diff options
| author | Sergey M․ <[email protected]> | 2017-02-16 04:57:42 +0700 |
|---|---|---|
| committer | Sergey M․ <[email protected]> | 2017-02-16 04:57:42 +0700 |
| commit | b898f0a173fa040ddf95dbd97650cec07a8f19f5 (patch) | |
| tree | 5b547a1e459fe7ce67cd4825ca8cdfe136f4493a | |
| parent | 2480b056c137e514662b70053ec2df1391b6c2ab (diff) | |
| download | youtube-dl-b898f0a173fa040ddf95dbd97650cec07a8f19f5.tar.gz youtube-dl-b898f0a173fa040ddf95dbd97650cec07a8f19f5.zip | |
[elpais] Fix typo and improve extraction (closes #12139)
| -rw-r--r-- | youtube_dl/extractor/elpais.py | 23 |
1 files changed, 18 insertions, 5 deletions
diff --git a/youtube_dl/extractor/elpais.py b/youtube_dl/extractor/elpais.py index 99e00cf3c..b89f6db62 100644 --- a/youtube_dl/extractor/elpais.py +++ b/youtube_dl/extractor/elpais.py @@ -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', '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): @@ -59,14 +71,15 @@ class ElPaisIE(InfoExtractor): video_url = prefix + video_suffix thumbnail_suffix = self._search_regex( r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", - webpage, 'thumbnail URL', fatal=False) + webpage, 'thumbnail URL', default=None) thumbnail = ( 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( - (r"tituloVideo\s*=\s*'([^']+)'", webpage, 'title', - r'<h2 class="entry-header entry-title.*?>(.*?)</h2>'), - webpage, 'title') + (r"tituloVideo\s*=\s*'([^']+)'", + r'<h2 class="entry-header entry-title.*?>(.*?)</h2>', + r'<h1[^>]+class="titulo"[^>]*>([^<]+)'), + webpage, 'title', default=None) or self._og_search_title(webpage) upload_date = unified_strdate(self._search_regex( r'<p class="date-header date-int updated"\s+title="([^"]+)">', webpage, 'upload date', default=None) or self._html_search_meta( |