mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-30 12:01:28 +00:00
[udemy] Add support for react rendition (closes #12744)
This commit is contained in:
parent
57e2cb6c3a
commit
3dfceb286c
|
@ -212,12 +212,15 @@ def _real_extract(self, url):
|
||||||
thumbnail = asset.get('thumbnail_url') or asset.get('thumbnailUrl')
|
thumbnail = asset.get('thumbnail_url') or asset.get('thumbnailUrl')
|
||||||
duration = float_or_none(asset.get('data', {}).get('duration'))
|
duration = float_or_none(asset.get('data', {}).get('duration'))
|
||||||
|
|
||||||
|
subtitles = {}
|
||||||
|
automatic_captions = {}
|
||||||
|
|
||||||
formats = []
|
formats = []
|
||||||
|
|
||||||
def extract_output_format(src):
|
def extract_output_format(src, f_id):
|
||||||
return {
|
return {
|
||||||
'url': src['url'],
|
'url': src['url'],
|
||||||
'format_id': '%sp' % (src.get('height') or format_id),
|
'format_id': '%sp' % (src.get('height') or f_id),
|
||||||
'width': int_or_none(src.get('width')),
|
'width': int_or_none(src.get('width')),
|
||||||
'height': int_or_none(src.get('height')),
|
'height': int_or_none(src.get('height')),
|
||||||
'vbr': int_or_none(src.get('video_bitrate_in_kbps')),
|
'vbr': int_or_none(src.get('video_bitrate_in_kbps')),
|
||||||
|
@ -237,22 +240,21 @@ def extract_output_format(src):
|
||||||
def add_output_format_meta(f, key):
|
def add_output_format_meta(f, key):
|
||||||
output = outputs.get(key)
|
output = outputs.get(key)
|
||||||
if isinstance(output, dict):
|
if isinstance(output, dict):
|
||||||
output_format = extract_output_format(output)
|
output_format = extract_output_format(output, key)
|
||||||
output_format.update(f)
|
output_format.update(f)
|
||||||
return output_format
|
return output_format
|
||||||
return f
|
return f
|
||||||
|
|
||||||
download_urls = asset.get('download_urls')
|
def extract_formats(source_list):
|
||||||
if isinstance(download_urls, dict):
|
if not isinstance(source_list, list):
|
||||||
video = download_urls.get('Video')
|
return
|
||||||
if isinstance(video, list):
|
for source in source_list:
|
||||||
for format_ in video:
|
video_url = source.get('file') or source.get('src')
|
||||||
video_url = format_.get('file')
|
if not video_url or not isinstance(video_url, compat_str):
|
||||||
if not video_url:
|
|
||||||
continue
|
continue
|
||||||
format_id = format_.get('label')
|
format_id = source.get('label')
|
||||||
f = {
|
f = {
|
||||||
'url': format_['file'],
|
'url': video_url,
|
||||||
'format_id': '%sp' % format_id,
|
'format_id': '%sp' % format_id,
|
||||||
'height': int_or_none(format_id),
|
'height': int_or_none(format_id),
|
||||||
}
|
}
|
||||||
|
@ -262,6 +264,10 @@ def add_output_format_meta(f, key):
|
||||||
f = add_output_format_meta(f, format_id)
|
f = add_output_format_meta(f, format_id)
|
||||||
formats.append(f)
|
formats.append(f)
|
||||||
|
|
||||||
|
download_urls = asset.get('download_urls')
|
||||||
|
if isinstance(download_urls, dict):
|
||||||
|
extract_formats(download_urls.get('Video'))
|
||||||
|
|
||||||
view_html = lecture.get('view_html')
|
view_html = lecture.get('view_html')
|
||||||
if view_html:
|
if view_html:
|
||||||
view_html_urls = set()
|
view_html_urls = set()
|
||||||
|
@ -294,6 +300,35 @@ def add_output_format_meta(f, key):
|
||||||
'height': height,
|
'height': height,
|
||||||
}, res))
|
}, res))
|
||||||
|
|
||||||
|
# react rendition since 2017.04.15 (see
|
||||||
|
# https://github.com/rg3/youtube-dl/issues/12744)
|
||||||
|
data = self._parse_json(
|
||||||
|
self._search_regex(
|
||||||
|
r'videojs-setup-data=(["\'])(?P<data>{.+?})\1', view_html,
|
||||||
|
'setup data', default='{}', group='data'), video_id,
|
||||||
|
transform_source=unescapeHTML, fatal=False)
|
||||||
|
if data and isinstance(data, dict):
|
||||||
|
extract_formats(data.get('sources'))
|
||||||
|
if not duration:
|
||||||
|
duration = int_or_none(data.get('duration'))
|
||||||
|
tracks = data.get('tracks')
|
||||||
|
if isinstance(tracks, list):
|
||||||
|
for track in tracks:
|
||||||
|
if not isinstance(track, dict):
|
||||||
|
continue
|
||||||
|
if track.get('kind') != 'captions':
|
||||||
|
continue
|
||||||
|
src = track.get('src')
|
||||||
|
if not src or not isinstance(src, compat_str):
|
||||||
|
continue
|
||||||
|
lang = track.get('language') or track.get(
|
||||||
|
'srclang') or track.get('label')
|
||||||
|
sub_dict = automatic_captions if track.get(
|
||||||
|
'autogenerated') is True else subtitles
|
||||||
|
sub_dict.setdefault(lang, []).append({
|
||||||
|
'url': src,
|
||||||
|
})
|
||||||
|
|
||||||
self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
|
self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
|
||||||
|
|
||||||
return {
|
return {
|
||||||
|
@ -302,7 +337,9 @@ def add_output_format_meta(f, key):
|
||||||
'description': description,
|
'description': description,
|
||||||
'thumbnail': thumbnail,
|
'thumbnail': thumbnail,
|
||||||
'duration': duration,
|
'duration': duration,
|
||||||
'formats': formats
|
'formats': formats,
|
||||||
|
'subtitles': subtitles,
|
||||||
|
'automatic_captions': automatic_captions,
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
|
Loading…
Reference in a new issue