Unify coding cookie

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

diff --git a/youtube_dl/extractor/wrzuta.py b/youtube_dl/extractor/wrzuta.py
index 830649214fbd893dc54419a84c95849ce4011e6b..0f53f1bcb85f409a71d77712b006a57146a9d513 100644 (file)
--- a/youtube_dl/extractor/wrzuta.py
+++ b/youtube_dl/extractor/wrzuta.py
@@ -1,12 +1,14 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     int_or_none,
     qualities,
+    remove_start,
 )
 
 
@@ -26,16 +28,17 @@ class WrzutaIE(InfoExtractor):
             'uploader_id': 'laboratoriumdextera',
             'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd',
         },
+        'skip': 'Redirected to wrzuta.pl',
     }, {
-        'url': 'http://jolka85.wrzuta.pl/audio/063jOPX5ue2/liber_natalia_szroeder_-_teraz_ty',
-        'md5': 'bc78077859bea7bcfe4295d7d7fc9025',
+        'url': 'http://vexling.wrzuta.pl/audio/01xBFabGXu6/james_horner_-_into_the_na_39_vi_world_bonus',
+        'md5': 'f80564fb5a2ec6ec59705ae2bf2ba56d',
         'info_dict': {
-            'id': '063jOPX5ue2',
-            'ext': 'ogg',
-            'title': 'Liber & Natalia Szroeder - Teraz Ty',
-            'duration': 203,
-            'uploader_id': 'jolka85',
-            'description': 'md5:2d2b6340f9188c8c4cd891580e481096',
+            'id': '01xBFabGXu6',
+            'ext': 'mp3',
+            'title': 'James Horner - Into The Na\'vi World [Bonus]',
+            'description': 'md5:30a70718b2cd9df3120fce4445b0263b',
+            'duration': 95,
+            'uploader_id': 'vexling',
         },
     }]
 
@@ -45,7 +48,10 @@ class WrzutaIE(InfoExtractor):
         typ = mobj.group('typ')
         uploader = mobj.group('uploader')
 
-        webpage = self._download_webpage(url, video_id)
+        webpage, urlh = self._download_webpage_handle(url, video_id)
+
+        if urlh.geturl() == 'http://www.wrzuta.pl/':
+            raise ExtractorError('Video removed', expected=True)
 
         quality = qualities(['SD', 'MQ', 'HQ', 'HD'])
 
@@ -82,10 +88,6 @@ class WrzutaIE(InfoExtractor):
         }
 
 
-_ENTRY_PATTERN = r'<a href="(?P<playlist_entry_url>[^"]+)" target="_blank" class="playlist\-file\-page">'
-_PLAYLIST_SIZE_PATTERN = r'<div class="playlist-counter">[0-9]+/([0-9]+)</div>'
-
-
 class WrzutaPlaylistIE(InfoExtractor):
     """
         this class covers extraction of wrzuta playlist entries
@@ -101,10 +103,7 @@ class WrzutaPlaylistIE(InfoExtractor):
     """
 
     IE_NAME = 'wrzuta.pl:playlist'
-
-    _VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/playlista/' \
-                 '(?P<id>[0-9a-zA-Z]+)/.*'
-
+    _VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/playlista/(?P<id>[0-9a-zA-Z]+)'
     _TESTS = [{
         'url': 'http://miromak71.wrzuta.pl/playlista/7XfO4vE84iR/moja_muza',
         'playlist_mincount': 14,
@@ -119,6 +118,9 @@ class WrzutaPlaylistIE(InfoExtractor):
             'id': '6Nj3wQHx756',
             'title': 'Lipiec - Lato 2015 Muzyka Świata',
         },
+    }, {
+        'url': 'http://miromak71.wrzuta.pl/playlista/7XfO4vE84iR',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -126,31 +128,31 @@ class WrzutaPlaylistIE(InfoExtractor):
         playlist_id = mobj.group('id')
         uploader = mobj.group('uploader')
 
-        entries = []
-
         webpage = self._download_webpage(url, playlist_id)
 
-        playlist_size = self._html_search_regex(_PLAYLIST_SIZE_PATTERN, webpage, 'Size of the playlist')
-        playlist_size = int(playlist_size) if playlist_size else 0
+        playlist_size = int_or_none(self._html_search_regex(
+            (r'<div[^>]+class=["\']playlist-counter["\'][^>]*>\d+/(\d+)',
+             r'<div[^>]+class=["\']all-counter["\'][^>]*>(.+?)</div>'),
+            webpage, 'playlist size', default=None))
 
-        playlist_title = self._og_search_title(webpage).replace('Playlista: ', '', 1)
+        playlist_title = remove_start(
+            self._og_search_title(webpage), 'Playlista: ')
 
+        entries = []
         if playlist_size:
-            entries = list(map(
-                lambda entry_url: self.url_result(entry_url),
-                re.findall(_ENTRY_PATTERN, webpage)
-            ))
-
+            entries = [
+                self.url_result(entry_url)
+                for _, entry_url in re.findall(
+                    r'<a[^>]+href=(["\'])(http.+?)\1[^>]+class=["\']playlist-file-page',
+                    webpage)]
             if playlist_size > len(entries):
                 playlist_content = self._download_json(
-                    'http://{uploader_id}.wrzuta.pl/xhr/get_playlist_offset/{playlist_id}'.format(
-                        uploader_id=uploader,
-                        playlist_id=playlist_id,
-                    ),
+                    'http://%s.wrzuta.pl/xhr/get_playlist_offset/%s' % (uploader, playlist_id),
                     playlist_id,
-                    'Downloading playlist content as JSON metadata',
-                    'Unable to download playlist content as JSON metadata',
-                )
-                entries += [self.url_result(entry['filelink']) for entry in playlist_content['files']]
+                    'Downloading playlist JSON',
+                    'Unable to download playlist JSON')
+                entries.extend([
+                    self.url_result(entry['filelink'])
+                    for entry in playlist_content.get('files', []) if entry.get('filelink')])
 
         return self.playlist_result(entries, playlist_id, playlist_title)