Add whitespace between text from different pages

Rutledge · Mar 27, 2023 · 53943ef · 53943ef
1 parent ea32c2a
commit 53943ef
Showing 1 changed file with 1 addition and 3 deletions.
diff --git a/services/file.py b/services/file.py
@@ -45,9 +45,7 @@ def extract_text_from_file(file: BufferedReader, mimetype: str) -> str:
     if mimetype == "application/pdf":
         # Extract text from pdf using PyPDF2
         reader = PdfReader(file)
-        extracted_text = ""
-        for page in reader.pages:
-            extracted_text += page.extract_text()
+        extracted_text = " ".join([page.extract_text() for page in reader.pages])
     elif mimetype == "text/plain" or mimetype == "text/markdown":
         # Read text from plain text file
         extracted_text = file.read().decode("utf-8")