[InfoExtractor] Support byte range for DASH

* adapted from https://github.com/ytdl-org/youtube-dl/pull/30279
* thx former GH user kikuyan
This commit is contained in:
dirkf 2024-01-27 15:37:08 +00:00
parent bec9180e89
commit 4eaeb9b2c6
5 changed files with 562 additions and 36 deletions

View File

@ -1126,6 +1126,72 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
'fps': 30,
}],
{},
), (
# https://github.com/ytdl-org/youtube-dl/issues/30235
# Bento4 generated test mpd
# mp4dash --mpd-name=manifest.mpd --no-split --use-segment-list mediafiles
'url_and_range',
'http://unknown/manifest.mpd', # mpd_url
'http://unknown/', # mpd_base_url
[{
'manifest_url': 'http://unknown/manifest.mpd',
'fragment_base_url': 'http://unknown/',
'ext': 'm4a',
'format_id': 'audio-und-mp4a.40.2',
'format_note': 'DASH audio',
'container': 'm4a_dash',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'none',
'tbr': 98.808,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'fragment_base_url': 'http://unknown/',
'ext': 'mp4',
'format_id': 'video-avc1',
'format_note': 'DASH video',
'container': 'mp4_dash',
'protocol': 'http_dash_segments',
'acodec': 'none',
'vcodec': 'avc1.4D401E',
'tbr': 699.597,
'width': 768,
'height': 432
}],
{},
), (
# https://github.com/ytdl-org/youtube-dl/issues/27575
# GPAC generated test mpd
# MP4Box -dash 10000 -single-file -out manifest.mpd mediafiles
'range_only',
'http://unknown/manifest.mpd', # mpd_url
'http://unknown/', # mpd_base_url
[{
'manifest_url': 'http://unknown/manifest.mpd',
'fragment_base_url': 'http://unknown/audio_dashinit.mp4',
'ext': 'm4a',
'format_id': '2',
'format_note': 'DASH audio',
'container': 'm4a_dash',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'none',
'tbr': 98.096,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'fragment_base_url': 'http://unknown/video_dashinit.mp4',
'ext': 'mp4',
'format_id': '1',
'format_note': 'DASH video',
'container': 'mp4_dash',
'protocol': 'http_dash_segments',
'acodec': 'none',
'vcodec': 'avc1.4D401E',
'tbr': 526.987,
'width': 768,
'height': 432
}],
{},
), (
'subtitles',
'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',

35
test/testdata/mpd/range_only.mpd vendored Normal file
View File

@ -0,0 +1,35 @@
<?xml version="1.0"?>
<!-- MPD file Generated with GPAC version 1.0.1-revrelease at 2021-11-27T20:53:11.690Z -->
<MPD xmlns="urn:mpeg:dash:schema:mpd:2011" minBufferTime="PT1.500S" type="static" mediaPresentationDuration="PT0H0M30.196S" maxSegmentDuration="PT0H0M10.027S" profiles="urn:mpeg:dash:profile:full:2011">
<ProgramInformation moreInformationURL="http://gpac.io">
<Title>manifest.mpd generated by GPAC</Title>
</ProgramInformation>
<Period duration="PT0H0M30.196S">
<AdaptationSet segmentAlignment="true" maxWidth="768" maxHeight="432" maxFrameRate="30000/1001" par="16:9" lang="und" startWithSAP="1">
<Representation id="1" mimeType="video/mp4" codecs="avc1.4D401E" width="768" height="432" frameRate="30000/1001" sar="1:1" bandwidth="526987">
<BaseURL>video_dashinit.mp4</BaseURL>
<SegmentList timescale="90000" duration="900000">
<Initialization range="0-881"/>
<SegmentURL mediaRange="882-876094" indexRange="882-925"/>
<SegmentURL mediaRange="876095-1466732" indexRange="876095-876138"/>
<SegmentURL mediaRange="1466733-1953615" indexRange="1466733-1466776"/>
<SegmentURL mediaRange="1953616-1994211" indexRange="1953616-1953659"/>
</SegmentList>
</Representation>
</AdaptationSet>
<AdaptationSet segmentAlignment="true" lang="und" startWithSAP="1">
<Representation id="2" mimeType="audio/mp4" codecs="mp4a.40.2" audioSamplingRate="48000" bandwidth="98096">
<AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
<BaseURL>audio_dashinit.mp4</BaseURL>
<SegmentList timescale="48000" duration="480000">
<Initialization range="0-752"/>
<SegmentURL mediaRange="753-124129" indexRange="753-796"/>
<SegmentURL mediaRange="124130-250544" indexRange="124130-124173"/>
<SegmentURL mediaRange="250545-374929" indexRange="250545-250588"/>
</SegmentList>
</Representation>
</AdaptationSet>
</Period>
</MPD>

