mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-10-08 22:14:53 +00:00
[downloader/mhtml] Add new downloader (#343)
This downloader is intended to be used for streams that consist of a timed sequence of stand-alone images, such as slideshows or thumbnail streams This can be used for implementing: https://github.com/ytdl-org/youtube-dl/issues/4974#issue-58006762 https://github.com/ytdl-org/youtube-dl/issues/4540#issuecomment-69574231 https://github.com/ytdl-org/youtube-dl/pull/11185#issuecomment-335554239 https://github.com/ytdl-org/youtube-dl/issues/9868 https://github.com/ytdl-org/youtube-dl/pull/14951 Authored by: fstirlitz
This commit is contained in:
felix
Notes:
pukkandan
2021-06-13 22:41:29 +05:30
This also adds extracting storyboards from DASH manifest as mhtml
@@ -24,7 +24,7 @@ class CanvasIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza|dako)/assets/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
||||
'md5': '68993eda72ef62386a15ea2cf3c93107',
|
||||
'md5': '37b2b7bb9b3dcaa05b67058dc3a714a9',
|
||||
'info_dict': {
|
||||
'id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
||||
'display_id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
||||
@@ -32,9 +32,9 @@ class CanvasIE(InfoExtractor):
|
||||
'title': 'Nachtwacht: De Greystook',
|
||||
'description': 'Nachtwacht: De Greystook',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 1468.04,
|
||||
'duration': 1468.02,
|
||||
},
|
||||
'expected_warnings': ['is not a supported codec', 'Unknown MIME type'],
|
||||
'expected_warnings': ['is not a supported codec'],
|
||||
}, {
|
||||
'url': 'https://mediazone.vrt.be/api/v1/canvas/assets/mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
|
||||
'only_matching': True,
|
||||
|
||||
@@ -2126,6 +2126,7 @@ class InfoExtractor(object):
|
||||
format_id.append(str(format_index))
|
||||
f = {
|
||||
'format_id': '-'.join(format_id),
|
||||
'format_note': name,
|
||||
'format_index': format_index,
|
||||
'url': manifest_url,
|
||||
'manifest_url': m3u8_url,
|
||||
@@ -2637,7 +2638,7 @@ class InfoExtractor(object):
|
||||
mime_type = representation_attrib['mimeType']
|
||||
content_type = representation_attrib.get('contentType', mime_type.split('/')[0])
|
||||
|
||||
if content_type in ('video', 'audio', 'text'):
|
||||
if content_type in ('video', 'audio', 'text') or mime_type == 'image/jpeg':
|
||||
base_url = ''
|
||||
for element in (representation, adaptation_set, period, mpd_doc):
|
||||
base_url_e = element.find(_add_ns('BaseURL'))
|
||||
@@ -2654,9 +2655,15 @@ class InfoExtractor(object):
|
||||
url_el = representation.find(_add_ns('BaseURL'))
|
||||
filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength') if url_el is not None else None)
|
||||
bandwidth = int_or_none(representation_attrib.get('bandwidth'))
|
||||
if representation_id is not None:
|
||||
format_id = representation_id
|
||||
else:
|
||||
format_id = content_type
|
||||
if mpd_id:
|
||||
format_id = mpd_id + '-' + format_id
|
||||
if content_type in ('video', 'audio'):
|
||||
f = {
|
||||
'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
|
||||
'format_id': format_id,
|
||||
'manifest_url': mpd_url,
|
||||
'ext': mimetype2ext(mime_type),
|
||||
'width': int_or_none(representation_attrib.get('width')),
|
||||
@@ -2676,6 +2683,17 @@ class InfoExtractor(object):
|
||||
'manifest_url': mpd_url,
|
||||
'filesize': filesize,
|
||||
}
|
||||
elif mime_type == 'image/jpeg':
|
||||
# See test case in VikiIE
|
||||
# https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1
|
||||
f = {
|
||||
'format_id': format_id,
|
||||
'ext': 'mhtml',
|
||||
'manifest_url': mpd_url,
|
||||
'format_note': 'DASH storyboards (jpeg)',
|
||||
'acodec': 'none',
|
||||
'vcodec': 'none',
|
||||
}
|
||||
representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
|
||||
|
||||
def prepare_template(template_name, identifiers):
|
||||
@@ -2694,7 +2712,8 @@ class InfoExtractor(object):
|
||||
t += c
|
||||
# Next, $...$ templates are translated to their
|
||||
# %(...) counterparts to be used with % operator
|
||||
t = t.replace('$RepresentationID$', representation_id)
|
||||
if representation_id is not None:
|
||||
t = t.replace('$RepresentationID$', representation_id)
|
||||
t = re.sub(r'\$(%s)\$' % '|'.join(identifiers), r'%(\1)d', t)
|
||||
t = re.sub(r'\$(%s)%%([^$]+)\$' % '|'.join(identifiers), r'%(\1)\2', t)
|
||||
t.replace('$$', '$')
|
||||
@@ -2811,7 +2830,7 @@ class InfoExtractor(object):
|
||||
'url': mpd_url or base_url,
|
||||
'fragment_base_url': base_url,
|
||||
'fragments': [],
|
||||
'protocol': 'http_dash_segments',
|
||||
'protocol': 'http_dash_segments' if mime_type != 'image/jpeg' else 'mhtml',
|
||||
})
|
||||
if 'initialization_url' in representation_ms_info:
|
||||
initialization_url = representation_ms_info['initialization_url']
|
||||
@@ -2822,7 +2841,7 @@ class InfoExtractor(object):
|
||||
else:
|
||||
# Assuming direct URL to unfragmented media.
|
||||
f['url'] = base_url
|
||||
if content_type in ('video', 'audio'):
|
||||
if content_type in ('video', 'audio') or mime_type == 'image/jpeg':
|
||||
formats.append(f)
|
||||
elif content_type == 'text':
|
||||
subtitles.setdefault(lang or 'und', []).append(f)
|
||||
|
||||
@@ -142,6 +142,7 @@ class VikiIE(VikiBaseIE):
|
||||
IE_NAME = 'viki'
|
||||
_VALID_URL = r'%s(?:videos|player)/(?P<id>[0-9]+v)' % VikiBaseIE._VALID_URL_BASE
|
||||
_TESTS = [{
|
||||
'note': 'Free non-DRM video with storyboards in MPD',
|
||||
'url': 'https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1',
|
||||
'info_dict': {
|
||||
'id': '1175236v',
|
||||
@@ -155,7 +156,6 @@ class VikiIE(VikiBaseIE):
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
|
||||
}, {
|
||||
'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
|
||||
'info_dict': {
|
||||
@@ -173,7 +173,6 @@ class VikiIE(VikiBaseIE):
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
'skip': 'Blocked in the US',
|
||||
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
|
||||
}, {
|
||||
# clip
|
||||
'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
|
||||
@@ -225,7 +224,6 @@ class VikiIE(VikiBaseIE):
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
|
||||
}, {
|
||||
# youtube external
|
||||
'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1',
|
||||
@@ -264,7 +262,6 @@ class VikiIE(VikiBaseIE):
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
Reference in New Issue
Block a user