Function parse_input_content

podcast_generate.py:177–225

Parse input content, supports URL, PDF or TXT files Args: input_path (str): URL address, PDF file path or TXT file path Returns: str: Parsed text content

(input_path)

def parse_input_content(input_path):
    """Parse input content, supports URL, PDF or TXT files

    Args:
        input_path (str): URL address, PDF file path or TXT file path

    Returns:
        str: Parsed text content
    """
    print(f"Parsing input: {input_path}")

    # Check if it's a URL
    if input_path.startswith(("http://", "https://")):
        print("URL detected, extracting web content...")
        result = extract_web_content(input_path)
        if result:
            title, content = result
            print(f"Web title: {title}")
            print(f"Content length: {len(content)} characters")
            return f"{title}\n\n{content}" if title else content
        else:
            print("Web content extraction failed")
            return None

    # Check if it's a PDF file
    elif input_path.lower().endswith(".pdf"):
        print("PDF file detected, extracting content...")
        content = extract_text_from_pdf(input_path)
        if content:
            print(f"PDF content length: {len(content)} characters")
            return content
        else:
            print("PDF content extraction failed")
            return None

    # Check if it's a TXT file
    elif input_path.lower().endswith(".txt"):
        print("TXT file detected, reading content...")
        content = extract_text_from_txt(input_path)
        if content:
            print(f"TXT file content length: {len(content)} characters")
            return content
        else:
            print("TXT file reading failed")
            return None

    else:
        print(f"Unsupported input format: {input_path}")
        return None


# =============== Dialogue Script Generation Function ===============