]> jfr.im git - yt-dlp.git/blobdiff - yt_dlp/extractor/nbc.py
[cleanup] Add more ruff rules (#10149)
[yt-dlp.git] / yt_dlp / extractor / nbc.py
index b3c28ab55d5bbaf1aa1bd797209cceb91f171f65..1da2cad3d48b62266fc9b4a42c53a8d1bb8c3e7a 100644 (file)
@@ -1,11 +1,12 @@
 import base64
 import json
 import re
+import urllib.parse
+import xml.etree.ElementTree
 
+from .adobepass import AdobePassIE
 from .common import InfoExtractor
 from .theplatform import ThePlatformIE, default_ns
-from .adobepass import AdobePassIE
-from ..compat import compat_urllib_parse_unquote
 from ..networking import HEADRequest
 from ..utils import (
     ExtractorError,
@@ -52,6 +53,8 @@ class NBCIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'chapters': 'count:1',
                 'tags': 'count:4',
                 'thumbnail': r're:https?://.+\.jpg',
+                'categories': ['Series/The Tonight Show Starring Jimmy Fallon'],
+                'media_type': 'Full Episode',
             },
             'params': {
                 'skip_download': 'm3u8',
@@ -130,6 +133,8 @@ class NBCIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'tags': 'count:10',
                 'age_limit': 0,
                 'thumbnail': r're:https?://.+\.jpg',
+                'categories': ['Series/Quantum Leap 2022'],
+                'media_type': 'Highlight',
             },
             'params': {
                 'skip_download': 'm3u8',
@@ -143,12 +148,12 @@ class NBCIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
             # Percent escaped url
             'url': 'https://www.nbc.com/up-all-night/video/day-after-valentine%27s-day/n2189',
             'only_matching': True,
-        }
+        },
     ]
 
     def _real_extract(self, url):
         permalink, video_id = self._match_valid_url(url).groups()
-        permalink = 'http' + compat_urllib_parse_unquote(permalink)
+        permalink = 'http' + urllib.parse.unquote(permalink)
         video_data = self._download_json(
             'https://friendship.nbc.co/v2/graphql', video_id, query={
                 'query': '''query bonanzaPage(
@@ -196,7 +201,7 @@ def _real_extract(self, url):
             'switch': 'HLSServiceSecure',
         }
         video_id = video_data['mpxGuid']
-        tp_path = 'NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id)
+        tp_path = 'NnzsPC/media/guid/{}/{}'.format(video_data.get('mpxAccountId') or '2410887629', video_id)
         tpm = self._download_theplatform_metadata(tp_path, video_id)
         title = tpm.get('title') or video_data.get('secondaryTitle')
         if video_data.get('locked'):
@@ -206,7 +211,7 @@ def _real_extract(self, url):
             query['auth'] = self._extract_mvpd_auth(
                 url, video_id, 'nbcentertainment', resource)
         theplatform_url = smuggle_url(update_url_query(
-            'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id),
+            'http://link.theplatform.com/s/NnzsPC/media/guid/{}/{}'.format(video_data.get('mpxAccountId') or '2410887629', video_id),
             query), {'force_smil_url': True})
 
         # Empty string or 0 can be valid values for these. So the check must be `is None`
@@ -248,7 +253,7 @@ def _real_extract(self, url):
 class NBCSportsVPlayerIE(InfoExtractor):
     _VALID_URL_BASE = r'https?://(?:vplayer\.nbcsports\.com|(?:www\.)?nbcsports\.com/vplayer)/'
     _VALID_URL = _VALID_URL_BASE + r'(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
-    _EMBED_REGEX = [r'(?:iframe[^>]+|var video|div[^>]+data-(?:mpx-)?)[sS]rc\s?=\s?"(?P<url>%s[^\"]+)' % _VALID_URL_BASE]
+    _EMBED_REGEX = [rf'(?:iframe[^>]+|var video|div[^>]+data-(?:mpx-)?)[sS]rc\s?=\s?"(?P<url>{_VALID_URL_BASE}[^\"]+)']
 
