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/2014-07-25/bringing-asylum-seekers-to-australia-would-give/5624716',
  15         'md5': 'dad6f8ad011a70d9ddf887ce6d5d0742',
  16         'info_dict': {
  17             'id': '5624716',
  18             'ext': 'mp4',
  19             'title': 'Bringing asylum seekers to Australia would give them right to asylum claims: professor',
  20             'description': 'md5:ba36fa5e27e5c9251fd929d339aea4af',
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group('id')
  27         webpage = self._download_webpage(url, video_id)
  28
  29         urls_info_json = self._search_regex(
  30             r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls',
  31             flags=re.DOTALL)
  32         urls_info = json.loads(urls_info_json.replace('\'', '"'))
  33         formats = [{
  34             'url': url_info['url'],
  35             'width': int(url_info['width']),
  36             'height': int(url_info['height']),
  37             'tbr': int(url_info['bitrate']),
  38             'filesize': int(url_info['filesize']),
  39         } for url_info in urls_info]
  40         self._sort_formats(formats)
  41
  42         return {
  43             'id': video_id,
  44             'title': self._og_search_title(webpage),
  45             'formats': formats,
  46             'description': self._og_search_description(webpage),
  47             'thumbnail': self._og_search_thumbnail(webpage),
  48         }