github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[NovaEmbed] Fix extractor

Browse source 
Closes #1570
This commit is contained in:
pukkandan 2021-11-12 03:12:53 +05:30
parent bf5f605e76
commit c1dc0ee56e
No known key found for this signature in database
GPG key ID: 0F00D95A001F4698
1 changed files with 27 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

33
yt_dlp/extractor/nova.py
View file

@ -10,6 +10,7 @@
int_or_none, int_or_none,
js_to_json, js_to_json,
qualities, qualities,
traverse_obj,
unified_strdate, unified_strdate,
url_or_none, url_or_none,
) )
@ -17,30 +18,44 @@
class NovaEmbedIE(InfoExtractor): class NovaEmbedIE(InfoExtractor):
_VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
_TEST = { _TESTS = [{
'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1', 'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1',
'md5': 'ee009bafcc794541570edd44b71cbea3',
'info_dict': { 'info_dict': {
'id': '8o0n0r', 'id': '8o0n0r',
'ext': 'mp4',
'title': '2180. díl', 'title': '2180. díl',
'thumbnail': r're:^https?://.*\.jpg', 'thumbnail': r're:^https?://.*\.jpg',
'duration': 2578, 'duration': 2578,
}, },
} 'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
'expected_warnings': ['DRM protected', 'Requested format is not available'],
}, {
'url': 'https://media.cms.nova.cz/embed/KybpWYvcgOa',
'info_dict': {
'id': 'KybpWYvcgOa',
'ext': 'mp4',
'title': 'Borhyová oslavila 60? Soutěžící z pořadu odboural moderátora Ondřeje Sokola',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 114,
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
has_drm = False
duration = None duration = None
formats = [] formats = []
player = self._parse_json( player = self._parse_json(
self._search_regex( self._search_regex(
r'Player\.init\s*\([^,]+,\s*(?:\w+\s*\?\s*{.+?}\s*:\s*)?({.+})\s*,\s*{.+?}\s*\)\s*;', r'Player\.init\s*\([^,]+,(?P<cndn>\s*\w+\s*\?)?\s*(?P<json>{(?(cndn).+?|.+)})\s*(?(cndn):|,\s*{.+?}\s*\)\s*;)',
webpage, 'player', default='{}'), video_id, fatal=False) webpage, 'player', default='{}', group='json'), video_id, fatal=False)
if player: if player:
for format_id, format_list in player['tracks'].items(): for format_id, format_list in player['tracks'].items():
if not isinstance(format_list, list): if not isinstance(format_list, list):
@ -48,6 +63,10 @@ def _real_extract(self, url):
for format_dict in format_list: for format_dict in format_list:
if not isinstance(format_dict, dict): if not isinstance(format_dict, dict):
continue continue
if (not self.get_param('allow_unplayable_formats')
and traverse_obj(format_dict, ('drm', 'keySystem'))):
has_drm = True
continue
format_url = url_or_none(format_dict.get('src')) format_url = url_or_none(format_dict.get('src'))
format_type = format_dict.get('type') format_type = format_dict.get('type')
ext = determine_ext(format_url) ext = determine_ext(format_url)
@ -104,6 +123,8 @@ def _real_extract(self, url):
f['format_id'] = f_id f['format_id'] = f_id
formats.append(f) formats.append(f)
if not formats and has_drm:
self.report_drm(video_id)
self._sort_formats(formats) self._sort_formats(formats)
title = self._og_search_title( title = self._og_search_title(