youtube-dl

commit: 49bd993fd9adbcf6b5c11a7ec11c2b4a552e49c5
parent f06a1cabe8b3831b5f2ff3bc27f5e7336c597e92
Author: Sergey M․ <dstftw@gmail.com>
Date:   Fri,  8 Feb 2019 00:09:50 +0700

[spankbang:playlist] Add extractor (closes #19145)

Diffstat:
M
youtube_dl/extractor/extractors.py
5
++++-
M
youtube_dl/extractor/spankbang.py
33
++++++++++++++++++++++++++++++++-

2 files changed, 36 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -1058,7 +1058,10 @@ from .southpark import (
     SouthParkEsIE,
     SouthParkNlIE
 )
-from .spankbang import SpankBangIE
+from .spankbang import (
+    SpankBangIE,
+    SpankBangPlaylistIE,
+)
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py
@@ -5,6 +5,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    orderedSet,
     parse_duration,
     parse_resolution,
     str_to_int,
@@ -12,7 +13,7 @@ from ..utils import (
 
 
 class SpankBangIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'
     _TESTS = [{
         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
         'md5': '1cc433e1d6aa14bc376535b8679302f7',
@@ -103,3 +104,33 @@ class SpankBangIE(InfoExtractor):
             'formats': formats,
             'age_limit': age_limit,
         }
+
+
+class SpankBangPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?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_mincount': 50,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
+
+        entries = [self.url_result(
+            'https://spankbang.com/%s/video' % video_id,
+            ie=SpankBangIE.ie_key(), video_id=video_id)
+            for video_id in orderedSet(re.findall(
+                r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
+
+        title = self._html_search_regex(
+            r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
+            fatal=False)
+
+        return self.playlist_result(entries, playlist_id, title)