Imported Upstream version 2015.01.16

[youtubedl] / youtube_dl / extractor / gorillavid.py

diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py
index ca5f7c4178e23fb6e10e644807175a65f042f296..ae24aff84fd85c6796c7a4374964f70629175f43 100644 (file)
--- a/youtube_dl/extractor/gorillavid.py
+++ b/youtube_dl/extractor/gorillavid.py
@@ -4,28 +4,33 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 )
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
 
 
 class GorillaVidIE(InfoExtractor):
-    IE_DESC = 'GorillaVid.in and daclips.in'
+    IE_DESC = 'GorillaVid.in, daclips.in, movpod.in and fastvideo.in'
     _VALID_URL = r'''(?x)
         https?://(?P<host>(?:www\.)?
-            (?:daclips\.in|gorillavid\.in))/
+            (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.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',
         'md5': '5ae4a3580620380619678ee4875893ba',
         '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',
         },
     }, {
@@ -43,9 +48,22 @@ class GorillaVidIE(InfoExtractor):
         'info_dict': {
             'id': '3rso4kdn6f9m',
             'ext': 'mp4',
-            'title': 'Micro Pig piglets ready on 16th July 2009',
+            'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
+            'thumbnail': 're:http://.*\.jpg',
+        }
+    }, {
+        # video with countdown timeout
+        'url': 'http://fastvideo.in/1qmdn1lmsmbw',
+        'md5': '8b87ec3f6564a3108a0e8e66594842ba',
+        'info_dict': {
+            'id': '1qmdn1lmsmbw',
+            'ext': 'mp4',
+            'title': 'Man of Steel - Trailer',
             'thumbnail': 're:http://.*\.jpg',
         },
+    }, {
+        'url': 'http://movpod.in/0wguyyxi1yca',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -54,14 +72,23 @@ class GorillaVidIE(InfoExtractor):
 
         webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), 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+
             name="([^"]+)"\s+
             (?:id="[^"]+"\s+)?
             value="([^"]*)"
             ''', webpage))
-        
+
         if fields['op'] == 'download1':
+            countdown = int_or_none(self._search_regex(
+                r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
+                webpage, 'countdown', default=None))
+            if countdown:
+                self._sleep(countdown, video_id)
+
             post = compat_urllib_parse.urlencode(fields)
 
             req = compat_urllib_request.Request(url, post)
@@ -69,14 +96,17 @@ 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', default=None) or self._og_search_title(webpage)
+        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,
             'quality': 1,
         }]