[periscope:user] Add new extractor for user pages

Closes #9388

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index aac85066fd6de4839f0fa28cbc498c63decfe00f..c9d1422e520112c46b9d6822ef17fa3be3543960 100644 (file)
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -561,7 +561,10 @@ from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
 from .people import PeopleIE
-from .periscope import PeriscopeIE
+from .periscope import (
+    PeriscopeIE,
+    PeriscopeUserIE,
+)
 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
index 514e9b4339be43b509f9c9a8a6d2b87187e5f056..0a4bc761d3a1729f7d653dcff63073678a48d5b4 100644 (file)
--- a/youtube_dl/extractor/periscope.py
+++ b/youtube_dl/extractor/periscope.py
@@ -7,6 +7,7 @@ from ..utils import parse_iso8601
 
 class PeriscopeIE(InfoExtractor):
     IE_DESC = 'Periscope'
+    IE_NAME = 'periscope'
     _VALID_URL = r'https?://(?:www\.)?periscope\.tv/[^/]+/(?P<id>[^/?#]+)'
     # Alive example URLs can be found here http://onperiscope.com/
     _TESTS = [{
@@ -79,3 +80,39 @@ class PeriscopeIE(InfoExtractor):
             'thumbnails': thumbnails,
             'formats': formats,
         }
+
+
+class PeriscopeUserIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.periscope\.tv/(?P<id>[^/]+)/?$'
+    IE_DESC = 'Periscope user videos'
+    IE_NAME = 'periscope:user'
+
+    _TEST = {
+        'url': 'https://www.periscope.tv/LularoeHusbandMike/',
+        'info_dict': {
+            'id': 'LularoeHusbandMike',
+            'title': 'LULAROE HUSBAND MIKE',
+        },
+        # Periscope only shows videos in the last 24 hours, so it's possible to
+        # get 0 videos
+        'playlist_mincount': 0,
+    }
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, user_id)
+
+        broadcast_data = self._parse_json(self._html_search_meta(
+            'broadcast-data', webpage, default='{}'), user_id)
+        username = broadcast_data.get('user', {}).get('display_name')
+        user_broadcasts = self._parse_json(
+            self._html_search_meta('user-broadcasts', webpage, default='{}'),
+            user_id)
+
+        entries = [
+            self.url_result(
+                'https://www.periscope.tv/%s/%s' % (user_id, broadcast['id']))
+            for broadcast in user_broadcasts.get('broadcasts', [])]
+
+        return self.playlist_result(entries, user_id, username)