mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 18:41:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

[extractor/common] Add support for $ in SegmentTemplate in MPD manifests

Browse source
This commit is contained in:
Sergey M․ 2016-07-24 10:27:16 +07:00
parent 111de00289
commit f094834857
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 50 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

49
youtube_dl/extractor/common.py
View file

@ -1481,6 +1481,13 @@ def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnot
compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict) compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict)
def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}): def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
"""
Parse formats from MPD manifest.
References:
1. MPEG-DASH Standard, ISO/IEC 23009-1:2014(E),
http://standards.iso.org/ittf/PubliclyAvailableStandards/c065274_ISO_IEC_23009-1_2014.zip
2. https://en.wikipedia.org/wiki/Dynamic_Adaptive_Streaming_over_HTTP
"""
if mpd_doc.get('type') == 'dynamic': if mpd_doc.get('type') == 'dynamic':
return [] return []
@ -1513,8 +1520,16 @@ def extract_multisegment_info(element, ms_parent_info):
s_e = segment_timeline.findall(_add_ns('S')) s_e = segment_timeline.findall(_add_ns('S'))
if s_e: if s_e:
ms_info['total_number'] = 0 ms_info['total_number'] = 0
ms_info['s'] = []
for s in s_e: for s in s_e:
ms_info['total_number'] += 1 + int(s.get('r', '0')) r = int(s.get('r', 0))
ms_info['total_number'] += 1 + r
ms_info['s'].append({
't': int(s.get('t', 0)),
# @d is mandatory (see [1, 5.3.9.6.2, Table 17, page 60])
'd': int(s.attrib['d']),
'r': r,
})
else: else:
timescale = segment_template.get('timescale') timescale = segment_template.get('timescale')
if timescale: if timescale:
@ -1551,7 +1566,7 @@ def extract_multisegment_info(element, ms_parent_info):
continue continue
representation_attrib = adaptation_set.attrib.copy() representation_attrib = adaptation_set.attrib.copy()
representation_attrib.update(representation.attrib) representation_attrib.update(representation.attrib)
# According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory # According to [1, 5.3.7.2, Table 9, page 41], @mimeType is mandatory
mime_type = representation_attrib['mimeType'] mime_type = representation_attrib['mimeType']
content_type = mime_type.split('/')[0] content_type = mime_type.split('/')[0]
if content_type == 'text': if content_type == 'text':
@ -1595,16 +1610,40 @@ def extract_multisegment_info(element, ms_parent_info):
representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration)) representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
media_template = representation_ms_info['media_template'] media_template = representation_ms_info['media_template']
media_template = media_template.replace('$RepresentationID$', representation_id) media_template = media_template.replace('$RepresentationID$', representation_id)
media_template = re.sub(r'\$(Number|Bandwidth)\$', r'%(\1)d', media_template) media_template = re.sub(r'\$(Number|Bandwidth|Time)\$', r'%(\1)d', media_template)
media_template = re.sub(r'\$(Number|Bandwidth)%([^$]+)\$', r'%(\1)\2', media_template) media_template = re.sub(r'\$(Number|Bandwidth|Time)%([^$]+)\$', r'%(\1)\2', media_template)
media_template.replace('$$', '$') media_template.replace('$$', '$')
# As per [1, 5.3.9.4.4, Table 16, page 55] $Number$ and $Time$
# can't be used at the same time
if '%(Number' in media_template:
representation_ms_info['segment_urls'] = [ representation_ms_info['segment_urls'] = [
media_template % { media_template % {
'Number': segment_number, 'Number': segment_number,
'Bandwidth': representation_attrib.get('bandwidth')} 'Bandwidth': representation_attrib.get('bandwidth'),
}
for segment_number in range( for segment_number in range(
representation_ms_info['start_number'], representation_ms_info['start_number'],
representation_ms_info['total_number'] + representation_ms_info['start_number'])] representation_ms_info['total_number'] + representation_ms_info['start_number'])]
else:
representation_ms_info['segment_urls'] = []
segment_time = 0
def add_segment_url():
representation_ms_info['segment_urls'].append(
media_template % {
'Time': segment_time,
'Bandwidth': representation_attrib.get('bandwidth'),
}
)
for num, s in enumerate(representation_ms_info['s']):
segment_time = s.get('t') or segment_time
add_segment_url()
for r in range(s.get('r', 0)):
segment_time += s['d']
add_segment_url()
segment_time += s['d']
if 'segment_urls' in representation_ms_info: if 'segment_urls' in representation_ms_info:
f.update({ f.update({
'segment_urls': representation_ms_info['segment_urls'], 'segment_urls': representation_ms_info['segment_urls'],