Add an extractor for videofy.me (closes #1171)

Also modify find_xpath_attr to accept values with spaces like for id="HQ on"

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index f15caf4b4050b83516f317474fc68088151572f1..c58ef260ae0d69f0b4e277d15f950614aa49b046 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -73,6 +73,7 @@ from .ustream import UstreamIE
 from .vbox7 import Vbox7IE
 from .veoh import VeohIE
 from .vevo import VevoIE
+from .videofyme import VideofyMeIE
 from .vimeo import VimeoIE, VimeoChannelIE
 from .vine import VineIE
 from .c56 import C56IE

diff --git a/youtube_dl/extractor/videofyme.py b/youtube_dl/extractor/videofyme.py
new file mode 100644 (file)
index 0000000..0410667
--- /dev/null
+++ b/youtube_dl/extractor/videofyme.py
@@ -0,0 +1,49 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import (
+    find_xpath_attr,
+    determine_ext,
+)
+
+class VideofyMeIE(InfoExtractor):
+    _VALID_URL = r'https?://(www.videofy.me/.+?|p.videofy.me/v)/(?P<id>\d+)(&|#|$)'
+    IE_NAME = u'videofy.me'
+
+    _TEST = {
+        u'url': u'http://www.videofy.me/thisisvideofyme/1100701',
+        u'file':  u'1100701.mp4',
+        u'md5': u'2046dd5758541d630bfa93e741e2fd79',
+        u'info_dict': {
+            u'title': u'This is VideofyMe',
+            u'description': None,
+            u'uploader': u'VideofyMe',
+            u'uploader_id': u'thisisvideofyme',
+        },
+        
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        config_xml = self._download_webpage('http://sunshine.videofy.me/?videoId=%s' % video_id,
+                                            video_id)
+        config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
+        video = config.find('video')
+        sources = video.find('sources')
+        url_node = find_xpath_attr(sources, 'source', 'id', 'HQ on')
+        if url_node is None:
+            url_node = find_xpath_attr(sources, 'source', 'id', 'HQ off')
+        video_url = url_node.find('url').text
+
+        return {'id': video_id,
+                'title': video.find('title').text,
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                'thumbnail': video.find('thumb').text,
+                'description': video.find('description').text,
+                'uploader': config.find('blog/name').text,
+                'uploader_id': video.find('identifier').text,
+                'view_count': re.search(r'\d+', video.find('views').text).group(),
+                }

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index cf2ea654e892c5f8882a4ecaae19bdcb5afbbbfd..59eeaf4a89084783e1ca2607840b3b7dfc4670f5 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -207,7 +207,7 @@ if sys.version_info >= (2,7):
     def find_xpath_attr(node, xpath, key, val):
         """ Find the xpath xpath[@key=val] """
         assert re.match(r'^[a-zA-Z]+$', key)
-        assert re.match(r'^[a-zA-Z@]*$', val)
+        assert re.match(r'^[a-zA-Z@\s]*$', val)
         expr = xpath + u"[@%s='%s']" % (key, val)
         return node.find(expr)
 else: