文号识别

import re
from pdfminer.high_level import extract_pages
from pdfminer.layout import LTTextContainer, LTChar

path = r'\\192.168.3.201\szse\regulatory_function\gkxx_jgsy_00000740626.pdf'


def main(file_path):
    featureData = []
    pageIndex = 1
    for page_layout in extract_pages(file_path):
        if (pageIndex > 0):
            for element in page_layout:
                if isinstance(element, LTTextContainer):
                    for text_line in element:
                        text = text_line.get_text()
                        for character in text_line:
                            if isinstance(character,LTChar) and 7.5 <= character.size < 11 and 10 < text.__len__() and re.findall(".*号.*", text).__len__() > 0:
                                featureData.append(str(text).replace('\n', '').replace(' ', ''))
                                break
    return featureData[0]
text = main(path)
print(text)