Prepare for upload.

[youtubedl] / youtube_dl / extractor / gorillavid.py

diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py
index 1ac1da8569e20b84c2baf38011488d6304a090cb..d23e3eac1aa7a46a82d21a527d06862f245b4e29 100644 (file)
--- a/youtube_dl/extractor/gorillavid.py
+++ b/youtube_dl/extractor/gorillavid.py
@@ -4,20 +4,22 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import (
-    ExtractorError,
-    determine_ext,
+from ..compat import (

     compat_urllib_parse,
     compat_urllib_request,
     compat_urllib_parse,
     compat_urllib_request,

+)
+from ..utils import (
+    ExtractorError,
+    encode_dict,

     int_or_none,
 )
 
 
 class GorillaVidIE(InfoExtractor):
     int_or_none,
 )
 
 
 class GorillaVidIE(InfoExtractor):

-    IE_DESC = 'GorillaVid.in, daclips.in, movpod.in and fastvideo.in'
+    IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com'

     _VALID_URL = r'''(?x)
         https?://(?P<host>(?:www\.)?
     _VALID_URL = r'''(?x)
         https?://(?P<host>(?:www\.)?

-            (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in))/
+            (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com))/

         (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
     '''
 
         (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
     '''
 


@@ -34,13 +36,7 @@ class GorillaVidIE(InfoExtractor):
         },
     }, {
         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
         },
     }, {
         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',

-        'md5': 'c9e293ca74d46cad638e199c3f3fe604',
-        'info_dict': {
-            'id': 'z08zf8le23c6',
-            'ext': 'mp4',
-            'title': 'Say something nice',
-            'thumbnail': 're:http://.*\.jpg',
-        },
+        'only_matching': True,

     }, {
         'url': 'http://daclips.in/3rso4kdn6f9m',
         'md5': '1ad8fd39bb976eeb66004d3a4895f106',
     }, {
         'url': 'http://daclips.in/3rso4kdn6f9m',
         'md5': '1ad8fd39bb976eeb66004d3a4895f106',


@@ -60,26 +56,39 @@ class GorillaVidIE(InfoExtractor):
             'title': 'Man of Steel - Trailer',
             'thumbnail': 're:http://.*\.jpg',
         },
             'title': 'Man of Steel - Trailer',
             'thumbnail': 're:http://.*\.jpg',
         },

+    }, {
+        'url': 'http://realvid.net/ctn2y6p2eviw',
+        'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
+        'info_dict': {
+            'id': 'ctn2y6p2eviw',
+            'ext': 'flv',
+            'title': 'rdx 1955',
+            'thumbnail': 're:http://.*\.jpg',
+        },

     }, {
         'url': 'http://movpod.in/0wguyyxi1yca',
         'only_matching': True,
     }, {
         'url': 'http://movpod.in/0wguyyxi1yca',
         'only_matching': True,

+    }, {
+        'url': 'http://filehoot.com/3ivfabn7573c.html',
+        'info_dict': {
+            'id': '3ivfabn7573c',
+            'ext': 'mp4',
+            'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
+            'thumbnail': 're:http://.*\.jpg',
+        }

     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 

-        webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id)
+        url = 'http://%s/%s' % (mobj.group('host'), 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)
 
 
         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))
+        fields = self._hidden_inputs(webpage)

 
         if fields['op'] == 'download1':
             countdown = int_or_none(self._search_regex(
 
         if fields['op'] == 'download1':
             countdown = int_or_none(self._search_regex(


@@ -88,7 +97,7 @@ class GorillaVidIE(InfoExtractor):
             if countdown:
                 self._sleep(countdown, video_id)
 
             if countdown:
                 self._sleep(countdown, video_id)
 

-            post = compat_urllib_parse.urlencode(fields)
+            post = compat_urllib_parse.urlencode(encode_dict(fields))

 
             req = compat_urllib_request.Request(url, post)
             req.add_header('Content-type', 'application/x-www-form-urlencoded')
 
             req = compat_urllib_request.Request(url, post)
             req.add_header('Content-type', 'application/x-www-form-urlencoded')


@@ -96,7 +105,7 @@ class GorillaVidIE(InfoExtractor):
             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 
         title = self._search_regex(
             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 
         title = self._search_regex(

-            r'style="z-index: [0-9]+;">([^<]+)</span>',
+            [r'style="z-index: [0-9]+;">([^<]+)</span>', r'<td nowrap>([^<]+)</td>', r'>Watch (.+) '],

             webpage, 'title', default=None) or self._og_search_title(webpage)
         video_url = self._search_regex(
             r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')
             webpage, 'title', default=None) or self._og_search_title(webpage)
         video_url = self._search_regex(
             r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')


@@ -106,7 +115,6 @@ class GorillaVidIE(InfoExtractor):
         formats = [{
             'format_id': 'sd',
             'url': video_url,
         formats = [{
             'format_id': 'sd',
             'url': video_url,

-            'ext': determine_ext(video_url),

             'quality': 1,
         }]
 
             'quality': 1,
         }]