mirror of https://github.com/yt-dlp/yt-dlp
[ie/dplay] Fix extractors (#10471)
Closes #1623, Closes #2138, Closes #2361, Closes #3841, Closes #8026, Closes #10421 Authored by: bashonlypull/10486/head
bashonly
4 months ago
committed by
GitHub
parent
e62fa6b0e0
commit
39e6c4cb44
@ -1,115 +0,0 @@
|
||||
import random
|
||||
import string
|
||||
import urllib.parse
|
||||
|
||||
from .discoverygo import DiscoveryGoBaseIE
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import ExtractorError
|
||||
|
||||
|
||||
class DiscoveryIE(DiscoveryGoBaseIE):
|
||||
_VALID_URL = r'''(?x)https?://
|
||||
(?P<site>
|
||||
go\.discovery|
|
||||
www\.
|
||||
(?:
|
||||
investigationdiscovery|
|
||||
discoverylife|
|
||||
animalplanet|
|
||||
ahctv|
|
||||
destinationamerica|
|
||||
sciencechannel|
|
||||
tlc
|
||||
)|
|
||||
watch\.
|
||||
(?:
|
||||
hgtv|
|
||||
foodnetwork|
|
||||
travelchannel|
|
||||
diynetwork|
|
||||
cookingchanneltv|
|
||||
motortrend
|
||||
)
|
||||
)\.com/tv-shows/(?P<show_slug>[^/]+)/(?:video|full-episode)s/(?P<id>[^./?#]+)'''
|
||||
_TESTS = [{
|
||||
'url': 'https://go.discovery.com/tv-shows/cash-cab/videos/riding-with-matthew-perry',
|
||||
'info_dict': {
|
||||
'id': '5a2f35ce6b66d17a5026e29e',
|
||||
'ext': 'mp4',
|
||||
'title': 'Riding with Matthew Perry',
|
||||
'description': 'md5:a34333153e79bc4526019a5129e7f878',
|
||||
'duration': 84,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # requires ffmpeg
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.investigationdiscovery.com/tv-shows/final-vision/full-episodes/final-vision',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://go.discovery.com/tv-shows/alaskan-bush-people/videos/follow-your-own-road',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# using `show_slug` is important to get the correct video data
|
||||
'url': 'https://www.sciencechannel.com/tv-shows/mythbusters-on-science/full-episodes/christmas-special',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_GEO_COUNTRIES = ['US']
|
||||
_GEO_BYPASS = False
|
||||
_API_BASE_URL = 'https://api.discovery.com/v1/'
|
||||
|
||||
def _real_extract(self, url):
|
||||
site, show_slug, display_id = self._match_valid_url(url).groups()
|
||||
|
||||
access_token = None
|
||||
cookies = self._get_cookies(url)
|
||||
|
||||
# prefer Affiliate Auth Token over Anonymous Auth Token
|
||||
auth_storage_cookie = cookies.get('eosAf') or cookies.get('eosAn')
|
||||
if auth_storage_cookie and auth_storage_cookie.value:
|
||||
auth_storage = self._parse_json(urllib.parse.unquote(
|
||||
urllib.parse.unquote(auth_storage_cookie.value)),
|
||||
display_id, fatal=False) or {}
|
||||
access_token = auth_storage.get('a') or auth_storage.get('access_token')
|
||||
|
||||
if not access_token:
|
||||
access_token = self._download_json(
|
||||
f'https://{site}.com/anonymous', display_id,
|
||||
'Downloading token JSON metadata', query={
|
||||
'authRel': 'authorization',
|
||||
'client_id': '3020a40c2356a645b4b4',
|
||||
'nonce': ''.join(random.choices(string.ascii_letters, k=32)),
|
||||
'redirectUri': 'https://www.discovery.com/',
|
||||
})['access_token']
|
||||
|
||||
headers = self.geo_verification_headers()
|
||||
headers['Authorization'] = 'Bearer ' + access_token
|
||||
|
||||
try:
|
||||
video = self._download_json(
|
||||
self._API_BASE_URL + 'content/videos',
|
||||
display_id, 'Downloading content JSON metadata',
|
||||
headers=headers, query={
|
||||
'embed': 'show.name',
|
||||
'fields': 'authenticated,description.detailed,duration,episodeNumber,id,name,parental.rating,season.number,show,tags',
|
||||
'slug': display_id,
|
||||
'show_slug': show_slug,
|
||||
})[0]
|
||||
video_id = video['id']
|
||||
stream = self._download_json(
|
||||
self._API_BASE_URL + 'streaming/video/' + video_id,
|
||||
display_id, 'Downloading streaming JSON metadata', headers=headers)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403):
|
||||
e_description = self._parse_json(
|
||||
e.cause.response.read().decode(), display_id)['description']
|
||||
if 'resource not available for country' in e_description:
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
if 'Authorized Networks' in e_description:
|
||||
raise ExtractorError(
|
||||
'This video is only available via cable service provider subscription that'
|
||||
' is not currently supported. You may want to use --cookies.', expected=True)
|
||||
raise ExtractorError(e_description)
|
||||
raise
|
||||
|
||||
return self._extract_video_info(video, stream, display_id)
|
||||
@ -1,171 +0,0 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
determine_ext,
|
||||
extract_attributes,
|
||||
int_or_none,
|
||||
parse_age_limit,
|
||||
remove_end,
|
||||
unescapeHTML,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class DiscoveryGoBaseIE(InfoExtractor):
|
||||
