[tf1] fix info extraction(fixes #8599)

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

diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py
index 46b4d91330c50b5fb27917a42ef69d07a1a36ad9..37cf3d3097c94b39f1b66ab11e0e651579f8d533 100644 (file)
--- a/youtube_dl/extractor/wat.py
+++ b/youtube_dl/extractor/wat.py
@@ -5,11 +5,14 @@ import re
 import hashlib
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    ExtractorError,
+    unified_strdate,
+)
 
 
 class WatIE(InfoExtractor):
-    _VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html'
+    _VALID_URL = r'(?:wat:(?P<real_id>\d{8})|http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html)'
     IE_NAME = 'wat.tv'
     _TESTS = [
         {
@@ -37,6 +40,7 @@ class WatIE(InfoExtractor):
                 'upload_date': '20140816',
                 'duration': 2910,
             },
+            'skip': "Ce contenu n'est pas disponible pour l'instant.",
         },
     ]
 
@@ -50,13 +54,20 @@ class WatIE(InfoExtractor):
         def real_id_for_chapter(chapter):
             return chapter['tc_start'].split('-')[0]
         mobj = re.match(self._VALID_URL, url)
-        short_id = mobj.group('short_id')
         display_id = mobj.group('display_id')
-        webpage = self._download_webpage(url, display_id or short_id)
-        real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id')
+        real_id = mobj.group('real_id')
+        if not real_id:
+            short_id = mobj.group('short_id')
+            webpage = self._download_webpage(url, display_id or short_id)
+            real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id')
 
         video_info = self.download_video_info(real_id)
 
+        error_desc = video_info.get('error_desc')
+        if error_desc:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error_desc), expected=True)
+
         geo_list = video_info.get('geoList')
         country = geo_list[0] if geo_list else ''
 
@@ -104,7 +115,7 @@ class WatIE(InfoExtractor):
             video_url = self._download_webpage(
                 'http://www.wat.tv/get%s?token=%s&getURL=1&country=%s' % (webid, compute_token(webid), country),
                 real_id,
-                'Downloding %s video URL' % fmt[0],
+                'Downloading %s video URL' % fmt[0],
                 'Failed to download %s video URL' % fmt[0],
                 False)
             if not video_url: