mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-06-27 17:08:32 +00:00
[ie/eagleplatform] Remove Extractors
This commit is contained in:
doe1080
parent
1722c55400
commit
8da4cd16fd
@ -570,10 +570,6 @@
|
|||||||
DWIE,
|
DWIE,
|
||||||
DWArticleIE,
|
DWArticleIE,
|
||||||
)
|
)
|
||||||
from .eagleplatform import (
|
|
||||||
ClipYouEmbedIE,
|
|
||||||
EaglePlatformIE,
|
|
||||||
)
|
|
||||||
from .ebaumsworld import EbaumsWorldIE
|
from .ebaumsworld import EbaumsWorldIE
|
||||||
from .ebay import EbayIE
|
from .ebay import EbayIE
|
||||||
from .egghead import (
|
from .egghead import (
|
||||||
|
|||||||
@ -1,215 +0,0 @@
|
|||||||
import functools
|
|
||||||
import re
|
|
||||||
|
|
||||||
from .common import InfoExtractor
|
|
||||||
from ..networking.exceptions import HTTPError
|
|
||||||
from ..utils import (
|
|
||||||
ExtractorError,
|
|
||||||
int_or_none,
|
|
||||||
smuggle_url,
|
|
||||||
unsmuggle_url,
|
|
||||||
url_or_none,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class EaglePlatformIE(InfoExtractor):
|
|
||||||
_VALID_URL = r'''(?x)
|
|
||||||
(?:
|
|
||||||
eagleplatform:(?P<custom_host>[^/]+):|
|
|
||||||
https?://(?P<host>.+?\.media\.eagleplatform\.com)/index/player\?.*\brecord_id=
|
|
||||||
)
|
|
||||||
(?P<id>\d+)
|
|
||||||
'''
|
|
||||||
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1']
|
|
||||||
_TESTS = [{
|
|
||||||
# http://lenta.ru/news/2015/03/06/navalny/
|
|
||||||
'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
|
|
||||||
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
|
|
||||||
'info_dict': {
|
|
||||||
'id': '227304',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'Навальный вышел на свободу',
|
|
||||||
'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
|
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
|
||||||
'duration': 87,
|
|
||||||
'view_count': int,
|
|
||||||
'age_limit': 0,
|
|
||||||
},
|
|
||||||
}, {
|
|
||||||
# http://muz-tv.ru/play/7129/
|
|
||||||
# http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
|
|
||||||
'url': 'eagleplatform:media.clipyou.ru:12820',
|
|
||||||
'md5': '358597369cf8ba56675c1df15e7af624',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '12820',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': "'O Sole Mio",
|
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
|
||||||
'duration': 216,
|
|
||||||
'view_count': int,
|
|
||||||
},
|
|
||||||
'skip': 'Georestricted',
|
|
||||||
}, {
|
|
||||||
# referrer protected video (https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/)
|
|
||||||
'url': 'eagleplatform:tvrainru.media.eagleplatform.com:582306',
|
|
||||||
'only_matching': True,
|
|
||||||
}]
|
|
||||||
|
|
||||||
@classmethod
|
|
||||||
def _extract_embed_urls(cls, url, webpage):
|
|
||||||
add_referer = functools.partial(smuggle_url, data={'referrer': url})
|
|
||||||
|
|
||||||
res = tuple(super()._extract_embed_urls(url, webpage))
|
|
||||||
if res:
|
|
||||||
return map(add_referer, res)
|
|
||||||
|
|
||||||
PLAYER_JS_RE = r'''
|
|
||||||
<script[^>]+
|
|
||||||
src=(?P<qjs>["\'])(?:https?:)?//(?P<host>(?:(?!(?P=qjs)).)+\.media\.eagleplatform\.com)/player/player\.js(?P=qjs)
|
|
||||||
.+?
