]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/abc.py
Merge tag 'upstream/2015.11.27.1'
[youtubedl] / 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/(?:[^/]+/){1,2}(?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 'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
50 'only_matching': True,
51 }]
52
53 def _real_extract(self, url):
54 video_id = self._match_id(url)
55 webpage = self._download_webpage(url, video_id)
56
57 mobj = re.search(
58 r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
59 webpage)
60 if mobj is None:
61 raise ExtractorError('Unable to extract video urls')
62
63 urls_info = self._parse_json(
64 mobj.group('json_data'), video_id, transform_source=js_to_json)
65
66 if not isinstance(urls_info, list):
67 urls_info = [urls_info]
68
69 if mobj.group('type') == 'YouTube':
70 return self.playlist_result([
71 self.url_result(url_info['url']) for url_info in urls_info])
72
73 formats = [{
74 'url': url_info['url'],
75 'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
76 'width': int_or_none(url_info.get('width')),
77 'height': int_or_none(url_info.get('height')),
78 'tbr': int_or_none(url_info.get('bitrate')),
79 'filesize': int_or_none(url_info.get('filesize')),
80 } for url_info in urls_info]
81
82 self._sort_formats(formats)
83
84 return {
85 'id': video_id,
86 'title': self._og_search_title(webpage),
87 'formats': formats,
88 'description': self._og_search_description(webpage),
89 'thumbnail': self._og_search_thumbnail(webpage),
90 }