351
test/testdata/mpd/subtitles.mpd vendored Normal file
View File

@ -0,0 +1,351 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Created with Unified Streaming Platform (version=1.10.18-20255) -->
<MPD
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns="urn:mpeg:dash:schema:mpd:2011"
xsi:schemaLocation="urn:mpeg:dash:schema:mpd:2011 http://standards.iso.org/ittf/PubliclyAvailableStandards/MPEG-DASH_schema_files/DASH-MPD.xsd"
type="static"
mediaPresentationDuration="PT14M48S"
maxSegmentDuration="PT1M"
minBufferTime="PT10S"
profiles="urn:mpeg:dash:profile:isoff-live:2011">
<Period
id="1"
duration="PT14M48S">
<BaseURL>dash/</BaseURL>
<AdaptationSet
id="1"
group="1"
contentType="audio"
segmentAlignment="true"
audioSamplingRate="48000"
mimeType="audio/mp4"
codecs="mp4a.40.2"
startWithSAP="1">
<AudioChannelConfiguration
schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011"
value="2" />
<Role schemeIdUri="urn:mpeg:dash:role:2011" value="main" />
<SegmentTemplate
timescale="48000"
initialization="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$.dash"
media="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$-$Time$.dash">
<SegmentTimeline>
<S t="0" d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="96256" r="2" />
<S d="95232" />
<S d="3584" />
</SegmentTimeline>
</SegmentTemplate>
<Representation
id="audio=128001"
bandwidth="128001">
</Representation>
</AdaptationSet>
<AdaptationSet
id="2"
group="3"
contentType="text"
lang="en"
mimeType="application/mp4"
codecs="stpp"
startWithSAP="1">
<Role schemeIdUri="urn:mpeg:dash:role:2011" value="subtitle" />
<SegmentTemplate
timescale="1000"
initialization="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$.dash"
media="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$-$Time$.dash">
<SegmentTimeline>
<S t="0" d="60000" r="9" />
<S d="24000" />
</SegmentTimeline>
</SegmentTemplate>
<Representation
id="textstream_eng=1000"
bandwidth="1000">
</Representation>
</AdaptationSet>
<AdaptationSet
id="3"
group="2"
contentType="video"
par="960:409"
minBandwidth="100000"
maxBandwidth="4482000"
maxWidth="1689"
maxHeight="720"
segmentAlignment="true"
mimeType="video/mp4"
codecs="avc1.4D401F"
startWithSAP="1">
<Role schemeIdUri="urn:mpeg:dash:role:2011" value="main" />
<SegmentTemplate
timescale="12288"
initialization="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$.dash"
media="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$-$Time$.dash">
<SegmentTimeline>
<S t="0" d="24576" r="443" />
</SegmentTimeline>
</SegmentTemplate>
<Representation
id="video=100000"
bandwidth="100000"
width="336"
height="144"
sar="2880:2863"
scanType="progressive">
</Representation>
<Representation
id="video=326000"
bandwidth="326000"
width="562"
height="240"
sar="115200:114929"
scanType="progressive">
</Representation>
<Representation
id="video=698000"
bandwidth="698000"
width="844"
height="360"
sar="86400:86299"
scanType="progressive">
</Representation>
<Representation
id="video=1493000"
bandwidth="1493000"
width="1126"
height="480"
sar="230400:230267"
scanType="progressive">
</Representation>
<Representation
id="video=4482000"
bandwidth="4482000"
width="1688"
height="720"
sar="86400:86299"
scanType="progressive">
</Representation>
</AdaptationSet>
</Period>
</MPD>

