From 50c911507b6d32522d2856cff6cf4460bd9893f6 Mon Sep 17 00:00:00 2001
From: misha shelemetyev <misha.shelemetyev@onforce.com>
Date: Fri, 8 Jul 2016 15:12:21 -0400
Subject: [PATCH] Lets fix vk videos

---
 README.md                    |  2 +-
 src/you_get/extractors/vk.py | 14 ++++++++------
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index aa7f61a0..d3d44b33 100644
--- a/README.md
+++ b/README.md
@@ -318,7 +318,7 @@ Use `--url`/`-u` to get a list of downloadable resource URLs extracted from the
 | :--: | :-- | :-----: | :-----: | :-----: |
 | **YouTube** | <https://www.youtube.com/>    |✓| | |
 | **Twitter** | <https://twitter.com/>        |✓|✓| |
-| VK          | <http://vk.com/>              |✓| | |
+| VK          | <http://vk.com/>              |✓|✓| |
 | Vine        | <https://vine.co/>            |✓| | |
 | Vimeo       | <https://vimeo.com/>          |✓| | |
 | Vidto       | <http://vidto.me/>            |✓| | |
diff --git a/src/you_get/extractors/vk.py b/src/you_get/extractors/vk.py
index 6ad6624d..ea3e3851 100644
--- a/src/you_get/extractors/vk.py
+++ b/src/you_get/extractors/vk.py
@@ -7,12 +7,14 @@ from ..common import *
 
 def get_video_info(url):
     video_page = get_content(url)
-    title = unescape_html(r1(r'"title":"([^"]+)"', video_page))
-    info = dict(re.findall(r'\\"url(\d+)\\":\\"([^"]+)\\"', video_page))
+    title = r1(r'<div class="vv_summary">(.[^>]+?)</div', video_page)
+    sources = re.findall(r'<source src=\"(.[^>]+?)"', video_page)
+
     for quality in ['1080', '720', '480', '360', '240']:
-        if quality in info:
-            url = re.sub(r'\\\\\\/', r'/', info[quality])
-            break
+        for source in sources:
+            if source.find(quality) != -1:
+                url = source
+                break
     assert url
     type, ext, size = url_info(url)
     print_info(site_info, title, type, size)
@@ -37,7 +39,7 @@ def get_image_info(url):
 
 def vk_download(url, output_dir='.', stream_type=None, merge=True, info_only=False, **kwargs):
     link = None
-    if re.match(r'vk.com/photo', url):
+    if re.match(r'(.+)z\=video(.+)', url):
         link, title, ext, size = get_video_info(url)
     elif re.match(r'(.+)vk\.com\/photo(.+)', url):
         link, title, ext, size = get_image_info(url)