mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-25 04:35:52 +01:00
[ie/NovaEmbed] Fix extractor (#7910)
Closes #8025 Authored by: std-move
This commit is contained in:
parent
a5e264d74b
commit
2269065ad6
@ -6,7 +6,6 @@
|
|||||||
determine_ext,
|
determine_ext,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
js_to_json,
|
js_to_json,
|
||||||
qualities,
|
|
||||||
traverse_obj,
|
traverse_obj,
|
||||||
unified_strdate,
|
unified_strdate,
|
||||||
url_or_none,
|
url_or_none,
|
||||||
@ -49,77 +48,52 @@ def _real_extract(self, url):
|
|||||||
duration = None
|
duration = None
|
||||||
formats = []
|
formats = []
|
||||||
|
|
||||||
player = self._parse_json(
|
def process_format_list(format_list, format_id=""):
|
||||||
self._search_regex(
|
nonlocal formats, has_drm
|
||||||
(r'(?:(?:replacePlaceholders|processAdTagModifier).*?:\s*)?(?:replacePlaceholders|processAdTagModifier)\s*\(\s*(?P<json>{.*?})\s*\)(?:\s*\))?\s*,',
|
if not isinstance(format_list, list):
|
||||||
r'Player\.init\s*\([^,]+,(?P<cndn>\s*\w+\s*\?)?\s*(?P<json>{(?(cndn).+?|.+)})\s*(?(cndn):|,\s*{.+?}\s*\)\s*;)'),
|
format_list = [format_list]
|
||||||
webpage, 'player', default='{}', group='json'), video_id, fatal=False)
|
for format_dict in format_list:
|
||||||
if player:
|
if not isinstance(format_dict, dict):
|
||||||
for format_id, format_list in player['tracks'].items():
|
continue
|
||||||
if not isinstance(format_list, list):
|
if (not self.get_param('allow_unplayable_formats')
|
||||||
format_list = [format_list]
|
and traverse_obj(format_dict, ('drm', 'keySystem'))):
|
||||||
for format_dict in format_list:
|
has_drm = True
|
||||||
if not isinstance(format_dict, dict):
|
continue
|
||||||
continue
|
format_url = url_or_none(format_dict.get('src'))
|
||||||
if (not self.get_param('allow_unplayable_formats')
|
format_type = format_dict.get('type')
|
||||||
and traverse_obj(format_dict, ('drm', 'keySystem'))):
|
ext = determine_ext(format_url)
|
||||||
has_drm = True
|
if (format_type == 'application/x-mpegURL'
|
||||||
continue
|
or format_id == 'HLS' or ext == 'm3u8'):
|
||||||
format_url = url_or_none(format_dict.get('src'))
|
formats.extend(self._extract_m3u8_formats(
|
||||||
format_type = format_dict.get('type')
|
format_url, video_id, 'mp4',
|
||||||
ext = determine_ext(format_url)
|
entry_protocol='m3u8_native', m3u8_id='hls',
|
||||||
if (format_type == 'application/x-mpegURL'
|
fatal=False))
|
||||||
or format_id == 'HLS' or ext == 'm3u8'):
|
elif (format_type == 'application/dash+xml'
|
||||||
formats.extend(self._extract_m3u8_formats(
|
or format_id == 'DASH' or ext == 'mpd'):
|
||||||
format_url, video_id, 'mp4',
|
formats.extend(self._extract_mpd_formats(
|
||||||
entry_protocol='m3u8_native', m3u8_id='hls',
|
format_url, video_id, mpd_id='dash', fatal=False))
|
||||||
fatal=False))
|
else:
|
||||||
elif (format_type == 'application/dash+xml'
|
formats.append({
|
||||||
or format_id == 'DASH' or ext == 'mpd'):
|
|
||||||
formats.extend(self._extract_mpd_formats(
|
|
||||||
format_url, video_id, mpd_id='dash', fatal=False))
|
|
||||||
else:
|
|
||||||
formats.append({
|
|
||||||
'url': format_url,
|
|
||||||
})
|
|
||||||
duration = int_or_none(player.get('duration'))
|
|
||||||
else:
|
|
||||||
# Old path, not actual as of 08.04.2020
|
|
||||||
bitrates = self._parse_json(
|
|
||||||
self._search_regex(
|
|
||||||
r'(?s)(?:src|bitrates)\s*=\s*({.+?})\s*;', webpage, 'formats'),
|
|
||||||
video_id, transform_source=js_to_json)
|
|
||||||
|
|
||||||
QUALITIES = ('lq', 'mq', 'hq', 'hd')
|
|
||||||
quality_key = qualities(QUALITIES)
|
|
||||||
|
|
||||||
for format_id, format_list in bitrates.items():
|
|
||||||
if not isinstance(format_list, list):
|
|
||||||
format_list = [format_list]
|
|
||||||
for format_url in format_list:
|
|
||||||
format_url = url_or_none(format_url)
|
|
||||||
if not format_url:
|
|
||||||
continue
|
|
||||||
if format_id == 'hls':
|
|
||||||
formats.extend(self._extract_m3u8_formats(
|
|
||||||
format_url, video_id, ext='mp4',
|
|
||||||
entry_protocol='m3u8_native', m3u8_id='hls',
|
|
||||||
fatal=False))
|
|
||||||
continue
|
|
||||||
f = {
|
|
||||||
'url': format_url,
|
'url': format_url,
|
||||||
}
|
})
|
||||||
f_id = format_id
|
|
||||||
for quality in QUALITIES:
|
player = self._search_json(
|
||||||
if '%s.mp4' % quality in format_url:
|
r'player:', webpage, 'player', video_id, fatal=False, end_pattern=r';\s*</script>')
|
||||||
f_id += '-%s' % quality
|
if player:
|
||||||
f.update({
|
for src in traverse_obj(player, ('lib', 'source', 'sources', ...)):
|
||||||
'quality': quality_key(quality),
|
process_format_list(src)
|
||||||
'format_note': quality.upper(),
|
duration = traverse_obj(player, ('sourceInfo', 'duration', {int_or_none}))
|
||||||
})
|
if not formats and not has_drm:
|
||||||
break
|
# older code path, in use before August 2023
|
||||||
f['format_id'] = f_id
|
player = self._parse_json(
|
||||||
formats.append(f)
|
self._search_regex(
|
||||||
|
(r'(?:(?:replacePlaceholders|processAdTagModifier).*?:\s*)?(?:replacePlaceholders|processAdTagModifier)\s*\(\s*(?P<json>{.*?})\s*\)(?:\s*\))?\s*,',
|
||||||
|
r'Player\.init\s*\([^,]+,(?P<cndn>\s*\w+\s*\?)?\s*(?P<json>{(?(cndn).+?|.+)})\s*(?(cndn):|,\s*{.+?}\s*\)\s*;)'),
|
||||||
|
webpage, 'player', group='json'), video_id)
|
||||||
|
if player:
|
||||||
|
for format_id, format_list in player['tracks'].items():
|
||||||
|
process_format_list(format_list, format_id)
|
||||||
|
duration = int_or_none(player.get('duration'))
|
||||||
|
|
||||||
if not formats and has_drm:
|
if not formats and has_drm:
|
||||||
self.report_drm(video_id)
|
self.report_drm(video_id)
|
||||||
|
Loading…
Reference in New Issue
Block a user