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