aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2016-06-18 04:06:19 +0700
committerSergey M․ <dstftw@gmail.com>2016-06-18 04:06:19 +0700
commit6929569403aeade9aced5c4103db652e9c16bdca (patch)
treecf095090dc5464fb749e9036456d6f4186f0dedb /youtube_dl/extractor
parenteb451890da79e686a218e42c9761df2a6f5b6ee3 (diff)
[mitele] Extract series metadata and make title more robust (Closes #9758)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/mitele.py49
1 files changed, 46 insertions, 3 deletions
diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py
index 3589c223d..5a00cd397 100644
--- a/youtube_dl/extractor/mitele.py
+++ b/youtube_dl/extractor/mitele.py
@@ -1,5 +1,8 @@
+# coding: utf-8
from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
@@ -8,6 +11,7 @@ from ..compat import (
from ..utils import (
get_element_by_attribute,
int_or_none,
+ remove_start,
)
@@ -15,7 +19,7 @@ class MiTeleIE(InfoExtractor):
IE_DESC = 'mitele.es'
_VALID_URL = r'https?://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
# MD5 is unstable
'info_dict': {
@@ -24,10 +28,31 @@ class MiTeleIE(InfoExtractor):
'ext': 'flv',
'title': 'Tor, la web invisible',
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
+ 'series': 'Diario de',
+ 'season': 'La redacción',
+ 'episode': 'Programa 144',
'thumbnail': 're:(?i)^https?://.*\.jpg$',
'duration': 2913,
},
- }
+ }, {
+ # no explicit title
+ 'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/temporada-6/programa-226/',
+ 'info_dict': {
+ 'id': 'eLZSwoEd1S3pVyUm8lc6F',
+ 'display_id': 'programa-226',
+ 'ext': 'flv',
+ 'title': 'Cuarto Milenio - Temporada 6 - Programa 226',
+ 'description': 'md5:50daf9fadefa4e62d9fc866d0c015701',
+ 'series': 'Cuarto Milenio',
+ 'season': 'Temporada 6',
+ 'episode': 'Programa 226',
+ 'thumbnail': 're:(?i)^https?://.*\.jpg$',
+ 'duration': 7312,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }]
def _real_extract(self, url):
display_id = self._match_id(url)
@@ -70,7 +95,22 @@ class MiTeleIE(InfoExtractor):
self._sort_formats(formats)
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(
r'data-media-id\s*=\s*"([^"]+)"', webpage,
@@ -83,6 +123,9 @@ class MiTeleIE(InfoExtractor):
'display_id': display_id,
'title': title,
'description': get_element_by_attribute('class', 'text', webpage),
+ 'series': series,
+ 'season': season,
+ 'episode': episode,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,