mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-10 01:02:13 +01:00
Remove _sort_formats from _extract_*_formats methods
Now _sort_formats should be called explicitly. _sort_formats has been added to all the necessary places in code. Closes #8051
This commit is contained in:
parent
395fd4b08a
commit
19dbaeece3
29 changed files with 56 additions and 21 deletions
|
@ -44,6 +44,7 @@ def _real_extract(self, url):
|
|||
'contentURL', webpage, 'm3u8 url', fatal=True)
|
||||
|
||||
formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._og_search_title(webpage).strip()
|
||||
description = self._og_search_description(webpage).strip()
|
||||
|
|
|
@ -120,6 +120,7 @@ def _real_extract(self, url):
|
|||
bc_info = self._download_json(req, user)
|
||||
m3u8_url = next(source['src'] for source in bc_info['sources'] if source['container'] == 'M2TS')
|
||||
formats = self._extract_m3u8_formats(m3u8_url, user, ext='mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': info['id'],
|
||||
|
|
|
@ -94,6 +94,7 @@ def _real_extract(self, url):
|
|||
xpath_with_ns('./media:thumbnail', NS_MAP)).get('url')
|
||||
|
||||
formats = self._extract_smil_formats(smil_url, display_id)
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
|
|
@ -122,6 +122,7 @@ def _real_extract(self, url):
|
|||
for entry in f4m_formats:
|
||||
# URLs without the extra param induce an 404 error
|
||||
entry.update({'extra_param_to_segment_url': hdcore_sign})
|
||||
self._sort_formats(f4m_formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
|
|
@ -48,6 +48,7 @@ def _real_extract(self, url):
|
|||
raise ExtractorError('Unable to find stream URL')
|
||||
|
||||
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
|
|
@ -1021,8 +1021,6 @@ def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None,
|
|||
'height': int_or_none(media_el.attrib.get('height')),
|
||||
'preference': preference,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return formats
|
||||
|
||||
def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
|
||||
|
@ -1143,7 +1141,6 @@ def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
|
|||
last_media = None
|
||||
formats.append(f)
|
||||
last_info = {}
|
||||
self._sort_formats(formats)
|
||||
return formats
|
||||
|
||||
@staticmethod
|
||||
|
@ -1317,8 +1314,6 @@ def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_para
|
|||
})
|
||||
continue
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return formats
|
||||
|
||||
def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
|
||||
|
@ -1536,7 +1531,6 @@ def extract_multisegment_info(element, ms_parent_info):
|
|||
existing_format.update(f)
|
||||
else:
|
||||
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
|
||||
self._sort_formats(formats)
|
||||
return formats
|
||||
|
||||
def _live_title(self, name):
|
||||
|
|
|
@ -57,6 +57,7 @@ def _real_extract(self, url):
|
|||
|
||||
formats = self._extract_m3u8_formats(
|
||||
video_data['videos']['variantplaylist']['uri'], video_id, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnails = [{
|
||||
'url': image['uri'],
|
||||
|
|
|
@ -38,6 +38,7 @@ def _real_extract(self, url):
|
|||
token_el = f4m_info.find('token')
|
||||
manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0'
|
||||
formats = self._extract_f4m_formats(manifest_url, display_id)
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
|
|
@ -63,18 +63,23 @@ def _real_extract(self, url):
|
|||
|
||||
video_title = info.get('playlist_title') or info.get('video_title')
|
||||
|
||||
entries = [{
|
||||
'id': compat_str(video_info['id']),
|
||||
'formats': self._extract_m3u8_formats(
|
||||
entries = []
|
||||
|
||||
for idx, video_info in enumerate(info['playlist']):
|
||||
formats = self._extract_m3u8_formats(
|
||||
video_info['src'], display_id, 'mp4', 'm3u8_native', m3u8_id='hls',
|
||||
note='Download m3u8 information for video %d' % (idx + 1)),
|
||||
'title': video_info['title'],
|
||||
'description': video_info.get('description'),
|
||||
'duration': parse_duration(video_info.get('video_length')),
|
||||
'webpage_url': video_info.get('href') or video_info.get('url'),
|
||||
'thumbnail': video_info.get('thumbnailURL'),
|
||||
'alt_title': video_info.get('secondary_title'),
|
||||
'timestamp': parse_iso8601(video_info.get('publishedDate')),
|
||||
} for idx, video_info in enumerate(info['playlist'])]
|
||||
