R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

return mpd_url for dash segmented formats(#8704)

Browse Source 
mpd_url construction rules can be found in Annex C section 4 in ISO/IEC 23009-1

- separate downloader specific params from other info_dict keys
- the mpd_url can be used with external programs like MP4Box and VLC 3
- it's needed to be passed to dash downloader to support live stream download
This commit is contained in:
remitamine 2016-03-13 11:05:38 +01:00
parent a42dfa629e
commit 9d81c7d78c
3 changed files with 30 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
youtube_dl/downloader/dash.py
View File

@ -18,9 +18,10 @@ class DashSegmentsFD(FragmentFD):
FD_NAME = 'dashsegments'
def real_download(self, filename, info_dict):
base_url = info_dict['url']
segment_urls = [info_dict['segment_urls'][0]] if self.params.get('test', False) else info_dict['segment_urls']
initialization_url = info_dict.get('initialization_url')
params = info_dict['_downloader_params']
base_url = params['base_url']
segment_urls = [params['segment_urls'][0]] if self.params.get('test', False) else params['segment_urls']
initialization_url = params.get('initialization_url')
ctx = {
'filename': filename,

33
youtube_dl/extractor/common.py
View File

@ -23,6 +23,7 @@ from ..compat import (
compat_urllib_error,
compat_urllib_parse,
compat_urlparse,
compat_urllib_parse_urlparse,
)
from ..utils import (
NO_DEFAULT,
@ -1386,12 +1387,11 @@ class InfoExtractor(object):
if res is False:
return []
mpd, urlh = res
mpd_base_url = re.match(r'https?://.+/', urlh.geturl()).group()
return self._parse_mpd_formats(
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, urlh.geturl(), 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_url='', formats_dict={}):
if mpd_doc.get('type') == 'dynamic':
return []
@ -1445,6 +1445,10 @@ class InfoExtractor(object):
ms_info['initialization_url'] = initialization.attrib['sourceURL']
return ms_info
mpd_base_url = mpd_url.rpartition('/')[0]
parsed_mpd_url = None
if mpd_base_url:
parsed_mpd_url = compat_urllib_parse_urlparse(mpd_url)
mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
formats = []
for period in mpd_doc.findall(_add_ns('Period')):
@ -1509,18 +1513,31 @@ class InfoExtractor(object):
media_template = re.sub(r'\$(Number|Bandwidth)(?:%(0\d+)d)?\$', r'%(\1)\2d', media_template)
media_template.replace('$$', '$')
representation_ms_info['segment_urls'] = [media_template % {'Number': segment_number, 'Bandwidth': representation_attrib.get('bandwidth')} for segment_number in range(representation_ms_info['start_number'], representation_ms_info['total_number'] + representation_ms_info['start_number'])]
if 'segment_urls' in representation_ms_info:
segment_urls = representation_ms_info.get('segment_urls')
if segment_urls:
fragment_mpd_url = segment_urls[0]
if parsed_mpd_url:
fragment_parts = ((period, 'id', 'period'), (adaptation_set, 'id', 'as'), (adaptation_set, 'group', 'track'))
params = {}
for ele, attr, frag_attr in fragment_parts:
frag_val = ele.attrib.get(attr)
if frag_val:
params[frag_attr] = frag_val
fragment = compat_urllib_parse.urlencode(params)
fragment_mpd_url = parsed_mpd_url._replace(fragment=fragment).geturl()
f.update({
'segment_urls': representation_ms_info['segment_urls'],
'url': fragment_mpd_url,
'_downloader_params': {
'segment_urls': segment_urls,
'base_url': base_url,
},
'protocol': 'http_dash_segments',
})
if 'initialization_url' in representation_ms_info:
initialization_url = representation_ms_info['initialization_url'].replace('$RepresentationID$', representation_id)
f.update({
f['_downloader_params'].update({
'initialization_url': initialization_url,
})
if not f.get('url'):
f['url'] = initialization_url
try:
existing_format = next(
fo for fo in formats

2
youtube_dl/extractor/generic.py
View File

@ -1320,7 +1320,7 @@ class GenericIE(InfoExtractor):
return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'] = self._parse_mpd_formats(
doc, video_id, mpd_base_url=url.rpartition('/')[0])
doc, video_id, mpd_url=url)
return info_dict
elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)