etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00
Code Issues Projects Releases Wiki Activity

[natgeo] extract m3u8 formats(closes #10959)

Browse source
This commit is contained in:
Remita Amine 2016-10-19 19:38:21 +01:00
parent 05b7996cab
commit 02af6ec707
1 changed files with 25 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
youtube_dl/extractor/nationalgeographic.py
View file

@ -4,6 +4,7 @@
from .common import InfoExtractor from .common import InfoExtractor
from .adobepass import AdobePassIE from .adobepass import AdobePassIE
from .theplatform import ThePlatformIE
from ..utils import ( from ..utils import (
smuggle_url, smuggle_url,
url_basename, url_basename,
@ -65,7 +66,7 @@ def _real_extract(self, url):
} }
class NationalGeographicIE(AdobePassIE): class NationalGeographicIE(ThePlatformIE, AdobePassIE):
IE_NAME = 'natgeo' IE_NAME = 'natgeo'
_VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/(?:videos|episodes)/(?P<id>[^/?]+)' _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/(?:videos|episodes)/(?P<id>[^/?]+)'
@ -110,25 +111,39 @@ def _real_extract(self, url):
release_url = self._search_regex( release_url = self._search_regex(
r'video_auth_playlist_url\s*=\s*"([^"]+)"', r'video_auth_playlist_url\s*=\s*"([^"]+)"',
webpage, 'release url') webpage, 'release url')
theplatform_path = self._search_regex(r'https?://link.theplatform.com/s/([^?]+)', release_url, 'theplatform path')
video_id = theplatform_path.split('/')[-1]
query = { query = {
'mbr': 'true', 'mbr': 'true',
'switch': 'http',
} }
is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False) is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False)
if is_auth == 'auth': if is_auth == 'auth':
auth_resource_id = self._search_regex( auth_resource_id = self._search_regex(
r"video_auth_resourceId\s*=\s*'([^']+)'", r"video_auth_resourceId\s*=\s*'([^']+)'",
webpage, 'auth resource id') webpage, 'auth resource id')
query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id) query['auth'] = self._extract_mvpd_auth(url, video_id, 'natgeo', auth_resource_id)
return { formats = []
'_type': 'url_transparent', subtitles = {}
'ie_key': 'ThePlatform', for key, value in (('switch', 'http'), ('manifest', 'm3u')):
'url': smuggle_url( tp_query = query.copy()
update_url_query(release_url, query), tp_query.update({
{'force_smil_url': True}), key: value,
})
tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query(release_url, tp_query), video_id, 'Downloading %s SMIL data' % value)
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
self._sort_formats(formats)
info = self._extract_theplatform_metadata(theplatform_path, display_id)
info.update({
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'display_id': display_id, 'display_id': display_id,
} })
return info
class NationalGeographicEpisodeGuideIE(InfoExtractor): class NationalGeographicEpisodeGuideIE(InfoExtractor):