_ Git - youtube-dl/blob - 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 )
  11
  12 NAMESPACE_MAP = {
  13     'media': 'http://search.yahoo.com/mrss/',
  14 }
  15
  16 # URL prefix to download the mp4 files directly instead of streaming via rtmp
  17 # Credits go to XBox-Maniac
  18 # http://board.jdownloader.org/showpost.php?p=185835&postcount=31
  19 RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/'
  20
  21
  22 class GameOneIE(InfoExtractor):
  23     _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)'
  24     _TESTS = [
  25         {
  26             'url': 'http://www.gameone.de/tv/288',
  27             'md5': '136656b7fb4c9cb4a8e2d500651c499b',
  28             'info_dict': {
  29                 'id': '288',
  30                 'ext': 'mp4',
  31                 'title': 'Game One - Folge 288',
  32                 'duration': 1238,
  33                 'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg',
  34                 'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1',
  35                 'age_limit': 16,
  36                 'upload_date': '20140513',
  37                 'timestamp': 1399980122,
  38             }
  39         },
  40         {
  41             'url': 'http://gameone.de/tv/220',
  42             'md5': '5227ca74c4ae6b5f74c0510a7c48839e',
  43             'info_dict': {
  44                 'id': '220',
  45                 'ext': 'mp4',
  46                 'upload_date': '20120918',
  47                 'description': 'Jet Set Radio HD, Tekken Tag Tournament 2, Source Filmmaker',
  48                 'timestamp': 1347971451,
  49                 'title': 'Game One - Folge 220',
  50                 'duration': 896,
  51                 'age_limit': 16,
  52             }
  53         }
  54
  55     ]
  56
  57     def _real_extract(self, url):
  58         mobj = re.match(self._VALID_URL, url)
  59         video_id = mobj.group('id')
  60
  61         webpage = self._download_webpage(url, video_id)
  62         og_video = self._og_search_video_url(webpage, secure=False)
  63         description = self._html_search_meta('description', webpage)
  64         age_limit = int(
  65             self._search_regex(
  66                 r'age=(\d+)',
  67                 self._html_search_meta(
  68                     'age-de-meta-label',
  69                     webpage),
  70                 'age_limit',
  71                 '0'))
  72         mrss_url = self._search_regex(r'mrss=([^&]+)', og_video, 'mrss')
  73
  74         mrss = self._download_xml(mrss_url, video_id, 'Downloading mrss')
  75         title = mrss.find('.//item/title').text
  76         thumbnail = mrss.find('.//item/image').get('url')
  77         timestamp = parse_iso8601(mrss.find('.//pubDate').text, delimiter=' ')
  78         content = mrss.find(xpath_with_ns('.//media:content', NAMESPACE_MAP))
  79         content_url = content.get('url')
  80
  81         content = self._download_xml(
  82             content_url,
  83             video_id,
  84             'Downloading media:content')
  85         rendition_items = content.findall('.//rendition')
  86         duration = int(rendition_items[0].get('duration').split('.')[0])
  87         formats = [
  88             {
  89                 'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text),
  90                 'width': int(r.get('width')),
  91                 'height': int(r.get('height')),
  92                 'tbr': int(r.get('bitrate')),
  93             }
  94             for r in rendition_items
  95         ]
  96         self._sort_formats(formats)
  97
  98         return {
  99             'id': video_id,
 100             'title': title,
 101             'thumbnail': thumbnail,
 102             'duration': duration,
 103             'formats': formats,
 104             'description': description,
 105             'age_limit': age_limit,
 106             'timestamp': timestamp,
 107         }
 108
 109
 110 class GameOnePlaylistIE(InfoExtractor):
 111     _VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$'
 112     IE_NAME = 'gameone:playlist'
 113     _TEST = {
 114         'url': 'http://www.gameone.de/tv',
 115         'info_dict': {
 116             'title': 'GameOne',
 117         },
 118         'playlist_mincount': 294,
 119     }
 120
 121     def _real_extract(self, url):
 122         webpage = self._download_webpage('http://www.gameone.de/tv', 'TV')
 123         max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage)))
 124         entries = [
 125             self.url_result('http://www.gameone.de/tv/%d' %
 126                             video_id, 'GameOne')
 127             for video_id in range(max_id, 0, -1)]
 128
 129         return {
 130             '_type': 'playlist',
 131             'title': 'GameOne',
 132             'entries': entries,
 133         }