Create utils/parser.py

utils/parser.py

@@ -0,0 +1,16 @@
+from pdfminer.high_level import extract_text
+import spacy
+
+nlp = spacy.load("en_core_web_sm")
+
+def parse_cv(file) -> tuple[str, str]:
+    text = extract_text(file)
+    doc = nlp(text)
+    education_keywords = ["Bachelor", "Master", "PhD", "High School", "Diploma"]
+    education_level = "Not Found"
+    for sent in doc.sents:
+        for keyword in education_keywords:
+            if keyword.lower() in sent.text.lower():
+                education_level = keyword
+                break
+    return text, education_level