aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/drtv.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/drtv.py')
-rw-r--r--youtube_dl/extractor/drtv.py228
1 files changed, 186 insertions, 42 deletions
diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py
index e4917014a..c0036adb6 100644
--- a/youtube_dl/extractor/drtv.py
+++ b/youtube_dl/extractor/drtv.py
@@ -1,20 +1,38 @@
# coding: utf-8
from __future__ import unicode_literals
+import binascii
+import hashlib
+import re
+
+
from .common import InfoExtractor
+from ..aes import aes_cbc_decrypt
+from ..compat import compat_urllib_parse_unquote
from ..utils import (
+ bytes_to_intlist,
ExtractorError,
int_or_none,
+ intlist_to_bytes,
float_or_none,
mimetype2ext,
- parse_iso8601,
- remove_end,
+ str_or_none,
+ try_get,
+ unified_timestamp,
update_url_query,
+ url_or_none,
)
class DRTVIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio/ondemand)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ (?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*|
+ (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode|program)/
+ )
+ (?P<id>[\da-z_-]+)
+ '''
_GEO_BYPASS = False
_GEO_COUNTRIES = ['DK']
IE_NAME = 'drtv'
@@ -26,25 +44,76 @@ class DRTVIE(InfoExtractor):
'ext': 'mp4',
'title': 'Klassen - Dårlig taber (10)',
'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
- 'timestamp': 1471991907,
- 'upload_date': '20160823',
+ 'timestamp': 1539085800,
+ 'upload_date': '20181009',
'duration': 606.84,
+ 'series': 'Klassen',
+ 'season': 'Klassen I',
+ 'season_number': 1,
+ 'season_id': 'urn:dr:mu:bundle:57d7e8216187a4031cfd6f6b',
+ 'episode': 'Episode 10',
+ 'episode_number': 10,
+ 'release_year': 2016,
},
- 'params': {
- 'skip_download': True,
- },
+ 'expected_warnings': ['Unable to download f4m manifest'],
}, {
+ # embed
'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
- 'md5': '2c37175c718155930f939ef59952474a',
'info_dict': {
- 'id': 'christiania-pusher-street-ryddes-drdkrjpo',
+ 'id': 'urn:dr:mu:programcard:57c926176187a50a9c6e83c6',
'ext': 'mp4',
- 'title': 'LIVE Christianias rydning af Pusher Street er i gang',
- 'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
+ 'title': 'christiania pusher street ryddes drdkrjpo',
+ 'description': 'md5:2a71898b15057e9b97334f61d04e6eb5',
'timestamp': 1472800279,
'upload_date': '20160902',
'duration': 131.4,
},
+ 'params': {
+ 'skip_download': True,
+ },
+ 'expected_warnings': ['Unable to download f4m manifest'],
+ }, {
+ # with SignLanguage formats
+ 'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder',
+ 'info_dict': {
+ 'id': 'historien-om-danmark-stenalder',
+ 'ext': 'mp4',
+ 'title': 'Historien om Danmark: Stenalder',
+ 'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a',
+ 'timestamp': 1546628400,
+ 'upload_date': '20190104',
+ 'duration': 3502.56,
+ 'formats': 'mincount:20',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'https://www.dr.dk/radio/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.dr.dk/drtv/se/bonderoeven_71769',
+ 'info_dict': {
+ 'id': '00951930010',
+ 'ext': 'mp4',
+ 'title': 'Bonderøven (1:8)',
+ 'description': 'md5:3cf18fc0d3b205745d4505f896af8121',
+ 'timestamp': 1546542000,
+ 'upload_date': '20190103',
+ 'duration': 2576.6,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'https://www.dr.dk/drtv/episode/bonderoeven_71769',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://dr-massive.com/drtv/se/bonderoeven_71769',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.dr.dk/drtv/program/jagten_220924',
+ 'only_matching': True,
}]
def _real_extract(self, url):
@@ -58,20 +127,45 @@ class DRTVIE(InfoExtractor):
video_id = self._search_regex(
(r'data-(?:material-identifier|episode-slug)="([^"]+)"',
- r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
- webpage, 'video id')
+ r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
+ webpage, 'video id', default=None)
+
+ if not video_id:
+ video_id = self._search_regex(
+ r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)',
+ webpage, 'urn', default=None)
+ if video_id:
+ video_id = compat_urllib_parse_unquote(video_id)
+
+ _PROGRAMCARD_BASE = 'https://www.dr.dk/mu-online/api/1.4/programcard'
+ query = {'expanded': 'true'}
- programcard = self._download_json(
- 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
- video_id, 'Downloading video JSON')
- data = programcard['Data'][0]
+ if video_id:
+ programcard_url = '%s/%s' % (_PROGRAMCARD_BASE, video_id)
+ else:
+ programcard_url = _PROGRAMCARD_BASE
+ page = self._parse_json(
+ self._search_regex(
+ r'data\s*=\s*({.+?})\s*(?:;|</script)', webpage,
+ 'data'), '1')['cache']['page']
+ page = page[list(page.keys())[0]]
+ item = try_get(
+ page, (lambda x: x['item'], lambda x: x['entries'][0]['item']),
+ dict)
+ video_id = item['customId'].split(':')[-1]
+ query['productionnumber'] = video_id
