2 from __future__ import unicode_literals
4 from .common import InfoExtractor
5 from ..utils import unified_strdate
8 class ElPaisIE(InfoExtractor):
9 _VALID_URL = r'https?://(?:[^.]+\.)?elpais\.com/.*/(?P<id>[^/#?]+)\.html(?:$|[?#])'
13 'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html',
14 'md5': '98406f301f19562170ec071b83433d55',
16 'id': 'tiempo-nuevo-recetas-viejas',
18 'title': 'Tiempo nuevo, recetas viejas',
19 'description': 'De lunes a viernes, a partir de las ocho de la mañana, Iñaki Gabilondo nos cuenta su visión de la actualidad nacional e internacional.',
20 'upload_date': '20140206',
24 def _real_extract(self, url):
25 video_id = self._match_id(url)
26 webpage = self._download_webpage(url, video_id)
28 prefix = self._html_search_regex(
29 r'var url_cache = "([^"]+)";', webpage, 'URL prefix')
30 video_suffix = self._search_regex(
31 r"URLMediaFile = url_cache \+ '([^']+)'", webpage, 'video URL')
32 video_url = prefix + video_suffix
33 thumbnail_suffix = self._search_regex(
34 r"URLMediaStill = url_cache \+ '([^']+)'", webpage, 'thumbnail URL',
37 None if thumbnail_suffix is None
38 else prefix + thumbnail_suffix)
39 title = self._html_search_regex(
40 '<h2 class="entry-header entry-title.*?>(.*?)</h2>',
42 date_str = self._search_regex(
43 r'<p class="date-header date-int updated"\s+title="([^"]+)">',
44 webpage, 'upload date', fatal=False)
45 upload_date = (None if date_str is None else unified_strdate(date_str))
51 'description': self._og_search_description(webpage),
52 'thumbnail': thumbnail,
53 'upload_date': upload_date,