youtube_dl/extractor/abc.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7
   8
   9 class ABCIE(InfoExtractor):
  10     IE_NAME = 'abc.net.au'
  11     _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
  12
  13     _TEST = {
  14         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
  15         'md5': 'cb3dd03b18455a661071ee1e28344d9f',
  16         'info_dict': {
  17             'id': '5868334',
  18             'ext': 'mp4',
  19             'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
  20             'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         urls_info_json = self._search_regex(
  29             r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls',
  30             flags=re.DOTALL)
  31         urls_info = json.loads(urls_info_json.replace('\'', '"'))
  32         formats = [{
  33             'url': url_info['url'],
  34             'width': int(url_info['width']),
  35             'height': int(url_info['height']),
  36             'tbr': int(url_info['bitrate']),
  37             'filesize': int(url_info['filesize']),
  38         } for url_info in urls_info]
  39         self._sort_formats(formats)
  40
  41         return {
  42             'id': video_id,
  43             'title': self._og_search_title(webpage),
  44             'formats': formats,
  45             'description': self._og_search_description(webpage),
  46             'thumbnail': self._og_search_thumbnail(webpage),
  47         }