Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -171,7 +171,9 @@ def find_sentences_with_keywords(text, keywords):
|
|
| 171 |
# Main function to process both PDFs based on the Excel file names and the sheet name
|
| 172 |
def process_pdfs_and_analyze_sentiment(file1, file2, sheet):
|
| 173 |
# Extract text from both PDFs based on the file name
|
| 174 |
-
|
|
|
|
|
|
|
| 175 |
# Use sheet name as the keyword to find relevant sentences
|
| 176 |
keywords = {
|
| 177 |
'GDP': ['GDP'],
|
|
@@ -187,8 +189,8 @@ def process_pdfs_and_analyze_sentiment(file1, file2, sheet):
|
|
| 187 |
sentences2 = find_sentences_with_keywords(text2, selected_keywords)
|
| 188 |
|
| 189 |
# Concatenate all sentences for each PDF
|
| 190 |
-
text_pdf1 = "
|
| 191 |
-
text_pdf2 = "
|
| 192 |
|
| 193 |
# Perform sentiment analysis on the extracted sentences for each PDF
|
| 194 |
result_pdf1 = fin_ext_bis(text_pdf1)
|
|
|
|
| 171 |
# Main function to process both PDFs based on the Excel file names and the sheet name
|
| 172 |
def process_pdfs_and_analyze_sentiment(file1, file2, sheet):
|
| 173 |
# Extract text from both PDFs based on the file name
|
| 174 |
+
pdf_file1 = file1.replace(".xlsx", ".pdf")
|
| 175 |
+
pdf_file2 = file2.replace(".xlsx", ".pdf")
|
| 176 |
+
text1, text2 =extract_and_paragraph(pdf_file1, pdf_file2, False)
|
| 177 |
# Use sheet name as the keyword to find relevant sentences
|
| 178 |
keywords = {
|
| 179 |
'GDP': ['GDP'],
|
|
|
|
| 189 |
sentences2 = find_sentences_with_keywords(text2, selected_keywords)
|
| 190 |
|
| 191 |
# Concatenate all sentences for each PDF
|
| 192 |
+
text_pdf1 = "\n".join(sentences1)
|
| 193 |
+
text_pdf2 = "\n".join(sentences2)
|
| 194 |
|
| 195 |
# Perform sentiment analysis on the extracted sentences for each PDF
|
| 196 |
result_pdf1 = fin_ext_bis(text_pdf1)
|