Update pipeline.py

pipeline.py

@@ -267,8 +267,12 @@ async def process_link_chunk_allOutput(link, iso, acc, saveLinkFolder, linksWith
 
     return all_output
 
-async def extractSources(doi, linksWithTexts, links, all_output, iso, acc, saveLinkFolder, niche_cases=None):
+from Bio import Entrez
+Entrez.email = "your_email@example.com"   # required by NCBI
+
+async def extractSources(meta, linksWithTexts, links, all_output, acc, saveLinkFolder, niche_cases=None):
     article_text = ""
+    iso, title, doi, pudID, features = meta["country"], meta["specific_location"], meta["ethnicity"], meta["sample_type"], meta["collection_date"], meta["isolate"], meta["title"], meta["doi"], meta["pubmed_id"], meta["all_features"]
     if doi != "unknown":
         link = 'https://doi.org/' + doi
         # get the file to create listOfFile for each id
@@ -365,9 +369,6 @@ async def extractSources(doi, linksWithTexts, links, all_output, iso, acc, saveL
         if more_linksWithTexts: linksWithTexts.update(more_linksWithTexts)   
     return linksWithTexts, links, all_output
 
-from Bio import Entrez
-Entrez.email = "your_email@example.com"   # required by NCBI
-
 # Main execution
 async def pipeline_with_gemini(accessions,stop_flag=None, save_df=None, niche_cases=None):
   # output: country, sample_type, ethnic, location, money_cost, time_cost, explain
@@ -503,7 +504,7 @@ async def pipeline_with_gemini(accessions,stop_flag=None, save_df=None, niche_ca
             acc_score["file_all_output"] = str(all_filename)    
       print("acc sscore for file all output: ", acc_score["file_all_output"])  
       if len(acc_score["file_all_output"]) == 0 or doi!="unknown":  
-          linksWithTexts, links, all_output = await extractSources(doi, linksWithTexts, links, all_output, iso, acc, sample_folder_id, niche_cases)
+          linksWithTexts, links, all_output = await extractSources(meta, linksWithTexts, links, all_output, acc, sample_folder_id, niche_cases)
           links = unique_preserve_order(links)
           print("this is links: ",links)
           acc_score["source"] = links
@@ -539,14 +540,14 @@ async def pipeline_with_gemini(accessions,stop_flag=None, save_df=None, niche_ca
                 temp_source = True      
             if temp_source:
                 print("temp source is true so have to try again search link")
-                linksWithTexts, links, all_output = await extractSources(doi, linksWithTexts, links, all_output, iso, acc, sample_folder_id, niche_cases)
+                linksWithTexts, links, all_output = await extractSources(meta, linksWithTexts, links, all_output, acc, sample_folder_id, niche_cases)
                 links = unique_preserve_order(links)
                 print("links: ", links)
                 acc_score["source"] = links
         except:
             try:
                 print("in the exception and start to get link")
-                linksWithTexts, links, all_output = await extractSources(doi, linksWithTexts, links, all_output, iso, acc, sample_folder_id, niche_cases)
+                linksWithTexts, links, all_output = await extractSources(meta, linksWithTexts, links, all_output, acc, sample_folder_id, niche_cases)
                 links = unique_preserve_order(links)
                 print("this is links: ",links)
                 acc_score["source"] = links