initial commit

app.py

@@ -79,39 +79,39 @@ with open('data/'+contracts_files[idx]) as f:
 # print(user_upload)
 
 # process upload
-if user_upload is not None:
-    print(user_upload.name, user_upload.type)
-    extension = user_upload.name.split('.')[-1].lower()
-    if extension == 'txt':
-        print('text file uploaded')
-         # To convert to a string based IO:
-        stringio = StringIO(user_upload.getvalue().decode("utf-8"))
-
-        # To read file as string:
-        contract_data = stringio.read()
-
-    elif extension == 'pdf':
-        import PyPDF4
-        try:
-            # Extracting Text from PDFs
-            pdfReader = PyPDF4.PdfFileReader(user_upload)
-            print(pdfReader.numPages)
-            contract_data = ''
-            for i in range(0, pdfReader.numPages):
-
-                print(i)
-                pageobj = pdfReader.getPage(i)
-                contract_data = contract_data + pageobj.extractText()
-        except:
-            st.warning('Unable to read PDF, please try another file')
-
-    elif extension == 'docx':
-        import docx2txt
-
-        contract_data = docx2txt.process(user_upload)
-
-    else:
-        st.warning('Unknown uploaded file type, please try again')
+# if user_upload is not None:
+#     print(user_upload.name, user_upload.type)
+#     extension = user_upload.name.split('.')[-1].lower()
+#     if extension == 'txt':
+#         print('text file uploaded')
+#          # To convert to a string based IO:
+#         stringio = StringIO(user_upload.getvalue().decode("utf-8"))
+#
+#         # To read file as string:
+#         contract_data = stringio.read()
+#
+#     elif extension == 'pdf':
+#         import PyPDF4
+#         try:
+#             # Extracting Text from PDFs
+#             pdfReader = PyPDF4.PdfFileReader(user_upload)
+#             print(pdfReader.numPages)
+#             contract_data = ''
+#             for i in range(0, pdfReader.numPages):
+#
+#                 print(i)
+#                 pageobj = pdfReader.getPage(i)
+#                 contract_data = contract_data + pageobj.extractText()
+#         except:
+#             st.warning('Unable to read PDF, please try another file')
+#
+#     elif extension == 'docx':
+#         import docx2txt
+#
+#         contract_data = docx2txt.process(user_upload)
+#
+#     else:
+#         st.warning('Unknown uploaded file type, please try again')
 
 results_drop = ['1', '2', '3']
 number_results = st.sidebar.selectbox('Select number of results', results_drop)