yt_dlp/extractor/_extractors.py

@@ -84,6 +84,7 @@ from .allstar import (
     AllstarIE,
     AllstarProfileIE,
 )
+
 from .alphaporno import AlphaPornoIE
 from .altcensored import (
     AltCensoredIE,
@@ -540,7 +541,7 @@ from .egghead import (
 from .eighttracks import EightTracksIE
 from .einthusan import EinthusanIE
 from .eitb import EitbIE
-from .elementorembed import ElementorEmbedIE
+from .elementorgeneral import ElementorGeneralIE
 from .elonet import ElonetIE
 from .elpais import ElPaisIE
 from .eltrecetv import ElTreceTVIE

yt_dlp/extractor/elementorembed.py

@@ -1,70 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import unescapeHTML, url_or_none
-from ..utils.traversal import traverse_obj
-
-
-class ElementorEmbedIE(InfoExtractor):
-    _VALID_URL = False
-    _WEBPAGE_TESTS = [{
-        'url': 'https://capitaltv.cy/2023/12/14/υγεια-και-ζωη-14-12-2023-δρ-ξενια-κωσταντινιδο/',
-        'info_dict': {
-            'id': 'KgzuxwuQwM4',
-            'ext': 'mp4',
-            'title': 'ΥΓΕΙΑ ΚΑΙ ΖΩΗ 14 12 2023 ΔΡ  ΞΕΝΙΑ ΚΩΣΤΑΝΤΙΝΙΔΟΥ',
-            'thumbnail': 'https://i.ytimg.com/vi/KgzuxwuQwM4/maxresdefault.jpg',
-            'playable_in_embed': True,
-            'tags': 'count:16',
-            'like_count': int,
-            'channel': 'Capital TV Cyprus',
-            'channel_id': 'UCR8LwVKTLGEXt4ZAErpCMrg',
-            'availability': 'public',
-            'description': 'md5:7a3308a22881aea4612358c4ba121f77',
-            'duration': 2891,
-            'upload_date': '20231214',
-            'uploader_id': '@capitaltvcyprus6389',
-            'live_status': 'not_live',
-            'channel_url': 'https://www.youtube.com/channel/UCR8LwVKTLGEXt4ZAErpCMrg',
-            'uploader_url': 'https://www.youtube.com/@capitaltvcyprus6389',
-            'uploader': 'Capital TV Cyprus',
-            'age_limit': 0,
-            'categories': ['News & Politics'],
-            'view_count': int,
-            'channel_follower_count': int,
-        },
-    }, {
-        'url': 'https://elementor.com/academy/theme-builder-collection/?playlist=76011151&video=9e59909',
-        'info_dict': {
-            'id': '?playlist=76011151&video=9e59909',
-            'title': 'Theme Builder Collection - Academy',
-            'age_limit': 0,
-            'timestamp': 1702196984.0,
-            'upload_date': '20231210',
-            'description': 'md5:7f52c52715ee9e54fd7f82210511673d',
-            'thumbnail': 'https://elementor.com/academy/wp-content/uploads/2021/07/Theme-Builder-1.png',
-        },
-        'playlist_count': 11,
-        'params': {
-            'skip_download': True,
-        },
-    }]
-    _WIDGET_REGEX = r'<div[^>]+class="[^"]*elementor-widget-video(?:-playlist)?[^"]*"[^>]*data-settings="([^"]*)"'
-
-    def _extract_from_webpage(self, url, webpage):
-        for data_settings in re.findall(self._WIDGET_REGEX, webpage):
-            data = self._parse_json(data_settings, None, fatal=False, transform_source=unescapeHTML)
-            if youtube_url := traverse_obj(data, ('youtube_url', {url_or_none})):
-                yield self.url_result(youtube_url, ie='Youtube')
-
-            for video in traverse_obj(data, ('tabs', lambda _, v: v['_id'], {dict})):
-                if youtube_url := traverse_obj(video, ('youtube_url', {url_or_none})):
-                    yield self.url_result(youtube_url, ie='Youtube')
-                if vimeo_url := traverse_obj(video, ('vimeo_url', {url_or_none})):
-                    yield self.url_result(vimeo_url, ie='Vimeo')
-                for direct_url in traverse_obj(video, (('hosted_url', 'external_url'), 'url', {url_or_none})):
-                    yield {
-                        'id': video['_id'],
-                        'url': direct_url,
-                        'title': video.get('title'),
-                    }

