Python PDF、WORD、EXCEL、PPTのテキストを読み込む

文書ディレクトリ

シーン

PDF

WORD

読み出し段落

表

を読み取る.

EXCEL

PPT

シーン
ファイル内のテキストの内容を取得(読み取り専用で書き込みなし)
PDF
インストール:pip install pdfminer3k

from io import StringIO
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, process_pdf

def read_pdf(path_pdf):
    with open(path_pdf, 'rb') as pdf:
        # resource manager
        # PDF     
        rsrcmgr = PDFResourceManager()
        #   str   
        outfp = StringIO()
        #   PDF   
        laparams = LAParams()
        #      
        device = TextConverter(rsrcmgr, outfp, laparams=laparams)
        #     
        process_pdf(rsrcmgr, device, pdf)
        #           
        content = outfp.getvalue()
        #     
        device.close()
        outfp.close()
        return content  # 

if __name__ == '__main__':
    lines = read_pdf('P020190716349644060705.pdf')
    print(lines)

WORD
インストール:pip install python-docx段落の読み込み

from docx import Document
#     
d = Document('a.docx')
#     
for paragraph in d.paragraphs:
    print(paragraph.text)

表の読み込み

from docx import Document
#     
d = Document('a.docx')
#     
for table in d.tables:
    for row in table.rows:
        for cell in row.cells:
            print(cell.text)

EXCEL

from pandas import read_excel

def xlsx2df(fname, sheet_name=0):
    return read_excel(fname, sheet_name)

PPT
インストール:pip install python-pptx

import pptx
#   PPT
p = pptx.Presentation('a.pptx')
#      
for slide in p.slides:
    #           
    for shape in slide.shapes:
        #    
        if isinstance(shape, pptx.shapes.placeholder.SlidePlaceholder):
            for paragraph in shape.text_frame.paragraphs:
                print(paragraph.text)
        #   
        if isinstance(shape, pptx.shapes.graphfrm.GraphicFrame):
            for cell in shape.table.iter_cells():
                print(cell.text)