)
default_ns = 'http://www.w3.org/2005/SMIL21/Language'
_x = lambda p: xpath_with_ns(p, {'smil': default_ns})
)
default_ns = 'http://www.w3.org/2005/SMIL21/Language'
_x = lambda p: xpath_with_ns(p, {'smil': default_ns})
def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'):
def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'):
- meta = self._download_xml(smil_url, video_id, note=note)
- try:
- error_msg = next(
- n.attrib['abstract']
- for n in meta.findall(_x('.//smil:ref'))
- if n.attrib.get('title') == 'Geographic Restriction' or n.attrib.get('title') == 'Expired')
- except StopIteration:
- pass
- else:
- raise ExtractorError(error_msg, expected=True)
+ meta = self._download_xml(smil_url, video_id, note=note, query={'format': 'SMIL'})
+ error_element = find_xpath_attr(meta, _x('.//smil:ref'), 'src')
+ if error_element is not None and error_element.attrib['src'].startswith(
+ 'http://link.theplatform.com/s/errorFiles/Unavailable.'):
+ raise ExtractorError(error_element.attrib['abstract'], expected=True)
meta, smil_url, video_id, namespace=default_ns,
# the parameters are from syfy.com, other sites may use others,
# they also work for nbc.com
f4m_params={'g': 'UXWGVKRWHFSP', 'hdcore': '3.0.3'},
transform_rtmp_url=lambda streamer, src: (streamer, 'mp4:' + src))
meta, smil_url, video_id, namespace=default_ns,
# the parameters are from syfy.com, other sites may use others,
# they also work for nbc.com
f4m_params={'g': 'UXWGVKRWHFSP', 'hdcore': '3.0.3'},
transform_rtmp_url=lambda streamer, src: (streamer, 'mp4:' + src))
- for _format in formats:
- ext = determine_ext(_format['url'])
- if ext == 'once':
- _format['ext'] = 'mp4'
-
- self._sort_formats(formats)
+ formats = []
+ for _format in smil_formats:
+ if OnceIE.suitable(_format['url']):
+ formats.extend(self._extract_once_formats(_format['url']))
+ else:
+ formats.append(_format)
for caption in captions:
lang, src, mime = caption.get('lang', 'en'), caption.get('src'), caption.get('type')
subtitles[lang] = [{
for caption in captions:
lang, src, mime = caption.get('lang', 'en'), caption.get('src'), caption.get('type')
subtitles[lang] = [{
'description': info['description'],
'thumbnail': info['defaultThumbnailUrl'],
'duration': int_or_none(info.get('duration'), 1000),
'description': info['description'],
'thumbnail': info['defaultThumbnailUrl'],
'duration': int_or_none(info.get('duration'), 1000),
}
class ThePlatformIE(ThePlatformBaseIE):
_VALID_URL = r'''(?x)
(?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
}
class ThePlatformIE(ThePlatformBaseIE):
_VALID_URL = r'''(?x)
(?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
'title': 'Blackberry\'s big, bold Z30',
'description': 'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.',
'duration': 247,
'title': 'Blackberry\'s big, bold Z30',
'description': 'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.',
'duration': 247,
'ext': 'flv',
'description': 'md5:ac330c9258c04f9d7512cf26b9595409',
'title': 'Tesla Model S: A second step towards a cleaner motoring future',
'ext': 'flv',
'description': 'md5:ac330c9258c04f9d7512cf26b9595409',
'title': 'Tesla Model S: A second step towards a cleaner motoring future',
'ext': 'mp4',
'description': 'md5:644ad9188d655b742f942bf2e06b002d',
'title': 'HIGHLIGHTS: USA bag first ever series Cup win',
'ext': 'mp4',
'description': 'md5:644ad9188d655b742f942bf2e06b002d',
