pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-23 12:40:11 +09:00
Code Issues Projects Releases Wiki Activity

[nrk] improve format extraction and geo-restriction detection (closes #24221)

Browse Source
This commit is contained in:
Remita Amine 2020-12-04 18:04:38 +01:00
parent e91df0c550
commit 5e95e18ce9
1 changed files with 21 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
youtube_dl/extractor/nrk.py
View File

@ -24,6 +24,11 @@ from ..utils import (
class NRKBaseIE(InfoExtractor): class NRKBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['NO'] _GEO_COUNTRIES = ['NO']
def _extract_nrk_formats(self, asset_url, video_id):
return self._extract_m3u8_formats(
re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url),
video_id, 'mp4', 'm3u8_native', fatal=False)
class NRKIE(NRKBaseIE): class NRKIE(NRKBaseIE):
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
@ -94,9 +99,7 @@ class NRKIE(NRKBaseIE):
if not format_url: if not format_url:
continue continue
if asset.get('format') == 'HLS' or determine_ext(format_url) == 'm3u8': if asset.get('format') == 'HLS' or determine_ext(format_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_nrk_formats(format_url, video_id))
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
self._sort_formats(formats) self._sort_formats(formats)
data = self._download_json( data = self._download_json(
@ -298,6 +301,7 @@ class NRKTVIE(NRKBaseIE):
title = data.get('fullTitle') or data.get('mainTitle') or data['title'] title = data.get('fullTitle') or data.get('mainTitle') or data['title']
video_id = data.get('id') or video_id video_id = data.get('id') or video_id
urls = []
entries = [] entries = []
conviva = data.get('convivaStatistics') or {} conviva = data.get('convivaStatistics') or {}
@ -314,19 +318,13 @@ class NRKTVIE(NRKBaseIE):
else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx))) else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx)))
for num, asset in enumerate(media_assets, 1): for num, asset in enumerate(media_assets, 1):
asset_url = asset.get('url') asset_url = asset.get('url')
if not asset_url: if not asset_url or asset_url in urls:
continue continue
formats = self._extract_akamai_formats(asset_url, video_id) formats = extract_nrk_formats(asset_url, video_id)
if not formats: if not formats:
continue continue
self._sort_formats(formats) self._sort_formats(formats)
# Some f4m streams may not work with hdcore in fragments' URLs
for f in formats:
extra_param = f.get('extra_param_to_segment_url')
if extra_param and 'hdcore' in extra_param:
del f['extra_param_to_segment_url']
entry_id, entry_title = video_id_and_title(num) entry_id, entry_title = video_id_and_title(num)
duration = parse_duration(asset.get('duration')) duration = parse_duration(asset.get('duration'))
subtitles = {} subtitles = {}
@ -346,8 +344,9 @@ class NRKTVIE(NRKBaseIE):
if not entries: if not entries:
media_url = data.get('mediaUrl') media_url = data.get('mediaUrl')
if media_url: if media_url and media_url not in urls:
formats = self._extract_akamai_formats(media_url, video_id) formats = extract_nrk_formats(media_url, video_id)
if formats:
self._sort_formats(formats) self._sort_formats(formats)
duration = parse_duration(data.get('duration')) duration = parse_duration(data.get('duration'))
entries = [{ entries = [{
@ -366,7 +365,7 @@ class NRKTVIE(NRKBaseIE):
} }
message_type = data.get('messageType', '') message_type = data.get('messageType', '')
# Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked* # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
if 'IsGeoBlocked' in message_type: if 'IsGeoBlocked' in message_type or try_get(data, lambda x: x['usageRights']['isGeoBlocked']) is Trues:
self.raise_geo_restricted( self.raise_geo_restricted(
msg=MESSAGES.get('ProgramIsGeoBlocked'), msg=MESSAGES.get('ProgramIsGeoBlocked'),
countries=self._GEO_COUNTRIES) countries=self._GEO_COUNTRIES)