Fix extraction from youtube.

[youtubedl] / youtube_dl / extractor / vimple.py

diff --git a/youtube_dl/extractor/vimple.py b/youtube_dl/extractor/vimple.py
index 33d370e1ceb1f0d6db418c8575830ac60d4294a4..c74b437668c62c7ac38d085433532c994ab8fbb7 100644 (file)
--- a/youtube_dl/extractor/vimple.py
+++ b/youtube_dl/extractor/vimple.py
@@ -1,86 +1,61 @@
-# coding: utf-8
 from __future__ import unicode_literals
 
-import base64
-import re
-import xml.etree.ElementTree
-import zlib
-
 from .common import InfoExtractor
 from ..utils import int_or_none
 
 
-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',
-            }
-        },
-    ]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+class SprutoBaseIE(InfoExtractor):
+    def _extract_spruto(self, spruto, video_id):
+        playlist = spruto['playlist'][0]
+        title = playlist['title']
+        video_id = playlist.get('videoId') or video_id
+        thumbnail = playlist.get('posterUrl') or playlist.get('thumbnailUrl')
+        duration = int_or_none(playlist.get('duration'))
 
-        iframe_url = 'http://player.vimple.ru/iframe/%s' % video_id
+        formats = [{
+            'url': f['url'],
+        } for f in playlist['video']]
+        self._sort_formats(formats)
 
-        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()
-
-        player = zlib.decompress(player[8:])
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }
 
-        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)
+class VimpleIE(SprutoBaseIE):
+    IE_DESC = 'Vimple - one-click video hosting'
+    _VALID_URL = r'https?://(?:player\.vimple\.(?:ru|co)/iframe|vimple\.(?:ru|co))/(?P<id>[\da-f-]{32,36})'
+    _TESTS = [{
+        'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf',
+        'md5': '2e750a330ed211d3fd41821c6ad9a279',
+        'info_dict': {
+            'id': 'c0f6b168-7dcd-4000-a97e-be70068039cf',
+            'ext': 'mp4',
+            'title': 'Sunset',
+            'duration': 20,
+            'thumbnail': r're:https?://.*?\.jpg',
+        },
+    }, {
+        'url': 'http://player.vimple.ru/iframe/52e1beec-1314-4a83-aeac-c61562eadbf9',
+        'only_matching': True,
+    }, {
+        'url': 'http://vimple.co/04506a053f124483b8fb05ed73899f19',
+        'only_matching': True,
+    }]
 
-        xml_data = xml.etree.ElementTree.fromstring(xml_data)
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
 
-        video = xml_data.find('Video')
-        quality = video.get('quality')
-        q_tag = video.find(quality.capitalize())
+        webpage = self._download_webpage(
+            'http://player.vimple.ru/iframe/%s' % video_id, video_id)
 
-        formats = [
-            {
-                'url': q_tag.get('url'),
-                'tbr': int(q_tag.get('bitrate')),
-                'filesize': int(q_tag.get('filesize')),
-                'format_id': quality,
-            },
-        ]
+        spruto = self._parse_json(
+            self._search_regex(
+                r'sprutoData\s*:\s*({.+?}),\r\n', webpage, 'spruto data'),
+            video_id)
 
-        return {
-            'id': video_id,
-            'title': video.find('Title').text,
-            'formats': formats,
-            'thumbnail': video.find('Poster').get('url'),
-            'duration': int_or_none(video.get('duration')),
-            'webpage_url': video.find('Share').get('videoPageUrl'),
-        }
+        return self._extract_spruto(spruto, video_id)