From 89b2983b3f4bd3160b1e8cccd70ee36c30ffe729 Mon Sep 17 00:00:00 2001
From: quinlander <rryanq@gmail.com>
Date: Sun, 14 Apr 2019 20:04:08 -0400
Subject: [PATCH] Added changba import and implemented simple changba extractor
 with single test

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

diff --git a/youtube_dl/extractor/changba.py b/youtube_dl/extractor/changba.py
new file mode 100644
index 000000000..1fbf7968f
--- /dev/null
+++ b/youtube_dl/extractor/changba.py
@@ -0,0 +1,51 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+import re
+
+class ChangbaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?changba\.com/s/(?P<id>[0-9A-Za-z-_]+)'
+    _TEST = {
+        'url': 'https://changba.com/s/0GHVw6vyXv9N2FhaFi2WJg',
+        'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
+        'info_dict': {
+            'id': '1152860688',
+            'ext': 'mp4',
+            'title': 'Video title goes here',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            # TODO more properties, either as:
+            # * A value
+            # * MD5 checksum; start the string with md5:
+            # * A regular expression; start the string with re:
+            # * Any Python type (for example int or float)
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        id = self._search_regex(r'workid=([0-9]+)', webpage, 'id')
+        isvideo = self._search_regex(r'&isvideo=([0-9])', webpage, 'isvideo')
+        title = self._search_regex(r'<div[^>]+class="title"[^>]*>([^<]+)', webpage, 'title')
+
+        if int(isvideo) == 0:
+            ext = 'mp3'
+            try:
+                url = self._search_regex(r'([a-z]+:\/\/[0-9a-z]+\.changba\.com\/[a-z]+\/[a-z]+\/[0-9]+\/[0-9]+\.mp3)', webpage, 'url')
+            except:
+                url = "http://lzscuw.changba.com/" + str(id) + ".mp3"
+        else:
+            ext = 'mp4'
+            try:
+                url = self._search_regex(r'([a-z]+:\/\/[0-9a-z]+\.changba\.com\/[a-z]+\/[a-z]+\/[0-9]+\/[0-9]+\.mp4)', webpage, 'url')
+            except:
+                url = "http://lzscuw.changba.com/" + str(id) + ".mp4"
+
+        return {
+            'url': url,
+            'id': id,
+            'ext': ext,
+            'title': title
+        }
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index cc19af5c4..a68849319 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -185,6 +185,7 @@ from .ceskatelevize import (
     CeskaTelevizeIE,
     CeskaTelevizePoradyIE,
 )
+from .changba import ChangbaIE
 from .channel9 import Channel9IE
 from .charlierose import CharlieRoseIE
 from .chaturbate import ChaturbateIE