[abc] Support YouTube embeds (fixes #6595)

This commit is contained in:
Yen Chi Hsuan 2015-08-30 01:08:55 +08:00
parent c88e118b3c
commit 17a647630b

View File

@ -1,16 +1,19 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
ExtractorError,
js_to_json,
)
class ABCIE(InfoExtractor): class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au' IE_NAME = 'abc.net.au'
_VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)' _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
_TEST = { _TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334', 'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
'md5': 'cb3dd03b18455a661071ee1e28344d9f', 'md5': 'cb3dd03b18455a661071ee1e28344d9f',
'info_dict': { 'info_dict': {
@ -19,16 +22,41 @@ class ABCIE(InfoExtractor):
'title': 'Australia to help staff Ebola treatment centre in Sierra Leone', 'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
'description': 'md5:809ad29c67a05f54eb41f2a105693a67', 'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
}, },
} }, {
'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
'md5': 'db2a5369238b51f9811ad815b69dc086',
'info_dict': {
'id': 'NvqvPeNZsHU',
'ext': 'mp4',
'upload_date': '20150816',
'uploader': 'ABC News (Australia)',
'description': 'Government backbencher Warren Entsch introduces a cross-party sponsored bill to legalise same-sex marriage, saying the bill is designed to promote "an inclusive Australia, not a divided one.". Read more here: http://ab.co/1Mwc6ef',
'uploader_id': 'NewsOnABC',
'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
},
'add_ie': ['Youtube'],
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
urls_info_json = self._search_regex( mobj = re.search(
r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls', r'inline(?P<type>Video|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
flags=re.DOTALL) webpage)
urls_info = json.loads(urls_info_json.replace('\'', '"')) if mobj is None:
raise ExtractorError('Unable to extract video urls')
urls_info = self._parse_json(
mobj.group('json_data'), video_id, transform_source=js_to_json)
if not isinstance(urls_info, list):
urls_info = [urls_info]
if mobj.group('type') == 'YouTube':
return self.playlist_result([
self.url_result(url_info['url']) for url_info in urls_info])
formats = [{ formats = [{
'url': url_info['url'], 'url': url_info['url'],
'width': int(url_info['width']), 'width': int(url_info['width']),