summary refs log tree commit diff
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-07-11 11:07:44 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2014-07-11 11:07:44 +0200
commit3a0879c8c801d27087396613d80f83c112a328f9 (patch)
tree81a4614b4c9e865ab7d1589396e6f75344f75d39
parentebf361ce1814f6cca1c9e630cfe19a9ed59d9fff (diff)
parente66ab17a3683bee57482ccce8f6b0a632f03d78e (diff)
downloadyoutube-dl-3a0879c8c801d27087396613d80f83c112a328f9.tar.gz
youtube-dl-3a0879c8c801d27087396613d80f83c112a328f9.tar.xz
youtube-dl-3a0879c8c801d27087396613d80f83c112a328f9.zip
Merge remote-tracking branch 'irtusb/vimple'
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/vimple.py84
2 files changed, 85 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index f43f3f702..44e1708ed 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -337,6 +337,7 @@ from .vimeo import (
     VimeoReviewIE,
     VimeoWatchLaterIE,
 )
+from .vimple import VimpleIE
 from .vine import (
     VineIE,
     VineUserIE,
diff --git a/youtube_dl/extractor/vimple.py b/youtube_dl/extractor/vimple.py
new file mode 100644
index 000000000..f3a807cd3
--- /dev/null
+++ b/youtube_dl/extractor/vimple.py
@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+import re
+import zlib
+import base64
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+
+
+class VimpleIE(InfoExtractor):
+    IE_DESC = 'Vimple.ru'
+    _VALID_URL = r'https?://(player.vimple.ru/iframe|vimple.ru)/(?P<id>[a-f0-9]{10,})'
+    _TESTS = [
+        # Quality: Large, from iframe
+        {
+            'url': 'http://player.vimple.ru/iframe/b132bdfd71b546d3972f9ab9a25f201c',
+            'info_dict': {
+                'id': 'b132bdfd71b546d3972f9ab9a25f201c',
+                'title': 'great-escape-minecraft.flv',
+                'ext': 'mp4',
+                'duration': 352,
+                'webpage_url': 'http://vimple.ru/b132bdfd71b546d3972f9ab9a25f201c',
+            },
+        },
+        # Quality: Medium, from mainpage
+        {
+            'url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd',
+            'info_dict': {
+                'id': 'a15950562888453b8e6f9572dc8600cd',
+                'title': 'DB 01',
+                'ext': 'flv',
+                'duration': 1484,
+                'webpage_url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd',
+            }
+        },
+    ]
+
+    # http://jsunpack-n.googlecode.com/svn-history/r63/trunk/swf.py
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        iframe_url = 'http://player.vimple.ru/iframe/%s' % video_id
+
+        iframe = self._download_webpage(iframe_url, video_id, note='Downloading iframe', errnote='unable to fetch iframe')
+        player_url = self._html_search_regex(r'"(http://player.vimple.ru/flash/.+?)"', iframe, 'player url')
+
+        player = self._request_webpage(player_url, video_id, note='Downloading swf player').read()
+
+        # http://stackoverflow.com/a/6804758
+        # http://stackoverflow.com/a/12073686
+        player = zlib.decompress(player[8:])
+
+        xml_pieces = re.findall(b'([a-zA-Z0-9 =+/]{500})', player)
+        xml_pieces = [piece[1:-1] for piece in xml_pieces]
+
+        xml_data = b''.join(xml_pieces)
+        xml_data = base64.b64decode(xml_data)
+
+        xml_data = xml.etree.ElementTree.fromstring(xml_data)
+
+        video = xml_data.find('Video')
+        quality = video.get('quality')
+        q_tag = video.find(quality.capitalize())
+
+        formats = [
+            {
+                'url': q_tag.get('url'),
+                'tbr': int(q_tag.get('bitrate')),
+                'filesize': int(q_tag.get('filesize')),
+                'format_id': quality,
+            },
+        ]
+
+        return {
+            'id': video_id,
+            'title': video.find('Title').text,
+            'formats': formats,
+            'thumbnail': video.find('Poster').get('url'),
+            'duration': int(video.get('duration')),
+            'webpage_url': video.find('Share').get('videoPageUrl'),
+        }