note='Download m3u8 information for video %d' % (idx + 1))
|
||||
self._sort_formats(formats)
|
||||
entries.append({
|
||||
'id': compat_str(video_info['id']),
|
||||
'formats': formats,
|
||||
'title': video_info['title'],
|
||||
'description': video_info.get('description'),
|
||||
'duration': parse_duration(video_info.get('video_length')),
|
||||
'webpage_url': video_info.get('href') or video_info.get('url'),
|
||||
'thumbnail': video_info.get('thumbnailURL'),
|
||||
'alt_title': video_info.get('secondary_title'),
|
||||
'timestamp': parse_iso8601(video_info.get('publishedDate')),
|
||||
})
|
||||
|
||||
return self.playlist_result(entries, display_id, video_title)
|
||||
|
|
|
@ -118,6 +118,8 @@ def extract_formats(protocol, manifest_url):
|
|||
if info.get(protocol):
|
||||
extract_formats(protocol, info[protocol])
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
|
|
|
@ -39,13 +39,13 @@ def _real_extract(self, url):
|
|||
hidden_inputs = self._hidden_inputs(webpage)
|
||||
title = hidden_inputs['media_title']
|
||||
|
||||
formats = []
|
||||
if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1':
|
||||
formats = self._extract_smil_formats(
|
||||
'http://www.dw.com/smil/v-%s' % media_id, media_id,
|
||||
transform_source=lambda s: s.replace(
|
||||
'rtmp://tv-od.dw.de/flash/',
|
||||
'http://tv-download.dw.de/dwtv_video/flv/'))
|
||||
self._sort_formats(formats)
|
||||
else:
|
||||
formats = [{'url': hidden_inputs['file_name']}]
|
||||
|
||||
|
|
|
@ -1310,6 +1310,7 @@ def _real_extract(self, url):
|
|||
'vcodec': 'none' if m.group('type') == 'audio' else None
|
||||
}]
|
||||
info_dict['direct'] = True
|
||||
self._sort_formats(formats)
|
||||
info_dict['formats'] = formats
|
||||
return info_dict
|
||||
|
||||
|
@ -1336,6 +1337,7 @@ def _real_extract(self, url):
|
|||
# Is it an M3U playlist?
|
||||
if first_bytes.startswith(b'#EXTM3U'):
|
||||
info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
|
||||
self._sort_formats(info_dict['formats'])
|
||||
return info_dict
|
||||
|
||||
# Maybe it's a direct link to a video?
|
||||
|
@ -1360,15 +1362,19 @@ def _real_extract(self, url):
|
|||
if doc.tag == 'rss':
|
||||
return self._extract_rss(url, video_id, doc)
|
||||
elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
|
||||
return self._parse_smil(doc, url, video_id)
|
||||
smil = self._parse_smil(doc, url, video_id)
|
||||
self._sort_formats(smil['formats'])
|
||||
return smil
|
||||
elif doc.tag == '{http://xspf.org/ns/0/}playlist':
|
||||
return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
|
||||
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
|
||||
info_dict['formats'] = self._parse_mpd_formats(
|
||||
doc, video_id, mpd_base_url=url.rpartition('/')[0])
|
||||
self._sort_formats(info_dict['formats'])
|
||||
return info_dict
|
||||
elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
|
||||
info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
|
||||
self._sort_formats(info_dict['formats'])
|
||||
return info_dict
|
||||
except compat_xml_parse_error:
|
||||
pass
|
||||
|
@ -2053,6 +2059,9 @@ def filter_video(urls):
|
|||
else:
|
||||
entry_info_dict['url'] = video_url
|
||||
|
||||
if entry_info_dict.get('formats'):
|
||||
self._sort_formats(entry_info_dict['formats'])
|
||||
|
||||
entries.append(entry_info_dict)
|
||||
|
||||
if len(entries) == 1:
|
||||
|
|
|
@ -130,6 +130,7 @@ def _real_extract(self, url):
|
|||
formats = self._extract_f4m_formats(
|
||||
'%s?hdnea=%s&hdcore=3.2.0' % (token_attrib['url'], token_auth),
|
||||
video_id, f4m_id='hds')
|
||||
self._sort_formats(formats)
|
||||
|
||||
categories_str = _v('meta_sports')
|
||||
categories = categories_str.split(',') if categories_str else []
|
||||
|
|
|
@ -37,6 +37,7 @@ def _real_extract(self, url):
|
|||
r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*location\.hash\.substring\(1\)',
|
||||
webpage, 'm3u8 url', group='url')
|
||||
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
|
|
|
@ -47,6 +47,7 @@ def _real_extract(self, url):
|
|||
video_url = self._download_json(request, video_id)['data']['videoUrl']
|
||||
f4m_url = xpath_text(self._download_xml(video_url, video_id), './to')
|
||||
formats = self._extract_f4m_formats(f4m_url, video_id)
|
||||
self._sort_formats(formats)
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._live_title('Матч ТВ - Прямой эфир'),
|
||||
|
|
|
@ -67,6 +67,7 @@ def _real_extract(self, url):
