Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-20 18:36:06 +08:00
Code Issues Releases Wiki Activity

[drtv] Add support for new URL schema (closes #23059)

Browse Source
This commit is contained in:
Sergey M․ 2019-11-14 01:45:04 +07:00
parent eb22d1b557
commit 5709d661a2
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 52 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
youtube_dl/extractor/drtv.py
View File

@ -17,6 +17,7 @@ from ..utils import (
float_or_none, float_or_none,
mimetype2ext, mimetype2ext,
str_or_none, str_or_none,
try_get,
unified_timestamp, unified_timestamp,
update_url_query, update_url_query,
url_or_none, url_or_none,
@ -24,7 +25,14 @@ from ..utils import (
class DRTVIE(InfoExtractor): 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)/
)
(?P<id>[\da-z_-]+)
'''
_GEO_BYPASS = False _GEO_BYPASS = False
_GEO_COUNTRIES = ['DK'] _GEO_COUNTRIES = ['DK']
IE_NAME = 'drtv' IE_NAME = 'drtv'
@ -83,6 +91,26 @@ class DRTVIE(InfoExtractor):
}, { }, {
'url': 'https://www.dr.dk/radio/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9', 'url': 'https://www.dr.dk/radio/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9',
'only_matching': True, '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,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -100,13 +128,32 @@ class DRTVIE(InfoExtractor):
webpage, 'video id', default=None) webpage, 'video id', default=None)
if not video_id: if not video_id:
video_id = compat_urllib_parse_unquote(self._search_regex( video_id = self._search_regex(
r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)', r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)',
webpage, 'urn')) 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'}
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
data = self._download_json( data = self._download_json(
'https://www.dr.dk/mu-online/api/1.4/programcard/%s' % video_id, programcard_url, video_id, 'Downloading video JSON', query=query)
video_id, 'Downloading video JSON', query={'expanded': 'true'})
title = str_or_none(data.get('Title')) or re.sub( title = str_or_none(data.get('Title')) or re.sub(
r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '', r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '',