Fix extraction from youtube.

[youtubedl] / youtube_dl / extractor / cloudy.py

diff --git a/youtube_dl/extractor/cloudy.py b/youtube_dl/extractor/cloudy.py
index ae5ba0015a0e5026f2db38eaa103417ddc8ce1da..85ca20eccd0c5bb2e8e39468d6ad62428d918059 100644 (file)
--- a/youtube_dl/extractor/cloudy.py
+++ b/youtube_dl/extractor/cloudy.py
@@ -1,97 +1,60 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..compat import (
-    compat_parse_qs,
-    compat_HTTPError,
-)
 from ..utils import (
-    ExtractorError,
-    HEADRequest,
-    remove_end,
+    str_to_int,
+    unified_strdate,
 )
 
 
 class CloudyIE(InfoExtractor):
     _IE_DESC = 'cloudy.ec'
-    _VALID_URL = r'''(?x)
-        https?://(?:www\.)?cloudy\.ec/
-        (?:v/|embed\.php\?id=)
-        (?P<id>[A-Za-z0-9]+)
-        '''
-    _EMBED_URL = 'http://www.cloudy.ec/embed.php?id=%s'
-    _API_URL = 'http://www.cloudy.ec/api/player.api.php'
-    _MAX_TRIES = 2
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
+    _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',
-        'md5': '5cb253ace826a42f35b4740539bedf07',
+        'md5': '29832b05028ead1b58be86bf319397ca',
         'info_dict': {
             'id': 'af511e2527aac',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Funny Cats and Animals Compilation june 2013',
+            'upload_date': '20130913',
+            'view_count': int,
         }
-    }
-
-    def _extract_video(self, video_id, file_key, error_url=None, try_num=0):
-
-        if try_num > self._MAX_TRIES - 1:
-            raise ExtractorError('Unable to extract video URL', expected=True)
+    }, {
+        'url': 'http://www.cloudy.ec/embed.php?autoplay=1&id=af511e2527aac',
+        'only_matching': True,
+    }]
 
-        form = {
-            'file': video_id,
-            'key': file_key,
-        }
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
 
-        if error_url:
-            form.update({
-                'numOfErrors': try_num,
-                'errorCode': '404',
-                'errorUrl': error_url,
+        webpage = self._download_webpage(
+            'https://www.cloudy.ec/embed.php', video_id, query={
+                'id': video_id,
+                'playerPage': 1,
+                'autoplay': 1,
             })
 
-        player_data = self._download_webpage(
-            self._API_URL, video_id, 'Downloading player data', query=form)
-        data = compat_parse_qs(player_data)
-
-        try_num += 1
+        info = self._parse_html5_media_entries(url, webpage, video_id)[0]
 
-        if 'error' in data:
-            raise ExtractorError(
-                '%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
-                expected=True)
+        webpage = self._download_webpage(
+            'https://www.cloudy.ec/v/%s' % video_id, video_id, fatal=False)
 
-        title = data.get('title', [None])[0]
-        if title:
-            title = remove_end(title, '&asdasdas').strip()
-
-        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_id, file_key, video_url, try_num)
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': title,
-        }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        if webpage:
+            info.update({
+                'title': self._search_regex(
+                    r'<h\d[^>]*>([^<]+)<', webpage, 'title'),
+                'upload_date': unified_strdate(self._search_regex(
+                    r'>Published at (\d{4}-\d{1,2}-\d{1,2})', webpage,
+                    'upload date', fatal=False)),
+                'view_count': str_to_int(self._search_regex(
+                    r'([\d,.]+) views<', webpage, 'view count', fatal=False)),
+            })
 
-        url = self._EMBED_URL % video_id
-        webpage = self._download_webpage(url, video_id)
+        if not info.get('title'):
+            info['title'] = video_id
 
-        file_key = self._search_regex(
-            [r'key\s*:\s*"([^"]+)"', r'filekey\s*=\s*"([^"]+)"'],
-            webpage, 'file_key')
+        info['id'] = video_id
 
-        return self._extract_video(video_id, file_key)
+        return info