[abc] add support for audio extraction
[youtube-dl] / youtube_dl / extractor / abc.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7     ExtractorError,
8     js_to_json,
9     int_or_none,
10 )
11
12
13 class ABCIE(InfoExtractor):
14     IE_NAME = 'abc.net.au'
15     _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
16
17     _TESTS = [{
18         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
19         'md5': 'cb3dd03b18455a661071ee1e28344d9f',
20         'info_dict': {
21             'id': '5868334',
22             'ext': 'mp4',
23             'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
24             'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
25         },
26     }, {
27         'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
28         'md5': 'db2a5369238b51f9811ad815b69dc086',
29         'info_dict': {
30             'id': 'NvqvPeNZsHU',
31             'ext': 'mp4',
32             'upload_date': '20150816',
33             'uploader': 'ABC News (Australia)',
34             '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',
35             'uploader_id': 'NewsOnABC',
36             'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
37         },
38         'add_ie': ['Youtube'],
39     }, {
40         'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
41         'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
42         'info_dict': {
43             'id': '6880080',
44             'ext': 'mp3',
45             'title': 'NAB lifts interest rates, following Westpac and CBA',
46             'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
47         },
48     }]
49
50     def _real_extract(self, url):
51         video_id = self._match_id(url)
52         webpage = self._download_webpage(url, video_id)
53
54         mobj = re.search(
55             r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
56             webpage)
57         if mobj is None:
58             raise ExtractorError('Unable to extract video urls')
59
60         urls_info = self._parse_json(
61             mobj.group('json_data'), video_id, transform_source=js_to_json)
62
63         if not isinstance(urls_info, list):
64             urls_info = [urls_info]
65
66         if mobj.group('type') == 'YouTube':
67             return self.playlist_result([
68                 self.url_result(url_info['url']) for url_info in urls_info])
69
70         formats = [{
71             'url': url_info['url'],
72             'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
73             'width': int_or_none(url_info.get('width')),
74             'height': int_or_none(url_info.get('height')),
75             'tbr': int_or_none(url_info.get('bitrate')),
76             'filesize': int_or_none(url_info.get('filesize')),
77         } for url_info in urls_info]
78
79         self._sort_formats(formats)
80
81         return {
82             'id': video_id,
83             'title': self._og_search_title(webpage),
84             'formats': formats,
85             'description': self._og_search_description(webpage),
86             'thumbnail': self._og_search_thumbnail(webpage),
87         }