From 5333bea24f70d141da33b1e6290323538b66ee7a Mon Sep 17 00:00:00 2001
From: Frederic Bournival <fredbournival@gmail.com>
Date: Sun, 19 Apr 2020 17:13:54 -0400
Subject: [PATCH] First implementation for the TV5UnisCa extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/tv5unisca.py  | 51 ++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)
 create mode 100644 youtube_dl/extractor/tv5unisca.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index e407ab3d9..8a24e8c95 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -1181,6 +1181,7 @@ from .tv2dk import (
 from .tv2hu import TV2HuIE
 from .tv4 import TV4IE
 from .tv5mondeplus import TV5MondePlusIE
+from .tv5unisca import TV5UnisCaIE
 from .tva import TVAIE
 from .tvanouvelles import (
     TVANouvellesIE,
diff --git a/youtube_dl/extractor/tv5unisca.py b/youtube_dl/extractor/tv5unisca.py
new file mode 100644
index 000000000..4f126d25e
--- /dev/null
+++ b/youtube_dl/extractor/tv5unisca.py
@@ -0,0 +1,51 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+from ..utils import (
+    get_element_by_id
+)
+
+import re
+
+
+class TV5UnisCaIE(InfoExtractor):
+    IE_DESC = 'TV5UNISCA'
+    _VALID_URL = r'https?://(?:www\.)?tv5unis\.ca/videos/(?P<id>[^?#]+)'
+    _TESTS = []
+    _GEO_BYPASS = False
+
+    def _real_extract(self, format_url):
+
+        display_id = self._match_id(format_url)
+        webpage = self._download_webpage(format_url, display_id)
+
+        next_data_dict = self._parse_json(
+            get_element_by_id('__NEXT_DATA__', webpage), display_id)\
+            .get('props').get('apolloState')
+
+        info_dict = self._json_ld(
+            next_data_dict['$ArtisanBlocksPageMetaData:50.blockConfiguration.pageMetaDataConfiguration']['jsonLd'],
+            display_id
+        )
+
+        formats = []
+        for key in filter(lambda k: re.match(r'\$Video:\d+\.encodings\.', k), next_data_dict.keys()):
+            format_ul = next_data_dict[key].get('url')
+            if not format_ul:
+                continue
+            if format_ul.endswith('.m3u8'):
+                formats.extend(self._extract_m3u8_formats(format_ul, display_id))
+            if format_ul.endswith('.ism/manifest'):
+                formats.extend(self._extract_ism_formats(format_ul, display_id, ism_id='mss', fatal=False))
+            if format_ul.endswith('.mp4'):
+                formats.append({
+                    'url': format_ul,
+                    'format_id': 'http'
+                })
+
+        info_dict['id'] = info_dict['display_id'] = display_id
+        info_dict['formats'] = formats
+
+        return info_dict