INNER CODE UNIT · Python
pdf_to_text
cognitivetech/ollama-ebook-summary · book2text.py:111
def pdf_to_text(pdf_path):
reader = PdfReader(pdf_path)
text = []
for page in reader.pages:
text.append(page.extract_text())
return '\n'.join(text)
def natural_sort_key(s):
"""
This function constructs a tuple of either integers (if the pattern matches digits)
or the original elements (if not). This tuple can be used as a key for sorting.
"""
return [int(text) if text.isdigit() else text.lower() for text in re.split('(\d+)', s)]
def process_files(directory, file_type):
data = []
print(directory)
files = sorted(os.listdir(directory), key=natural_sort_key)