Update app.py
Browse files
app.py
CHANGED
|
@@ -29,16 +29,19 @@ if document_file is not None:
|
|
| 29 |
st.error("A dokumentum mérete túl nagy. Kérlek válassz egy kisebb méretű dokumentumot!")
|
| 30 |
else:
|
| 31 |
if document_file.type == "application/pdf":
|
|
|
|
| 32 |
with pdfplumber.open(document_file) as pdf:
|
| 33 |
document_text = ""
|
| 34 |
for page in pdf.pages:
|
| 35 |
document_text += page.extract_text()
|
| 36 |
elif document_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
|
|
|
|
| 37 |
docx_file = docx.Document(document_file)
|
| 38 |
document_text = ""
|
| 39 |
for paragraph in docx_file.paragraphs:
|
| 40 |
document_text += paragraph.text
|
| 41 |
elif document_file.type == "application/msword":
|
|
|
|
| 42 |
doc_file = docx.Document(document_file)
|
| 43 |
document_text = ""
|
| 44 |
for paragraph in doc_file.paragraphs:
|
|
|
|
| 29 |
st.error("A dokumentum mérete túl nagy. Kérlek válassz egy kisebb méretű dokumentumot!")
|
| 30 |
else:
|
| 31 |
if document_file.type == "application/pdf":
|
| 32 |
+
# PDF fájl feldolgozása lapozás útján
|
| 33 |
with pdfplumber.open(document_file) as pdf:
|
| 34 |
document_text = ""
|
| 35 |
for page in pdf.pages:
|
| 36 |
document_text += page.extract_text()
|
| 37 |
elif document_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
|
| 38 |
+
# DOCX fájl feldolgozása részletekben
|
| 39 |
docx_file = docx.Document(document_file)
|
| 40 |
document_text = ""
|
| 41 |
for paragraph in docx_file.paragraphs:
|
| 42 |
document_text += paragraph.text
|
| 43 |
elif document_file.type == "application/msword":
|
| 44 |
+
# DOC fájl feldolgozása részletekben
|
| 45 |
doc_file = docx.Document(document_file)
|
| 46 |
document_text = ""
|
| 47 |
for paragraph in doc_file.paragraphs:
|