[cleanup] Misc (#10075)

Closes #10303
Authored by: bashonly, seproDev, jucor, c-basalt

Co-authored-by: sepro <4618135+seproDev@users.noreply.github.com>
Co-authored-by: Julien Cornebise <julien@cornebise.com>
Co-authored-by: c-basalt <117849907+c-basalt@users.noreply.github.com>

yt_dlp/extractor/arcpublishing.py

@@ -4,6 +4,7 @@ from .common import InfoExtractor
 from ..utils import (
     extract_attributes,
     int_or_none,
+    join_nonempty,
     parse_iso8601,
     try_get,
 )
@@ -136,7 +137,7 @@ class ArcPublishingIE(InfoExtractor):
             else:
                 vbr = int_or_none(s.get('bitrate'))
                 formats.append({
-                    'format_id': f'{stream_type}-{vbr}' if vbr else stream_type,
+                    'format_id': join_nonempty(stream_type, vbr),
                     'vbr': vbr,
                     'width': int_or_none(s.get('width')),
                     'height': int_or_none(s.get('height')),

yt_dlp/extractor/arkena.py

@@ -131,8 +131,8 @@ class ArkenaIE(InfoExtractor):
                             formats.extend(self._extract_f4m_formats(
                                 href, video_id, f4m_id='hds', fatal=False))
                         elif mime_type == 'application/dash+xml':
-                            formats.extend(self._extract_f4m_formats(
-                                href, video_id, f4m_id='hds', fatal=False))
+                            formats.extend(self._extract_mpd_formats(
+                                href, video_id, mpd_id='dash', fatal=False))
                         elif mime_type == 'application/vnd.ms-sstr+xml':
                             formats.extend(self._extract_ism_formats(
                                 href, video_id, ism_id='mss', fatal=False))

yt_dlp/extractor/bandcamp.py

@@ -41,7 +41,7 @@ class BandcampIE(InfoExtractor):
             'uploader_id': 'youtube-dl',
             'thumbnail': 'https://f4.bcbits.com/img/a3216802731_5.jpg',
         },
-        '_skip': 'There is a limit of 200 free downloads / month for the test song',
+        'skip': 'There is a limit of 200 free downloads / month for the test song',
     }, {
         # free download
         'url': 'http://benprunty.bandcamp.com/track/lanius-battle',

yt_dlp/extractor/brightcove.py

@@ -18,6 +18,7 @@ from ..utils import (
     fix_xml_ampersands,
     float_or_none,
     int_or_none,
+    join_nonempty,
     js_to_json,
     mimetype2ext,
     parse_iso8601,
@@ -538,12 +539,7 @@ class BrightcoveNewBaseIE(AdobePassIE):
                     })
 
                 def build_format_id(kind):
-                    format_id = kind
-                    if tbr:
-                        format_id += f'-{int(tbr)}k'
-                    if height:
-                        format_id += f'-{height}p'
-                    return format_id
+                    return join_nonempty(kind, tbr and f'{int(tbr)}k', height and f'{height}p')
 
                 if src or streaming_src:
                     f.update({

yt_dlp/extractor/cbsnews.py

@@ -1,6 +1,5 @@
 import base64
 import re
-import urllib.error
 import urllib.parse
 import zlib
 

yt_dlp/extractor/dailymail.py

@@ -2,6 +2,7 @@ from .common import InfoExtractor
 from ..utils import (
     determine_protocol,
     int_or_none,
+    join_nonempty,
     try_get,
     unescapeHTML,
 )
@@ -52,7 +53,7 @@ class DailyMailIE(InfoExtractor):
             is_hls = container == 'M2TS'
             protocol = 'm3u8_native' if is_hls else determine_protocol({'url': rendition_url})
             formats.append({
-                'format_id': ('hls' if is_hls else protocol) + (f'-{tbr}' if tbr else ''),
+                'format_id': join_nonempty('hls' if is_hls else protocol, tbr),
                 'url': rendition_url,
                 'width': int_or_none(rendition.get('frameWidth')),
                 'height': int_or_none(rendition.get('frameHeight')),

yt_dlp/extractor/eitb.py

@@ -1,6 +1,11 @@
 from .common import InfoExtractor
 from ..networking import Request
-from ..utils import float_or_none, int_or_none, parse_iso8601
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    join_nonempty,
+    parse_iso8601,
+)
 
