R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Extract SBSNewsIE from SBSIE

Browse Source
This commit is contained in:
Pete Johns 2019-05-12 20:42:56 +10:00
parent c66cc3cc5b
commit 744df7ab32
2 changed files with 38 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
youtube_dl/extractor/extractors.py
View File

@ -1005,7 +1005,10 @@ from .safari import (
) )
from .sapo import SapoIE from .sapo import SapoIE
from .savefrom import SaveFromIE from .savefrom import SaveFromIE
from .sbs import SBSIE from .sbs import (
SBSIE,
SBSNewsIE,
)
from .screencast import ScreencastIE from .screencast import ScreencastIE
from .screencastomatic import ScreencastOMaticIE from .screencastomatic import ScreencastOMaticIE
from .scrippsnetworks import ScrippsNetworksWatchIE from .scrippsnetworks import ScrippsNetworksWatchIE

65
youtube_dl/extractor/sbs.py
View File

@ -1,8 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
smuggle_url, smuggle_url,
@ -12,23 +10,9 @@ from ..utils import (
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|news)/(?:video/)?(?:single/)?([0-9]+|[0-9a-z-]+)' _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand|news)/video/(?:single/)?(?P<id>[0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.sbs.com.au/news/are-the-campaigns-working-voters-speak-out',
'md5': '2b73ddcbb597f24a87167826c47398f8',
'info_dict': {
'id': 'Vznr2YGb83mF',
'ext': 'mp4',
'title': 'Are the campaigns cutting through?',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:http://.*\.jpg',
'duration': 146,
'timestamp': 1557552900,
'upload_date': '20190511',
'uploader': 'SBSC',
}
}, {
# Original URL is handled by the generic IE which finds the iframe: # Original URL is handled by the generic IE which finds the iframe:
# http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation # http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation
'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed', 'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed',
@ -52,21 +36,8 @@ class SBSIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
def video_id_from_page_contents(self, url):
page_contents = self._download_webpage(url, None)
video_id = self._search_regex(r'id="video-(\d+)"', page_contents, 'video id')
return video_id
def video_id(self, url):
ID_BEARING_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand|news)/video/(?:single/)?(?P<id>[0-9]+)'
match = re.match(ID_BEARING_URL, url)
if match:
return match.group('id')
else:
return self.video_id_from_page_contents(url)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self.video_id(url) video_id = self._video_id(url)
player_params = self._download_json( player_params = self._download_json(
'http://www.sbs.com.au/api/video_pdkvars/id/%s?form=json' % video_id, video_id) 'http://www.sbs.com.au/api/video_pdkvars/id/%s?form=json' % video_id, video_id)
@ -93,3 +64,35 @@ class SBSIE(InfoExtractor):
'id': video_id, 'id': video_id,
'url': smuggle_url(self._proto_relative_url(theplatform_url), {'force_smil_url': True}), 'url': smuggle_url(self._proto_relative_url(theplatform_url), {'force_smil_url': True}),
} }
def _video_id(self, url):
return self._match_id(url)
class SBSNewsIE(SBSIE):
_VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/news/(?P<id>[0-9a-z-]+)'
_TESTS = [{
'url': 'https://www.sbs.com.au/news/are-the-campaigns-working-voters-speak-out',
'only_matching': True,
'md5': '2b73ddcbb597f24a87167826c47398f8',
'info_dict': {
'id': 'Vznr2YGb83mF',
'ext': 'mp4',
'title': 'Are the campaigns cutting through?',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:http://.*\.jpg',
'duration': 146,
'timestamp': 1557552900,
'upload_date': '20190511',
'uploader': 'SBSC',
},
}, {
'url': 'https://www.sbs.com.au/news/sbs-world-news-bulletin-may-11',
'only_matching': True,
}]
def _video_id(self, url):
slug = self._match_id(url)
page_contents = self._download_webpage(url, slug)
return self._search_regex(r'id="video-(\d+)"', page_contents, 'video id')