[youtube] Improve chapters extraction (closes #13247)

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

diff --git a/youtube_dl/extractor/viu.py b/youtube_dl/extractor/viu.py
index 1a81b484541a00648cec80b7106886c20b615dd1..db6a65d2ed93b233b050561c56fa7b6133ddb1b7 100644 (file)
--- a/youtube_dl/extractor/viu.py
+++ b/youtube_dl/extractor/viu.py
@@ -25,7 +25,7 @@ class ViuBaseIE(InfoExtractor):
                 'userid': 'guest',
                 'useridtype': 'guest',
                 'ver': '1.0'
-            })
+            }, headers=self.geo_verification_headers())
         self._auth_token = viu_auth_res.info()['X-VIU-AUTH']
 
     def _call_api(self, path, *args, **kwargs):
@@ -44,7 +44,7 @@ class ViuBaseIE(InfoExtractor):
 
 
 class ViuIE(ViuBaseIE):
-    _VALID_URL = r'(?:viu:|https?://www\.viu\.com/[a-z]{2}/media/)(?P<id>\d+)'
+    _VALID_URL = r'(?:viu:|https?://[^/]+\.viu\.com/[a-z]{2}/media/)(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://www.viu.com/en/media/1116705532?containerId=playlist-22168059',
         'info_dict': {
@@ -69,6 +69,9 @@ class ViuIE(ViuBaseIE):
             'skip_download': 'm3u8 download',
         },
         'skip': 'Geo-restricted to Indonesia',
+    }, {
+        'url': 'https://india.viu.com/en/media/1126286865',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -86,13 +89,17 @@ class ViuIE(ViuBaseIE):
         m3u8_url = None
         url_path = video_data.get('urlpathd') or video_data.get('urlpath')
         tdirforwhole = video_data.get('tdirforwhole')
-        hls_file = video_data.get('hlsfile')
+        # #EXT-X-BYTERANGE is not supported by native hls downloader
+        # and ffmpeg (#10955)
+        # hls_file = video_data.get('hlsfile')
+        hls_file = video_data.get('jwhlsfile')
         if url_path and tdirforwhole and hls_file:
             m3u8_url = '%s/%s/%s' % (url_path, tdirforwhole, hls_file)
         else:
-            m3u8_url = re.sub(
-                r'(/hlsc_)[a-z]+(\d+\.m3u8)',
-                r'\1whe\2', video_data['href'])
+            # m3u8_url = re.sub(
+            #     r'(/hlsc_)[a-z]+(\d+\.m3u8)',
+            #     r'\1whe\2', video_data['href'])
+            m3u8_url = video_data['href']
         formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
         self._sort_formats(formats)