_ Git - youtube-dl/blob - youtube_dl/extractor/gamestar.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     int_or_none,
   9     parse_duration,
  10     str_to_int,
  11     unified_strdate,
  12 )
  13
  14
  15 class GameStarIE(InfoExtractor):
  16     _VALID_URL = r'https?://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
  17     _TEST = {
  18         'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
  19         'md5': '96974ecbb7fd8d0d20fca5a00810cea7',
  20         'info_dict': {
  21             'id': '76110',
  22             'ext': 'mp4',
  23             'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
  24             'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den vollständigen Trailer an.',
  25             'thumbnail': 'http://images.gamestar.de/images/idgwpgsgp/bdb/2494525/600x.jpg',
  26             'upload_date': '20140728',
  27             'duration': 17
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         webpage = self._download_webpage(url, video_id)
  34
  35         og_title = self._og_search_title(webpage)
  36         title = re.sub(r'\s*- Video (bei|-) GameStar\.de$', '', og_title)
  37
  38         url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id
  39
  40         description = self._og_search_description(webpage).strip()
  41
  42         thumbnail = self._proto_relative_url(
  43             self._og_search_thumbnail(webpage), scheme='http:')
  44
  45         upload_date = unified_strdate(self._html_search_regex(
  46             r'<span style="float:left;font-size:11px;">Datum: ([0-9]+\.[0-9]+\.[0-9]+)&nbsp;&nbsp;',
  47             webpage, 'upload_date', fatal=False))
  48
  49         duration = parse_duration(self._html_search_regex(
  50             r'&nbsp;&nbsp;Länge: ([0-9]+:[0-9]+)</span>', webpage, 'duration',
  51             fatal=False))
  52
  53         view_count = str_to_int(self._html_search_regex(
  54             r'&nbsp;&nbsp;Zuschauer: ([0-9\.]+)&nbsp;&nbsp;', webpage,
  55             'view_count', fatal=False))
  56
  57         comment_count = int_or_none(self._html_search_regex(
  58             r'>Kommentieren \(([0-9]+)\)</a>', webpage, 'comment_count',
  59             fatal=False))
  60
  61         return {
  62             'id': video_id,
  63             'title': title,
  64             'url': url,
  65             'ext': 'mp4',
  66             'thumbnail': thumbnail,
  67             'description': description,
  68             'upload_date': upload_date,
  69             'duration': duration,
  70             'view_count': view_count,
  71             'comment_count': comment_count
  72         }