Raphaël G. Git Repositories - youtubedl/blob - 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'https?://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         'skip': 'this video has expired',
  27     }, {
  28         'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
  29         'md5': 'db2a5369238b51f9811ad815b69dc086',
  30         'info_dict': {
  31             'id': 'NvqvPeNZsHU',
  32             'ext': 'mp4',
  33             'upload_date': '20150816',
  34             'uploader': 'ABC News (Australia)',
  35             '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',
  36             'uploader_id': 'NewsOnABC',
  37             'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
  38         },
  39         'add_ie': ['Youtube'],
  40         'skip': 'Not accessible from Travis CI server',
  41     }, {
  42         'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
  43         'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
  44         'info_dict': {
  45             'id': '6880080',
  46             'ext': 'mp3',
  47             'title': 'NAB lifts interest rates, following Westpac and CBA',
  48             'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
  49         },
  50     }, {
  51         'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
  52         'only_matching': True,
  53     }]
  54
  55     def _real_extract(self, url):
  56         video_id = self._match_id(url)
  57         webpage = self._download_webpage(url, video_id)
  58
  59         mobj = re.search(
  60             r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
  61             webpage)
  62         if mobj is None:
  63             expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
  64             if expired:
  65                 raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
  66             raise ExtractorError('Unable to extract video urls')
  67
  68         urls_info = self._parse_json(
  69             mobj.group('json_data'), video_id, transform_source=js_to_json)
  70
  71         if not isinstance(urls_info, list):
  72             urls_info = [urls_info]
  73
  74         if mobj.group('type') == 'YouTube':
  75             return self.playlist_result([
  76                 self.url_result(url_info['url']) for url_info in urls_info])
  77
  78         formats = [{
  79             'url': url_info['url'],
  80             'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
  81             'width': int_or_none(url_info.get('width')),
  82             'height': int_or_none(url_info.get('height')),
  83             'tbr': int_or_none(url_info.get('bitrate')),
  84             'filesize': int_or_none(url_info.get('filesize')),
  85         } for url_info in urls_info]
  86
  87         self._sort_formats(formats)
  88
  89         return {
  90             'id': video_id,
  91             'title': self._og_search_title(webpage),
  92             'formats': formats,
  93             'description': self._og_search_description(webpage),
  94             'thumbnail': self._og_search_thumbnail(webpage),
  95         }