32
test/testdata/mpd/url_and_range.mpd vendored Normal file
View File

@ -0,0 +1,32 @@
<?xml version="1.0" ?>
<MPD xmlns="urn:mpeg:dash:schema:mpd:2011" profiles="urn:mpeg:dash:profile:isoff-live:2011" minBufferTime="PT10.01S" mediaPresentationDuration="PT30.097S" type="static">
<!-- Created with Bento4 mp4-dash.py, VERSION=2.0.0-639 -->
<Period>
<!-- Video -->
<AdaptationSet mimeType="video/mp4" segmentAlignment="true" startWithSAP="1" maxWidth="768" maxHeight="432">
<Representation id="video-avc1" codecs="avc1.4D401E" width="768" height="432" scanType="progressive" frameRate="30000/1001" bandwidth="699597">
<SegmentList timescale="1000" duration="10010">
<Initialization sourceURL="video-frag.mp4" range="36-746"/>
<SegmentURL media="video-frag.mp4" mediaRange="747-876117"/>
<SegmentURL media="video-frag.mp4" mediaRange="876118-1466913"/>
<SegmentURL media="video-frag.mp4" mediaRange="1466914-1953954"/>
<SegmentURL media="video-frag.mp4" mediaRange="1953955-1994652"/>
</SegmentList>
</Representation>
</AdaptationSet>
<!-- Audio -->
<AdaptationSet mimeType="audio/mp4" startWithSAP="1" segmentAlignment="true">
<Representation id="audio-und-mp4a.40.2" codecs="mp4a.40.2" bandwidth="98808" audioSamplingRate="48000">
<AudioChannelConfiguration schemeIdUri="urn:mpeg:mpegB:cicp:ChannelConfiguration" value="2"/>
<SegmentList timescale="1000" duration="10010">
<Initialization sourceURL="audio-frag.mp4" range="32-623"/>
<SegmentURL media="audio-frag.mp4" mediaRange="624-124199"/>
<SegmentURL media="audio-frag.mp4" mediaRange="124200-250303"/>
<SegmentURL media="audio-frag.mp4" mediaRange="250304-374365"/>
<SegmentURL media="audio-frag.mp4" mediaRange="374366-374836"/>
</SegmentList>
</Representation>
</AdaptationSet>
</Period>
</MPD>

