[arnes] Add new extractor(closes #28483)

youtube_dl/extractor/arnes.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+)
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+    remove_start,
+)
+
+
+class ArnesIE(InfoExtractor):
+    IE_NAME = 'video.arnes.si'
+    IE_DESC = 'Arnes Video'
+    _VALID_URL = r'https?://video\.arnes\.si/(?:[a-z]{2}/)?(?:watch|embed|api/(?:asset|public/video))/(?P<id>[0-9a-zA-Z]{12})'
+    _TESTS = [{
+        'url': 'https://video.arnes.si/watch/a1qrWTOQfVoU?t=10',
+        'md5': '4d0f4d0a03571b33e1efac25fd4a065d',
+        'info_dict': {
+            'id': 'a1qrWTOQfVoU',
+            'ext': 'mp4',
+            'title': 'Linearna neodvisnost, definicija',
+            'description': 'Linearna neodvisnost, definicija',
+            'license': 'PRIVATE',
+            'creator': 'Polona Oblak',
+            'timestamp': 1585063725,
+            'upload_date': '20200324',
+            'channel': 'Polona Oblak',
+            'channel_id': 'q6pc04hw24cj',
+            'channel_url': 'https://video.arnes.si/?channel=q6pc04hw24cj',
+            'duration': 596.75,
+            'view_count': int,
+            'tags': ['linearna_algebra'],
+            'start_time': 10,
+        }
+    }, {
+        'url': 'https://video.arnes.si/api/asset/s1YjnV7hadlC/play.mp4',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/embed/s1YjnV7hadlC',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/en/watch/s1YjnV7hadlC',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/embed/s1YjnV7hadlC?t=123&hideRelated=1',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/api/public/video/s1YjnV7hadlC',
+        'only_matching': True,
+    }]
+    _BASE_URL = 'https://video.arnes.si'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            self._BASE_URL + '/api/public/video/' + video_id, video_id)['data']
+        title = video['title']
+
+        formats = []
+        for media in (video.get('media') or []):
+            media_url = media.get('url')
+            if not media_url:
+                continue
+            formats.append({
+                'url': self._BASE_URL + media_url,
+                'format_id': remove_start(media.get('format'), 'FORMAT_'),
+                'format_note': media.get('formatTranslation'),
+                'width': int_or_none(media.get('width')),
+                'height': int_or_none(media.get('height')),
+            })
+        self._sort_formats(formats)
+
+        channel = video.get('channel') or {}
+        channel_id = channel.get('url')
+        thumbnail = video.get('thumbnailUrl')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': self._BASE_URL + thumbnail,
+            'description': video.get('description'),
+            'license': video.get('license'),
+            'creator': video.get('author'),
+            'timestamp': parse_iso8601(video.get('creationTime')),
+            'channel': channel.get('name'),
+            'channel_id': channel_id,
+            'channel_url': self._BASE_URL + '/?channel=' + channel_id if channel_id else None,
+            'duration': float_or_none(video.get('duration'), 1000),
+            'view_count': int_or_none(video.get('views')),
+            'tags': video.get('hashtags'),
+            'start_time': int_or_none(compat_parse_qs(
+                compat_urllib_parse_urlparse(url).query).get('t', [None])[0]),
+        }

youtube_dl/extractor/extractors.py

@@ -72,6 +72,7 @@ from .arte import (
     ArteTVEmbedIE,
     ArteTVPlaylistIE,
 )
+from .arnes import ArnesIE
 from .asiancrush import (
     AsianCrushIE,
     AsianCrushPlaylistIE,

youtube_dl/extractor/youtube.py

@@ -1959,7 +1959,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
                             invidio\.us
                         )/
                         (?:
-                            (?:channel|c|user|feed)/|
+                            (?:channel|c|user|feed|hashtag)/|
                             (?:playlist|watch)\?.*?\blist=|
                             (?!(?:watch|embed|v|e)\b)
                         )
@@ -2245,6 +2245,13 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
     }, {
         'url': 'https://www.youtube.com/TheYoungTurks/live',
         'only_matching': True,
+    }, {
+        'url': 'https://www.youtube.com/hashtag/cctv9',
+        'info_dict': {
+            'id': 'cctv9',
+            'title': '#cctv9',
+        },
+        'playlist_mincount': 350,
     }]
 
     @classmethod
@@ -2392,6 +2399,14 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             for entry in self._post_thread_entries(renderer):
                 yield entry
 
