Switch codebase to use sanitized_Request instead of

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

diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py
index bf5e44d88981c062ee846abc9086004db5793f47..36baf3245353604ac67af1500029c4be6a67ed4f 100644 (file)
--- a/youtube_dl/extractor/iprima.py
+++ b/youtube_dl/extractor/iprima.py
@@ -6,11 +6,15 @@ from random import random
 from math import floor
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_request
+from ..utils import (
+    ExtractorError,
+    remove_end,
+    sanitized_Request,
+)
 
 
 class IPrimaIE(InfoExtractor):
-    _VALID_URL = r'https?://play\.iprima\.cz/[^?#]+/(?P<id>[^?#]+)'
+    _VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)'
 
     _TESTS = [{
         'url': 'http://play.iprima.cz/particka/particka-92',
@@ -18,14 +22,27 @@ class IPrimaIE(InfoExtractor):
             'id': '39152',
             'ext': 'flv',
             'title': 'Partička (92)',
-            'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6',
+            'description': 'md5:74e9617e51bca67c3ecfb2c6f9766f45',
             'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
         },
         'params': {
-            'skip_download': True,
+            'skip_download': True,  # requires rtmpdump
         },
-    },
-    ]
+    }, {
+        'url': 'http://play.iprima.cz/particka/tchibo-particka-jarni-moda',
+        'info_dict': {
+            'id': '9718337',
+            'ext': 'flv',
+            'title': 'Tchibo Partička - Jarní móda',
+            'thumbnail': 're:^http:.*\.jpg$',
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+    }, {
+        'url': 'http://play.iprima.cz/zpravy-ftv-prima-2752015',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -33,11 +50,16 @@ class IPrimaIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        player_url = 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % (
-                         floor(random()*1073741824),
-                         floor(random()*1073741824))
+        if re.search(r'Nemáte oprávnění přistupovat na tuto stránku\.\s*</div>', webpage):
+            raise ExtractorError(
+                '%s said: You do not have permission to access this page' % self.IE_NAME, expected=True)
+
+        player_url = (
+            'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' %
+            (floor(random() * 1073741824), floor(random() * 1073741824))
+        )
 
-        req = compat_urllib_request.Request(player_url)
+        req = sanitized_Request(player_url)
         req.add_header('Referer', url)
         playerpage = self._download_webpage(req, video_id)
 
@@ -56,7 +78,8 @@ class IPrimaIE(InfoExtractor):
                 continue
 
             real_id = self._search_regex(
-                r'Prima-[0-9]{10}-([0-9]+)_', filename, 'real video id')
+                r'Prima-(?:[0-9]{10}|WEB)-([0-9]+)[-_]',
+                filename, 'real video id')
 
             if format_id == 'lq':
                 quality = 0
@@ -79,8 +102,10 @@ class IPrimaIE(InfoExtractor):
 
         return {
             'id': real_id,
-            'title': self._og_search_title(webpage),
+            'title': remove_end(self._og_search_title(webpage), ' | Prima PLAY'),
             'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
-            'description': self._og_search_description(webpage),
+            'description': self._search_regex(
+                r'<p[^>]+itemprop="description"[^>]*>([^<]+)',
+                webpage, 'description', default=None),
         }