 
 class EitbIE(InfoExtractor):
@@ -37,12 +42,9 @@ class EitbIE(InfoExtractor):
             if not video_url:
                 continue
             tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000)
-            format_id = 'http'
-            if tbr:
-                format_id += f'-{int(tbr)}'
             formats.append({
                 'url': rendition['PMD_URL'],
-                'format_id': format_id,
+                'format_id': join_nonempty('http', int_or_none(tbr)),
                 'width': int_or_none(rendition.get('FRAME_WIDTH')),
                 'height': int_or_none(rendition.get('FRAME_HEIGHT')),
                 'tbr': tbr,

yt_dlp/extractor/eporner.py

@@ -29,9 +29,6 @@ class EpornerIE(InfoExtractor):
             'view_count': int,
             'age_limit': 18,
         },
-        'params': {
-            'proxy': '127.0.0.1:8118',
-        },
     }, {
         # New (May 2016) URL layout
         'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',

yt_dlp/extractor/go.py

@@ -5,6 +5,7 @@ from ..utils import (
     ExtractorError,
     determine_ext,
     int_or_none,
+    join_nonempty,
     parse_age_limit,
     remove_end,
     remove_start,
@@ -287,7 +288,7 @@ class GoIE(AdobePassIE):
                     if mobj:
                         height = int(mobj.group(2))
                         f.update({
-                            'format_id': (f'{format_id}-' if format_id else '') + f'{height}P',
+                            'format_id': join_nonempty(format_id, f'{height}P'),
                             'width': int(mobj.group(1)),
                             'height': height,
                         })

yt_dlp/extractor/hbo.py

@@ -3,6 +3,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
+    join_nonempty,
     parse_duration,
     urljoin,
     xpath_element,
@@ -69,7 +70,7 @@ class HBOBaseIE(InfoExtractor):
                 height = format_info.get('height')
                 fmt = {
                     'url': path,
-                    'format_id': 'http{}'.format(f'-{height}p' if height else ''),
+                    'format_id': join_nonempty('http'. height and f'{height}p'),
                     'width': format_info.get('width'),
                     'height': height,
                 }

yt_dlp/extractor/hketv.py

@@ -44,9 +44,6 @@ class HKETVIE(InfoExtractor):
             'duration': 907,
             'subtitles': {},
         },
-        'params': {
-            'geo_verification_proxy': '<HK proxy here>',
-        },
         'skip': 'Geo restricted to HK',
     }]
 

yt_dlp/extractor/instagram.py

@@ -453,7 +453,7 @@ class InstagramIE(InstagramBaseIE):
             else:
                 self.report_warning('Main webpage is locked behind the login page. Retrying with embed webpage (some metadata might be missing).')
                 webpage = self._download_webpage(
-                    f'{url}/embed/', video_id, note='Downloading embed webpage', fatal=False)
+                    f'{url}/embed/', video_id, note='Downloading embed webpage', fatal=False) or ''
                 additional_data = self._search_json(
                     r'window\.__additionalDataLoaded\s*\(\s*[^,]+,', webpage, 'additional data', video_id, fatal=False)
                 if not additional_data and not media:

yt_dlp/extractor/iwara.py

@@ -2,7 +2,6 @@ import functools
 import hashlib
 import json
 import time
-import urllib.error
 import urllib.parse
 
 from .common import InfoExtractor

yt_dlp/extractor/nbc.py

@@ -16,6 +16,7 @@ from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    join_nonempty,
     mimetype2ext,
     parse_age_limit,
     parse_duration,
@@ -498,10 +499,8 @@ class NBCNewsIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                     m3u8_id=format_id, fatal=False))
                 continue
             tbr = int_or_none(va.get('bitrate'), 1000)
-            if tbr:
-                format_id += f'-{tbr}'
             formats.append({
-                'format_id': format_id,
+                'format_id': join_nonempty(format_id, tbr),
                 'url': public_url,
                 'width': int_or_none(va.get('width')),
                 'height': int_or_none(va.get('height')),

yt_dlp/extractor/nhl.py

@@ -2,6 +2,7 @@ from .common import InfoExtractor
 from ..utils import (
     determine_ext,
     int_or_none,
+    join_nonempty,
     parse_duration,
     parse_iso8601,
 )
@@ -41,7 +42,7 @@ class NHLBaseIE(InfoExtractor):
             else:
                 height = int_or_none(playback.get('height'))
                 formats.append({
-                    'format_id': playback.get('name', 'http' + (f'-{height}p' if height else '')),
+                    'format_id': playback.get('name') or join_nonempty('http', height and f'{height}p'),
                     'url': playback_url,
                     'width': int_or_none(playback.get('width')),
                     'height': height,

yt_dlp/extractor/peloton.py

@@ -41,7 +41,7 @@ class PelotonIE(InfoExtractor):
         }, 'params': {
             'skip_download': 'm3u8',
         },
-        '_skip': 'Account needed',
+        'skip': 'Account needed',
     }, {
         'url': 'https://members.onepeloton.com/classes/player/26603d53d6bb4de1b340514864a6a6a8',
         'info_dict': {
@@ -61,7 +61,7 @@ class PelotonIE(InfoExtractor):
         }, 'params': {
             'skip_download': 'm3u8',
         },
-        '_skip': 'Account needed',
+        'skip': 'Account needed',
     }]
 
