From 6f59aa934bd5842a57d4c27ace0f3735be18ac27 Mon Sep 17 00:00:00 2001
From: Yen Chi Hsuan <yan12125@gmail.com>
Date: Fri, 6 May 2016 02:14:39 +0800
Subject: [PATCH] [periscope:user] Add new extractor for user pages
Closes #9388
---
youtube_dl/extractor/extractors.py | 5 +++-
youtube_dl/extractor/periscope.py | 37 ++++++++++++++++++++++++++++++
2 files changed, 41 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index aac85066fd..c9d1422e52 100644
--- 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 514e9b4339..0a4bc761d3 100644
--- 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)