Changes

app.py

@@ -14,6 +14,7 @@ from datetime import date
 import numpy as np
 import spacy
 import re
+import docx2txt 
 from sentence_transformers import SentenceTransformer, util
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
@@ -85,16 +86,24 @@ def process_pdf_file(file: bytes =  File(...)):
     return {"content": text}    
 
 @app.post("/uploadJobDescriptionPDF_Fname/")
-def process_pdf_file1(file: bytes =  File(...), data: str = str):
+def process_pdf_file1(file: bytes =  File(...), FileName: str = str):
     # Save file locally for processing
     text =''
-    reserve_pdf_on_memory = io.BytesIO(file)
-    load_pdf = PyPDF2.PdfReader(reserve_pdf_on_memory)
-    for page in load_pdf.pages:
-                text += page.extract_text()
     print(text)
+    if FileName.endswith("pdf"):
+        reserve_pdf_on_memory = io.BytesIO(file)
+        load_pdf = PyPDF2.PdfReader(reserve_pdf_on_memory)
+        for page in load_pdf.pages:
+            text += page.extract_text()
+       
+    elif FileName.endswith("doc") or FileName.endswith("docx"):
+        text = docx2txt.process(file.decode("utf-8"))
+        text = text.read()
+    
+    else:
+        text = file.decode('utf-8')
     # Process saved file
-    return {"content": data}  
+    return {"content": text}  
 @app.get("/ProfileMatch") 
 def ProfileMatchResults():
    dbQuery = "select * from profilematch"
@@ -124,7 +133,7 @@ def ExtractSkills(skill_data: SkillDetails):
 
 @app.post("/uploadJobDescription/")
 def create_upload_file(file: bytes = File(...)):
-    content = file.encode('utf-8').strip()
+    content =  file.decode('utf-8')
     lines = content.split('\n')
     return {"content": lines}
 

requirements.txt

@@ -10,4 +10,5 @@ spacy
 en-core-web-lg @https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.7.1/en_core_web_lg-3.7.1-py3-none-any.whl
 fastapi
 uvicorn
-python-multipart
+python-multipart
+docx2txt