[mitele] Extract series metadata and make title more robust (Closes #9758)

This commit is contained in:
Sergey M․ 2016-06-18 04:06:19 +07:00
parent eb451890da
commit 6929569403
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -1,5 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_parse_urlencode, compat_urllib_parse_urlencode,
@ -8,6 +11,7 @@
from ..utils import ( from ..utils import (
get_element_by_attribute, get_element_by_attribute,
int_or_none, int_or_none,
remove_start,
) )
@ -15,7 +19,7 @@ class MiTeleIE(InfoExtractor):
IE_DESC = 'mitele.es' IE_DESC = 'mitele.es'
_VALID_URL = r'https?://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/' _VALID_URL = r'https?://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
_TEST = { _TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
# MD5 is unstable # MD5 is unstable
'info_dict': { 'info_dict': {
@ -24,10 +28,31 @@ class MiTeleIE(InfoExtractor):
'ext': 'flv', 'ext': 'flv',
'title': 'Tor, la web invisible', 'title': 'Tor, la web invisible',
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f', 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
'series': 'Diario de',
'season': 'La redacción',
'episode': 'Programa 144',
'thumbnail': 're:(?i)^https?://.*\.jpg$', 'thumbnail': 're:(?i)^https?://.*\.jpg$',
'duration': 2913, 'duration': 2913,
}, },
} }, {
# no explicit title
'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/temporada-6/programa-226/',
'info_dict': {
'id': 'eLZSwoEd1S3pVyUm8lc6F',
'display_id': 'programa-226',
'ext': 'flv',
'title': 'Cuarto Milenio - Temporada 6 - Programa 226',
'description': 'md5:50daf9fadefa4e62d9fc866d0c015701',
'series': 'Cuarto Milenio',
'season': 'Temporada 6',
'episode': 'Programa 226',
'thumbnail': 're:(?i)^https?://.*\.jpg$',
'duration': 7312,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
@ -70,7 +95,22 @@ def _real_extract(self, url):
self._sort_formats(formats) self._sort_formats(formats)
title = self._search_regex( title = self._search_regex(
r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>', webpage, 'title') r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>',
webpage, 'title', default=None)
mobj = re.search(r'''(?sx)
class="Destacado-text"[^>]*>.*?<h1>\s*
<span>(?P<series>[^<]+)</span>\s*
<span>(?P<season>[^<]+)</span>\s*
<span>(?P<episode>[^<]+)</span>''', webpage)
series, season, episode = mobj.groups() if mobj else [None] * 3
if not title:
if mobj:
title = '%s - %s - %s' % (series, season, episode)
else:
title = remove_start(self._search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), 'Ver online ')
video_id = self._search_regex( video_id = self._search_regex(
r'data-media-id\s*=\s*"([^"]+)"', webpage, r'data-media-id\s*=\s*"([^"]+)"', webpage,
@ -83,6 +123,9 @@ def _real_extract(self, url):
'display_id': display_id, 'display_id': display_id,
'title': title, 'title': title,
'description': get_element_by_attribute('class', 'text', webpage), 'description': get_element_by_attribute('class', 'text', webpage),
'series': series,
'season': season,
'episode': episode,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,