|
|
||||||
'''
|
|
||||||
# "Basic usage" embedding (see http://dultonmedia.github.io/eplayer/)
|
|
||||||
mobj = re.search(
|
|
||||||
rf'''(?xs)
|
|
||||||
{PLAYER_JS_RE}
|
|
||||||
<div[^>]+
|
|
||||||
class=(?P<qclass>["\'])eagleplayer(?P=qclass)[^>]+
|
|
||||||
data-id=["\'](?P<id>\d+)
|
|
||||||
''', webpage)
|
|
||||||
if mobj is not None:
|
|
||||||
return [add_referer('eagleplatform:{host}:{id}'.format(**mobj.groupdict()))]
|
|
||||||
# Generalization of "Javascript code usage", "Combined usage" and
|
|
||||||
# "Usage without attaching to DOM" embeddings (see
|
|
||||||
# http://dultonmedia.github.io/eplayer/)
|
|
||||||
mobj = re.search(
|
|
||||||
r'''(?xs)
|
|
||||||
%s
|
|
||||||
<script>
|
|
||||||
.+?
|
|
||||||
new\s+EaglePlayer\(
|
|
||||||
(?:[^,]+\s*,\s*)?
|
|
||||||
{
|
|
||||||
.+?
|
|
||||||
\bid\s*:\s*["\']?(?P<id>\d+)
|
|
||||||
.+?
|
|
||||||
}
|
|
||||||
\s*\)
|
|
||||||
.+?
|
|
||||||
</script>
|
|
||||||
''' % PLAYER_JS_RE, webpage) # noqa: UP031
|
|
||||||
if mobj is not None:
|
|
||||||
return [add_referer('eagleplatform:{host}:{id}'.format(**mobj.groupdict()))]
|
|
||||||
|
|
||||||
@staticmethod
|
|
||||||
def _handle_error(response):
|
|
||||||
status = int_or_none(response.get('status', 200))
|
|
||||||
if status != 200:
|
|
||||||
raise ExtractorError(' '.join(response['errors']), expected=True)
|
|
||||||
|
|
||||||
def _download_json(self, url_or_request, video_id, *args, **kwargs):
|
|
||||||
try:
|
|
||||||
response = super()._download_json(
|
|
||||||
url_or_request, video_id, *args, **kwargs)
|
|
||||||
except ExtractorError as ee:
|
|
||||||
if isinstance(ee.cause, HTTPError):
|
|
||||||
response = self._parse_json(ee.cause.response.read().decode('utf-8'), video_id)
|
|
||||||
self._handle_error(response)
|
|
||||||
raise
|
|
||||||
return response
|
|
||||||
|
|
||||||
def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'):
|
|
||||||
return self._download_json(url_or_request, video_id, note)['data'][0]
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
|
||||||
url, smuggled_data = unsmuggle_url(url, {})
|
|
||||||
|
|
||||||
mobj = self._match_valid_url(url)
|
|
||||||
host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
|
|
||||||
|
|
||||||
headers = {}
|
|
||||||
query = {
|
|
||||||
'id': video_id,
|
|
||||||
}
|
|
||||||
|
|
||||||
referrer = smuggled_data.get('referrer')
|
|
||||||
if referrer:
|
|
||||||
headers['Referer'] = referrer
|
|
||||||
query['referrer'] = referrer
|
|
||||||
|
|
||||||
player_data = self._download_json(
|
|
||||||
f'http://{host}/api/player_data', video_id,
|
|
||||||
headers=headers, query=query)
|
|
||||||
|
|
||||||
media = player_data['data']['playlist']['viewports'][0]['medialist'][0]
|
|
||||||
|
|
||||||
title = media['title']
|
|
||||||
description = media.get('description')
|
|
||||||
thumbnail = self._proto_relative_url(media.get('snapshot'), 'http:')
|
|
||||||
duration = int_or_none(media.get('duration'))
|
|
||||||
view_count = int_or_none(media.get('views'))
|
|
||||||
|
|
||||||
age_restriction = media.get('age_restriction')
|
|
||||||
age_limit = None
|
|
||||||
if age_restriction:
|
|
||||||
age_limit = 0 if age_restriction == 'allow_all' else 18
|
|
||||||
|
|
||||||
secure_m3u8 = self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:')
|
|
||||||
|
|
||||||
formats = []
|
|
||||||
|
|
||||||
m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
|
|
||||||
m3u8_formats = self._extract_m3u8_formats(
|
|
||||||
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
|
||||||
m3u8_id='hls', fatal=False)
|
|
||||||
formats.extend(m3u8_formats)
|
|
||||||
|
|
||||||
m3u8_formats_dict = {}
|
|
||||||
for f in m3u8_formats:
|
