youtube_dl/extractor/vrt.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import float_or_none
   8
   9
  10 class VRTIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:deredactie|sporza|cobra)\.be/cm/(?:[^/]+/)+(?P<id>[^/]+)/*'
  12     _TESTS = [
  13         # deredactie.be
  14         {
  15             'url': 'http://deredactie.be/cm/vrtnieuws/videozone/programmas/journaal/EP_141025_JOL',
  16             'md5': '4cebde1eb60a53782d4f3992cbd46ec8',
  17             'info_dict': {
  18                 'id': '2129880',
  19                 'ext': 'flv',
  20                 'title': 'Het journaal L - 25/10/14',
  21                 'description': None,
  22                 'timestamp': 1414271750.949,
  23                 'upload_date': '20141025',
  24                 'duration': 929,
  25             }
  26         },
  27         # sporza.be
  28         {
  29             'url': 'http://sporza.be/cm/sporza/videozone/programmas/extratime/EP_141020_Extra_time',
  30             'md5': '11f53088da9bf8e7cfc42456697953ff',
  31             'info_dict': {
  32                 'id': '2124639',
  33                 'ext': 'flv',
  34                 'title': 'Bekijk Extra Time van 20 oktober',
  35                 'description': 'md5:83ac5415a4f1816c6a93f8138aef2426',
  36                 'timestamp': 1413835980.560,
  37                 'upload_date': '20141020',
  38                 'duration': 3238,
  39             }
  40         },
  41         # cobra.be
  42         {
  43             'url': 'http://cobra.be/cm/cobra/videozone/rubriek/film-videozone/141022-mv-ellis-cafecorsari',
  44             'md5': '78a2b060a5083c4f055449a72477409d',
  45             'info_dict': {
  46                 'id': '2126050',
  47                 'ext': 'flv',
  48                 'title': 'Bret Easton Ellis in Café Corsari',
  49                 'description': 'md5:f699986e823f32fd6036c1855a724ee9',
  50                 'timestamp': 1413967500.494,
  51                 'upload_date': '20141022',
  52                 'duration': 661,
  53             }
  54         },
  55     ]
  56
  57     def _real_extract(self, url):
  58         video_id = self._match_id(url)
  59
  60         webpage = self._download_webpage(url, video_id)
  61
  62         video_id = self._search_regex(
  63             r'data-video-id="([^"]+)_[^"]+"', webpage, 'video id', fatal=False)
  64
  65         formats = []
  66         mobj = re.search(
  67             r'data-video-iphone-server="(?P<server>[^"]+)"\s+data-video-iphone-path="(?P<path>[^"]+)"',
  68             webpage)
  69         if mobj:
  70             formats.extend(self._extract_m3u8_formats(
  71                 '%s/%s' % (mobj.group('server'), mobj.group('path')),
  72                 video_id, 'mp4'))
  73         mobj = re.search(r'data-video-src="(?P<src>[^"]+)"', webpage)
  74         if mobj:
  75             formats.extend(self._extract_f4m_formats(
  76                 '%s/manifest.f4m' % mobj.group('src'), video_id))
  77         self._sort_formats(formats)
  78
  79         title = self._og_search_title(webpage)
  80         description = self._og_search_description(webpage, default=None)
  81         thumbnail = self._og_search_thumbnail(webpage)
  82         timestamp = float_or_none(self._search_regex(
  83             r'data-video-sitestat-pubdate="(\d+)"', webpage, 'timestamp', fatal=False), 1000)
  84         duration = float_or_none(self._search_regex(
  85             r'data-video-duration="(\d+)"', webpage, 'duration', fatal=False), 1000)
  86
  87         return {
  88             'id': video_id,
  89             'title': title,
  90             'description': description,
  91             'thumbnail': thumbnail,
  92             'timestamp': timestamp,
  93             'duration': duration,
  94             'formats': formats,
  95         }