     _TESTS = [{
         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI',
@@ -262,8 +267,8 @@ class NBCSportsVPlayerIE(InfoExtractor):
             'uploader': 'NBCU-SPORTS',
             'duration': 72.818,
             'chapters': [],
-            'thumbnail': r're:^https?://.*\.jpg$'
-        }
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
     }, {
         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/PEgOtlNcC_y2',
         'only_matching': True,
@@ -284,7 +289,7 @@ class NBCSportsIE(InfoExtractor):
 
     _TESTS = [{
         # iframe src
-        'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
+        'url': 'https://www.nbcsports.com/watch/nfl/profootballtalk/pft-pm/unpacking-addisons-reckless-driving-citation',
         'info_dict': {
             'id': 'PHJSaFWbrTY9',
             'ext': 'mp4',
@@ -296,7 +301,7 @@ class NBCSportsIE(InfoExtractor):
             'chapters': [],
             'thumbnail': 'https://hdliveextra-a.akamaihd.net/HD/image_sports/NBCU_Sports_Group_-_nbcsports/253/303/izzodps.jpg',
             'duration': 528.395,
-        }
+        },
     }, {
         # data-mpx-src
         'url': 'https://www.nbcsports.com/philadelphia/philadelphia-phillies/bruce-bochy-hector-neris-hes-idiot',
@@ -334,7 +339,7 @@ class NBCSportsStreamIE(AdobePassIE):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         live_source = self._download_json(
-            'http://stream.nbcsports.com/data/live_sources_%s.json' % video_id,
+            f'http://stream.nbcsports.com/data/live_sources_{video_id}.json',
             video_id)
         video_source = live_source['videoSources'][0]
         title = video_source['title']
@@ -379,7 +384,7 @@ class NBCNewsIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
     _TESTS = [
         {
             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
-            'md5': 'cf4bc9e6ce0130f00f545d80ecedd4bf',
+            'md5': 'fb3dcd2d7b1dd9804305fa2fc95ab610',  # md5 tends to fluctuate
             'info_dict': {
                 'id': '269389891880',
                 'ext': 'mp4',
@@ -387,6 +392,8 @@ class NBCNewsIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
                 'timestamp': 1401363060,
                 'upload_date': '20140529',
+                'duration': 46.0,
+                'thumbnail': 'https://media-cldnry.s-nbcnews.com/image/upload/MSNBC/Components/Video/140529/p_tweet_snow_140529.jpg',
             },
         },
         {
@@ -402,7 +409,7 @@ class NBCNewsIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
         },
         {
             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
-            'md5': '8eb831eca25bfa7d25ddd83e85946548',
+            'md5': '40d0e48c68896359c80372306ece0fc3',
             'info_dict': {
                 'id': '394064451844',
                 'ext': 'mp4',
@@ -410,11 +417,13 @@ class NBCNewsIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
                 'timestamp': 1423104900,
                 'upload_date': '20150205',
+                'duration': 1236.0,
+                'thumbnail': 'https://media-cldnry.s-nbcnews.com/image/upload/MSNBC/Components/Video/__NEW/nn_netcast_150204.jpg',
             },
         },
         {
             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
-            'md5': '4a8c4cec9e1ded51060bdda36ff0a5c0',
+            'md5': 'ffb59bcf0733dc3c7f0ace907f5e3939',
             'info_dict': {
                 'id': 'n431456',
                 'ext': 'mp4',
@@ -422,11 +431,13 @@ class NBCNewsIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'description': 'md5:d22d1281a24f22ea0880741bb4dd6301',
                 'upload_date': '20150922',
                 'timestamp': 1442917800,
+                'duration': 37.0,
+                'thumbnail': 'https://media-cldnry.s-nbcnews.com/image/upload/MSNBC/Components/Video/__NEW/x_lon_vwhorn_150922.jpg',
             },
         },
         {
             'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
-            'md5': '118d7ca3f0bea6534f119c68ef539f71',
+            'md5': '693d1fa21d23afcc9b04c66b227ed9ff',
             'info_dict': {
                 'id': '669831235788',
                 'ext': 'mp4',
@@ -434,6 +445,8 @@ class NBCNewsIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
                 'upload_date': '20160420',
                 'timestamp': 1461152093,
+                'duration': 69.0,
+                'thumbnail': 'https://media-cldnry.s-nbcnews.com/image/upload/MSNBC/Components/Video/201604/2016-04-20T11-35-09-133Z--1280x720.jpg',
             },
         },
         {
@@ -447,6 +460,7 @@ class NBCNewsIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'timestamp': 1406937606,
                 'upload_date': '20140802',
+                'duration': 940.0,
             },
         },
         {
@@ -485,7 +499,7 @@ def _real_extract(self, url):
                 continue
             tbr = int_or_none(va.get('bitrate'), 1000)
             if tbr:
-                format_id += '-%d' % tbr
+                format_id += f'-{tbr}'
             formats.append({
                 'format_id': format_id,
                 'url': public_url,
@@ -535,6 +549,7 @@ class NBCOlympicsIE(InfoExtractor):
             'upload_date': '20160815',
             'uploader': 'NBCU-SPORTS',
         },
+        'skip': '404 Not Found',
     }
 
