Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-04 08:29:57 +01:00
Code Issues Packages Projects Releases Wiki Activity

[nbcolympics] Update extractor for 2020 olympics (#621)

Browse Source 
Fixes: https://github.com/yt-dlp/yt-dlp/issues/617#issuecomment-891834323

Authored by: wesnm
This commit is contained in:
Wes 2021-08-03 23:19:44 -05:00 committed by GitHub
parent 888299e6ca
commit 3e376d183e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 13 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
yt_dlp/extractor/nbc.py
View File

@ -12,6 +12,7 @@
int_or_none, int_or_none,
parse_age_limit, parse_age_limit,
parse_duration, parse_duration,
RegexNotFoundError,
smuggle_url, smuggle_url,
try_get, try_get,
unified_timestamp, unified_timestamp,
@ -460,7 +461,7 @@ def _real_extract(self, url):
class NBCOlympicsIE(InfoExtractor): class NBCOlympicsIE(InfoExtractor):
IE_NAME = 'nbcolympics' IE_NAME = 'nbcolympics'
_VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)' _VALID_URL = r'https?://www\.nbcolympics\.com/videos?/(?P<id>[0-9a-z-]+)'
_TEST = { _TEST = {
# Geo-restricted to US # Geo-restricted to US
@ -483,13 +484,18 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
drupal_settings = self._parse_json(self._search_regex( try:
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', drupal_settings = self._parse_json(self._search_regex(
webpage, 'drupal settings'), display_id) r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
webpage, 'drupal settings'), display_id)
iframe_url = drupal_settings['vod']['iframe_url'] iframe_url = drupal_settings['vod']['iframe_url']
theplatform_url = iframe_url.replace( theplatform_url = iframe_url.replace(
'vplayer.nbcolympics.com', 'player.theplatform.com') 'vplayer.nbcolympics.com', 'player.theplatform.com')
except RegexNotFoundError:
theplatform_url = self._search_regex(
r"([\"'])embedUrl\1: *([\"'])(?P<embedUrl>.+)\2",
webpage, 'embedding URL', group="embedUrl")
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',