Replace a couple more problematic links

CHANGELOG.md

@@ -15,6 +15,8 @@ The format is based on Keep a Changelog, and this project adheres to Semantic Ve
 ### Fixed
 
 - Replace "www.grants.gov/web/grants/search-grants.html" with "grants.gov/search-grants"
+- Replace "www.grants.gov/web/grants/forms/sf-424-family.html" with "grants.gov/forms/forms-repository/sf-424-family"
+- Replace "www.cdc.gov/grants/dictionary/index.html" with "www.cdc.gov/grants/dictionary/index.html"
 
 ## [1.37.0] - 2023-11-21
 

bloom_nofos/nofos/nofo.py

@@ -37,11 +37,29 @@ def replace_chars(file_content):
         ("\u00A8", "\u25FB"),
         # from () U+007F DELETE to (◻) U+25FB WHITE MEDIUM SQUARE
         ("\u007F", "\u25FB"),
-        # replace this "page not found" url with the new one
+    ]
+
+    for _from, _to in replacement_chars:
+        file_content = file_content.replace(_from, _to)
+
+    return file_content
+
+
+def replace_links(file_content):
+    # grants.gov/web links are broken and don't redirect _and_ say they are 200 🙄
+    replacement_chars = [
         (
             "www.grants.gov/web/grants/search-grants.html",
             "grants.gov/search-grants",
         ),
+        (
+            "www.grants.gov/web/grants/forms/sf-424-family.html",
+            "grants.gov/forms/forms-repository/sf-424-family",
+        ),
+        (
+            "www.cdc.gov/grants/dictionary/index.html",
+            "www.cdc.gov/grants/dictionary-of-terms/",
+        ),
     ]
 
     for _from, _to in replacement_chars:

bloom_nofos/nofos/views.py

@@ -85,6 +85,7 @@
     preserve_table_heading_links,
     remove_google_tracking_info_from_links,
     replace_chars,
+    replace_links,
     replace_src_for_inline_images,
     suggest_all_nofo_fields,
     suggest_nofo_title,
@@ -297,8 +298,10 @@ def nofo_import(request, pk=None):
             )
             return redirect(view_path, **kwargs)
 
-        # replace problematic characters on import
+        # replace problematic characters/links on import
         cleaned_content = replace_chars(file_content)
+        cleaned_content = replace_links(file_content)
+
         soup = BeautifulSoup(cleaned_content, "html.parser")  # Parse the cleaned HTML
         soup = add_body_if_no_body(soup)