Added posibility to import PDF files

Author: ViktorUw

app/main.py

@@ -61,6 +61,13 @@ def main():
         st.success("Your summary is ready:")
         st.markdown(result)
 
+        st.download_button(
+            label="Download summary",
+            data=result,
+            file_name="summary.txt",
+            mime="text/plain"
+        )
+
 
 if __name__ == "__main__":
     main()

app/src/file_processor.py

@@ -3,6 +3,7 @@
 import os
 from typing import Optional
 from docx import Document
+import fitz
 #from tests import test_file_ext
 
 class FileProcessor:
@@ -11,7 +12,8 @@ def __init__(self):
         self.file_type: None
         self.supported_types = {
             ".txt": self._read_txt,
-            ".docx": self._read_docx
+            ".docx": self._read_docx,
+            ".pdf": self._read_pdf,
         }
         self.content = None
 
@@ -37,6 +39,13 @@ def  _read_docx(self) -> str:
             text.append(para.text)
         return "\n".join(text)
 
+    def _read_pdf(self) -> str:
+        doc = fitz.open(self.file)
+        text = ""
+        for page in doc:
+            text += page.get_text()
+        return text
+    
 
     def get_content(self) -> Optional[str]:
         if not self.file:

app/tests/test_file_ext.py

@@ -7,7 +7,7 @@
 
 @pytest.mark.parametrize("file_name, expected", [
     (".jpeg", False),
-    (".pdf", False),
+    (".pdf", True),
     (".zip", False),
     (".txt", True),
     (".docx", True),

requirements.txt

@@ -5,4 +5,5 @@ requests
 typing
 pytest
 openai
-python-docx
+python-docx
+pyMuPDF