From: Ken Swenson <flat@esoteric.moe>
Date: Fri, 9 Nov 2018 21:49:20 +0000 (-0500)
Subject: [tiktok] Add extractor (closes #18108)
X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=1ead840d2c18d4add340117f676fd6694f0650d3;p=youtube-dl

[tiktok] Add extractor (closes #18108)
---

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index cd91c0fcb..547331078 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -1124,6 +1124,7 @@ from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .thisoldhouse import ThisOldHouseIE
 from .threeqsdn import ThreeQSDNIE
+from .tiktok import TikTokIE
 from .tinypic import TinyPicIE
 from .tmz import (
     TMZIE,
diff --git a/youtube_dl/extractor/tiktok.py b/youtube_dl/extractor/tiktok.py
new file mode 100644
index 000000000..d71b09c66
--- /dev/null
+++ b/youtube_dl/extractor/tiktok.py
@@ -0,0 +1,79 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+    int_or_none,
+    str_or_none,
+    try_get,
+    url_or_none,
+)
+
+
+class TikTokIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://m.tiktok.com/v/6606727368545406213.html',
+        'md5': 'd584b572e92fcd48888051f238022420',
+        'info_dict': {
+            'id': '6606727368545406213',
+            'ext': 'mp4',
+            'title': 'Zureeal on TikTok',
+            'thumbnail': r're:^https?://.*~noop.image',
+            'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay',
+            'uploader': 'Zureeal',
+            'width': 540,
+            'height': 960,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        data = self._parse_json(
+            self._search_regex(
+                r'var\s+data\s*=\s*({.+?});', webpage, 'data'
+            ), video_id)
+
+        title = self._og_search_title(webpage)
+
+        description = str_or_none(try_get(data, lambda x: x['desc']))
+        width = int_or_none(try_get(data, lambda x: x['video']['width']))
+        height = int_or_none(try_get(data, lambda x: x['video']['height']))
+
+        formats = []
+
+        for count, (key, label) in enumerate((('play_addr_lowbr', 'Low'), ('play_addr', 'Normal'), ('download_addr', 'Download')), -2):
+            for format in try_get(data, lambda x: x['video'][key]['url_list']):
+                format_url = url_or_none(format)
+                if not format_url:
+                    continue
+                formats.append({
+                    'url': format_url,
+                    'ext': 'mp4',
+                    'height': height,
+                    'width': width,
+                    'format_note': label,
+                    'quality': count
+                })
+
+        self._sort_formats(formats)
+
+        uploader = try_get(data, lambda x: x['author']['nickname'], compat_str)
+
+        thumbnail = url_or_none(
+            try_get(
+                data, lambda x: x['video']['cover']['url_list'][0], compat_str))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'uploader': uploader,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'width': width,
+            'height': height,
+        }