+
     def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
         geo_countries = [country.upper()]
         self._initialize_geo_bypass({
             'countries': geo_countries,
         })
         disco_base = 'https://%s/' % disco_host
-        token = self._download_json(
-            disco_base + 'token', display_id, 'Downloading token',
-            query={
-                'realm': realm,
-            })['data']['attributes']['token']
         headers = {
             'Referer': url,
-            'Authorization': 'Bearer ' + token,
         }
+        self._update_disco_api_headers(headers, disco_base, display_id, realm)
+        try:
             video = self._download_json(
                 disco_base + 'content/videos/' + display_id, display_id,
                 headers=headers, query={
@@ -176,31 +205,28 @@ class DPlayIE(InfoExtractor):
                     'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
                     'include': 'images,primaryChannel,show,tags'
                 })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
+                self._process_errors(e, geo_countries)
+            raise
         video_id = video['data']['id']
         info = video['data']['attributes']
         title = info['name'].strip()
         formats = []
         try:
-            streaming = self._download_json(
-                disco_base + 'playback/videoPlaybackInfo/' + video_id,
-                display_id, headers=headers)['data']['attributes']['streaming']
+            streaming = self._download_video_playback_info(
+                disco_base, video_id, headers)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
-                info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
-                error = info['errors'][0]
-                error_code = error.get('code')
-                if error_code == 'access.denied.geoblocked':
-                    self.raise_geo_restricted(countries=geo_countries)
-                elif error_code == 'access.denied.missingpackage':
-                    self.raise_login_required()
-                raise ExtractorError(info['errors'][0]['detail'], expected=True)
+                self._process_errors(e, geo_countries)
             raise
-        for format_id, format_dict in streaming.items():
+        for format_dict in streaming:
             if not isinstance(format_dict, dict):
                 continue
             format_url = format_dict.get('url')
             if not format_url:
                 continue
+            format_id = format_dict.get('type')
             ext = determine_ext(format_url)
             if format_id == 'dash' or ext == 'mpd':
                 formats.extend(self._extract_mpd_formats(
@@ -248,7 +274,7 @@ class DPlayIE(InfoExtractor):
             'id': video_id,
             'display_id': display_id,
             'title': title,
-            'description': info.get('description'),
+            'description': strip_or_none(info.get('description')),
             'duration': float_or_none(info.get('videoDuration'), 1000),
             'timestamp': unified_timestamp(info.get('publishStart')),
             'series': series,
@@ -268,3 +294,75 @@ class DPlayIE(InfoExtractor):
         host = 'disco-api.' + domain if domain[0] == 'd' else 'eu2-prod.disco-api.com'
         return self._get_disco_api_info(
             url, display_id, host, 'dplay' + country, country)
+
+
+class DiscoveryPlusIE(DPlayIE):
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/video' + DPlayIE._PATH_REGEX
+    _TESTS = [{
+        'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
+        'info_dict': {
+            'id': '1140794',
+            'display_id': 'property-brothers-forever-home/food-and-family',
+            'ext': 'mp4',
+            'title': 'Food and Family',
+            'description': 'The brothers help a Richmond family expand their single-level home.',
+            'duration': 2583.113,
+            'timestamp': 1609304400,
+            'upload_date': '20201230',
+            'creator': 'HGTV',
+            'series': 'Property Brothers: Forever Home',
+            'season_number': 1,
+            'episode_number': 1,
+        },
+        'skip': 'Available for Premium users',
+    }]
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers['x-disco-client'] = 'WEB:UNKNOWN:dplus_us:15.0.0'
+
+    def _download_video_playback_info(self, disco_base, video_id, headers):
+        return self._download_json(
+            disco_base + 'playback/v3/videoPlaybackInfo',
+            video_id, headers=headers, data=json.dumps({
+                'deviceInfo': {
+                    'adBlocker': False,
+                },
+                'videoId': video_id,
+                'wisteriaProperties': {
+                    'platform': 'desktop',
+                },
+            }).encode('utf-8'))['data']['attributes']['streaming']
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        return self._get_disco_api_info(
+            url, display_id, 'us1-prod-direct.discoveryplus.com', 'go', 'us')
+
+
+class HGTVDeIE(DPlayIE):
+    _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayIE._PATH_REGEX
+    _TESTS = [{
+        'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/',
+        'info_dict': {
+            'id': '151205',
+            'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette',
+            'ext': 'mp4',
+            'title': 'Wer braucht schon eine Toilette',
+            'description': 'md5:05b40a27e7aed2c9172de34d459134e2',
+            'duration': 1177.024,
+            'timestamp': 1595705400,
+            'upload_date': '20200725',
+            'creator': 'HGTV',
+            'series': 'Tiny House - klein, aber oho',
+            'season_number': 3,
+            'episode_number': 3,
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        return self._get_disco_api_info(
+            url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de')

youtube_dl/extractor/extractors.py

@@ -288,7 +288,11 @@ from .douyutv import (
     DouyuShowIE,
     DouyuTVIE,
 )
-from .dplay import DPlayIE
+from .dplay import (
+    DPlayIE,
+    DiscoveryPlusIE,
+    HGTVDeIE,
+)
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE

