From 082dfa495e6e4e7a3a8da36b93e04b7c7a4525f2 Mon Sep 17 00:00:00 2001
From: Fynn <fynn_kroeger@web.de>
Date: Mon, 6 Sep 2021 14:10:01 +0200
Subject: [PATCH] [snapchat] Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/snapchat.py   | 64 ++++++++++++++++++++++++++++++
 2 files changed, 65 insertions(+)
 create mode 100644 youtube_dl/extractor/snapchat.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 6e8fc3961..58ce207d3 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -1109,6 +1109,7 @@ from .sky import (
 from .slideshare import SlideshareIE
 from .slideslive import SlidesLiveIE
 from .slutload import SlutloadIE
+from .snapchat import SnapchatIE
 from .snotr import SnotrIE
 from .sohu import SohuIE
 from .sonyliv import SonyLIVIE
diff --git a/youtube_dl/extractor/snapchat.py b/youtube_dl/extractor/snapchat.py
new file mode 100644
index 000000000..37389d5d6
--- /dev/null
+++ b/youtube_dl/extractor/snapchat.py
@@ -0,0 +1,64 @@
+# coding: utf-8
+from __future__ import unicode_literals
+import re
+
+from ..utils import unified_timestamp, parse_duration
+from .common import InfoExtractor
+
+
+class SnapchatIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?story.snapchat\.com/o/(?P<id>\w+)'
+    _TEST = {
+        'url': 'https://story.snapchat.com/o/W7_EDlXWTBiXAEEniNoMPwAAYuz9_1mcdex8MAXndPyIOAXndPyFyAO1OAA',
+        'md5': 'ab1900981cadcd955aae32a526096cbd',
+        'info_dict': {
+            'id': 'W7_EDlXWTBiXAEEniNoMPwAAYuz9_1mcdex8MAXndPyIOAXndPyFyAO1OAA',
+            'ext': 'mp4',
+            'title': 'W7_EDlXWTBiXAEEniNoMPwAAYuz9_1mcdex8MAXndPyIOAXndPyFyAO1OAA',
+            'thumbnail': 'https://s.sc-cdn.net/p9mgs8YyMZzfFRls4HGZxwXWBGVF-cEa6ZYPuCT2xPk=/default/preview.jpg',
+            'description': '#spotlight',
+            'timestamp': 1622914559,
+            'upload_date': '20210605',
+            'view_count': 62100,
+            'uploader_id': None
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        schema_video_object_raw = self._html_search_regex(r'<script data-react-helmet="true" type="application/ld\+json">(.+)</script>',
+                                                          webpage, 'schema_video_object')
+        schema_video_object = self._parse_json(schema_video_object_raw, video_id, fatal=True)
+        video_url = schema_video_object.get('contentUrl')
+        title = schema_video_object.get('name')
+        if not title:
+            matching = re.match(r'sc-cdn.net/\w+/(\w+)', video_url)
+            if matching:
+                title = matching.group(1)
+        if not title:
+            title = video_id
+
+        try:
+            views = schema_video_object.get('interactionStatistic').get('userInteractionCount')
+        except AttributeError:
+            views = None
+
+        try:
+            uploader_id = schema_video_object.get('creator').get('alternateName')
+        except AttributeError:
+            uploader_id = None
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'ext': 'mp4',
+            'thumbnail': schema_video_object.get('thumbnailUrl'),
+            'timestamp': unified_timestamp(schema_video_object.get('uploadDate')),
+            'description': schema_video_object.get('description'),
+            'duration': parse_duration(schema_video_object.get('duration')),
+            'view_count': views,
+            'uploader_id': uploader_id
+        }