From 04fe6cd5a406bb0767314d3a66cdb75b479c050d Mon Sep 17 00:00:00 2001
From: misha shelemetyev <misha.shelemetyev@onforce.com>
Date: Thu, 7 Jul 2016 16:57:38 -0400
Subject: [PATCH] you get vk photos

---
 src/you_get/extractors/vk.py | 38 +++++++++++++++++++++++++++++++-----
 1 file changed, 33 insertions(+), 5 deletions(-)

diff --git a/src/you_get/extractors/vk.py b/src/you_get/extractors/vk.py
index c83dc48e..6ad6624d 100644
--- a/src/you_get/extractors/vk.py
+++ b/src/you_get/extractors/vk.py
@@ -4,7 +4,8 @@ __all__ = ['vk_download']
 
 from ..common import *
 
-def vk_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
+
+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))
@@ -13,12 +14,39 @@ def vk_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
             url = re.sub(r'\\\\\\/', r'/', info[quality])
             break
     assert url
-
     type, ext, size = url_info(url)
-
     print_info(site_info, title, type, size)
-    if not info_only:
-        download_urls([url], title, ext, size, output_dir, merge=merge)
+
+    return url, title, ext, size
+
+
+def get_image_info(url):
+    image_page = get_content(url)
+    # used for title - vk page owner
+    page_of = re.findall(r'Sender:</dt><dd><a href=.*>(.[^>]+?)</a', image_page)
+    # used for title - date when photo was uploaded
+    photo_date = re.findall(r'<span class="item_date">(.[^>]+?)</span', image_page)
+
+    title = (' ').join(page_of + photo_date)
+    image_link = r1(r'href="([^"]+)" class=\"mva_item\" target="_blank">Download full size', image_page)
+    type, ext, size = url_info(image_link)
+    print_info(site_info, title, type, size)
+
+    return image_link, title, ext, size
+
+
+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):
+        link, title, ext, size = get_video_info(url)
+    elif re.match(r'(.+)vk\.com\/photo(.+)', url):
+        link, title, ext, size = get_image_info(url)
+    else:
+        raise NotImplementedError('Nothing to download here')
+
+    if not info_only and link is not None:
+        download_urls([link], title, ext, size, output_dir, merge=merge)
+
 
 site_info = "VK.com"
 download = vk_download