MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 14:59:29 +01:00
Code Issues Projects Releases Wiki Activity

[nbc] Fix ThePlatform embedded videos

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-10-27 01:14:17 +01:00
parent 15956b5aa1
commit 10e3d73472
2 changed files with 22 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
youtube_dl/extractor/nbc.py
View File

@ -26,8 +26,7 @@ class NBCIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url') theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url')
if theplatform_url.startswith('//'): if theplatform_url.startswith('//'):
@ -57,7 +56,7 @@ class NBCNewsIE(InfoExtractor):
'md5': 'b2421750c9f260783721d898f4c42063', 'md5': 'b2421750c9f260783721d898f4c42063',
'info_dict': { 'info_dict': {
'id': 'I1wpAI_zmhsQ', 'id': 'I1wpAI_zmhsQ',
'ext': 'flv', 'ext': 'mp4',
'title': 'How Twitter Reacted To The Snowden Interview', 'title': 'How Twitter Reacted To The Snowden Interview',
'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64', 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
}, },
@ -97,6 +96,8 @@ def _real_extract(self, url):
] ]
for base_url in base_urls: for base_url in base_urls:
if not base_url:
continue
playlist_url = base_url + '?form=MPXNBCNewsAPI' playlist_url = base_url + '?form=MPXNBCNewsAPI'
all_videos = self._download_json(playlist_url, title)['videos'] all_videos = self._download_json(playlist_url, title)['videos']

34
youtube_dl/extractor/theplatform.py
View File

@ -6,6 +6,7 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_str, compat_str,
determine_ext,
ExtractorError, ExtractorError,
xpath_with_ns, xpath_with_ns,
) )
@ -34,10 +35,21 @@ class ThePlatformIE(InfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
} }
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
if mobj.group('config'):
config_url = url+ '&form=json'
config_url = config_url.replace('swf/', 'config/')
config_url = config_url.replace('onsite/', 'onsite/config/')
config = self._download_json(config_url, video_id, 'Downloading config')
smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
else:
smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
'format=smil&mbr=true'.format(video_id))
def _get_info(self, video_id, smil_url):
meta = self._download_xml(smil_url, video_id) meta = self._download_xml(smil_url, video_id)
try: try:
error_msg = next( error_msg = next(
n.attrib['abstract'] n.attrib['abstract']
@ -89,10 +101,14 @@ def _get_info(self, video_id, smil_url):
for f in switch.findall(_x('smil:video')): for f in switch.findall(_x('smil:video')):
attr = f.attrib attr = f.attrib
vbr = int(attr['system-bitrate']) // 1000 vbr = int(attr['system-bitrate']) // 1000
ext = determine_ext(attr['src'])
if ext == 'once':
ext = 'mp4'
formats.append({ formats.append({
'format_id': compat_str(vbr), 'format_id': compat_str(vbr),
'url': attr['src'], 'url': attr['src'],
'vbr': vbr, 'vbr': vbr,
'ext': ext,
}) })
self._sort_formats(formats) self._sort_formats(formats)
@ -104,17 +120,3 @@ def _get_info(self, video_id, smil_url):
'thumbnail': info['defaultThumbnailUrl'], 'thumbnail': info['defaultThumbnailUrl'],
'duration': info['duration']//1000, 'duration': info['duration']//1000,
} }
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
if mobj.group('config'):
config_url = url+ '&form=json'
config_url = config_url.replace('swf/', 'config/')
config_url = config_url.replace('onsite/', 'onsite/config/')
config = self._download_json(config_url, video_id, 'Downloading config')
smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
else:
smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
'format=smil&mbr=true'.format(video_id))
return self._get_info(video_id, smil_url)