X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgorillavid.py;h=d23e3eac1aa7a46a82d21a527d06862f245b4e29;hb=7079f8ff1fe524a5711957a426066b94a22a605e;hp=7e8b9f7062996b80b778253609a8fff8cef2db07;hpb=77abae55df363fc005ad664a7fd1946e8866b43f;p=youtube-dl

diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py
index 7e8b9f706..d23e3eac1 100644
--- a/youtube_dl/extractor/gorillavid.py
+++ b/youtube_dl/extractor/gorillavid.py
@@ -1,38 +1,126 @@
-# coding: utf-8
+# -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+from ..utils import (
+    ExtractorError,
+    encode_dict,
+    int_or_none,
+)
+
 
 class GorillaVidIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www.)?gorillavid.in/(?:embed-)?(?P<id>\w+)(?:\-\d+x\d+)?(?:.html)?'
-    _TEST = {
-        'url': "http://gorillavid.in/z08zf8le23c6",
-        'md5': 'c9e293ca74d46cad638e199c3f3fe604',
+    IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com'
+    _VALID_URL = r'''(?x)
+        https?://(?P<host>(?:www\.)?
+            (?: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)?
+    '''
+
+    _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-6GK87Rc8bzQ',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
+        'only_matching': True,
+    }, {
+        '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',
+        }
+    }, {
+        # 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://realvid.net/ctn2y6p2eviw',
+        'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
         'info_dict': {
-            'id': 'z08zf8le23c6',
+            'id': 'ctn2y6p2eviw',
+            'ext': 'flv',
+            'title': 'rdx 1955',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://movpod.in/0wguyyxi1yca',
+        'only_matching': True,
+    }, {
+        'url': 'http://filehoot.com/3ivfabn7573c.html',
+        'info_dict': {
+            'id': '3ivfabn7573c',
             'ext': 'mp4',
-            'title': 'Say something nice',
+            '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')
 
+        url = 'http://%s/%s' % (mobj.group('host'), video_id)
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r"name=['\"]fname['\"]\s+value=['\"](.*?)['\"]", webpage, u"video title")
 
-        # download embed page again with cookies to get url
-        embed_url = "http://gorillavid.in/embed-{0}-960x480.html".format(video_id)
-        webpage = self._download_webpage(embed_url, video_id, note=u'Downloading webpage again (with cookie)')
-        url = self._html_search_regex(r'file:\s+["\'](http://.*?video.\w{3})["\']', webpage, url)
+        if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        fields = self._hidden_inputs(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(encode_dict(fields))
+
+            req = compat_urllib_request.Request(url, post)
+            req.add_header('Content-type', 'application/x-www-form-urlencoded')
 
-        info_dict = {
+            webpage = self._download_webpage(req, video_id, 'Downloading video page')
+
+        title = self._search_regex(
+            [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')
+        thumbnail = self._search_regex(
+            r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False)
+
+        formats = [{
+            'format_id': 'sd',
+            'url': video_url,
+            'quality': 1,
+        }]
+
+        return {
             'id': video_id,
             'title': title,
-            'url': url,
+            'thumbnail': thumbnail,
+            'formats': formats,
         }
-
-        return info_dict