MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-03 10:14:42 +01:00
Code Issues Projects Releases Wiki Activity

[sbs] Simplify

Browse Source
This commit is contained in:
Sergey M․ 2015-07-18 02:43:18 +06:00
parent dac4d5be12
commit 3c283a381e
1 changed files with 16 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
youtube_dl/extractor/sbs.py
View File

@ -2,12 +2,11 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import remove_end
class SBSIE(InfoExtractor): class SBSIE(InfoExtractor):
IE_DESC = 'sbs.com.au' IE_DESC = 'sbs.com.au'
_VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/(?:single/)?(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand|news)/video/(?:single/)?(?P<id>[0-9]+)'
_TESTS = [{ _TESTS = [{
# Original URL is handled by the generic IE which finds the iframe: # Original URL is handled by the generic IE which finds the iframe:
@ -17,43 +16,36 @@ class SBSIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '320403011771', 'id': '320403011771',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Dingo Conservation', 'title': 'Dingo Conservation (The Feed)',
'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction', 'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
'thumbnail': 're:http://.*\.jpg', 'thumbnail': 're:http://.*\.jpg',
'duration': 308,
}, },
'add_ies': ['generic'],
}, { }, {
'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed', 'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
'only_matching': True, 'only_matching': True,
}, {
'url': 'http://www.sbs.com.au/news/video/471395907773/The-Feed-July-9',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
# the video is in the following iframe webpage = self._download_webpage(
iframe_url = 'http://www.sbs.com.au/ondemand/video/single/' + video_id + '?context=web' 'http://www.sbs.com.au/ondemand/video/single/%s?context=web' % video_id, video_id)
webpage = self._download_webpage(iframe_url, video_id)
player_params = self._search_regex( player_params = self._parse_json(
r'(?s)(playerParams.+?releaseUrls.+?\n)', self._search_regex(
webpage, 'playerParams') r'(?s)var\s+playerParams\s*=\s*({.+?});', webpage, 'playerParams'),
player_params_js = self._search_regex( video_id)
r'({.*})',
player_params, 'player_param_js')
player_params_json = self._parse_json(player_params_js, video_id) urls = player_params['releaseUrls']
theplatform_url = (urls.get('progressive') or urls.get('standard') or
theplatform_url = player_params_json.get('releaseUrls')['progressive'] or player_params_json.get('releaseUrls')['standard'] urls.get('html') or player_params['relatedItemsURL'])
title = remove_end(self._og_search_title(webpage, default=video_id, fatal=False), ' (The Feed)')
description = self._html_search_meta('description', webpage)
thumbnail = self._og_search_thumbnail(webpage)
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',
'id': video_id, 'id': video_id,
'url': theplatform_url, 'url': theplatform_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
} }