Refactor fetch_paper_data to ensure DOI and PDF URL are valid before fetching citation and title

fetch_paper_data.py

@@ -52,19 +52,20 @@ def fetch_paper_data(id):
         else:
             doi = fetch_arxiv_doi(id)
             pdf_url = f"https://arxiv.org/pdf/{id}"
-        citation = fetch_citation(doi).replace('\n', ' ').replace("<i>", "").replace("</i>", "").strip()
-        title = fetch_title(doi).replace('\n', ' ').strip()
-        data['status'] = 'success'
-        data['data'] = {}
-        data['data']['doi'] = doi
-        data['data']['title'] = title
-        data['data']['pdf_url'] = pdf_url
-        data['data']['citation'] = citation
+        if doi and pdf_url:
+            citation = fetch_citation(doi).replace('\n', ' ').replace("<i>", "").replace("</i>", "").strip()
+            title = fetch_title(doi).replace('\n', ' ').strip()
+            data['status'] = 'success'
+            data['data'] = {}
+            data['data']['doi'] = doi
+            data['data']['title'] = title
+            data['data']['pdf_url'] = pdf_url
+            data['data']['citation'] = citation
     except Exception as e:
         data['status'] = 'error'
         print(str(e))
     return json.dumps(data, indent=4, ensure_ascii=False)
 
 if __name__ == '__main__':
-    data = fetch_pmc_pdf('PMC317040')
+    data = fetch_paper_data('PMC317040')
     print(data)