youtube-dl

commit: fda6d237a5b664cc8a9a45562d4113c51fd0280d
parent 5d9f6cbc5afa033b6f1cfd2abe4327e366da2ad1
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sun, 23 Feb 2020 06:47:11 +0700

[wistia] Add support for multiple generic embeds (closes #8347, closes #11385)

Diffstat:
M
youtube_dl/extractor/generic.py
17
+++++++++--------
M
youtube_dl/extractor/wistia.py
31
++++++++++++++++---------------

2 files changed, 25 insertions(+), 23 deletions(-)
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -2537,14 +2537,15 @@ class GenericIE(InfoExtractor):
                 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
 
         # Look for embedded Wistia player
-        wistia_url = WistiaIE._extract_url(webpage)
-        if wistia_url:
-            return {
-                '_type': 'url_transparent',
-                'url': self._proto_relative_url(wistia_url),
-                'ie_key': WistiaIE.ie_key(),
-                'uploader': video_uploader,
-            }
+        wistia_urls = WistiaIE._extract_urls(webpage)
+        if wistia_urls:
+            playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
+            for entry in playlist['entries']:
+                entry.update({
+                    '_type': 'url_transparent',
+                    'uploader': video_uploader,
+                })
+            return playlist
 
         # Look for SVT player
         svt_url = SVTIE._extract_url(webpage)
diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py
@@ -45,22 +45,23 @@ class WistiaIE(InfoExtractor):
     # https://wistia.com/support/embed-and-share/video-on-your-website
     @staticmethod
     def _extract_url(webpage):
-        match = re.search(
-            r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage)
-        if match:
-            return unescapeHTML(match.group('url'))
+        urls = WistiaIE._extract_urls(webpage)
+        return urls[0] if urls else None
 
-        match = re.search(
-            r'''(?sx)
-                <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
-                <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
-            ''', webpage)
-        if match:
-            return 'wistia:%s' % match.group('id')
-
-        match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage)
-        if match:
-            return 'wistia:%s' % match.group('id')
+    @staticmethod
+    def _extract_urls(webpage):
+        urls = []
+        for match in re.finditer(
+                r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage):
+            urls.append(unescapeHTML(match.group('url')))
+        for match in re.finditer(
+                r'''(?sx)
+                    <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
+                ''', webpage):
+            urls.append('wistia:%s' % match.group('id'))
+        for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):
+            urls.append('wistia:%s' % match.group('id'))
+        return urls
 
     def _real_extract(self, url):
         video_id = self._match_id(url)