[nrk:skole] Fix extraction

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

diff --git a/youtube_dl/extractor/leeco.py b/youtube_dl/extractor/leeco.py
index d0cd3f5919350117a1babe44df1e1ea6ff4bb3c5..63f581cd9fe44013ce8ec85ce540d04d0df73713 100644 (file)
--- a/youtube_dl/extractor/leeco.py
+++ b/youtube_dl/extractor/leeco.py
@@ -11,7 +11,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_ord,
     compat_str,
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
 )
 from ..utils import (
     determine_ext,
@@ -28,7 +28,7 @@ from ..utils import (
 
 class LeIE(InfoExtractor):
     IE_DESC = '乐视网'
-    _VALID_URL = r'http://www\.le\.com/ptv/vplay/(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://(?:www\.le\.com/ptv/vplay|sports\.le\.com/video)/(?P<id>\d+)\.html'
 
     _URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
 
@@ -69,6 +69,9 @@ class LeIE(InfoExtractor):
             'hls_prefer_native': True,
         },
         'skip': 'Only available in China',
+    }, {
+        'url': 'http://sports.le.com/video/25737697.html',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -122,7 +125,7 @@ class LeIE(InfoExtractor):
             'domain': 'www.le.com'
         }
         play_json_req = sanitized_Request(
-            'http://api.le.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
+            'http://api.le.com/mms/out/video/playJson?' + compat_urllib_parse_urlencode(params)
         )
         cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
         if cn_verification_proxy:
@@ -151,7 +154,7 @@ class LeIE(InfoExtractor):
         for format_id in formats:
             if format_id in dispatch:
                 media_url = playurl['domain'][0] + dispatch[format_id][0]
-                media_url += '&' + compat_urllib_parse.urlencode({
+                media_url += '&' + compat_urllib_parse_urlencode({
                     'm3v': 1,
                     'format': 1,
                     'expect': 3,
@@ -196,7 +199,7 @@ class LeIE(InfoExtractor):
 
 
 class LePlaylistIE(InfoExtractor):
-    _VALID_URL = r'http://[a-z]+\.le\.com/[a-z]+/(?P<id>[a-z0-9_]+)'
+    _VALID_URL = r'https?://[a-z]+\.le\.com/(?!video)[a-z]+/(?P<id>[a-z0-9_]+)'
 
     _TESTS = [{
         'url': 'http://www.le.com/tv/46177.html',
@@ -217,14 +220,8 @@ class LePlaylistIE(InfoExtractor):
         'playlist_mincount': 96
     }, {
         'url': 'http://tv.le.com/pzt/lswjzzjc/index.shtml',
-        'info_dict': {
-            'id': 'lswjzzjc',
-            # The title should be "劲舞青春", but I can't find a simple way to
-            # determine the playlist title
-            'title': '乐视午间自制剧场',
-            'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
-        },
-        'playlist_mincount': 7
+        # This series is moved to http://www.le.com/tv/10005297.html
+        'only_matching': True,
     }, {
         'url': 'http://www.le.com/comic/92063.html',
         'only_matching': True,
@@ -311,7 +308,7 @@ class LetvCloudIE(InfoExtractor):
             }
             self.sign_data(data)
             return self._download_json(
-                'http://api.letvcloud.com/gpc.php?' + compat_urllib_parse.urlencode(data),
+                'http://api.letvcloud.com/gpc.php?' + compat_urllib_parse_urlencode(data),
                 media_id, 'Downloading playJson data for type %s' % cf)
 
         play_json = get_play_json(cf, time.time())
@@ -338,7 +335,7 @@ class LetvCloudIE(InfoExtractor):
             formats.append({
                 'url': url,
                 'ext': determine_ext(decoded_url),
-                'format_id': int_or_none(play_url.get('vtype')),
+                'format_id': str_or_none(play_url.get('vtype')),
                 'format_note': str_or_none(play_url.get('definition')),
                 'width': int_or_none(play_url.get('vwidth')),
                 'height': int_or_none(play_url.get('vheight')),