Fixed case where links could be missed

- Fixed case where links could be missed - Simplified fetching thumbnail URL - Updated download sites
bbtufty · Oct 25, 2024 · 50a261c · 50a261c
1 parent 522d90a
commit 50a261c
Show file tree

Hide file tree

Showing 4 changed files with 10 additions and 6 deletions.
diff --git a/CHANGES.rst b/CHANGES.rst
@@ -1,6 +1,7 @@
 0.3 (Unreleased)
 ================
 
+- Fixed case where links could be missed [#13]
 - GUI updates [#12]
 - Logging updates [#11]
 - Update docs to reflect region preferences [#10]

diff --git a/nxbrew_dl/configs/general.yml b/nxbrew_dl/configs/general.yml
@@ -3,6 +3,7 @@ dl_sites:
   - "FreeDL"
   - "GoFile"
   - "HexLoad"
+  - "HexUpload"
   - "MegaUp"
   - "MixDrop"
 

diff --git a/nxbrew_dl/util/download_tools.py b/nxbrew_dl/util/download_tools.py
@@ -284,7 +284,12 @@ def parse_base_game(
             finding_links = False
 
     # Finally, hunt through to the next tag WITHOUT a link in
-    tag = tag.find_next("p", href=False)
+    found_links = True
+    while found_links:
+        tag = tag.find_next("p", href=False)
+        links = tag.find_all("a", href=True)
+        if len(links) == 0:
+            found_links = False
 
     return tag, base_game_dict
 

diff --git a/nxbrew_dl/util/html_tools.py b/nxbrew_dl/util/html_tools.py
@@ -127,10 +127,7 @@ def get_thumb_url(soup):
         soup (bs4.BeautifulSoup): soup object to find languages in
     """
 
-    # Get the main content, then find the first figure which we'll take as the thumbnail
-    content = soup.find("div", {"id": "content"})
-    thumb = content.findAll("figure")[0]
-    img = thumb.find("img")
-    url = img["src"]
+    img = soup.find("meta", {"property": "og:image"})
+    url = img["content"]
 
     return url