Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -5,7 +5,7 @@ import io
|
|
5 |
|
6 |
|
7 |
|
8 |
-
def search_pdf(pdf_file,
|
9 |
search_results = []
|
10 |
if isinstance(pdf_file, io.BytesIO): # Handling Streamlit case
|
11 |
doc = fitz.open(stream=pdf_file.getvalue(), filetype="pdf")
|
@@ -17,13 +17,17 @@ def search_pdf(pdf_file, search_term):
|
|
17 |
# Split the text into lines and filter out empty lines
|
18 |
lines = [line.strip() for line in text.split('\n') if line.strip()]
|
19 |
cleaned_text = '\n'.join(lines)
|
20 |
-
|
|
|
|
|
|
|
|
|
21 |
search_results.append((page_num + 1, cleaned_text))
|
22 |
return search_results
|
23 |
|
24 |
def final_result(pdf_file, search_term):
|
25 |
split_search = search_term.split(' ')
|
26 |
-
results = search_pdf(pdf_file, split_search
|
27 |
output_text = ""
|
28 |
if results:
|
29 |
for page_num, text in results:
|
|
|
5 |
|
6 |
|
7 |
|
8 |
+
def search_pdf(pdf_file, split_search):
|
9 |
search_results = []
|
10 |
if isinstance(pdf_file, io.BytesIO): # Handling Streamlit case
|
11 |
doc = fitz.open(stream=pdf_file.getvalue(), filetype="pdf")
|
|
|
17 |
# Split the text into lines and filter out empty lines
|
18 |
lines = [line.strip() for line in text.split('\n') if line.strip()]
|
19 |
cleaned_text = '\n'.join(lines)
|
20 |
+
k = 0
|
21 |
+
for i in range(len(split_search)):
|
22 |
+
if split_search[i].lower() in cleaned_text.lower():
|
23 |
+
k = k + 1
|
24 |
+
if k == len(split_search):
|
25 |
search_results.append((page_num + 1, cleaned_text))
|
26 |
return search_results
|
27 |
|
28 |
def final_result(pdf_file, search_term):
|
29 |
split_search = search_term.split(' ')
|
30 |
+
results = search_pdf(pdf_file, split_search)
|
31 |
output_text = ""
|
32 |
if results:
|
33 |
for page_num, text in results:
|