Add support for https for all extractors as preventive and future-proof measure
[youtube-dl] / youtube_dl / extractor / vuclip.py
index c2aa497bfa39b99b4d233403ca274b4ff6d56595..eaa888f005cc61c53b8f45c3e3b93633083b17ed 100644 (file)
@@ -3,8 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse_urlparse,
+)
+from ..utils import (
     ExtractorError,
     parse_duration,
     qualities,
@@ -12,7 +14,7 @@ from ..utils import (
 
 
 class VuClipIE(InfoExtractor):
-    _VALID_URL = r'http://(?:m\.)?vuclip\.com/w\?.*?cid=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:m\.)?vuclip\.com/w\?.*?cid=(?P<id>[0-9]+)'
 
     _TEST = {
         'url': 'http://m.vuclip.com/w?cid=922692425&fid=70295&z=1010&nvar&frm=index.html',
@@ -25,12 +27,9 @@ class VuClipIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
 
-        #webpage = self._download_webpage(url, video_id)
-        import io
-        webpage = io.open('922692425_http_-_m.vuclip.com_wcid=922692425_fid=70295_z=1010_nvar_frm=index.html.dump', encoding='utf-8').read()
         ad_m = re.search(
             r'''value="No.*?" onClick="location.href='([^"']+)'"''', webpage)
         if ad_m:
@@ -50,12 +49,12 @@ class VuClipIE(InfoExtractor):
         links_code = self._search_regex(
             r'''(?xs)
                 (?:
-                    <img\s+src="/im/play.gif".*?>|
+                    <img\s+src="[^"]*/play.gif".*?>|
                     <!--\ player\ end\ -->\s*</div><!--\ thumb\ end-->
                 )
                 (.*?)
                 (?:
-                    <a\s+href="fblike'|<div\s+class="social">
+                    <a\s+href="fblike|<div\s+class="social">
                 )
             ''', webpage, 'links')
         title = self._html_search_regex(