|
||||||
if f.get('height') is not None:
|
|
||||||
m3u8_formats_dict[f['height']] = f
|
|
||||||
|
|
||||||
mp4_data = self._download_json(
|
|
||||||
# Secure mp4 URL is constructed according to Player.prototype.mp4 from
|
|
||||||
# http://lentaru.media.eagleplatform.com/player/player.js
|
|
||||||
re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4s', secure_m3u8),
|
|
||||||
video_id, 'Downloading mp4 JSON', fatal=False)
|
|
||||||
if mp4_data:
|
|
||||||
for format_id, format_url in mp4_data.get('data', {}).items():
|
|
||||||
if not url_or_none(format_url):
|
|
||||||
continue
|
|
||||||
height = int_or_none(format_id)
|
|
||||||
if height is not None and m3u8_formats_dict.get(height):
|
|
||||||
f = m3u8_formats_dict[height].copy()
|
|
||||||
f.update({
|
|
||||||
'format_id': f['format_id'].replace('hls', 'http'),
|
|
||||||
'protocol': 'http',
|
|
||||||
})
|
|
||||||
else:
|
|
||||||
f = {
|
|
||||||
'format_id': f'http-{format_id}',
|
|
||||||
'height': int_or_none(format_id),
|
|
||||||
}
|
|
||||||
f['url'] = format_url
|
|
||||||
formats.append(f)
|
|
||||||
|
|
||||||
return {
|
|
||||||
'id': video_id,
|
|
||||||
'title': title,
|
|
||||||
'description': description,
|
|
||||||
'thumbnail': thumbnail,
|
|
||||||
'duration': duration,
|
|
||||||
'view_count': view_count,
|
|
||||||
'age_limit': age_limit,
|
|
||||||
'formats': formats,
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
class ClipYouEmbedIE(InfoExtractor):
|
|
||||||
_VALID_URL = False
|
|
||||||
|
|
||||||
@classmethod
|
|
||||||
def _extract_embed_urls(cls, url, webpage):
|
|
||||||
mobj = re.search(
|
|
||||||
r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
|
|
||||||
if mobj is not None:
|
|
||||||
yield smuggle_url('eagleplatform:{host}:{id}'.format(**mobj.groupdict()), {'referrer': url})
|
|
||||||
@ -1010,38 +1010,6 @@ class GenericIE(InfoExtractor):
|
|||||||
},
|
},
|
||||||
'add_ie': ['Kaltura'],
|
'add_ie': ['Kaltura'],
|
||||||
},
|
},
|
||||||
# referrer protected EaglePlatform embed
|
|
||||||
{
|
|
||||||
'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '582306',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
|
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
|
||||||
'duration': 3382,
|
|
||||||
'view_count': int,
|
|
||||||
},
|
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
|
||||||
},
|
|
||||||
# ClipYou (EaglePlatform) embed (custom URL)
|
|
||||||
{
|
|
||||||
'url': 'http://muz-tv.ru/play/7129/',
|
|
||||||
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
|
|
||||||
'info_dict': {
|
|
||||||
'id': '12820',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': "'O Sole Mio",
|
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
|
||||||
'duration': 216,
|
|
||||||
'view_count': int,
|
|
||||||
},
|
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
|
||||||
'skip': 'This video is unavailable.',
|
|
||||||
},
|
|
||||||
# Pladform embed
|
# Pladform embed
|
||||||
{
|
{
|
||||||
'url': 'http://muz-tv.ru/kinozal/view/7400/',
|
'url': 'http://muz-tv.ru/kinozal/view/7400/',
|
||||||
|
|||||||
@ -3,6 +3,7 @@
|
|||||||
|
|
||||||
|
|
||||||
class LiveJournalIE(InfoExtractor):
|
class LiveJournalIE(InfoExtractor):
|
||||||
|
_WORKING = False
|
||||||
_VALID_URL = r'https?://(?:[^.]+\.)?livejournal\.com/video/album/\d+.+?\bid=(?P<id>\d+)'
|
_VALID_URL = r'https?://(?:[^.]+\.)?livejournal\.com/video/album/\d+.+?\bid=(?P<id>\d+)'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'https://andrei-bt.livejournal.com/video/album/407/?mode=view&id=51272',
|
'url': 'https://andrei-bt.livejournal.com/video/album/407/?mode=view&id=51272',
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user