Imported Upstream version 2014.11.21

[youtubedl] / youtube_dl / extractor / gorillavid.py

diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py
index aa15cafc3e169e41708ab2079e20ad0e8b91ce0c..e21e57510d346b3425a37aa12b3bd9c65668bb83 100644 (file)
--- a/youtube_dl/extractor/gorillavid.py
+++ b/youtube_dl/extractor/gorillavid.py
@@ -5,6 +5,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     determine_ext,
     compat_urllib_parse,
     compat_urllib_request,
@@ -12,7 +13,14 @@ from ..utils import (
 
 
 class GorillaVidIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gorillavid\.in/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?'
+    IE_DESC = 'GorillaVid.in, daclips.in and movpod.in'
+    _VALID_URL = r'''(?x)
+        https?://(?P<host>(?:www\.)?
+            (?:daclips\.in|gorillavid\.in|movpod\.in))/
+        (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
+    '''
+
+    _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
 
     _TESTS = [{
         'url': 'http://gorillavid.in/06y9juieqpmi',
@@ -20,7 +28,7 @@ class GorillaVidIE(InfoExtractor):
         'info_dict': {
             'id': '06y9juieqpmi',
             'ext': 'flv',
-            'title': 'Rebecca Black My Moment Official Music Video Reaction',
+            'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
@@ -32,15 +40,28 @@ class GorillaVidIE(InfoExtractor):
             'title': 'Say something nice',
             'thumbnail': 're:http://.*\.jpg',
         },
+    }, {
+        'url': 'http://daclips.in/3rso4kdn6f9m',
+        'md5': '1ad8fd39bb976eeb66004d3a4895f106',
+        'info_dict': {
+            'id': '3rso4kdn6f9m',
+            'ext': 'mp4',
+            'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
+            'thumbnail': 're:http://.*\.jpg',
+        }
+    }, {
+        'url': 'http://movpod.in/0wguyyxi1yca',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        url = 'http://gorillavid.in/%s' % video_id
+        webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id)
 
-        webpage = self._download_webpage(url, video_id)
+        if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
         fields = dict(re.findall(r'''(?x)<input\s+
             type="hidden"\s+
@@ -57,14 +78,14 @@ class GorillaVidIE(InfoExtractor):
 
             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 
-        title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title')
-        thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail')
-        url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url')
+        title = self._search_regex(r'style="z-index: [0-9]+;">([^<]+)</span>', webpage, 'title')
+        video_url = self._search_regex(r'file\s*:\s*\'(http[^\']+)\',', webpage, 'file url')
+        thumbnail = self._search_regex(r'image\s*:\s*\'(http[^\']+)\',', webpage, 'thumbnail', fatal=False)
 
         formats = [{
             'format_id': 'sd',
-            'url': url,
-            'ext': determine_ext(url),
+            'url': video_url,
+            'ext': determine_ext(video_url),
             'quality': 1,
         }]