|
|||
formats.extend(self._extract_f4m_formats(
|
||||
file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
|
||||
display_id, f4m_id=loc))
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._search_regex(
|
||||
r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>', webpage, 'title')
|
||||
|
|
|
@ -63,6 +63,7 @@ def _real_extract(self, url):
|
|||
if determine_ext(media_url) == 'f4m':
|
||||
formats = self._extract_f4m_formats(
|
||||
media_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id, f4m_id='hds')
|
||||
self._sort_formats(formats)
|
||||
else:
|
||||
formats = [{
|
||||
'url': media_url,
|
||||
|
|
|
@ -31,6 +31,7 @@ def _real_extract(self, url):
|
|||
formats = self._extract_smil_formats(
|
||||
'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml' % video_id,
|
||||
video_id)
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
|
|
@ -49,6 +49,7 @@ def _real_extract(self, url):
|
|||
# f4m_url = server + relative_url
|
||||
f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url']
|
||||
f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
|
||||
self._sort_formats(f4m_formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
|
|
@ -209,6 +209,7 @@ def _real_extract(self, url):
|
|||
png = self._download_webpage(png_url, video_id, 'Downloading url information')
|
||||
m3u8_url = _decrypt_url(png)
|
||||
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
|
|
@ -38,6 +38,7 @@ def _real_extract(self, url):
|
|||
item['file'], video_id, ext='mp4', entry_protocol='m3u8_native'))
|
||||
elif item.get('type') == '':
|
||||
formats.append({'url': item['file']})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
|
|
@ -77,6 +77,7 @@ def _real_extract(self, url):
|
|||
raise ExtractorError('This video is DRM protected.', expected=True)
|
||||
|
||||
formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
video = self._download_json(
|
||||
'%s/%s/%s?%s' % (
|
||||
|
|
|
@ -99,6 +99,7 @@ def _real_extract(self, url):
|
|||
webpage, 'hls file')
|
||||
|
||||
formats = self._extract_m3u8_formats(hls, video_id, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._search_regex(
|
||||
r'sportboxPlayer\.node_title\s*=\s*"([^"]+)"', webpage, 'title')
|
||||
|
|
|
@ -82,6 +82,7 @@ def _real_extract(self, url):
|
|||
)
|
||||
formats = self._extract_m3u8_formats(
|
||||
token_info['tokenizedUrl'], episode, ext='mp4', entry_protocol='m3u8_native')
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': embed_data['videoId'],
|
||||
|
|
|
@ -69,6 +69,7 @@ def _real_extract(self, url):
|
|||
apu = self._search_regex(r"apu='([^']+)'", webpage, 'apu')
|
||||
m3u8_url = codecs.decode(apu, 'rot_13')[::-1]
|
||||
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
|
|
@ -111,6 +111,7 @@ def _real_extract(self, url):
|
|||
|
||||
video_url = xpath_text(video, './/video_url', 'video url', fatal=True)
|
||||
formats = self._extract_f4m_formats(video_url, video_id, f4m_id='hds')
|
||||
self._sort_formats(formats)
|
||||
|
||||
data = self._download_json(
|
||||
'http://videomore.ru/video/tracks/%s.json' % video_id,
|
||||
|
|
|
@ -50,6 +50,7 @@ def _real_extract(self, url):
|
|||
|
||||
playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename)
|
||||
formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._og_search_title(webpage, default=display_id)
|
||||
description = self._og_search_description(webpage, default=None)
|
||||
|
|
|
@ -151,6 +151,7 @@ def extract_part(part_id):
|
|||
smil_url = '%s/%s/video/%s/smil.xml' % (base_url, lecture_slug, part_id)
|
||||
smil = self._download_smil(smil_url, lecture_id)
|
||||
info = self._parse_smil(smil, smil_url, lecture_id)
|
||||
self._sort_formats(info['formats'])
|
||||
info['id'] = lecture_id if not multipart else '%s_part%s' % (lecture_id, part_id)
|
||||
info['display_id'] = lecture_slug if not multipart else '%s_part%s' % (lecture_slug, part_id)
|
||||
if multipart:
|
||||
|
|
|
@ -41,10 +41,12 @@ def _real_extract(self, url):
|
|||
m = re.search(r'ynet - HOT -- (["\']+)(?P<title>.+?)\1', title)
|
||||
if m:
|
||||
title = m.group('title')
|
||||
formats = self._extract_f4m_formats(f4m_url, video_id)
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': self._extract_f4m_formats(f4m_url, video_id),
|
||||
'formats': formats,
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
}
|
||||
|
|
Loading…
Reference in a new issue