about summary refs log tree commit diff
path: root/youtube_dl/extractor/hgtv.py
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2017-06-23 00:42:42 +0700
committerSergey M․ <dstftw@gmail.com>2017-06-23 00:42:42 +0700
commitfa3ea7223ac4d547c848e2df44504158ee0099f5 (patch)
treeef918bed9ccd02fac8772ec980195ef65d52c3fe /youtube_dl/extractor/hgtv.py
parent0f4a5a73e70172c0accbd2e936d08988d065b3b1 (diff)
downloadyoutube-dl-fa3ea7223ac4d547c848e2df44504158ee0099f5.tar.gz
youtube-dl-fa3ea7223ac4d547c848e2df44504158ee0099f5.tar.xz
youtube-dl-fa3ea7223ac4d547c848e2df44504158ee0099f5.zip
[hgtv.com:show] Relax video config regex and update test (closes #13279, closes #13461)
Diffstat (limited to 'youtube_dl/extractor/hgtv.py')
-rw-r--r--youtube_dl/extractor/hgtv.py15
1 files changed, 10 insertions, 5 deletions
diff --git a/youtube_dl/extractor/hgtv.py b/youtube_dl/extractor/hgtv.py
index e854300c7..4d4b06824 100644
--- a/youtube_dl/extractor/hgtv.py
+++ b/youtube_dl/extractor/hgtv.py
@@ -7,14 +7,19 @@ from .common import InfoExtractor
 class HGTVComShowIE(InfoExtractor):
     IE_NAME = 'hgtv.com:show'
     _VALID_URL = r'https?://(?:www\.)?hgtv\.com/shows/[^/]+/(?P<id>[^/?#&]+)'
-    _TEST = {
-        'url': 'http://www.hgtv.com/shows/flip-or-flop/flip-or-flop-full-episodes-videos',
+    _TESTS = [{
+        # data-module="video"
+        'url': 'http://www.hgtv.com/shows/flip-or-flop/flip-or-flop-full-episodes-season-4-videos',
         'info_dict': {
-            'id': 'flip-or-flop-full-episodes-videos',
+            'id': 'flip-or-flop-full-episodes-season-4-videos',
             'title': 'Flip or Flop Full Episodes',
         },
         'playlist_mincount': 15,
-    }
+    }, {
+        # data-deferred-module="video"
+        'url': 'http://www.hgtv.com/shows/good-bones/episodes/an-old-victorian-house-gets-a-new-facelift',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -23,7 +28,7 @@ class HGTVComShowIE(InfoExtractor):
 
         config = self._parse_json(
             self._search_regex(
-                r'(?s)data-module=["\']video["\'][^>]*>.*?<script[^>]+type=["\']text/x-config["\'][^>]*>(.+?)</script',
+                r'(?s)data-(?:deferred)?-module=["\']video["\'][^>]*>.*?<script[^>]+type=["\']text/x-config["\'][^>]*>(.+?)</script',
                 webpage, 'video config'),
             display_id)['channels'][0]