Fix import + flake8

Closes #7623
Authored by: bashonly

README.md

@@ -157,6 +157,7 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
 * yt-dlp's sanitization of invalid characters in filenames is different/smarter than in youtube-dl. You can use `--compat-options filename-sanitization` to revert to youtube-dl's behavior
 * yt-dlp tries to parse the external downloader outputs into the standard progress output if possible (Currently implemented: [~~aria2c~~](https://github.com/yt-dlp/yt-dlp/issues/5931)). You can use `--compat-options no-external-downloader-progress` to get the downloader output as-is
 * yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filter` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this
+* yt-dlp versions between 2021.11.10 and 2023.06.21 estimated `filesize_approx` values for fragmented/manifest formats. This was added for convenience in [f2fe69](https://github.com/yt-dlp/yt-dlp/commit/f2fe69c7b0d208bdb1f6292b4ae92bc1e1a7444a), but was reverted in [0dff8e](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) due to the potentially extreme inaccuracy of the estimated values. Use `--compat-options manifest-filesize-approx` to keep extracting the estimated values
 * yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests.
 
 For ease of use, a few more compat options are available:
@@ -1801,7 +1802,7 @@ The following extractors use this feature:
 #### youtube
 * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
 * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
-* `player_client`: Clients to extract video data from. The main clients are `web`, `android` and `ios` with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mweb`, `mweb_embedscreen` and `tv_embedded` (agegate bypass) with no variants. By default, `android,web,ios` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. You can use `all` to use all the clients, and `default` for the default clients.
+* `player_client`: Clients to extract video data from. The main clients are `web`, `android` and `ios` with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mweb`, `mweb_embedscreen` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,android,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. You can use `all` to use all the clients, and `default` for the default clients.
 * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
 * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
 * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)

yt_dlp/YoutubeDL.py

@@ -2764,7 +2764,8 @@ class YoutubeDL:
                 format['dynamic_range'] = 'SDR'
             if format.get('aspect_ratio') is None:
                 format['aspect_ratio'] = try_call(lambda: round(format['width'] / format['height'], 2))
-            if (not format.get('manifest_url')  # For fragmented formats, "tbr" is often max bitrate and not average
+            # For fragmented formats, "tbr" is often max bitrate and not average
+            if (('manifest-filesize-approx' in self.params['compat_opts'] or not format.get('manifest_url'))
                     and info_dict.get('duration') and format.get('tbr')
                     and not format.get('filesize') and not format.get('filesize_approx')):
                 format['filesize_approx'] = int(info_dict['duration'] * format['tbr'] * (1024 / 8))
@@ -3550,7 +3551,7 @@ class YoutubeDL:
             reject = lambda k, v: v is None or k.startswith('__') or k in {
                 'requested_downloads', 'requested_formats', 'requested_subtitles', 'requested_entries',
                 'entries', 'filepath', '_filename', 'filename', 'infojson_filename', 'original_url',
-                'playlist_autonumber', '_format_sort_fields',
+                'playlist_autonumber',
             }
         else:
             reject = lambda k, v: False

yt_dlp/downloader/dash.py

@@ -15,13 +15,16 @@ class DashSegmentsFD(FragmentFD):
     FD_NAME = 'dashsegments'
 
     def real_download(self, filename, info_dict):
-        if info_dict.get('is_live') and set(info_dict['protocol'].split('+')) != {'http_dash_segments_generator'}:
+        if 'http_dash_segments_generator' in info_dict['protocol'].split('+'):
+            real_downloader = None  # No external FD can support --live-from-start
+        else:
+            if info_dict.get('is_live'):
                 self.report_error('Live DASH videos are not supported')
-
-        real_start = time.time()
             real_downloader = get_suitable_downloader(
                 info_dict, self.params, None, protocol='dash_frag_urls', to_stdout=(filename == '-'))
 
