From e0350009ded3344964249867e219cb9586f5b5a3 Mon Sep 17 00:00:00 2001
From: Smacking Potato <smackingpotato@proton.me>
Date: Wed, 20 Nov 2024 00:51:13 +0000
Subject: [PATCH] [motherless] improve and tidy patterns

---
 gallery_dl/extractor/motherless.py | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/gallery_dl/extractor/motherless.py b/gallery_dl/extractor/motherless.py
index d13122fa6a..1054e4482e 100644
--- a/gallery_dl/extractor/motherless.py
+++ b/gallery_dl/extractor/motherless.py
@@ -26,7 +26,7 @@ class MotherlessExtractor(Extractor):
 class MotherlessMediaExtractor(MotherlessExtractor):
     """Extractor for a single image/video from motherless.com"""
 
-    pattern = ROOT_URL_PATTERN + "/((?!GV|GI|G)[A-Z0-9]+)$"
+    pattern = ROOT_URL_PATTERN + "/(?!G)([A-Z0-9]+)$"
     example = "https://motherless.com/ABC123"
     directory_fmt = ("{category}",)
 
@@ -107,8 +107,8 @@ def items(self):
 
         page = self.request(f"{self.root}/G{self.gallery_id}").text
         data = {
-            "gallery_id" : self.gallery_id, 
-            "gallery_title": get_gallery_name_from_homepage(page), 
+            "gallery_id" : self.gallery_id,
+            "gallery_title": get_gallery_name_from_homepage(page),
             "uploader": get_gallery_uploader(page),
             "count": get_gallery_image_count(page)}
 
@@ -137,7 +137,7 @@ def items(self):
         self.gallery_id = re.match(self.pattern, self.url).group(1)
         page = self.request(f"{self.root}/G{self.gallery_id}").text
         data = {
-            "gallery_id" : self.gallery_id, 
+            "gallery_id" : self.gallery_id,
             "gallery_title": get_gallery_name_from_homepage(page),
             "uploader": get_gallery_uploader(page),
             "count": get_gallery_video_count(page)}
@@ -167,11 +167,11 @@ def items(self):
         self.gallery_id = re.match(self.pattern, self.url).group(1)
         page = self.request(f"{self.root}/G{self.gallery_id}").text
         data = {
-            "gallery_id" : self.gallery_id, 
-            "gallery_title": get_gallery_name_from_homepage(page), 
+            "gallery_id" : self.gallery_id,
+            "gallery_title": get_gallery_name_from_homepage(page),
             "uploader": get_gallery_uploader(page),
             "count": get_gallery_image_count(page) + get_gallery_video_count(page)}
-        
+
         yield Message.Directory, data
 
         for id, url, extension, title, num in get_images(self):
@@ -205,10 +205,10 @@ def get_images(extractor):
         page = extractor.request(f"{extractor.root}/GI{extractor.gallery_id}?page={n}").text
         page_count = 0
 
-        for result in re.finditer(f' src="https:\/\/cdn5-thumbs\.motherlessmedia\.com\/thumbs\/([A-Z0-9]+?)\.(jpg|gif)"[\s\S]+?alt="(.+)"', page):
+        for result in re.finditer(f' src="https://cdn5-thumbs\.motherlessmedia\.com/thumbs/([A-Z0-9]+?)\.([a-zA-Z]+)"[\s\S]+?alt="(.+)"', page):
             id = result.group(1)
-            url = f"https://cdn5-images.motherlessmedia.com/images/{id}.jpg"
             extension = result.group(2)
+            url = f"https://cdn5-images.motherlessmedia.com/images/{id}.{extension}"
             title = result.group(3)
             page_count += 1
 
@@ -228,7 +228,7 @@ def get_videos(extractor):
         page = extractor.request(f"{extractor.root}/GV{extractor.gallery_id}?page={n}").text
         page_count = 0
 
-        for result in re.finditer(f'thumbs\/([A-Z0-9]+?)-strip\.jpg" alt="(.+)"', page):
+        for result in re.finditer('thumbs/([A-Z0-9]+?)-strip\.jpg" alt="(.+)"', page):
             id = result.group(1)
             url = f"https://cdn5-videos.motherlessmedia.com/videos/{id}.mp4"
             title = result.group(2)
@@ -274,7 +274,7 @@ def get_media_date(page_data):
         return (datetime.now(timezone.utc) - timedelta(days=days_ago)).replace(hour=0, minute=0, second=0, microsecond=0)
 
 def get_media_uploader(page_data):
-    username_html = re.search('class="username">\s+(.+[^\s])\s+<\/span>', page_data).group(1)
+    username_html = re.search('class="username">\s+(.+\S)\s+</span>', page_data).group(1)
     return text.remove_html(username_html)
 
 def get_image_id(image_url):