データ分析pdfドキュメントの読み出し

pythonでpdfドキュメントを読み込む
pythonのサードパーティ製ライブラリpdfminter 3 kを使用しています

from pdfminer.pdfparser import PDFParser,PDFDocument
from pdfminer.pdfinterp import PDFResourceManager,PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice
from pdfminer.layout import LAParams
from pdfminer.converter import PDFPageAggregator
reader = open('dd2.pdf','rb')

#             
parser = PDFParser(reader)

#PDF     
doc= PDFDocument()

#          
parser.set_document(doc)
doc.set_parser(parser)

#     
doc.initialize('')

#  PDF     
resource = PDFResourceManager()

#     
laparam = LAParams()

#       
device = PDFPageAggregator(resource,laparams=laparam)

#  PDF     
interpreter = PDFPageInterpreter(resource,device)

#             
for page in doc.get_pages():
    #          
    interpreter.process_page(page)
    #          
    layout = device.get_result()

    for out in layout:
        if hasattr(out,'get_text'):
            print(out.get_text())