+    def _rich_grid_entries(self, contents):
+        for content in contents:
+            video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
+            if video_renderer:
+                entry = self._video_entry(video_renderer)
+                if entry:
+                    yield entry
+
     @staticmethod
     def _build_continuation_query(continuation, ctp=None):
         query = {
@@ -2442,55 +2457,60 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         if not tab_content:
             return
         slr_renderer = try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
-        if not slr_renderer:
-            return
-        is_channels_tab = tab.get('title') == 'Channels'
-        continuation = None
-        slr_contents = try_get(slr_renderer, lambda x: x['contents'], list) or []
-        for slr_content in slr_contents:
-            if not isinstance(slr_content, dict):
-                continue
-            is_renderer = try_get(slr_content, lambda x: x['itemSectionRenderer'], dict)
-            if not is_renderer:
-                continue
-            isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
-            for isr_content in isr_contents:
-                if not isinstance(isr_content, dict):
+        if slr_renderer:
+            is_channels_tab = tab.get('title') == 'Channels'
+            continuation = None
+            slr_contents = try_get(slr_renderer, lambda x: x['contents'], list) or []
+            for slr_content in slr_contents:
+                if not isinstance(slr_content, dict):
                     continue
-                renderer = isr_content.get('playlistVideoListRenderer')
-                if renderer:
-                    for entry in self._playlist_entries(renderer):
-                        yield entry
-                    continuation = self._extract_continuation(renderer)
+                is_renderer = try_get(slr_content, lambda x: x['itemSectionRenderer'], dict)
+                if not is_renderer:
                     continue
-                renderer = isr_content.get('gridRenderer')
-                if renderer:
-                    for entry in self._grid_entries(renderer):
-                        yield entry
-                    continuation = self._extract_continuation(renderer)
-                    continue
-                renderer = isr_content.get('shelfRenderer')
-                if renderer:
-                    for entry in self._shelf_entries(renderer, not is_channels_tab):
-                        yield entry
-                    continue
-                renderer = isr_content.get('backstagePostThreadRenderer')
-                if renderer:
-                    for entry in self._post_thread_entries(renderer):
-                        yield entry
-                    continuation = self._extract_continuation(renderer)
-                    continue
-                renderer = isr_content.get('videoRenderer')
-                if renderer:
-                    entry = self._video_entry(renderer)
-                    if entry:
-                        yield entry
+                isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
+                for isr_content in isr_contents:
+                    if not isinstance(isr_content, dict):
+                        continue
+                    renderer = isr_content.get('playlistVideoListRenderer')
+                    if renderer:
+                        for entry in self._playlist_entries(renderer):
+                            yield entry
+                        continuation = self._extract_continuation(renderer)
+                        continue
+                    renderer = isr_content.get('gridRenderer')
+                    if renderer:
+                        for entry in self._grid_entries(renderer):
+                            yield entry
+                        continuation = self._extract_continuation(renderer)
+                        continue
+                    renderer = isr_content.get('shelfRenderer')
+                    if renderer:
+                        for entry in self._shelf_entries(renderer, not is_channels_tab):
+                            yield entry
+                        continue
+                    renderer = isr_content.get('backstagePostThreadRenderer')
+                    if renderer:
+                        for entry in self._post_thread_entries(renderer):
+                            yield entry
+                        continuation = self._extract_continuation(renderer)
+                        continue
+                    renderer = isr_content.get('videoRenderer')
+                    if renderer:
+                        entry = self._video_entry(renderer)
+                        if entry:
+                            yield entry
 
+                if not continuation:
+                    continuation = self._extract_continuation(is_renderer)
             if not continuation:
-                continuation = self._extract_continuation(is_renderer)
-
-        if not continuation:
-            continuation = self._extract_continuation(slr_renderer)
+                continuation = self._extract_continuation(slr_renderer)
+        else:
+            rich_grid_renderer = tab_content.get('richGridRenderer')
+            if not rich_grid_renderer:
+                return
+            for entry in self._rich_grid_entries(rich_grid_renderer.get('contents') or []):
+                yield entry
+            continuation = self._extract_continuation(rich_grid_renderer)
 
         headers = {
             'x-youtube-client-name': '1',
@@ -2586,6 +2606,12 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
                         yield entry
                     continuation = self._extract_continuation(continuation_renderer)
                     continue
+                renderer = continuation_item.get('richItemRenderer')
+                if renderer:
+                    for entry in self._rich_grid_entries(continuation_items):
+                        yield entry
+                    continuation = self._extract_continuation({'contents': continuation_items})
+                    continue
 
             break
 
@@ -2642,7 +2668,8 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
         selected_tab = self._extract_selected_tab(tabs)
         renderer = try_get(
             data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
-        playlist_id = title = description = None
+        playlist_id = item_id
+        title = description = None
         if renderer:
             channel_title = renderer.get('title') or item_id
             tab_title = selected_tab.get('title')
@@ -2651,12 +2678,16 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
                 title += ' - %s' % tab_title
             description = renderer.get('description')
             playlist_id = renderer.get('externalId')
-        renderer = try_get(
-            data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
-        if renderer:
-            title = renderer.get('title')
-            description = None
-            playlist_id = item_id
+        else:
+            renderer = try_get(
+                data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
+            if renderer:
+                title = renderer.get('title')
+            else:
+                renderer = try_get(
+                    data, lambda x: x['header']['hashtagHeaderRenderer'], dict)
+                if renderer:
+                    title = try_get(renderer, lambda x: x['hashtag']['simpleText'])
         playlist = self.playlist_result(
             self._entries(selected_tab, identity_token),
             playlist_id=playlist_id, playlist_title=title,