View File

@ -183,6 +183,8 @@ class InfoExtractor(object):
fragment_base_url
* "duration" (optional, int or float)
* "filesize" (optional, int)
* "range" (optional, str of the form "start-end"
to use in HTTP Range header)
* preference Order number of this format. If this field is
present and not None, the formats get sorted
by this field, regardless of all other values.
@ -2296,15 +2298,27 @@ class InfoExtractor(object):
def extract_Initialization(source):
initialization = source.find(_add_ns('Initialization'))
if initialization is not None:
ms_info['initialization_url'] = initialization.attrib['sourceURL']
ms_info['initialization_url'] = initialization.get('sourceURL') or base_url
initialization_url_range = initialization.get('range')
if initialization_url_range:
ms_info['initialization_url_range'] = initialization_url_range
segment_list = element.find(_add_ns('SegmentList'))
if segment_list is not None:
extract_common(segment_list)
extract_Initialization(segment_list)
segment_urls_e = segment_list.findall(_add_ns('SegmentURL'))
if segment_urls_e:
ms_info['segment_urls'] = [segment.attrib['media'] for segment in segment_urls_e]
segment_urls = traverse_obj(segment_urls_e, (
Ellipsis, T(lambda e: e.attrib), 'media'))
if segment_urls:
ms_info['segment_urls'] = segment_urls
segment_urls_range = traverse_obj(segment_urls_e, (
Ellipsis, T(lambda e: e.attrib), 'mediaRange',
T(lambda r: re.findall(r'^\d+-\d+$', r)), 0))
if segment_urls_range:
ms_info['segment_urls_range'] = segment_urls_range
if not segment_urls:
ms_info['segment_urls'] = [base_url for _ in segment_urls_range]
else:
segment_template = element.find(_add_ns('SegmentTemplate'))
if segment_template is not None:
@ -2443,6 +2457,11 @@ class InfoExtractor(object):
def location_key(location):
return 'url' if re.match(r'^https?://', location) else 'path'
def calc_segment_duration():
return float_or_none(
representation_ms_info['segment_duration'],
representation_ms_info['timescale']) if 'segment_duration' in representation_ms_info else None
if 'segment_urls' not in representation_ms_info and 'media' in representation_ms_info:
media_template = prepare_template('media', ('Number', 'Bandwidth', 'Time'))
@ -2512,28 +2531,37 @@ class InfoExtractor(object):
'duration': duration,
})
segment_index += 1
representation_ms_info['fragments'] = fragments
elif 'segment_urls' in representation_ms_info:
elif 'segment_urls_range' in representation_ms_info:
# Segment URLs with mediaRange
# Example: https://kinescope.io/200615537/master.mpd
# https://github.com/ytdl-org/youtube-dl/issues/30235
# or any mpd generated with Bento4 `mp4dash --no-split --use-segment-list`
segment_duration = calc_segment_duration()
for segment_url, segment_url_range in zip(
representation_ms_info['segment_urls'], representation_ms_info['segment_urls_range']):
fragments.append({
location_key(segment_url): segment_url,
'range': segment_url_range,
'duration': segment_duration,
})
else:
# Segment URLs with no SegmentTimeline
# Example: https://www.seznam.cz/zpravy/clanek/cesko-zasahne-vitr-o-sile-vichrice-muze-byt-i-zivotu-nebezpecny-39091
# https://github.com/ytdl-org/youtube-dl/pull/14844
fragments = []
segment_duration = float_or_none(
representation_ms_info['segment_duration'],
representation_ms_info['timescale']) if 'segment_duration' in representation_ms_info else None
segment_duration = calc_segment_duration()
for segment_url in representation_ms_info['segment_urls']:
fragment = {
fragments.append({
location_key(segment_url): segment_url,
}
if segment_duration:
fragment['duration'] = segment_duration
fragments.append(fragment)
'duration': segment_duration,
})
representation_ms_info['fragments'] = fragments
# If there is a fragments key available then we correctly recognized fragmented media.
# Otherwise we will assume unfragmented media with direct access. Technically, such
# assumption is not necessarily correct since we may simply have no support for
# some forms of fragmented media renditions yet, but for now we'll use this fallback.
if 'fragments' in representation_ms_info:
base_url = representation_ms_info['base_url']
f.update({
# NB: mpd_url may be empty when MPD manifest is parsed from a string
'url': mpd_url or base_url,
@ -2541,16 +2569,30 @@ class InfoExtractor(object):
'fragments': [],
'protocol': 'http_dash_segments',
})
if 'initialization_url' in representation_ms_info:
if 'initialization_url' in representation_ms_info and 'initialization_url_range' in representation_ms_info:
# Initialization URL with range (accompanied by Segment URLs with mediaRange above)
# https://github.com/ytdl-org/youtube-dl/issues/30235
initialization_url = representation_ms_info['initialization_url']
f['fragments'].append({
location_key(initialization_url): initialization_url,
'range': representation_ms_info['initialization_url_range'],
})
elif 'initialization_url' in representation_ms_info:
initialization_url = representation_ms_info['initialization_url']
if not f.get('url'):
f['url'] = initialization_url
f['fragments'].append({location_key(initialization_url): initialization_url})
elif 'initialization_url_range' in representation_ms_info:
# no Initialization URL but range (accompanied by no Segment URLs but mediaRange above)
# https://github.com/ytdl-org/youtube-dl/issues/27575
f['fragments'].append({
location_key(base_url): base_url,
'range': representation_ms_info['initialization_url_range'],
})
f['fragments'].extend(representation_ms_info['fragments'])
else:
# Assuming direct URL to unfragmented media.
f['url'] = base_url
formats.append(f)
if not period_duration:
period_duration = sum(traverse_obj(representation_ms_info, (
'fragments', Ellipsis, 'duration', T(float_or_none))))
else:
# Assuming direct URL to unfragmented media.
f['url'] = representation_ms_info['base_url']