Skip to content

A feature-rich command-line audio/video downloader

[ie/once] Remove extractor (#13164)

bashonlyf475e8b529d1
diff --git a/yt_dlp/extractor/espn.py b/yt_dlp/extractor/espn.py
index 552f9af12e..37e74bc08e 100644
--- a/yt_dlp/extractor/espn.py
+++ b/yt_dlp/extractor/espn.py
@@ -5,7 +5,6 @@ import urllib.parse
from .adobepass import AdobePassIE
from .common import InfoExtractor
-from .once import OnceIE
from ..utils import (
determine_ext,
dict_get,
@@ -16,7 +15,7 @@ from ..utils import (
)
-class ESPNIE(OnceIE):
+class ESPNIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
@@ -131,9 +130,7 @@ class ESPNIE(OnceIE):
return
format_urls.add(source_url)
ext = determine_ext(source_url)
- if OnceIE.suitable(source_url):
- formats.extend(self._extract_once_formats(source_url))
- elif ext == 'smil':
+ if ext == 'smil':
formats.extend(self._extract_smil_formats(
source_url, video_id, fatal=False))
elif ext == 'f4m':
diff --git a/yt_dlp/extractor/gamespot.py b/yt_dlp/extractor/gamespot.py
index cd3f9655d8..2799a27bac 100644
--- a/yt_dlp/extractor/gamespot.py
+++ b/yt_dlp/extractor/gamespot.py
@@ -1,9 +1,9 @@
import urllib.parse
-from .once import OnceIE
+from .common import InfoExtractor
-class GameSpotIE(OnceIE):
+class GameSpotIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
diff --git a/yt_dlp/extractor/once.py b/yt_dlp/extractor/once.py
deleted file mode 100644
index 989f10abb1..0000000000
--- a/yt_dlp/extractor/once.py
+++ /dev/null
@@ -1,40 +0,0 @@
-import re
-
-from .common import InfoExtractor
-
-
-class OnceIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
- _VALID_URL = r'https?://.+?\.unicornmedia\.com/now/(?:ads/vmap/)?[^/]+/[^/]+/(?P<domain_id>[^/]+)/(?P<application_id>[^/]+)/(?:[^/]+/)?(?P<media_item_id>[^/]+)/content\.(?:once|m3u8|mp4)'
- ADAPTIVE_URL_TEMPLATE = 'http://once.unicornmedia.com/now/master/playlist/%s/%s/%s/content.m3u8'
- PROGRESSIVE_URL_TEMPLATE = 'http://once.unicornmedia.com/now/media/progressive/%s/%s/%s/%s/content.mp4'
-
- def _extract_once_formats(self, url, http_formats_preference=None):
- domain_id, application_id, media_item_id = re.match(
- OnceIE._VALID_URL, url).groups()
- formats = self._extract_m3u8_formats(
- self.ADAPTIVE_URL_TEMPLATE % (
- domain_id, application_id, media_item_id),
- media_item_id, 'mp4', m3u8_id='hls', fatal=False)
- progressive_formats = []
- for adaptive_format in formats:
- # Prevent advertisement from embedding into m3u8 playlist (see
- # https://github.com/ytdl-org/youtube-dl/issues/8893#issuecomment-199912684)
- adaptive_format['url'] = re.sub(
- r'\badsegmentlength=\d+', r'adsegmentlength=0', adaptive_format['url'])
- rendition_id = self._search_regex(
- r'/now/media/playlist/[^/]+/[^/]+/([^/]+)',
- adaptive_format['url'], 'redition id', default=None)
- if rendition_id:
- progressive_format = adaptive_format.copy()
- progressive_format.update({
- 'url': self.PROGRESSIVE_URL_TEMPLATE % (
- domain_id, application_id, rendition_id, media_item_id),
- 'format_id': adaptive_format['format_id'].replace(
- 'hls', 'http'),
- 'protocol': 'http',
- 'preference': http_formats_preference,
- })
- progressive_formats.append(progressive_format)
- self._check_formats(progressive_formats, media_item_id)
- formats.extend(progressive_formats)
- return formats
diff --git a/yt_dlp/extractor/theplatform.py b/yt_dlp/extractor/theplatform.py
