[canal13cl] Add test and improve extraction (#2498)

This commit is contained in:
Philipp Hagemeister 2014-03-03 12:53:11 +01:00
parent f92259c026
commit 9f62eaf4ef
2 changed files with 34 additions and 18 deletions

View File

@ -1,32 +1,48 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
class Canal13clIE(InfoExtractor): class Canal13clIE(InfoExtractor):
_VALID_URL = r'^http://(?:www\.)?13\.cl/' _VALID_URL = r'^http://(?:www\.)?13\.cl/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
IE_NAME = 'Canal13cl' _TEST = {
'url': 'http://www.13.cl/t13/nacional/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
'md5': '4cb1fa38adcad8fea88487a078831755',
'info_dict': {
'id': '1403022125',
'display_id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
'ext': 'mp4',
'title': 'El "círculo de hierro" de Michelle Bachelet en su regreso a La Moneda',
'description': '(Foto: Agencia Uno) En nueve días más, Michelle Bachelet va a asumir por segunda vez como presidenta de la República. Entre aquellos que la acompañarán hay caras que se repiten y otras que se consolidan en su entorno de colaboradores más cercanos.',
}
}
def _real_extract(self, url): def _real_extract(self, url):
webpage = self._download_webpage(url, url) mobj = re.match(self._VALID_URL, url)
video_id = self._html_search_regex( display_id = mobj.group('id')
r'http://streaming.13.cl/(.*)\.mp4',
webpage, u'video_id') webpage = self._download_webpage(url, display_id)
title = self._html_search_regex(
r'(articuloTitulo = \"(.*?)\"|(.*?)\|)', title = self._html_search_meta(
webpage, u'title') 'twitter:title', webpage, 'title', fatal=True)
description = self._html_search_meta(
'twitter:description', webpage, 'description')
url = self._html_search_regex( url = self._html_search_regex(
r'articuloVideo = \"(.*?)\"', r'articuloVideo = \"(.*?)\"', webpage, 'url')
webpage, u'url') real_id = self._search_regex(
thumbnail = self._html_search_regex ( r'[^0-9]([0-9]{7,})[^0-9]', url, 'id', default=display_id)
r'articuloImagen = \"(.*?)\"', thumbnail = self._html_search_regex(
webpage, u'thumbnail') r'articuloImagen = \"(.*?)\"', webpage, 'thumbnail')
return { return {
'video_id': video_id, 'id': real_id,
'display_id': display_id,
'url': url, 'url': url,
'title': title, 'title': title,
'description': description,
'ext': 'mp4', 'ext': 'mp4',
'thumbnail': thumbnail 'thumbnail': thumbnail,
} }

View File

@ -436,14 +436,14 @@ class InfoExtractor(object):
if secure: regexes = self._og_regexes('video:secure_url') + regexes if secure: regexes = self._og_regexes('video:secure_url') + regexes
return self._html_search_regex(regexes, html, name, **kargs) return self._html_search_regex(regexes, html, name, **kargs)
def _html_search_meta(self, name, html, display_name=None): def _html_search_meta(self, name, html, display_name=None, fatal=False):
if display_name is None: if display_name is None:
display_name = name display_name = name
return self._html_search_regex( return self._html_search_regex(
r'''(?ix)<meta r'''(?ix)<meta
(?=[^>]+(?:itemprop|name|property)=["\']%s["\']) (?=[^>]+(?:itemprop|name|property)=["\']%s["\'])
[^>]+content=["\']([^"\']+)["\']''' % re.escape(name), [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
html, display_name, fatal=False) html, display_name, fatal=fatal)
def _dc_search_uploader(self, html): def _dc_search_uploader(self, html):
return self._html_search_meta('dc.creator', html, 'uploader') return self._html_search_meta('dc.creator', html, 'uploader')