pdfminer.six -使用`extract_pages` API提取图形/图像

from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice
from pdfminer.layout import LAParams
from pdfminer.converter import PDFPageAggregator

fp = open('example.pdf', 'rb')
parser = PDFParser(fp)
document = PDFDocument(parser)

rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)

for page in PDFPage.create_pages(document):
    interpreter.process_page(page)
    layout = device.get_result()
    for element in layout:
        if isinstance(element, LTImage):
            # 处理图像
        elif isinstance(element, LTFigure):
            # 处理图形