index b73bea18fd..ebe2ac2962 100644
--- a/yt_dlp/extractor/theplatform.py
+++ b/yt_dlp/extractor/theplatform.py
@@ -4,7 +4,6 @@ import re
import time
from .adobepass import AdobePassIE
-from .once import OnceIE
from ..networking import HEADRequest, Request
from ..utils import (
ExtractorError,
@@ -26,7 +25,7 @@ default_ns = 'http://www.w3.org/2005/SMIL21/Language'
_x = lambda p: xpath_with_ns(p, {'smil': default_ns})
-class ThePlatformBaseIE(OnceIE):
+class ThePlatformBaseIE(AdobePassIE):
_TP_TLD = 'com'
def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'):
@@ -54,16 +53,13 @@ class ThePlatformBaseIE(OnceIE):
formats = []
for _format in smil_formats:
- if OnceIE.suitable(_format['url']):
- formats.extend(self._extract_once_formats(_format['url']))
- else:
- media_url = _format['url']
- if determine_ext(media_url) == 'm3u8':
- hdnea2 = self._get_cookies(media_url).get('hdnea2')
- if hdnea2:
- _format['url'] = update_url_query(media_url, {'hdnea3': hdnea2.value})
+ media_url = _format['url']
+ if determine_ext(media_url) == 'm3u8':
+ hdnea2 = self._get_cookies(media_url).get('hdnea2')
+ if hdnea2:
+ _format['url'] = update_url_query(media_url, {'hdnea3': hdnea2.value})
- formats.append(_format)
+ formats.append(_format)
return formats, subtitles
@@ -129,7 +125,7 @@ class ThePlatformBaseIE(OnceIE):
return self._parse_theplatform_metadata(info)
-class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
+class ThePlatformIE(ThePlatformBaseIE):
_VALID_URL = r'''(?x)
(?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
(?:(?:(?:[^/]+/)+select/)?(?P<media>media/(?:guid/\d+/)?)?|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
diff --git a/yt_dlp/extractor/voxmedia.py b/yt_dlp/extractor/voxmedia.py
index e9b0047a47..995ef21859 100644
--- a/yt_dlp/extractor/voxmedia.py
+++ b/yt_dlp/extractor/voxmedia.py
@@ -1,7 +1,6 @@
import urllib.parse
from .common import InfoExtractor
-from .once import OnceIE
from ..utils import (
ExtractorError,
int_or_none,
@@ -10,7 +9,7 @@ from ..utils import (
)
-class VoxMediaVolumeIE(OnceIE):
+class VoxMediaVolumeIE(InfoExtractor):
_VALID_URL = r'https?://volume\.vox-cdn\.com/embed/(?P<id>[0-9a-f]{9})'
def _real_extract(self, url):
@@ -57,7 +56,8 @@ class VoxMediaVolumeIE(OnceIE):
if not provider_video_id:
continue
if provider_video_type == 'brightcove':
- info['formats'] = self._extract_once_formats(provider_video_id)
+ # TODO: Find embed example or confirm that Vox has stopped using Brightcove
+ raise ExtractorError('Vox Brightcove embeds are currently unsupported')
else:
info.update({
'_type': 'url_transparent',
@@ -155,20 +155,6 @@ class VoxMediaIE(InfoExtractor):
},
}],
'skip': 'Page no longer contain videos',
- }, {
- # volume embed, Brightcove Once
- 'url': 'https://www.recode.net/2014/6/17/11628066/post-post-pc-ceo-the-full-code-conference-video-of-microsofts-satya',
- 'md5': '2dbc77b8b0bff1894c2fce16eded637d',
- 'info_dict': {
- 'id': '1231c973d',
- 'ext': 'mp4',
- 'title': 'Post-Post-PC CEO: The Full Code Conference Video of Microsoft\'s Satya Nadella',
- 'description': 'The longtime veteran was chosen earlier this year as the software giant\'s third leader in its history.',
- 'timestamp': 1402938000,
- 'upload_date': '20140616',
- 'duration': 4114,
- },
- 'add_ie': ['VoxMediaVolume'],
}]
def _real_extract(self, url):