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     parse_iso8601,
  11 )
  12
  13
  14 class ABCIE(InfoExtractor):
  15     IE_NAME = 'abc.net.au'
  16     _VALID_URL = r'https?://(?:www\.)?abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
  17
  18     _TESTS = [{
  19         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
  20         'md5': 'cb3dd03b18455a661071ee1e28344d9f',
  21         'info_dict': {
  22             'id': '5868334',
  23             'ext': 'mp4',
  24             'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
  25             'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
  26         },
  27         'skip': 'this video has expired',
  28     }, {
  29         'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
  30         'md5': 'db2a5369238b51f9811ad815b69dc086',
  31         'info_dict': {
  32             'id': 'NvqvPeNZsHU',
  33             'ext': 'mp4',
  34             'upload_date': '20150816',
  35             'uploader': 'ABC News (Australia)',
  36             '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',
  37             'uploader_id': 'NewsOnABC',
  38             'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
  39         },
  40         'add_ie': ['Youtube'],
  41         'skip': 'Not accessible from Travis CI server',
  42     }, {
  43         'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
  44         'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
  45         'info_dict': {
  46             'id': '6880080',
  47             'ext': 'mp3',
  48             'title': 'NAB lifts interest rates, following Westpac and CBA',
  49             'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
  50         },
  51     }, {
  52         'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
  53         'only_matching': True,
  54     }]
  55
  56     def _real_extract(self, url):
  57         video_id = self._match_id(url)
  58         webpage = self._download_webpage(url, video_id)
  59
  60         mobj = re.search(
  61             r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
  62             webpage)
  63         if mobj is None:
  64             expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
  65             if expired:
  66                 raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
  67             raise ExtractorError('Unable to extract video urls')
  68
  69         urls_info = self._parse_json(
  70             mobj.group('json_data'), video_id, transform_source=js_to_json)
  71
  72         if not isinstance(urls_info, list):
  73             urls_info = [urls_info]
  74
  75         if mobj.group('type') == 'YouTube':
  76             return self.playlist_result([
  77                 self.url_result(url_info['url']) for url_info in urls_info])
  78
  79         formats = [{
  80             'url': url_info['url'],
  81             'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
  82             'width': int_or_none(url_info.get('width')),
  83             'height': int_or_none(url_info.get('height')),
  84             'tbr': int_or_none(url_info.get('bitrate')),
  85             'filesize': int_or_none(url_info.get('filesize')),
  86         } for url_info in urls_info]
  87
  88         self._sort_formats(formats)
  89
  90         return {
  91             'id': video_id,
  92             'title': self._og_search_title(webpage),
  93             'formats': formats,
  94             'description': self._og_search_description(webpage),
  95             'thumbnail': self._og_search_thumbnail(webpage),
  96         }
  97
  98
  99 class ABCIViewIE(InfoExtractor):
 100     IE_NAME = 'abc.net.au:iview'
 101     _VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
 102
 103     # ABC iview programs are normally available for 14 days only.
 104     _TESTS = [{
 105         'url': 'http://iview.abc.net.au/programs/diaries-of-a-broken-mind/ZX9735A001S00',
 106         'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
 107         'info_dict': {
 108             'id': 'ZX9735A001S00',
 109             'ext': 'mp4',
 110             'title': 'Diaries Of A Broken Mind',
 111             'description': 'md5:7de3903874b7a1be279fe6b68718fc9e',
 112             'upload_date': '20161010',
 113             'uploader_id': 'abc2',
 114             'timestamp': 1476064920,
 115         },
 116         'skip': 'Video gone',
 117     }]
 118
 119     def _real_extract(self, url):
 120         video_id = self._match_id(url)
 121         webpage = self._download_webpage(url, video_id)
 122         video_params = self._parse_json(self._search_regex(
 123             r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id)
 124         title = video_params.get('title') or video_params['seriesTitle']
 125         stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
 126
 127         formats = self._extract_akamai_formats(stream['hds-unmetered'], video_id)
 128         self._sort_formats(formats)
 129
 130         subtitles = {}
 131         src_vtt = stream.get('captions', {}).get('src-vtt')
 132         if src_vtt:
 133             subtitles['en'] = [{
 134                 'url': src_vtt,
 135                 'ext': 'vtt',
 136             }]
 137
 138         return {
 139             'id': video_id,
 140             'title': title,
 141             'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
 142             'thumbnail': self._html_search_meta(['og:image', 'twitter:image:src'], webpage),
 143             'duration': int_or_none(video_params.get('eventDuration')),
 144             'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
 145             'series': video_params.get('seriesTitle'),
 146             'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
 147             'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage, default=None)),
 148             'episode': self._html_search_meta('episode_title', webpage, default=None),
 149             'uploader_id': video_params.get('channel'),
 150             'formats': formats,
 151             'subtitles': subtitles,
 152         }