midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[mediaset] extract unprotected M3U and MPD manifests(closes #17204)

Browse source
This commit is contained in:
Remita Amine 2019-11-04 02:01:01 +01:00
parent a6e6673e82
commit ef382405c6
1 changed files with 8 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
youtube_dl/extractor/mediaset.py
View file

@ -62,7 +62,6 @@ class MediasetIE(ThePlatformBaseIE):
'uploader': 'Canale 5', 'uploader': 'Canale 5',
'uploader_id': 'C5', 'uploader_id': 'C5',
}, },
'expected_warnings': ['HTTP Error 403: Forbidden'],
}, { }, {
# clip # clip
'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680', 'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
@ -109,6 +108,11 @@ class MediasetIE(ThePlatformBaseIE):
entries.append(embed_url) entries.append(embed_url)
return entries return entries
def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
for video in smil.findall(self._xpath_ns('.//video', namespace)):
video.attrib['src'] = re.sub(r'(https?://vod05)t(-mediaset-it\.akamaized\.net/.+?.mpd)\?.+', r'\1\2', video.attrib['src'])
return super()._parse_smil_formats(smil, smil_url, video_id, namespace, f4m_params, transform_rtmp_url)
def _real_extract(self, url): def _real_extract(self, url):
guid = self._match_id(url) guid = self._match_id(url)
tp_path = 'PR1GhC/media/guid/2702976343/' + guid tp_path = 'PR1GhC/media/guid/2702976343/' + guid
@ -118,14 +122,15 @@ class MediasetIE(ThePlatformBaseIE):
subtitles = {} subtitles = {}
first_e = None first_e = None
for asset_type in ('SD', 'HD'): for asset_type in ('SD', 'HD'):
for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'): # TODO: fixup ISM+none manifest URLs
for f in ('MPEG4', 'MPEG-DASH+none', 'M3U+none'):
try: try:
tp_formats, tp_subtitles = self._extract_theplatform_smil( tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), { update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
'mbr': 'true', 'mbr': 'true',
'formats': f, 'formats': f,
'assetTypes': asset_type, 'assetTypes': asset_type,
}), guid, 'Downloading %s %s SMIL data' % (f, asset_type)) }), guid, 'Downloading %s %s SMIL data' % (f.split('+')[0], asset_type))
except ExtractorError as e: except ExtractorError as e:
if not first_e: if not first_e:
first_e = e first_e = e