From 411324c1ab57ddfffbcf61ff9dfa262fe69a7fe8 Mon Sep 17 00:00:00 2001
From: gfabiano <gfabiano40@gmail.com>
Date: Mon, 19 Jun 2017 16:08:16 +0200
Subject: [PATCH] [globalnews] Add new extractor (close #13430)

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/globalnews.py | 56 ++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)
 create mode 100644 youtube_dl/extractor/globalnews.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index edbb4bdde..0c831bdd9 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -389,6 +389,7 @@ from .gfycat import GfycatIE
 from .giantbomb import GiantBombIE
 from .giga import GigaIE
 from .glide import GlideIE
+from .globalnews import GlobalNewsIE
 from .globo import (
     GloboIE,
     GloboArticleIE,
diff --git a/youtube_dl/extractor/globalnews.py b/youtube_dl/extractor/globalnews.py
new file mode 100644
index 000000000..f8dc934cf
--- /dev/null
+++ b/youtube_dl/extractor/globalnews.py
@@ -0,0 +1,56 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class GlobalNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?globalnews\.ca/video/(?P<id>\d+)'
+    _TEST = {
+        'url': "http://globalnews.ca/video/2066998/focus-montreal-doulia-hamad-and-nebras-m-warsi",
+        'info_dict': {
+            'title': "Focus Montreal: Doulia Hamad and Nebras M. Warsi",
+            'id': '469088323881',
+            'ext': 'mp4',
+            'upload_date': '20150621',
+            'description': 'md5:2998a348701a91ddf70fbb773b016a7f',
+            'timestamp': 1434908705,
+            'uploader': 'SHWM-NEW',
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(
+            url,
+            display_id
+        )
+
+        account_id = self._search_regex((
+            r'svp\.platformAccount\s*=\s*(["\']+)(?P<account>.+?)\1',
+            r'svp\.(?:videoSMILUrl|metadataUrl)\s*=\s*(["\']+).*?theplatform[^/]+/(?:s|f)/(?P<account>[^/]+?/).*?\1'),
+            webpage,
+            'account id',
+            group='account'
+        )[:-1]
+        feed_id = self._search_regex((
+            r'svp\.feedId\s*=\s*(["\']+)(?P<feed>.+?)\1',
+            r'svp\.metadataUrl\s*=\s*(["\']+).*?theplatform[^/]+/f/[^/]+?/(?P<feed>[^?/&#]+).*?\1'),
+            webpage,
+            'feed id',
+            group='feed'
+        )
+        platform_id = self._search_regex((
+            r'<span[^<]+class=(["\'])[^\'"]+?the_platform_id_(?P<platformId>\d+)\1\s+?data-v_count_id=\1\2\1',
+            r'svp\.setContentId\(\s*([\'"])(?P<platformId>\d+)\1.*?loadCallback'),
+            webpage,
+            'platform id',
+            group='platformId'
+        )
+
+        return {
+            'display_id': display_id,
+            '_type': 'url_transparent',
+            'url': 'http://feed.theplatform.com/f/%s/%s?byId=%s' % (account_id, feed_id, platform_id),
+            'ie_key': 'ThePlatformFeed'
+        }