yt_dlp/extractor/elementorgeneral.py

@@ -0,0 +1,94 @@
+from .common import InfoExtractor
+import re
+from ..utils import (
+    traverse_obj,
+    clean_html,
+    unescapeHTML,
+)
+
+
+class ElementorGeneralIE(InfoExtractor):
+    _VALID_URL = False
+    _WEBPAGE_TESTS = [{
+        'url': 'https://capitaltv.cy/2023/12/14/υγεια-και-ζωη-14-12-2023-δρ-ξενια-κωσταντινιδο/',
+        'info_dict': {
+            'id': 'KgzuxwuQwM4',
+            'ext': 'mp4',
+            'title': 'ΥΓΕΙΑ ΚΑΙ ΖΩΗ 14 12 2023 ΔΡ  ΞΕΝΙΑ ΚΩΣΤΑΝΤΙΝΙΔΟΥ',
+            'thumbnail': 'https://i.ytimg.com/vi/KgzuxwuQwM4/maxresdefault.jpg',
+            'playable_in_embed': True,
+            'tags': 'count:16',
+            'like_count': int,
+            'channel': 'Capital TV Cyprus',
+            'channel_id': 'UCR8LwVKTLGEXt4ZAErpCMrg',
+            'availability': 'public',
+            'description': 'md5:7a3308a22881aea4612358c4ba121f77',
+            'duration': 2891,
+            'upload_date': '20231214',
+            'uploader_id': '@capitaltvcyprus6389',
+            'live_status': 'not_live',
+            'channel_url': 'https://www.youtube.com/channel/UCR8LwVKTLGEXt4ZAErpCMrg',
+            'uploader_url': 'https://www.youtube.com/@capitaltvcyprus6389',
+            'uploader': 'Capital TV Cyprus',
+            'age_limit': 0,
+            'categories': ['News & Politics'],
+            'view_count': int,
+            'channel_follower_count': int,
+        },
+    }, {
+        'url': 'https://elementor.com/academy/theme-builder-collection/?playlist=76011151&video=9e59909',
+        'info_dict': {
+            'id': '?playlist=76011151&video=9e59909',
+            'title': 'Theme Builder Collection - Academy',
+            'age_limit': 0,
+            'timestamp': 1702196984.0,
+            'upload_date': '20231210',
+            'description': 'md5:7f52c52715ee9e54fd7f82210511673d',
+            'thumbnail': 'https://elementor.com/academy/wp-content/uploads/2021/07/Theme-Builder-1.png',
+        },
+        'playlist_mincount': 2,
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _extract_from_webpage(self, url, webpage):
+        for element in re.findall(r'<div[^>]+class="[^"]*elementor-widget-(?:video|video-playlist)[^"]*"[^>]*data-settings="([^"]*)"', webpage):
+            data_settings = unescapeHTML(clean_html(element))
+            data = self._parse_json(data_settings, None, fatal=False)
+            tabs = data.get('tabs', [])
+            if tabs:  # Handling playlists
+                for tab in tabs:
+                    video_url = tab.get('youtube_url') or tab.get('vimeo_url') or tab.get('dailymotion_url') or tab.get('videopress_url')
+                    if video_url:
+                        title = tab.get('title') or self._og_search_title(webpage)
+                        thumbnail = tab.get('thumbnail', {}).get('url') or self._og_search_thumbnail(webpage)
+                        ie_key = self._get_ie_key(video_url)
+                        yield self._build_result(video_url, title, thumbnail, ie_key)
+            else:
+                video_url = data.get('youtube_url') or data.get('vimeo_url') or data.get('dailymotion_url') or data.get('videopress_url')
+                title = data.get('title') or self._og_search_title(webpage)
+                thumbnail = traverse_obj(data, ('image_overlay', 'url')) or self._og_search_thumbnail(webpage)
+                ie_key = self._get_ie_key(video_url)
+                yield self._build_result(video_url, title, thumbnail, ie_key)
+
+    def _get_ie_key(self, url):
+        if 'youtube' in url or 'youtu.be' in url:
+            return 'Youtube'
+        elif 'vimeo' in url:
+            return 'Vimeo'
+        elif 'dailymotion' in url:
+            return 'Dailymotion'
+        elif 'videopress' in url:
+            return 'Videopress'
+        return 'Generic'
+
+    def _build_result(self, video_url, title, thumbnail, ie_key):
+        return {
+            'id': video_url,
+            'title': title,
+            '_type': 'url_transparent',
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'ie_key': ie_key,
+        }