Set upstream metadata fields: Bug-Database, Bug-Submit, Repository, Repository-Browse.

[youtubedl] / youtube_dl / extractor / vodlocker.py

diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py
index affef650726d716b7e80aaab5c66dab3bc3ddc28..02c9617d297926b75b62cfdd5a4b33f085a9741a 100644 (file)
--- a/youtube_dl/extractor/vodlocker.py
+++ b/youtube_dl/extractor/vodlocker.py
@@ -1,16 +1,17 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
 from .common import InfoExtractor
 from ..utils import (
-    compat_urllib_parse,
-    compat_urllib_request,
+    ExtractorError,
+    NO_DEFAULT,
+    sanitized_Request,
+    urlencode_postdata,
 )
 
 
 class VodlockerIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
+    _VALID_URL = r'https?://(?:www\.)?vodlocker\.(?:com|city)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
 
     _TESTS = [{
         'url': 'http://vodlocker.com/e8wvyzz4sl42',
@@ -19,40 +20,56 @@ class VodlockerIE(InfoExtractor):
             'id': 'e8wvyzz4sl42',
             'ext': 'mp4',
             'title': 'Germany vs Brazil',
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
         },
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        fields = dict(re.findall(r'''(?x)<input\s+
-            type="hidden"\s+
-            name="([^"]+)"\s+
-            (?:id="[^"]+"\s+)?
-            value="([^"]*)"
-            ''', webpage))
+        if any(p in webpage for p in (
+                '>THIS FILE WAS DELETED<',
+                '>File Not Found<',
+                'The file you were looking for could not be found, sorry for any inconvenience.<',
+                '>The file was removed')):
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        fields = self._hidden_inputs(webpage)
 
         if fields['op'] == 'download1':
             self._sleep(3, video_id)  # they do detect when requests happen too fast!
-            post = compat_urllib_parse.urlencode(fields)
-            req = compat_urllib_request.Request(url, post)
+            post = urlencode_postdata(fields)
+            req = sanitized_Request(url, post)
             req.add_header('Content-type', 'application/x-www-form-urlencoded')
             webpage = self._download_webpage(
                 req, video_id, 'Downloading video page')
 
+        def extract_file_url(html, default=NO_DEFAULT):
+            return self._search_regex(
+                r'file:\s*"(http[^\"]+)",', html, 'file url', default=default)
+
+        video_url = extract_file_url(webpage, default=None)
+
+        if not video_url:
+            embed_url = self._search_regex(
+                r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?vodlocker\.(?:com|city)/embed-.+?)\1',
+                webpage, 'embed url', group='url')
+            embed_webpage = self._download_webpage(
+                embed_url, video_id, 'Downloading embed webpage')
+            video_url = extract_file_url(embed_webpage)
+            thumbnail_webpage = embed_webpage
+        else:
+            thumbnail_webpage = webpage
+
         title = self._search_regex(
             r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
         thumbnail = self._search_regex(
-            r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
-        url = self._search_regex(
-            r'file:\s*"(http[^\"]+)",', webpage, 'file url')
+            r'image:\s*"(http[^\"]+)",', thumbnail_webpage, 'thumbnail', fatal=False)
 
         formats = [{
             'format_id': 'sd',
-            'url': url,
+            'url': video_url,
         }]
 
         return {