Update upstream source from tag 'upstream/2020.06.16.1'

[youtubedl] / youtube_dl / extractor / vidzi.py

diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py
index d0556297e449dfffa277bcc0e339347e91f12aec..42ea4952c381b497b6f01abcb44212339563e0a3 100644 (file)
--- a/youtube_dl/extractor/vidzi.py
+++ b/youtube_dl/extractor/vidzi.py
@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class VidziIE(InfoExtractor):
 
 
 class VidziIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
+    _VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc|si|nu)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'

     _TESTS = [{
         'url': 'http://vidzi.tv/cghql9yq6emu.html',
         'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
     _TESTS = [{
         'url': 'http://vidzi.tv/cghql9yq6emu.html',
         'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',


@@ -28,10 +28,16 @@ class VidziIE(InfoExtractor):
         },
     }, {
         'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html',
         },
     }, {
         'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html',

-        'skip_download': True,
+        'only_matching': True,

     }, {
         'url': 'http://vidzi.cc/cghql9yq6emu.html',
     }, {
         'url': 'http://vidzi.cc/cghql9yq6emu.html',

-        'skip_download': True,
+        'only_matching': True,
+    }, {
+        'url': 'https://vidzi.si/rph9gztxj1et.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://vidzi.nu/cghql9yq6emu.html',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):


@@ -42,15 +48,17 @@ class VidziIE(InfoExtractor):
         title = self._html_search_regex(
             r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
 
         title = self._html_search_regex(
             r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
 

-        packed_codes = [mobj.group(0) for mobj in re.finditer(
-            PACKED_CODES_RE, webpage)]
-        for num, pc in enumerate(packed_codes, 1):
-            code = decode_packed_codes(pc).replace('\\\'', '\'')
+        codes = [webpage]
+        codes.extend([
+            decode_packed_codes(mobj.group(0)).replace('\\\'', '\'')
+            for mobj in re.finditer(PACKED_CODES_RE, webpage)])
+        for num, code in enumerate(codes, 1):

             jwplayer_data = self._parse_json(
                 self._search_regex(
                     r'setup\(([^)]+)\)', code, 'jwplayer data',
             jwplayer_data = self._parse_json(
                 self._search_regex(
                     r'setup\(([^)]+)\)', code, 'jwplayer data',

-                    default=NO_DEFAULT if num == len(packed_codes) else '{}'),
-                video_id, transform_source=js_to_json)
+                    default=NO_DEFAULT if num == len(codes) else '{}'),
+                video_id, transform_source=lambda s: js_to_json(
+                    re.sub(r'\s*\+\s*window\[.+?\]', '', s)))

             if jwplayer_data:
                 break
 
             if jwplayer_data:
                 break