[periscope] Add extractor (Closes #5850, closes #6459)

2 files changed, 67 insertions, 0 deletions

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 922d9b3d8..bd86a5be2 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -432,6 +432,7 @@ from .orf import (
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
+from .periscope import PeriscopeIE
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
diff --git a/youtube_dl/extractor/periscope.py b/youtube_dl/extractor/periscope.py
new file mode 100644
index 000000000..5219e1a75
--- /dev/null
+++ b/youtube_dl/extractor/periscope.py
@@ -0,0 +1,66 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    unescapeHTML,
+)
+
+
+class PeriscopeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?periscope\.tv/w/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'https://www.periscope.tv/w/aJUQnjY3MjA3ODF8NTYxMDIyMDl2zCg2pECBgwTqRpQuQD352EMPTKQjT4uqlM3cgWFA-g==',
+        'md5': '65b57957972e503fcbbaeed8f4fa04ca',
+        'info_dict': {
+            'id': '56102209',
+            'ext': 'mp4',
+            'title': 'Bec Boop - 🚠✈️🇬🇧 Fly above #London in Emirates Air Line cable car at night 🇬🇧✈️🚠 #BoopScope 🎀💗',
+            'timestamp': 1438978559,
+            'upload_date': '20150807',
+            'uploader': 'Bec Boop',
+            'uploader_id': '1465763',
+        },
+        'skip': 'Expires in 24 hours',
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        replay = self._download_json(
+            'https://api.periscope.tv/api/v2/getAccessPublic?token=%s' % video_id, video_id)
+
+        video_url = replay['replay_url']
+
+        webpage = self._download_webpage(url, video_id)
+
+        broadcast_data = self._parse_json(
+            unescapeHTML(self._html_search_meta(
+                'broadcast-data', webpage, 'broadcast data', fatal=True)),
+            video_id)
+
+        broadcast = broadcast_data['broadcast']
+        status = broadcast['status']
+
+        uploader = broadcast.get('user_display_name') or broadcast_data.get('user', {}).get('display_name')
+        uploader_id = broadcast.get('user_id') or broadcast_data.get('user', {}).get('id')
+
+        title = '%s - %s' % (uploader, status) if uploader else status
+        timestamp = parse_iso8601(broadcast.get('created_at'))
+
+        thumbnails = [{
+            'url': broadcast[image],
+        } for image in ('image_url', 'image_url_small') if broadcast.get(image)]
+
+        return {
+            'id': broadcast.get('id') or video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'protocol': 'm3u8_native',
+            'title': title,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'thumbnails': thumbnails,
+        }