_VALID_URL_TEMPLATE = r'''(?x)https?://(?:www\.)?(?:
|
||||
discovery|
|
||||
investigationdiscovery|
|
||||
discoverylife|
|
||||
animalplanet|
|
||||
ahctv|
|
||||
destinationamerica|
|
||||
sciencechannel|
|
||||
tlc|
|
||||
velocitychannel
|
||||
)go\.com/%s(?P<id>[^/?#&]+)'''
|
||||
|
||||
def _extract_video_info(self, video, stream, display_id):
|
||||
title = video['name']
|
||||
|
||||
if not stream:
|
||||
if video.get('authenticated') is True:
|
||||
raise ExtractorError(
|
||||
'This video is only available via cable service provider subscription that'
|
||||
' is not currently supported. You may want to use --cookies.', expected=True)
|
||||
else:
|
||||
raise ExtractorError('Unable to find stream')
|
||||
STREAM_URL_SUFFIX = 'streamUrl'
|
||||
formats = []
|
||||
for stream_kind in ('', 'hds'):
|
||||
suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX
|
||||
stream_url = stream.get(f'{stream_kind}{suffix}')
|
||||
if not stream_url:
|
||||
continue
|
||||
if stream_kind == '':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
stream_url, display_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
elif stream_kind == 'hds':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
stream_url, display_id, f4m_id=stream_kind, fatal=False))
|
||||
|
||||
video_id = video.get('id') or display_id
|
||||
description = video.get('description', {}).get('detailed')
|
||||
duration = int_or_none(video.get('duration'))
|
||||
|
||||
series = video.get('show', {}).get('name')
|
||||
season_number = int_or_none(video.get('season', {}).get('number'))
|
||||
episode_number = int_or_none(video.get('episodeNumber'))
|
||||
|
||||
tags = video.get('tags')
|
||||
age_limit = parse_age_limit(video.get('parental', {}).get('rating'))
|
||||
|
||||
subtitles = {}
|
||||
captions = stream.get('captions')
|
||||
if isinstance(captions, list):
|
||||
for caption in captions:
|
||||
subtitle_url = url_or_none(caption.get('fileUrl'))
|
||||
if not subtitle_url or not subtitle_url.startswith('http'):
|
||||
continue
|
||||
lang = caption.get('fileLang', 'en')
|
||||
ext = determine_ext(subtitle_url)
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'url': subtitle_url,
|
||||
'ext': 'ttml' if ext == 'xml' else ext,
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'series': series,
|
||||
'season_number': season_number,
|
||||
'episode_number': episode_number,
|
||||
'tags': tags,
|
||||
'age_limit': age_limit,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
|
||||
class DiscoveryGoIE(DiscoveryGoBaseIE):
|
||||
_VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+'
|
||||
_GEO_COUNTRIES = ['US']
|
||||
_TEST = {
|
||||
'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/',
|
||||
'info_dict': {
|
||||
'id': '58c167d86b66d12f2addeb01',
|
||||
'ext': 'mp4',
|
||||
'title': 'Reaper Madness',
|
||||
'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78',
|
||||
'duration': 2519,
|
||||
'series': 'Bering Sea Gold',
|
||||
'season_number': 8,
|
||||
'episode_number': 6,
|
||||
'age_limit': 14,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
container = extract_attributes(
|
||||
self._search_regex(
|
||||
r'(<div[^>]+class=["\']video-player-container[^>]+>)',
|
||||
webpage, 'video container'))
|
||||
|
||||
video = self._parse_json(
|
||||
container.get('data-video') or container.get('data-json'),
|
||||
display_id)
|
||||
|
||||
stream = video.get('stream')
|
||||
|
||||
return self._extract_video_info(video, stream, display_id)
|
||||
|
||||
|
||||
class DiscoveryGoPlaylistIE(DiscoveryGoBaseIE):
|
||||
_VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % ''
|
||||
_TEST = {
|
||||
'url': 'https://www.discoverygo.com/bering-sea-gold/',
|
||||
'info_dict': {
|
||||
'id': 'bering-sea-gold',
|
||||
'title': 'Bering Sea Gold',
|
||||
'description': 'md5:cc5c6489835949043c0cc3ad66c2fa0e',
|
||||
},
|
||||
'playlist_mincount': 6,
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if DiscoveryGoIE.suitable(url) else super().suitable(url)
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
entries = []
|
||||
for mobj in re.finditer(r'data-json=(["\'])(?P<json>{.+?})\1', webpage):
|
||||
data = self._parse_json(
|
||||
mobj.group('json'), display_id,
|
||||
transform_source=unescapeHTML, fatal=False)
|
||||
if not isinstance(data, dict) or data.get('type') != 'episode':
|
||||
continue
|
||||
episode_url = data.get('socialUrl')
|
||||
if not episode_url:
|
||||
continue
|
||||
entries.append(self.url_result(
|
||||
episode_url, ie=DiscoveryGoIE.ie_key(),
|
||||
video_id=data.get('id')))
|
||||
|
||||
return self.playlist_result(
|
||||
entries, display_id,
|
||||
remove_end(self._og_search_title(
|
||||
webpage, fatal=False), ' | Discovery GO'),
|
||||
self._og_search_description(webpage))
|
||||
Loading…
Reference in New Issue