Merge pull request #185 from dod-advana/hotfix/samm_spider

changed display_doc_type for the docs
dod-advana · Aug 10, 2023 · e873a08 · e873a08
2 parents 3ae68b1 + 9ca3efd
commit e873a08
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/dataPipelines/gc_scrapy/gc_scrapy/spiders/samm_spider.py b/dataPipelines/gc_scrapy/gc_scrapy/spiders/samm_spider.py
@@ -69,7 +69,7 @@ def parse_document_page_chapters(self, response, chapter, chapter_title):
 
         doc_num = chapter
         doc_type = "SAMM"
-        display_doc_type = "SAMM"
+        display_doc_type = "Document"
         doc_name = " ".join([doc_type, chapter])
         doc_name = doc_name.replace(" ", "_")
 
@@ -107,7 +107,7 @@ def parse_document_page_memos(self, response, doc_title, doc_name, publication_d
                 doc_type = "SAMM Policy Memoranda"
 
                 doc_name = self.ascii_clean(doc_name.replace(" ", "_"))
-                display_doc_type = "SAMM"
+                display_doc_type = "Memorandum"
 
                 doc_name = re.sub(r'[\(\),]', '', doc_name)  # Remove parentheses and commas
                 doc_name = re.sub(r'[\W_\.]+$', '', doc_name)  # Remove any special characters at the end