check if title is extracted, if not set failure

agr_literature_service/lit_processing/pdf2tei/pdf2tei.py

@@ -6,6 +6,7 @@
 from fastapi import UploadFile
 from sqlalchemy import create_engine
 from sqlalchemy.orm import sessionmaker
+from lxml import etree
 
 from agr_literature_service.api.crud.referencefile_crud import get_main_pdf_referencefile_id, download_file, file_upload
 from agr_literature_service.api.crud.workflow_tag_crud import get_jobs, job_change_atp_code
@@ -57,7 +58,10 @@ def main():
                     "is_annotation": None,
                     "mod_abbreviation": mod_abbreviation
                 }
-                if response.content == "[NO_BLOCKS] PDF parsing resulted in empty content":
+                root = etree.fromstring(response.content)  # Check for empty elements that indicate failure
+                title = root.xpath('//tei:title[@level="a"]', namespaces={'tei': 'http://www.tei-c.org/ns/1.0'})
+                if (response.content == "[NO_BLOCKS] PDF parsing resulted in empty content" or title is None or
+                        title[0].text is None):
                     job_change_atp_code(db, reference_workflow_tag_id, "on_failed")
                 else:
                     file_upload(db=db, metadata=metadata, file=UploadFile(file=BytesIO(response.content),

requirements.txt

@@ -52,3 +52,4 @@ bs4==0.0.1                   # No update needed.
 elasticsearch==7.13.4        # No update needed.
 retry==0.9.2                 # No update needed.
 cachetools==5.3.1            # Updated for better performance.
+lxml==4.9.4