Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/gamestar.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     parse_duration,
   8     str_to_int,
   9     unified_strdate,
  10 )
  11
  12
  13 class GameStarIE(InfoExtractor):
  14     _VALID_URL = r'http://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
  15     _TEST = {
  16         'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
  17         'md5': '96974ecbb7fd8d0d20fca5a00810cea7',
  18         'info_dict': {
  19             'id': '76110',
  20             'ext': 'mp4',
  21             'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
  22             '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.',
  23             'thumbnail': 'http://images.gamestar.de/images/idgwpgsgp/bdb/2494525/600x.jpg',
  24             'upload_date': '20140728',
  25             'duration': 17
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         webpage = self._download_webpage(url, video_id)
  32
  33         og_title = self._og_search_title(webpage)
  34         title = og_title.replace(' - Video bei GameStar.de', '').strip()
  35
  36         url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id
  37
  38         description = self._og_search_description(webpage).strip()
  39
  40         thumbnail = self._proto_relative_url(
  41             self._og_search_thumbnail(webpage), scheme='http:')
  42
  43         upload_date = unified_strdate(self._html_search_regex(
  44             r'<span style="float:left;font-size:11px;">Datum: ([0-9]+\.[0-9]+\.[0-9]+)&nbsp;&nbsp;',
  45             webpage, 'upload_date', fatal=False))
  46
  47         duration = parse_duration(self._html_search_regex(
  48             r'&nbsp;&nbsp;Länge: ([0-9]+:[0-9]+)</span>', webpage, 'duration',
  49             fatal=False))
  50
  51         view_count = str_to_int(self._html_search_regex(
  52             r'&nbsp;&nbsp;Zuschauer: ([0-9\.]+)&nbsp;&nbsp;', webpage,
  53             'view_count', fatal=False))
  54
  55         comment_count = int_or_none(self._html_search_regex(
  56             r'>Kommentieren \(([0-9]+)\)</a>', webpage, 'comment_count',
  57             fatal=False))
  58
  59         return {
  60             'id': video_id,
  61             'title': title,
  62             'url': url,
  63             'ext': 'mp4',
  64             'thumbnail': thumbnail,
  65             'description': description,
  66             'upload_date': upload_date,
  67             'duration': duration,
  68             'view_count': view_count,
  69             'comment_count': comment_count
  70         }