youtube_dl/extractor/gameone.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 (
   8     xpath_with_ns,
   9     parse_iso8601,
  10     float_or_none,
  11     int_or_none,
  12 )
  13
  14 NAMESPACE_MAP = {
  15     'media': 'http://search.yahoo.com/mrss/',
  16 }
  17
  18 # URL prefix to download the mp4 files directly instead of streaming via rtmp
  19 # Credits go to XBox-Maniac
  20 # http://board.jdownloader.org/showpost.php?p=185835&postcount=31
  21 RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/'
  22
  23
  24 class GameOneIE(InfoExtractor):
  25     _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)'
  26     _TESTS = [
  27         {
  28             'url': 'http://www.gameone.de/tv/288',
  29             'md5': '136656b7fb4c9cb4a8e2d500651c499b',
  30             'info_dict': {
  31                 'id': '288',
  32                 'ext': 'mp4',
  33                 'title': 'Game One - Folge 288',
  34                 'duration': 1238,
  35                 'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg',
  36                 'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1',
  37                 'age_limit': 16,
  38                 'upload_date': '20140513',
  39                 'timestamp': 1399980122,
  40             }
  41         },
  42         {
  43             'url': 'http://gameone.de/tv/220',
  44             'md5': '5227ca74c4ae6b5f74c0510a7c48839e',
  45             'info_dict': {
  46                 'id': '220',
  47                 'ext': 'mp4',
  48                 'upload_date': '20120918',
  49                 'description': 'Jet Set Radio HD, Tekken Tag Tournament 2, Source Filmmaker',
  50                 'timestamp': 1347971451,
  51                 'title': 'Game One - Folge 220',
  52                 'duration': 896.62,
  53                 'age_limit': 16,
  54             }
  55         }
  56
  57     ]
  58
  59     def _real_extract(self, url):
  60         video_id = self._match_id(url)
  61
  62         webpage = self._download_webpage(url, video_id)
  63         og_video = self._og_search_video_url(webpage, secure=False)
  64         description = self._html_search_meta('description', webpage)
  65         age_limit = int(
  66             self._search_regex(
  67                 r'age=(\d+)',
  68                 self._html_search_meta(
  69                     'age-de-meta-label',
  70                     webpage),
  71                 'age_limit',
  72                 '0'))
  73         mrss_url = self._search_regex(r'mrss=([^&]+)', og_video, 'mrss')
  74
  75         mrss = self._download_xml(mrss_url, video_id, 'Downloading mrss')
  76         title = mrss.find('.//item/title').text
  77         thumbnail = mrss.find('.//item/image').get('url')
  78         timestamp = parse_iso8601(mrss.find('.//pubDate').text, delimiter=' ')
  79         content = mrss.find(xpath_with_ns('.//media:content', NAMESPACE_MAP))
  80         content_url = content.get('url')
  81
  82         content = self._download_xml(
  83             content_url,
  84             video_id,
  85             'Downloading media:content')
  86         rendition_items = content.findall('.//rendition')
  87         duration = float_or_none(rendition_items[0].get('duration'))
  88         formats = [
  89             {
  90                 'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text),
  91                 'width': int_or_none(r.get('width')),
  92                 'height': int_or_none(r.get('height')),
  93                 'tbr': int_or_none(r.get('bitrate')),
  94             }
  95             for r in rendition_items
  96         ]
  97         self._sort_formats(formats)
  98
  99         return {
 100             'id': video_id,
 101             'title': title,
 102             'thumbnail': thumbnail,
 103             'duration': duration,
 104             'formats': formats,
 105             'description': description,
 106             'age_limit': age_limit,
 107             'timestamp': timestamp,
 108         }
 109
 110
 111 class GameOnePlaylistIE(InfoExtractor):
 112     _VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$'
 113     IE_NAME = 'gameone:playlist'
 114     _TEST = {
 115         'url': 'http://www.gameone.de/tv',
 116         'info_dict': {
 117             'title': 'GameOne',
 118         },
 119         'playlist_mincount': 294,
 120     }
 121
 122     def _real_extract(self, url):
 123         webpage = self._download_webpage('http://www.gameone.de/tv', 'TV')
 124         max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage)))
 125         entries = [
 126             self.url_result('http://www.gameone.de/tv/%d' %
 127                             video_id, 'GameOne')
 128             for video_id in range(max_id, 0, -1)]
 129
 130         return {
 131             '_type': 'playlist',
 132             'title': 'GameOne',
 133             'entries': entries,
 134         }