[util] Move compatibility functions out of util

[youtube-dl] / youtube_dl / extractor / cloudy.py

diff --git a/youtube_dl/extractor/cloudy.py b/youtube_dl/extractor/cloudy.py
index 73c6e3d499f09ae27672444e9c5721385d70377d..abf8cc280b3d6f1aeefe8219a1fd0ea5d1224be1 100644 (file)
--- a/youtube_dl/extractor/cloudy.py
+++ b/youtube_dl/extractor/cloudy.py
@@ -4,47 +4,73 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_parse_qs,
     compat_urllib_parse,
+    compat_HTTPError,
+)
+from ..utils import (
+    ExtractorError,
+    HEADRequest,
+    remove_end,
 )
 
 
 class CloudyIE(InfoExtractor):
+    _IE_DESC = 'cloudy.ec and videoraj.ch'
     _VALID_URL = r'''(?x)
-        https?://(?:www\.)?cloudy\.ec/
+        https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.ch)/
         (?:v/|embed\.php\?id=)
         (?P<id>[A-Za-z0-9]+)
         '''
-    _API_URL = 'http://www.cloudy.ec/api/player.api.php?%s'
-    _TEST = {
-        'url': 'https://www.cloudy.ec/v/af511e2527aac',
-        'md5': '5cb253ace826a42f35b4740539bedf07',
-        'info_dict': {
-            'id': 'af511e2527aac',
-            'ext': 'flv',
-            'title': 'Funny Cats and Animals Compilation june 2013',
+    _EMBED_URL = 'http://www.%s/embed.php?id=%s'
+    _API_URL = 'http://www.%s/api/player.api.php?%s'
+    _MAX_TRIES = 2
+    _TESTS = [
+        {
+            'url': 'https://www.cloudy.ec/v/af511e2527aac',
+            'md5': '5cb253ace826a42f35b4740539bedf07',
+            'info_dict': {
+                'id': 'af511e2527aac',
+                'ext': 'flv',
+                'title': 'Funny Cats and Animals Compilation june 2013',
+            }
+        },
+        {
+            'url': 'http://www.videoraj.ch/v/47f399fd8bb60',
+            'md5': '7d0f8799d91efd4eda26587421c3c3b0',
+            'info_dict': {
+                'id': '47f399fd8bb60',
+                'ext': 'flv',
+                'title': 'Burning a New iPhone 5 with Gasoline - Will it Survive?',
+            }
         }
-    }
+    ]
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+    def _extract_video(self, video_host, video_id, file_key, error_url=None, try_num=0):
 
-        url = 'http://www.cloudy.ec/embed.php?id=%s' % video_id
-        webpage = self._download_webpage(url, video_id)
+        if try_num > self._MAX_TRIES - 1:
+            raise ExtractorError('Unable to extract video URL', expected=True)
 
-        file_key = self._search_regex(
-            r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
-        data_url = self._API_URL % compat_urllib_parse.urlencode({
+        form = {
             'file': video_id,
             'key': file_key,
-        })
+        }
+
+        if error_url:
+            form.update({
+                'numOfErrors': try_num,
+                'errorCode': '404',
+                'errorUrl': error_url,
+            })
+
+        data_url = self._API_URL % (video_host, compat_urllib_parse.urlencode(form))
         player_data = self._download_webpage(
             data_url, video_id, 'Downloading player data')
         data = compat_parse_qs(player_data)
 
+        try_num += 1
+
         if 'error' in data:
             raise ExtractorError(
                 '%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
@@ -52,16 +78,33 @@ class CloudyIE(InfoExtractor):
 
         title = data.get('title', [None])[0]
         if title:
-            title = title.replace('&asdasdas', '').strip()
+            title = remove_end(title, '&asdasdas').strip()
 
-        formats = []
-        formats.append({
-            'format_id': 'sd',
-            'url': data.get('url', [None])[0],
-        })
+        video_url = data.get('url', [None])[0]
+
+        if video_url:
+            try:
+                self._request_webpage(HEADRequest(video_url), video_id, 'Checking video URL')
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]:
+                    self.report_warning('Invalid video URL, requesting another', video_id)
+                    return self._extract_video(video_host, video_id, file_key, video_url, try_num)
 
         return {
             'id': video_id,
+            'url': video_url,
             'title': title,
-            'formats': formats,
         }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_host = mobj.group('host')
+        video_id = mobj.group('id')
+
+        url = self._EMBED_URL % (video_host, video_id)
+        webpage = self._download_webpage(url, video_id)
+
+        file_key = self._search_regex(
+            r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
+
+        return self._extract_video(video_host, video_id, file_key)