def analyze_pdf_page_content()

in seed/util/preprocess.py [0:0]

• 17 lines of code
• 6 McCabe index (conditional complexity)

def analyze_pdf_page_content(pdf_path, text_length_thres=600):
    document = fitz.open(pdf_path)
    page_analysis = defaultdict(list)

    for page_num in range(len(document)):
        page = document.load_page(page_num)
        text = page.get_text("text")
        image_list = page.get_images(full=True)

        text_length = len(text)
        num_images = len(image_list)

        if text_length > text_length_thres and num_images == 0:
            content_type = 'Text'
        elif text_length <= text_length_thres and num_images > 0:
            content_type = 'Image'
        else:
            content_type = 'Mixed'            

        page_analysis[content_type].append(page_num)

    return dict(page_analysis)