pdfTitle

def pdfTitle(path):
    featureData = []
    pageIndex = 1
    for page_layout in extract_pages(path, page_numbers=[0], maxpages=1):  # page_numbers=[0], maxpages=1 页码
        if pageIndex == 1:
            for element in page_layout:
                if isinstance(element, LTTextContainer):
                    for text_line in element:
                        text = text_line.get_text()
                        fontSizeMax = 0
                        for character in text_line:
                            if isinstance(character, LTChar) and (
                                    character.size > fontSizeMax and character.size >= 16):
                                fontSizeMax = character.size
                        if (fontSizeMax > 0):
                            feature = [text.strip(), pageIndex, text_line.y0, fontSizeMax]
                            featureData.append(feature)
    feature_list = sorted(featureData, key=lambda featureData: (featureData[1], -int(featureData[2])))
    data = [i[0] for i in feature_list]
    data = str('&'.join(data)).replace(' ','').strip('&').replace('&&《','《').replace('》&','》')
    return data