Merge remote-tracking branch 'duncankl/airmozilla'

[youtube-dl] / youtube_dl / extractor / mitele.py

diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py
index df7fde87c88dcee538309e0468ff34d2c9a3996c..d8897eb90d526b7b7d2e5a5ace5bec84ebb40031 100644 (file)
--- a/youtube_dl/extractor/mitele.py
+++ b/youtube_dl/extractor/mitele.py
@@ -1,11 +1,13 @@
 from __future__ import unicode_literals
 
-import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
+    compat_urlparse,
+)
+from ..utils import (
     get_element_by_attribute,
     parse_duration,
     strip_jsonp,
@@ -14,9 +16,9 @@ from ..utils import (
 
 class MiTeleIE(InfoExtractor):
     IE_NAME = 'mitele.es'
-    _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/'
+    _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
         'md5': '6a75fe9d0d3275bead0cb683c616fddb',
         'info_dict': {
@@ -27,15 +29,13 @@ class MiTeleIE(InfoExtractor):
             'display_id': 'programa-144',
             'duration': 2913,
         },
-    }
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        episode = mobj.group('episode')
+        episode = self._match_id(url)
         webpage = self._download_webpage(url, episode)
         embed_data_json = self._search_regex(
-            r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
-            flags=re.DOTALL
+            r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
         ).replace('\'', '"')
         embed_data = json.loads(embed_data_json)
 
@@ -43,7 +43,7 @@ class MiTeleIE(InfoExtractor):
         if not domain.startswith('http'):
             # only happens in telecinco.es videos
             domain = 'http://' + domain
-        info_url = compat_urllib_parse.urljoin(
+        info_url = compat_urlparse.urljoin(
             domain,
             compat_urllib_parse.unquote(embed_data['flashvars']['host'])
         )