Spaces:
Sleeping
Sleeping
Update contract_missing_clausses.py
Browse files- contract_missing_clausses.py +13 -8
contract_missing_clausses.py
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
import openai
|
| 2 |
-
import
|
| 3 |
import logging
|
| 4 |
|
| 5 |
# Configure logging
|
|
@@ -79,16 +79,21 @@ class ContractMissingClauses:
|
|
| 79 |
try:
|
| 80 |
|
| 81 |
LOGGER.info("Analyzing contract and extracting pdf page...")
|
| 82 |
-
|
| 83 |
-
# Initialize pdfplumber
|
| 84 |
-
pdf = pdfplumber.open(pdf_file.name)
|
| 85 |
|
| 86 |
result = ''
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
return result
|
|
|
|
| 92 |
except Exception as e:
|
| 93 |
# If an error occurs during the key-value extraction process, log the error
|
| 94 |
LOGGER.error(f"Error occurred while extracting pdf page: {str(e)}")
|
|
|
|
| 1 |
import openai
|
| 2 |
+
from PyPDF2 import PdfReader
|
| 3 |
import logging
|
| 4 |
|
| 5 |
# Configure logging
|
|
|
|
| 79 |
try:
|
| 80 |
|
| 81 |
LOGGER.info("Analyzing contract and extracting pdf page...")
|
|
|
|
|
|
|
|
|
|
| 82 |
|
| 83 |
result = ''
|
| 84 |
+
|
| 85 |
+
pdf = PdfReader(pdf_file_path.name)
|
| 86 |
+
|
| 87 |
+
# Extract text from each page and pass it to the process_text function
|
| 88 |
+
for page_number in range(len(pdf.pages)):
|
| 89 |
+
|
| 90 |
+
# Extract text from the page
|
| 91 |
+
page = pdf.pages[page_number]
|
| 92 |
+
text = page.extract_text()
|
| 93 |
+
result += self.get_missing_clauses(contract)
|
| 94 |
+
|
| 95 |
return result
|
| 96 |
+
|
| 97 |
except Exception as e:
|
| 98 |
# If an error occurs during the key-value extraction process, log the error
|
| 99 |
LOGGER.error(f"Error occurred while extracting pdf page: {str(e)}")
|