youtube-dl

commit: 0fa67c1d686c1c25b467906307cafefa885c4a80
parent 365b3cc72dc265d20ece3e57f6abe590eb026544
Author: Remita Amine <remitamine@gmail.com>
Date:   Sun, 27 Dec 2020 08:55:51 +0100

[generic] Add support for VHX Embeds(#27546)

Diffstat:
M
youtube_dl/extractor/generic.py
22
++++++++++++++++++++--
M
youtube_dl/extractor/vimeo.py
7
+++++++

2 files changed, 27 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -67,7 +67,10 @@ from .tube8 import Tube8IE
 from .mofosex import MofosexEmbedIE
 from .spankwire import SpankwireIE
 from .youporn import YouPornIE
-from .vimeo import VimeoIE
+from .vimeo import (
+    VimeoIE,
+    VHXEmbedIE,
+)
 from .dailymotion import DailymotionIE
 from .dailymail import DailyMailIE
 from .onionstudios import OnionStudiosIE
@@ -2193,7 +2196,18 @@ class GenericIE(InfoExtractor):
         #     'params': {
         #         'force_generic_extractor': True,
         #     },
-        # }
+        # },
+        {
+            # VHX Embed
+            'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
+            'info_dict': {
+                'id': '858208',
+                'ext': 'mp4',
+                'title': 'Untitled',
+                'uploader_id': 'user80538407',
+                'uploader': 'OTT Videos',
+            },
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -2571,6 +2585,10 @@ class GenericIE(InfoExtractor):
         if vimeo_urls:
             return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
 
+        vhx_url = VHXEmbedIE._extract_url(webpage)
+        if vhx_url:
+            return self.url_result(vhx_url, VHXEmbedIE.ie_key())
+
         vid_me_embed_url = self._search_regex(
             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
             webpage, 'vid.me embed', default=None)
diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
@@ -1119,6 +1119,12 @@ class VHXEmbedIE(VimeoBaseInfoExtractor):
     IE_NAME = 'vhx:embed'
     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
+        return unescapeHTML(mobj.group(1)) if mobj else None
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
@@ -1127,5 +1133,6 @@ class VHXEmbedIE(VimeoBaseInfoExtractor):
             'ott data'), video_id, js_to_json)['config_url']
         config = self._download_json(config_url, video_id)
         info = self._parse_config(config, video_id)
+        info['id'] = video_id
         self._vimeo_sort_formats(info['formats'])
         return info