30 lines
879 B
Python
30 lines
879 B
Python
import pdfplumber
|
|
import sys
|
|
|
|
|
|
def extract_pdf_text(pdf_path, output_path):
|
|
try:
|
|
with pdfplumber.open(pdf_path) as pdf:
|
|
text = ""
|
|
for i, page in enumerate(pdf.pages):
|
|
page_text = page.extract_text()
|
|
if page_text:
|
|
text += f"=== Page {i + 1} ===\n"
|
|
text += page_text + "\n\n"
|
|
|
|
with open(output_path, "w", encoding="utf-8") as f:
|
|
f.write(text)
|
|
print(f"Extracted {len(pdf.pages)} pages from {pdf_path}")
|
|
return True
|
|
except Exception as e:
|
|
print(f"Error extracting {pdf_path}: {e}")
|
|
return False
|
|
|
|
|
|
if __name__ == "__main__":
|
|
# Extract CH390 datasheet
|
|
extract_pdf_text("CH390DS1.PDF", "CH390DS1.txt")
|
|
|
|
# Extract STM32F103C8 datasheet
|
|
extract_pdf_text("stm32f103c8.pdf", "stm32f103c8.txt")
|