youtube_dl/extractor/youtube.py

@@ -326,52 +326,57 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
 class YoutubeIE(YoutubeBaseInfoExtractor):
     IE_DESC = 'YouTube.com'
+    _INVIDIOUS_SITES = (
+        # invidious-redirect websites
+        r'(?:www\.)?redirect\.invidious\.io',
+        r'(?:(?:www|dev)\.)?invidio\.us',
+        # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
+        r'(?:(?:www|no)\.)?invidiou\.sh',
+        r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
+        r'(?:www\.)?invidious\.kabi\.tk',
+        r'(?:www\.)?invidious\.13ad\.de',
+        r'(?:www\.)?invidious\.mastodon\.host',
+        r'(?:www\.)?invidious\.zapashcanon\.fr',
+        r'(?:www\.)?invidious\.kavin\.rocks',
+        r'(?:www\.)?invidious\.tube',
+        r'(?:www\.)?invidiou\.site',
+        r'(?:www\.)?invidious\.site',
+        r'(?:www\.)?invidious\.xyz',
+        r'(?:www\.)?invidious\.nixnet\.xyz',
+        r'(?:www\.)?invidious\.drycat\.fr',
+        r'(?:www\.)?tube\.poal\.co',
+        r'(?:www\.)?tube\.connect\.cafe',
+        r'(?:www\.)?vid\.wxzm\.sx',
+        r'(?:www\.)?vid\.mint\.lgbt',
+        r'(?:www\.)?yewtu\.be',
+        r'(?:www\.)?yt\.elukerio\.org',
+        r'(?:www\.)?yt\.lelux\.fi',
+        r'(?:www\.)?invidious\.ggc-project\.de',
+        r'(?:www\.)?yt\.maisputain\.ovh',
+        r'(?:www\.)?invidious\.13ad\.de',
+        r'(?:www\.)?invidious\.toot\.koeln',
+        r'(?:www\.)?invidious\.fdn\.fr',
+        r'(?:www\.)?watch\.nettohikari\.com',
+        r'(?:www\.)?kgg2m7yk5aybusll\.onion',
+        r'(?:www\.)?qklhadlycap4cnod\.onion',
+        r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
+        r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
+        r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
+        r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
+        r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
+        r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
+    )
     _VALID_URL = r"""(?x)^
                      (
                          (?:https?://|//)                                    # http(s):// or protocol-independent URL
-                         (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
-                            (?:www\.)?deturl\.com/www\.youtube\.com/|
-                            (?:www\.)?pwnyoutube\.com/|
-                            (?:www\.)?hooktube\.com/|
-                            (?:www\.)?yourepeat\.com/|
-                            tube\.majestyc\.net/|
-                            # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
-                            (?:(?:www|dev)\.)?invidio\.us/|
-                            (?:(?:www|no)\.)?invidiou\.sh/|
-                            (?:(?:www|fi)\.)?invidious\.snopyta\.org/|
-                            (?:www\.)?invidious\.kabi\.tk/|
-                            (?:www\.)?invidious\.13ad\.de/|
-                            (?:www\.)?invidious\.mastodon\.host/|
-                            (?:www\.)?invidious\.zapashcanon\.fr/|
-                            (?:www\.)?invidious\.kavin\.rocks/|
-                            (?:www\.)?invidious\.tube/|
-                            (?:www\.)?invidiou\.site/|
-                            (?:www\.)?invidious\.site/|
-                            (?:www\.)?invidious\.xyz/|
-                            (?:www\.)?invidious\.nixnet\.xyz/|
-                            (?:www\.)?invidious\.drycat\.fr/|
-                            (?:www\.)?tube\.poal\.co/|
-                            (?:www\.)?tube\.connect\.cafe/|
-                            (?:www\.)?vid\.wxzm\.sx/|
-                            (?:www\.)?vid\.mint\.lgbt/|
-                            (?:www\.)?yewtu\.be/|
-                            (?:www\.)?yt\.elukerio\.org/|
-                            (?:www\.)?yt\.lelux\.fi/|
-                            (?:www\.)?invidious\.ggc-project\.de/|
-                            (?:www\.)?yt\.maisputain\.ovh/|
-                            (?:www\.)?invidious\.13ad\.de/|
-                            (?:www\.)?invidious\.toot\.koeln/|
-                            (?:www\.)?invidious\.fdn\.fr/|
-                            (?:www\.)?watch\.nettohikari\.com/|
-                            (?:www\.)?kgg2m7yk5aybusll\.onion/|
-                            (?:www\.)?qklhadlycap4cnod\.onion/|
-                            (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
-                            (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
-                            (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
-                            (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
-                            (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
-                            (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/|
-                            youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
+                         (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
+                            (?:www\.)?deturl\.com/www\.youtube\.com|
+                            (?:www\.)?pwnyoutube\.com|
+                            (?:www\.)?hooktube\.com|
+                            (?:www\.)?yourepeat\.com|
+                            tube\.majestyc\.net|
+                            %(invidious)s|
+                            youtube\.googleapis\.com)/                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                          (?:                                                  # the various things that can precede the ID:
                              (?:(?:v|embed|e)/(?!videoseries))                # v/ or embed/ or e/
@@ -386,6 +391,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             youtu\.be|                                        # just youtu.be/xxxx
                             vid\.plus|                                        # or vid.plus/xxxx
                             zwearz\.com/watch|                                # or zwearz.com/watch/xxxx
+                            %(invidious)s
                          )/
                          |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
                          )
@@ -398,7 +404,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         )
                      )
                      (?(1).+)?                                                # if we found the ID, everything can follow
-                     $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
+                     $""" % {
+        'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
+        'invidious': '|'.join(_INVIDIOUS_SITES),
+    }
     _PLAYER_INFO_RE = (
         r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
         r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
@@ -906,6 +915,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'https://invidio.us/watch?v=BaW_jenozKc',
             'only_matching': True,
         },
+        {
+            'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
+            'only_matching': True,
+        },
+        {
+            # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
+            'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
+            'only_matching': True,
+        },
         {
             # DRM protected
             'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',