fix: extractor for speakerdeck.com

mikf · Jun 13, 2024 · 230c018 · 230c018
1 parent c6fc028
commit 230c018
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/gallery_dl/extractor/speakerdeck.py b/gallery_dl/extractor/speakerdeck.py
@@ -8,6 +8,8 @@
 
 """Extractors for https://speakerdeck.com/"""
 
+import re
+
 from .common import Extractor, Message
 from .. import text
 
@@ -60,4 +62,5 @@ def get_image_urls(self):
         """Extract and return a list of all image-urls"""
         page = self.request("https://speakerdeck.com/player/" +
                             self.presentation_id).text
+        page = re.sub(r"\s+", " ", page.replace("\n", " "))
         return list(text.extract_iter(page, 'js-sd-slide" data-url="', '"'))