Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 17:22:31 +01:00
Code Issues Releases Activity

[elpais] Fix typo and improve extraction (closes #12139)

Browse Source
This commit is contained in:
Sergey M․ 2017-02-16 04:57:42 +07:00
parent 2480b056c1
commit b898f0a173
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 18 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
youtube_dl/extractor/elpais.py
View File

@ -39,6 +39,18 @@ class ElPaisIE(InfoExtractor):
'description': 'La nave portaba cientos de ánforas y se hundió cerca de la isla de Cabrera por razones desconocidas', 'description': 'La nave portaba cientos de ánforas y se hundió cerca de la isla de Cabrera por razones desconocidas',
'upload_date': '20170127', 'upload_date': '20170127',
}, },
}, {
'url': 'http://epv.elpais.com/epv/2017/02/14/programa_la_voz_de_inaki/1487062137_075943.html',
'info_dict': {
'id': '1487062137_075943',
'ext': 'mp4',
'title': 'Disyuntivas',
'description': 'md5:a0fb1485c4a6a8a917e6f93878e66218',
'upload_date': '20170214',
},
'params': {
'skip_download': True,
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -59,14 +71,15 @@ def _real_extract(self, url):
video_url = prefix + video_suffix video_url = prefix + video_suffix
thumbnail_suffix = self._search_regex( thumbnail_suffix = self._search_regex(
r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'",
webpage, 'thumbnail URL', fatal=False) webpage, 'thumbnail URL', default=None)
thumbnail = ( thumbnail = (
None if thumbnail_suffix is None None if thumbnail_suffix is None
else prefix + thumbnail_suffix) else prefix + thumbnail_suffix) or self._og_search_thumbnail(webpage)
title = self._html_search_regex( title = self._html_search_regex(
(r"tituloVideo\s*=\s*'([^']+)'", webpage, 'title', (r"tituloVideo\s*=\s*'([^']+)'",
r'<h2 class="entry-header entry-title.*?>(.*?)</h2>'), r'<h2 class="entry-header entry-title.*?>(.*?)</h2>',
webpage, 'title') r'<h1[^>]+class="titulo"[^>]*>([^<]+)'),
webpage, 'title', default=None) or self._og_search_title(webpage)
upload_date = unified_strdate(self._search_regex( upload_date = unified_strdate(self._search_regex(
r'<p class="date-header date-int updated"\s+title="([^"]+)">', r'<p class="date-header date-int updated"\s+title="([^"]+)">',
webpage, 'upload date', default=None) or self._html_search_meta( webpage, 'upload date', default=None) or self._html_search_meta(