Fix "invalid escape sequences" error on Python 3.6

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

diff --git a/youtube_dl/extractor/soundgasm.py b/youtube_dl/extractor/soundgasm.py
index e568ff18cd7002df8c9dfa99c3bc162498833f0e..e004e2c5ab12705c8d9ff5e12b25f53579539c72 100644 (file)
--- a/youtube_dl/extractor/soundgasm.py
+++ b/youtube_dl/extractor/soundgasm.py
@@ -4,10 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import clean_html
 
 
 class SoundgasmIE(InfoExtractor):
+    IE_NAME = 'soundgasm'
     _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_\-]+)/(?P<title>[0-9a-zA-Z_\-]+)'
     _TEST = {
         'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
@@ -27,7 +27,7 @@ class SoundgasmIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
         audio_url = self._html_search_regex(
             r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL')
-        audio_id = re.split('\/|\.', audio_url)[-2]
+        audio_id = re.split(r'\/|\.', audio_url)[-2]
         description = self._html_search_regex(
             r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description',
             fatal=False)
@@ -40,37 +40,25 @@ class SoundgasmIE(InfoExtractor):
             'description': description
         }
 
+
 class SoundgasmProfileIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[0-9a-zA-Z_\-]+)/?$'
+    IE_NAME = 'soundgasm:profile'
+    _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[^/]+)/?(?:\#.*)?$'
     _TEST = {
         'url': 'http://soundgasm.net/u/ytdl',
-        'playlist_count': 1,
         'info_dict': {
-            '_type': 'playlist',
             'id': 'ytdl',
-            'title': 'ytdl'
-        }
+        },
+        'playlist_count': 1,
     }
 
     def _real_extract(self, url):
         profile_id = self._match_id(url)
-        webpage = self._download_webpage(url, profile_id)
-
-        ids = re.findall(r'''<a\s+href=".+?/u/%s/([^/]+)">''' % re.escape(profile_id), webpage)
-        ids = [clean_html(id) for id in ids]
 
-        entries = []
-        for id in ids:
-            entries.append({
-                '_type': 'url',
-                'url': ('http://soundgasm.net/u/%s/%s' % (profile_id, id))
-            })
+        webpage = self._download_webpage(url, profile_id)
 
-        info_dict = {
-            '_type': 'playlist',
-            'id': profile_id,
-            'title': profile_id,
-            'entries': entries
-        }
+        entries = [
+            self.url_result(audio_url, 'Soundgasm')
+            for audio_url in re.findall(r'href="([^"]+/u/%s/[^"]+)' % profile_id, webpage)]
 
-        return info_dict;
+        return self.playlist_result(entries, profile_id)