Merge tag 'upstream/2016.12.01'

[youtubedl] / youtube_dl / extractor / videomega.py

diff --git a/youtube_dl/extractor/videomega.py b/youtube_dl/extractor/videomega.py
index eb309a7cdf99b3ebc4bde755fe09d47505516f28..4f0dcd18c7f28ab17aec58c814d53fd8ae21e7ac 100644 (file)
--- a/youtube_dl/extractor/videomega.py
+++ b/youtube_dl/extractor/videomega.py
@@ -4,41 +4,50 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_request
+from ..utils import (
+    decode_packed_codes,
+    sanitized_Request,
+)
 
 
 class VideoMegaIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://
-        (?:www\.)?videomega\.tv/
-        (?:iframe\.php|cdn\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
-        '''
-    _TEST = {
-        'url': 'http://videomega.tv/?ref=4GNA688SU99US886ANG4',
-        'md5': 'bf5c2f95c4c917536e80936af7bc51e1',
+    _VALID_URL = r'(?:videomega:|https?://(?:www\.)?videomega\.tv/(?:(?:view|iframe|cdn)\.php)?\?ref=)(?P<id>[A-Za-z0-9]+)'
+    _TESTS = [{
+        'url': 'http://videomega.tv/cdn.php?ref=AOSQBJYKIDDIKYJBQSOA',
+        'md5': 'cc1920a58add3f05c6a93285b84fb3aa',
         'info_dict': {
-            'id': '4GNA688SU99US886ANG4',
+            'id': 'AOSQBJYKIDDIKYJBQSOA',
             'ext': 'mp4',
-            'title': 'BigBuckBunny_320x180',
+            'title': '1254207',
             'thumbnail': 're:^https?://.*\.jpg$',
         }
-    }
+    }, {
+        'url': 'http://videomega.tv/cdn.php?ref=AOSQBJYKIDDIKYJBQSOA&width=1070&height=600',
+        'only_matching': True,
+    }, {
+        'url': 'http://videomega.tv/view.php?ref=090051111052065112106089103052052103089106112065052111051090',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         iframe_url = 'http://videomega.tv/cdn.php?ref=%s' % video_id
-        req = compat_urllib_request.Request(iframe_url)
+        req = sanitized_Request(iframe_url)
         req.add_header('Referer', url)
+        req.add_header('Cookie', 'noadvtday=0')
         webpage = self._download_webpage(req, video_id)
 
         title = self._html_search_regex(
-            r'<title>(.*?)</title>', webpage, 'title')
+            r'<title>(.+?)</title>', webpage, 'title')
         title = re.sub(
-            r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s?|\s?-\svideomega\.tv$)', '', title)
+            r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s*|\s*-\svideomega\.tv$)', '', title)
         thumbnail = self._search_regex(
             r'<video[^>]+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
+
+        real_codes = decode_packed_codes(webpage)
         video_url = self._search_regex(
-            r'<source[^>]+?src="([^"]+)"', webpage, 'video URL')
+            r'"src"\s*,\s*"([^"]+)"', real_codes, 'video URL')
 
         return {
             'id': video_id,