'title': 'HIGHLIGHTS: USA bag first ever series Cup win',
}
}, {
'url': 'http://player.theplatform.com/p/NnzsPC/widget/select/media/4Y0TlYUr_ZT7',
'only_matching': True,
}, {
'url': 'http://player.theplatform.com/p/2E2eJC/nbcNewsOffsite?guid=tdy_or_siri_150701',
}
}, {
'url': 'http://player.theplatform.com/p/NnzsPC/widget/select/media/4Y0TlYUr_ZT7',
'only_matching': True,
}, {
'url': 'http://player.theplatform.com/p/2E2eJC/nbcNewsOffsite?guid=tdy_or_siri_150701',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1435752600,
'upload_date': '20150701',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1435752600,
'upload_date': '20150701',
- 'categories': ['Today/Shows/Orange Room', 'Today/Sections/Money', 'Today/Topics/Tech', "Today/Topics/Editor's picks"],
+ 'uploader': 'NBCU-NEWS',
- relative_path = url.split('http://link.theplatform.com/s/')[1].split('?')[0]
- clear_text = hex_to_str(flags + expiration_date + str_to_hex(relative_path))
+ relative_path = re.match(r'https?://link.theplatform.com/s/([^?]+)', url).group(1)
+ clear_text = hex_to_bytes(flags + expiration_date + str_to_hex(relative_path))
checksum = hmac.new(sig_key.encode('ascii'), clear_text, hashlib.sha1).hexdigest()
sig = flags + expiration_date + checksum + str_to_hex(sig_secret)
return '%s&sig=%s' % (url, sig)
checksum = hmac.new(sig_key.encode('ascii'), clear_text, hashlib.sha1).hexdigest()
sig = flags + expiration_date + checksum + str_to_hex(sig_secret)
return '%s&sig=%s' % (url, sig)
webpage, 'smil url', group='url')
path = self._search_regex(
r'link\.theplatform\.com/s/((?:[^/?#&]+/)+[^/?#&]+)', smil_url, 'path')
webpage, 'smil url', group='url')
path = self._search_regex(
r'link\.theplatform\.com/s/((?:[^/?#&]+/)+[^/?#&]+)', smil_url, 'path')
elif mobj.group('config'):
config_url = url + '&form=json'
config_url = config_url.replace('swf/', 'config/')
elif mobj.group('config'):
config_url = url + '&form=json'
config_url = config_url.replace('swf/', 'config/')
sig = smuggled_data.get('sig')
if sig:
smil_url = self._sign_url(smil_url, sig['key'], sig['secret'])
formats, subtitles = self._extract_theplatform_smil(smil_url, video_id)
sig = smuggled_data.get('sig')
if sig:
smil_url = self._sign_url(smil_url, sig['key'], sig['secret'])
formats, subtitles = self._extract_theplatform_smil(smil_url, video_id)
ret = self.get_metadata(path, video_id)
combined_subtitles = self._merge_subtitles(ret.get('subtitles', {}), subtitles)
ret = self.get_metadata(path, video_id)
combined_subtitles = self._merge_subtitles(ret.get('subtitles', {}), subtitles)
_TEST = {
# From http://player.theplatform.com/p/7wvmTC/MSNBCEmbeddedOffSite?guid=n_hardball_5biden_140207
'url': 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207',
_TEST = {
# From http://player.theplatform.com/p/7wvmTC/MSNBCEmbeddedOffSite?guid=n_hardball_5biden_140207
'url': 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207',
- smil_url = item['plfile$url'] + '&format=SMIL&Tracking=true&Embedded=true&formats=MPEG4,F4M'
- cur_video_id = url_basename(smil_url)
+ smil_url = item['plfile$url'] + '&mbr=true'
+ cur_video_id = ThePlatformIE._match_id(smil_url)
if first_video_id is None:
first_video_id = cur_video_id
duration = float_or_none(item.get('plfile$duration'))
if first_video_id is None:
first_video_id = cur_video_id
duration = float_or_none(item.get('plfile$duration'))