     _MANIFEST_URL_TEMPLATE = '%s?hdnea=%s'
@@ -199,7 +199,7 @@ class PelotonLiveIE(InfoExtractor):
         'params': {
             'skip_download': 'm3u8',
         },
-        '_skip': 'Account needed',
+        'skip': 'Account needed',
     }
 
     def _real_extract(self, url):

yt_dlp/extractor/performgroup.py

@@ -1,5 +1,5 @@
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import int_or_none, join_nonempty
 
 
 class PerformGroupIE(InfoExtractor):
@@ -50,11 +50,8 @@ class PerformGroupIE(InfoExtractor):
             if not c_url:
                 continue
             tbr = int_or_none(c.get('bitrate'), 1000)
-            format_id = 'http'
-            if tbr:
-                format_id += f'-{tbr}'
             formats.append({
-                'format_id': format_id,
+                'format_id': join_nonempty('http', tbr),
                 'url': c_url,
                 'tbr': tbr,
                 'width': int_or_none(c.get('width')),

yt_dlp/extractor/pr0gramm.py

@@ -1,9 +1,9 @@
 import datetime as dt
+import functools
 import json
 import urllib.parse
 
 from .common import InfoExtractor
-from ..compat import functools
 from ..utils import (
     ExtractorError,
     float_or_none,

yt_dlp/extractor/prosiebensat1.py

@@ -7,6 +7,7 @@ from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    join_nonempty,
     merge_dicts,
     unified_strdate,
 )
@@ -147,13 +148,13 @@ class ProSiebenSat1BaseIE(InfoExtractor):
                                 'page_url': 'http://www.prosieben.de',
                                 'tbr': tbr,
                                 'ext': 'flv',
-                                'format_id': 'rtmp{}'.format(f'-{tbr}' if tbr else ''),
+                                'format_id': join_nonempty('rtmp', tbr),
                             })
                         else:
                             formats.append({
                                 'url': source_url,
                                 'tbr': tbr,
-                                'format_id': 'http{}'.format(f'-{tbr}' if tbr else ''),
+                                'format_id': join_nonempty('http', tbr),
                             })
 
         return {

yt_dlp/extractor/tubetugraz.py

@@ -21,7 +21,7 @@ class TubeTuGrazBaseIE(InfoExtractor):
         if not urlh:
             return
 
-        content, urlh = self._download_webpage_handle(
+        response = self._download_webpage_handle(
             urlh.url, None, fatal=False, headers={'referer': urlh.url},
             note='logging in', errnote='unable to log in',
             data=urlencode_postdata({
@@ -30,7 +30,11 @@ class TubeTuGrazBaseIE(InfoExtractor):
                 'j_username': username,
                 'j_password': password,
             }))
-        if not urlh or urlh.url == 'https://tube.tugraz.at/paella/ui/index.html':
+        if not response:
+            return
+
+        content, urlh = response
+        if urlh.url == 'https://tube.tugraz.at/paella/ui/index.html':
             return
 
         if not self._html_search_regex(
@@ -39,7 +43,7 @@ class TubeTuGrazBaseIE(InfoExtractor):
             self.report_warning('unable to login: incorrect password')
             return
 
-        content, urlh = self._download_webpage_handle(
+        urlh = self._request_webpage(
             urlh.url, None, fatal=False, headers={'referer': urlh.url},
             note='logging in with TFA', errnote='unable to log in with TFA',
             data=urlencode_postdata({

yt_dlp/extractor/twitter.py

@@ -14,6 +14,7 @@ from ..utils import (
     float_or_none,
     format_field,
     int_or_none,
+    join_nonempty,
     make_archive_id,
     remove_end,
     str_or_none,
@@ -107,7 +108,7 @@ class TwitterBaseIE(InfoExtractor):
             tbr = int_or_none(dict_get(variant, ('bitrate', 'bit_rate')), 1000) or None
             f = {
                 'url': variant_url,
-                'format_id': 'http' + (f'-{tbr}' if tbr else ''),
+                'format_id': join_nonempty('http', tbr),
                 'tbr': tbr,
             }
             self._search_dimensions_in_video_url(f, variant_url)