- title = remove_end(self._og_search_title(
- webpage, default=None), ' | TV | DR') or data['Title']
+ data = self._download_json(
+ programcard_url, video_id, 'Downloading video JSON', query=query)
+
+ title = str_or_none(data.get('Title')) or re.sub(
+ r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '',
+ self._og_search_title(webpage))
description = self._og_search_description(
webpage, default=None) or data.get('Description')
- timestamp = parse_iso8601(data.get('CreatedTime'))
+ timestamp = unified_timestamp(
+ data.get('PrimaryBroadcastStartTime') or data.get('SortDateTime'))
thumbnail = None
duration = None
@@ -81,28 +175,66 @@ class DRTVIE(InfoExtractor):
formats = []
subtitles = {}
- for asset in data['Assets']:
+ assets = []
+ primary_asset = data.get('PrimaryAsset')
+ if isinstance(primary_asset, dict):
+ assets.append(primary_asset)
+ secondary_assets = data.get('SecondaryAssets')
+ if isinstance(secondary_assets, list):
+ for secondary_asset in secondary_assets:
+ if isinstance(secondary_asset, dict):
+ assets.append(secondary_asset)
+
+ def hex_to_bytes(hex):
+ return binascii.a2b_hex(hex.encode('ascii'))
+
+ def decrypt_uri(e):
+ n = int(e[2:10], 16)
+ a = e[10 + n:]
+ data = bytes_to_intlist(hex_to_bytes(e[10:10 + n]))
+ key = bytes_to_intlist(hashlib.sha256(
+ ('%s:sRBzYNXBzkKgnjj8pGtkACch' % a).encode('utf-8')).digest())
+ iv = bytes_to_intlist(hex_to_bytes(a))
+ decrypted = aes_cbc_decrypt(data, key, iv)
+ return intlist_to_bytes(
+ decrypted[:-decrypted[-1]]).decode('utf-8').split('?')[0]
+
+ for asset in assets:
kind = asset.get('Kind')
if kind == 'Image':
- thumbnail = asset.get('Uri')
+ thumbnail = url_or_none(asset.get('Uri'))
elif kind in ('VideoResource', 'AudioResource'):
duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
restricted_to_denmark = asset.get('RestrictedToDenmark')
- spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
+ asset_target = asset.get('Target')
for link in asset.get('Links', []):
uri = link.get('Uri')
if not uri:
+ encrypted_uri = link.get('EncryptedUri')
+ if not encrypted_uri:
+ continue
+ try:
+ uri = decrypt_uri(encrypted_uri)
+ except Exception:
+ self.report_warning(
+ 'Unable to decrypt EncryptedUri', video_id)
+ continue
+ uri = url_or_none(uri)
+ if not uri:
continue
target = link.get('Target')
format_id = target or ''
- preference = None
- if spoken_subtitles:
+ if asset_target in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'):
preference = -1
- format_id += '-spoken-subtitles'
+ format_id += '-%s' % asset_target
+ elif asset_target == 'Default':
+ preference = 1
+ else:
+ preference = None
if target == 'HDS':
f4m_formats = self._extract_f4m_formats(
uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
- video_id, preference, f4m_id=format_id)
+ video_id, preference, f4m_id=format_id, fatal=False)
if kind == 'AudioResource':
for f in f4m_formats:
f['vcodec'] = 'none'
@@ -110,7 +242,8 @@ class DRTVIE(InfoExtractor):
elif target == 'HLS':
formats.extend(self._extract_m3u8_formats(
uri, video_id, 'mp4', entry_protocol='m3u8_native',
- preference=preference, m3u8_id=format_id))
+ preference=preference, m3u8_id=format_id,
+ fatal=False))
else:
bitrate = link.get('Bitrate')
if bitrate:
@@ -121,20 +254,24 @@ class DRTVIE(InfoExtractor):
'tbr': int_or_none(bitrate),
'ext': link.get('FileFormat'),
'vcodec': 'none' if kind == 'AudioResource' else None,
+ 'preference': preference,
})
- subtitles_list = asset.get('SubtitlesList')
- if isinstance(subtitles_list, list):
- LANGS = {
- 'Danish': 'da',
- }
- for subs in subtitles_list:
- if not subs.get('Uri'):
- continue
- lang = subs.get('Language') or 'da'
- subtitles.setdefault(LANGS.get(lang, lang), []).append({
- 'url': subs['Uri'],
- 'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
- })
+ subtitles_list = asset.get('SubtitlesList') or asset.get('Subtitleslist')
+ if isinstance(subtitles_list, list):
+ LANGS = {
+ 'Danish': 'da',
+ }
+ for subs in subtitles_list:
+ if not isinstance(subs, dict):
+ continue
+ sub_uri = url_or_none(subs.get('Uri'))
+ if not sub_uri:
+ continue
+ lang = subs.get('Language') or 'da'
+ subtitles.setdefault(LANGS.get(lang, lang), []).append({
+ 'url': sub_uri,
+ 'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
+ })
if not formats and restricted_to_denmark:
self.raise_geo_restricted(
@@ -152,6 +289,13 @@ class DRTVIE(InfoExtractor):
'duration': duration,
'formats': formats,
'subtitles': subtitles,
+ 'series': str_or_none(data.get('SeriesTitle')),
+ 'season': str_or_none(data.get('SeasonTitle')),
+ 'season_number': int_or_none(data.get('SeasonNumber')),
+ 'season_id': str_or_none(data.get('SeasonUrn')),
+ 'episode': str_or_none(data.get('EpisodeTitle')),
+ 'episode_number': int_or_none(data.get('EpisodeNumber')),
+ 'release_year': int_or_none(data.get('ProductionYear')),
}
generated by cgit v1.2.3 (git 2.26.2) at 2025-11-04 09:53:32 +0000