Python读取docx, pdf, xlsx

read_info_from_file.py

from logging import info
import os, pdfplumber, docx, xlrd
import sys
from win32com import client as wc

def doc2docx(file):
    word = wc.Dispatch("Word.Application")
    doc = word.Documents.Open(doc_path+'/'+file)
    doc.SaveAs(doc_path+'/'+'{}x'.format(file), 12)
    doc.Close()
    word.Quit()

def search_pdf(doc):
    try:
        with pdfplumber.open(doc_path+'/'+doc) as pdf:
            for page in pdf.pages:
                if name in page.extract_text():
                    print('pdf:', doc)
                    info_fd.write('pdf: %s\n' % doc)
                    return
    except Exception as e:
        print(e)

def search_word(doc):
    try:
        if doc.endswith('doc'):
            if not os.path.exists(doc_path+'/'+'{}x'.format(doc)):
                doc2docx(doc)
            doc += 'x'
        word = docx.Document(doc_path+'/'+doc)
        for para in word.paragraphs:
            if name in para.text:
                print('word:', doc)
                info_fd.write('word: %s\n' % doc)
                return
    except Exception as e:
        print(e)

def search_excel(doc):
    try:
        sheets = xlrd.open_workbook(doc_path+'/'+doc).sheets()
        for sheet in sheets:
            for i in range(sheet.nrows):
                for j in range(len(sheet.row(i))):
                    if name in str(sheet.cell_value(i, j)):
                        print('excel:', doc)
                        info_fd.write('excel: %s\n' % doc)
                        return
    except Exception as e:
        print(e)