yt_dlp/extractor/viewlift.py

@@ -5,6 +5,7 @@ from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     int_or_none,
+    join_nonempty,
     parse_age_limit,
     traverse_obj,
 )
@@ -120,7 +121,7 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
                 'height', default=None))
             formats.append({
                 'url': video_asset_url,
-                'format_id': 'http{}'.format(f'-{bitrate}' if bitrate else ''),
+                'format_id': join_nonempty('http', bitrate),
                 'tbr': bitrate,
                 'height': height,
                 'vcodec': video_asset.get('codec'),

yt_dlp/extractor/weibo.py

@@ -52,6 +52,7 @@ class WeiboBaseIE(InfoExtractor):
             })
 
     def _weibo_download_json(self, url, video_id, *args, fatal=True, note='Downloading JSON metadata', **kwargs):
+        # XXX: Always fatal; _download_webpage_handle only returns False (not a tuple) on error
         webpage, urlh = self._download_webpage_handle(url, video_id, *args, fatal=fatal, note=note, **kwargs)
         if urllib.parse.urlparse(urlh.url).netloc == 'passport.weibo.com':
             self._update_visitor_cookies(urlh.url, video_id)

yt_dlp/extractor/wsj.py

@@ -2,6 +2,7 @@ from .common import InfoExtractor
 from ..utils import (
     float_or_none,
     int_or_none,
+    join_nonempty,
     unified_strdate,
 )
 
@@ -76,7 +77,7 @@ class WSJIE(InfoExtractor):
             tbr = int_or_none(v.get('bitrate'))
             formats.append({
                 'url': mp4_url,
-                'format_id': 'http' + (f'-{tbr}' if tbr else ''),
+                'format_id': join_nonempty('http', tbr),
                 'tbr': tbr,
                 'width': int_or_none(v.get('width')),
                 'height': int_or_none(v.get('height')),

yt_dlp/extractor/yahoo.py

@@ -8,6 +8,7 @@ from ..utils import (
     ExtractorError,
     clean_html,
     int_or_none,
+    join_nonempty,
     mimetype2ext,
     parse_iso8601,
     traverse_obj,
@@ -213,7 +214,7 @@ class YahooIE(InfoExtractor):
                 tbr = int_or_none(s.get('bitrate'))
                 formats.append({
                     'url': s_url,
-                    'format_id': fmt + (f'-{tbr}' if tbr else ''),
+                    'format_id': join_nonempty(fmt, tbr),
                     'width': int_or_none(s.get('width')),
                     'height': int_or_none(s.get('height')),
                     'tbr': tbr,
@@ -371,12 +372,13 @@ class YahooJapanNewsIE(InfoExtractor):
                         url, content_id, 'mp4', 'm3u8_native',
                         m3u8_id='hls', fatal=False))
             else:
+                bitrate = int_or_none(vid.get('bitrate'))
                 formats.append({
                     'url': url,
-                    'format_id': f'http-{vid.get("bitrate")}',
+                    'format_id': join_nonempty('http', bitrate),
                     'height': int_or_none(vid.get('height')),
                     'width': int_or_none(vid.get('width')),
-                    'tbr': int_or_none(vid.get('bitrate')),
+                    'tbr': bitrate,
                 })
         self._remove_duplicate_formats(formats)
 

yt_dlp/extractor/yandexdisk.py

@@ -5,6 +5,7 @@ from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    join_nonempty,
     mimetype2ext,
     try_get,
     urljoin,
@@ -116,12 +117,9 @@ class YandexDiskIE(InfoExtractor):
             else:
                 size = video.get('size') or {}
                 height = int_or_none(size.get('height'))
-                format_id = 'hls'
-                if height:
-                    format_id += f'-{height}p'
                 formats.append({
                     'ext': 'mp4',
-                    'format_id': format_id,
+                    'format_id': join_nonempty('hls', height and f'{height}p'),
                     'height': height,
                     'protocol': 'm3u8_native',
                     'url': format_url,

yt_dlp/extractor/youtube.py

@@ -4,6 +4,7 @@ import collections
 import copy
 import datetime as dt
 import enum
+import functools
 import hashlib
 import itertools
 import json
@@ -20,7 +21,6 @@ import urllib.parse
 
 from .common import InfoExtractor, SearchInfoExtractor
 from .openload import PhantomJSwrapper
-from ..compat import functools
 from ..jsinterp import JSInterpreter
 from ..networking.exceptions import HTTPError, network_exceptions
 from ..utils import (