Refactor text handling in fix_text function and simplify title escaping in paper_data function

main.py

@@ -19,7 +19,7 @@ def fix_text(text):
             fixed_text += word.encode('latin1').decode('utf-8')+" "
         except:
             fixed_text += word+" "
-    return fixed_text.encode('utf-8').decode().replace("\n", "\\n").replace("\\n", "\\\\n").replace('\\', '\\\\')
+    return fixed_text.encode('utf-8').decode()
 
 def paper_data(paper_data, wait_time=5):
     data = {"status": "success"}
@@ -32,7 +32,7 @@ def paper_data(paper_data, wait_time=5):
                 doi = details.get("doi")
                 pdf_url = details.get("pdf_url")
                 title = details.get("title")
-                title = html.escape(title.encode('unicode-escape').decode().replace('\\\\', '\\'))
+                title = html.escape(title)
                 citation = details.get("citation")
                 if not all([paper_id, doi, pdf_url, title, citation]):
                     print(f"Skipping paper with ID: {paper_id} (missing details)")
@@ -100,8 +100,8 @@ def test(uaccess_key):
         "Economics": {
             "2501.00578":{
                 "paper_id":"2501.00578",
-                "doi":"https://doi.org/10.48550/arXiv.2501.00578",
-                "title":"The Limits of Tolerance",
+                "doi":"https://doi.org/10.1002/alz.14328",
+                "title":"Bound-State Beta Decay of $\\mathbf{\\mathrm{^{205}{Tl}^{81+}}}$ Ions and the LOREX Project",
                 "category":"Economics",
                 "pdf_url":"https://arxiv.org/pdf/2501.00578",
                 "citation":"Miller, A. D. (2025). The limits of tolerance (Version 1). arXiv. https://doi.org/10.48550/ARXIV.2501.00578",