     def _real_extract(self, url):
@@ -553,7 +568,7 @@ def _real_extract(self, url):
         except RegexNotFoundError:
             theplatform_url = self._search_regex(
                 r"([\"'])embedUrl\1: *([\"'])(?P<embedUrl>.+)\2",
-                webpage, 'embedding URL', group="embedUrl")
+                webpage, 'embedding URL', group='embedUrl')
 
         return {
             '_type': 'url_transparent',
@@ -578,6 +593,7 @@ class NBCOlympicsStreamIE(AdobePassIE):
             'params': {
                 'skip_download': 'm3u8',
             },
+            'skip': 'Livestream',
         }, {
             'note': 'Plain m3u8 source URL',
             'url': 'https://stream.nbcolympics.com/gymnastics-event-finals-mens-floor-pommel-horse-womens-vault-bars',
@@ -589,6 +605,7 @@ class NBCOlympicsStreamIE(AdobePassIE):
             'params': {
                 'skip_download': 'm3u8',
             },
+            'skip': 'Livestream',
         },
     ]
 
@@ -606,7 +623,7 @@ def _real_extract(self, url):
 
         source_url = self._download_json(
             f'https://api-leap.nbcsports.com/feeds/assets/{pid}?application=NBCOlympics&platform=desktop&format=nbc-player&env=staging',
-            pid, 'Downloading leap config'
+            pid, 'Downloading leap config',
         )['videoSources'][0]['cdnSources']['primary'][0]['sourceUrl']
 
         if event_config.get('cdnToken'):
@@ -791,8 +808,10 @@ def _real_extract(self, url):
             smil = self._download_xml(
                 f'https://link.theplatform.com/s/{pdk_acct}/{player_id}', video_id,
                 note='Downloading SMIL data', query=query, fatal=is_live)
-        subtitles = self._parse_smil_subtitles(smil, default_ns) if smil else {}
-        for video in smil.findall(self._xpath_ns('.//video', default_ns)) if smil else []:
+            if not isinstance(smil, xml.etree.ElementTree.Element):
+                smil = None
+        subtitles = self._parse_smil_subtitles(smil, default_ns) if smil is not None else {}
+        for video in smil.findall(self._xpath_ns('.//video', default_ns)) if smil is not None else []:
             info['duration'] = float_or_none(remove_end(video.get('dur'), 'ms'), 1000)
             video_src_url = video.get('src')
             ext = mimetype2ext(video.get('type'), default=determine_ext(video_src_url))