[SpankBangPlaylist] Add new extractor

youtube_dl/extractor/extractors.py

@@ -1058,7 +1058,10 @@
     SouthParkEsIE,
     SouthParkNlIE
 )
-from .spankbang import SpankBangIE
+from .spankbang import (
+    SpankBangIE,
+    SpankBangPlaylistIE,
+)
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE

youtube_dl/extractor/spankbang.py

@@ -8,6 +8,7 @@
     parse_duration,
     parse_resolution,
     str_to_int,
+    urljoin,
 )
 
 
@@ -94,3 +95,39 @@ def _real_extract(self, url):
             'formats': formats,
             'age_limit': age_limit,
         }
+
+
+class SpankBangPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist'
+    _TEST = {
+        'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
+        'info_dict': {
+            'id': 'ug0k',
+            'title': 'Big Ass Titties playlist',
+        },
+        'playlist_mincount': 2,
+    }
+
+    def _extract_entries(self, webpage, p_id):
+        video_items = re.findall(r'<div[^>]+class=[\'"].*?video-item[^>]*>\s*(.+?)>', webpage)
+
+        entries = []
+        for div in video_items:
+            page_url = self._search_regex(
+                r'href="/?(' + p_id + '-[\da-z]+/playlist/[^"]+)', div, 'page url', default=None)
+
+            if page_url:
+                page = self._download_webpage(urljoin('http://spankbang.com', page_url), p_id)
+                canonical_url = self._search_regex(
+                    r'link rel="canonical" href="(.+?)"', page, 'canonical url')
+                entries.append(self.url_result(canonical_url, SpankBangIE.ie_key()))
+        return entries
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = self._extract_entries(webpage, playlist_id)
+        title = self._search_regex(r'<h1>(.+)</h1>', webpage, 'playlist_title', fatal=False)
+
+        return self.playlist_result(entries, playlist_id, title)