+        real_start = time.time()
+
         requested_formats = [{**info_dict, **fmt} for fmt in info_dict.get('requested_formats', [])]
         args = []
         for fmt in requested_formats or [info_dict]:

yt_dlp/downloader/external.py

@@ -335,7 +335,7 @@ class Aria2cFD(ExternalFD):
         cmd += ['--auto-file-renaming=false']
 
         if 'fragments' in info_dict:
-            cmd += ['--file-allocation=none', '--uri-selector=inorder']
+            cmd += ['--uri-selector=inorder']
             url_list_file = '%s.frag.urls' % tmpfilename
             url_list = []
             for frag_index, fragment in enumerate(info_dict['fragments']):

yt_dlp/extractor/ntvde.py

@@ -4,9 +4,11 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     js_to_json,
-    traverse_obj,
+    url_or_none,
 )
 
+from ..utils.traversal import traverse_obj
+
 
 class NTVDeIE(InfoExtractor):
     IE_NAME = 'n-tv.de'
@@ -36,10 +38,10 @@ class NTVDeIE(InfoExtractor):
             r'article:\s*', webpage, 'info', video_id, transform_source=js_to_json)
 
         player_data = self._search_json(
-            r'\$\(\s*"\#playerwrapper"\s*\)\s*\.data\(\s*"player",\s*',
+            r'\$\(\s*"#playerwrapper"\s*\)\s*\.data\(\s*"player",\s*',
             webpage, 'player data', video_id,
             transform_source=lambda s: js_to_json(re.sub(r'ivw:[^},]+', '', s)))
-        vdata = traverse_obj(player_data, ('setup', 'source'))
+        vdata = traverse_obj(player_data, ('setup', 'source')) or {}
 
         formats = []
         if vdata.get('progressive'):
@@ -49,8 +51,7 @@ class NTVDeIE(InfoExtractor):
             })
         if vdata.get('hls'):
             formats.extend(self._extract_m3u8_formats(
-                vdata['hls'], video_id, ext='mp4', entry_protocol='m3u8_native',
-                quality=1, m3u8_id='hls', fatal=False))
+                vdata['hls'], video_id, 'mp4', m3u8_id='hls', fatal=False))
         if vdata.get('dash'):
             formats.extend(self._extract_mpd_formats(vdata['dash'], video_id, fatal=False))
 
@@ -63,7 +64,7 @@ class NTVDeIE(InfoExtractor):
                 'timestamp': ('publishedDateAsUnixTimeStamp', {int_or_none}),
             }),
             **traverse_obj(vdata, {
-                'thumbnail': 'poster',
+                'thumbnail': ('poster', {url_or_none}),
                 'duration': ('length', {int_or_none}),
             }),
             'formats': formats,

yt_dlp/extractor/youtube.py

@@ -3619,7 +3619,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _get_requested_clients(self, url, smuggled_data):
         requested_clients = []
-        default = ['android', 'web', 'ios']
+        default = ['ios', 'android', 'web']
         allowed_clients = sorted(
             (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
             key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)

yt_dlp/options.py

@@ -471,12 +471,12 @@ def create_parser():
                 'no-attach-info-json', 'embed-thumbnail-atomicparsley', 'no-external-downloader-progress',
                 'embed-metadata', 'seperate-video-versions', 'no-clean-infojson', 'no-keep-subs', 'no-certifi',
                 'no-youtube-channel-redirect', 'no-youtube-unavailable-videos', 'no-youtube-prefer-utc-upload-date',
-                'prefer-legacy-http-handler'
+                'prefer-legacy-http-handler', 'manifest-filesize-approx'
             }, 'aliases': {
-                'youtube-dl': ['all', '-multistreams', '-playlist-match-filter'],
-                'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter'],
+                'youtube-dl': ['all', '-multistreams', '-playlist-match-filter', '-manifest-filesize-approx'],
+                'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx'],
                 '2021': ['2022', 'no-certifi', 'filename-sanitization', 'no-youtube-prefer-utc-upload-date'],
-                '2022': ['no-external-downloader-progress', 'playlist-match-filter', 'prefer-legacy-http-handler'],
+                '2022': ['no-external-downloader-progress', 'playlist-match-filter', 'prefer-legacy-http-handler', 'manifest-filesize-approx'],
             }
         }, help=(
             'Options that can help keep compatibility with youtube-dl or youtube-dlc '