diff options
author | Yen Chi Hsuan <yan12125@gmail.com> | 2015-08-30 01:08:55 +0800 |
---|---|---|
committer | Yen Chi Hsuan <yan12125@gmail.com> | 2015-08-30 01:08:55 +0800 |
commit | 17a647630b504c730d77e71faf248628e45529c5 (patch) | |
tree | 102f977bb24a134e99fcad99d51e760532e6aca5 /youtube_dl/extractor/abc.py | |
parent | c88e118b3cfb611bf2eae300a13885772481134f (diff) |
[abc] Support YouTube embeds (fixes #6595)
Diffstat (limited to 'youtube_dl/extractor/abc.py')
-rw-r--r-- | youtube_dl/extractor/abc.py | 42 |
1 files changed, 35 insertions, 7 deletions
diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index dc0fb85d6..06acf50d8 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -1,16 +1,19 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor +from ..utils import ( + ExtractorError, + js_to_json, +) class ABCIE(InfoExtractor): IE_NAME = 'abc.net.au' _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', 'md5': 'cb3dd03b18455a661071ee1e28344d9f', 'info_dict': { @@ -19,16 +22,41 @@ class ABCIE(InfoExtractor): 'title': 'Australia to help staff Ebola treatment centre in Sierra Leone', '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): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - urls_info_json = self._search_regex( - r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls', - flags=re.DOTALL) - urls_info = json.loads(urls_info_json.replace('\'', '"')) + mobj = re.search( + r'inline(?P<type>Video|YouTube)Data\.push\((?P<json_data>[^)]+)\);', + webpage) + 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 = [{ 'url': url_info['url'], 'width': int(url_info['width']), |