Deal with file and directories, xlsx and extract text from pdf

catalog.py

import os
import re
from PyPDF2 import PdfFileReader
import textract
import csv
from openpyxl import Workbook
from openpyxl.writer.write_only import WriteOnlyCell

class Catloger(object):

    paper_count = 0
    sub_name = 5100001
    page_count = 0
    topic_name = ''
    cata_list = []

    def del_prefix(self, filename):
        print(filename)
        res = re.findall('([0-9]{7}_)', filename)
        if res:
            new_name = filename.replace(res[0], '')
            print(new_name)
            os.rename(filename, new_name)
        pass;

    def clear_cache_file(self, dirname):
        for item in os.listdir(dirname):
            if item.startswith('~') or item.startswith('.'):
                print(item)
                os.remove(item)

    def regular_name(self, dirname):
        count = -1
        filename = os.path.basename(dirname)
        for item in os.listdir(dirname):
            if item.endswith('.pdf') and 'copyright' not in item:
                self.paper_count += 1
                pdf = PdfFileReader(open(item, 'rb'))
                count = pdf.getNumPages()
                print('[', str(self.paper_count), filename, ']', item, str(count))
                self.record(self.paper_count, self.page_count + 1,
                                self.topic_name, textract.process(item))
        new_name = str(self.sub_name + self.page_count)
        self.page_count += count
        return new_name

    def record(self, num, page_start, topic, content):
        self.cata_list.append({
            '序号': num,
            '起始页': page_start,
            'Topic': topic,
            '内容摘录': content[0:200]
        })

    def save2csv(self, path):
        filename = 'catalog.csv'
        path = os.path.join(path, filename)
        with open(path, 'w') as csvfile:
            fieldnames = ['序号', '起始页', 'Topic', '内容摘录']
            writer = csv.DictWriter(csvfile, fieldnames)

            writer.writeheader()
            writer.writerows(self.cata_list)
            print('Save csv file to:', path)

    def save2xlsx(self, path):
        filename = 'catalog.xlsx'
        path = os.path.join(path, filename)
        wb = Workbook(write_only=True)
        ws = wb.create_sheet()
        
        fieldnames = ['序号', '起始页', 'Topic', '内容摘录']
        ws.append(fieldnames)
        for cata in self.cata_list:
            print(cata['内容摘录'])
            content_cell = WriteOnlyCell(ws, value=cata['内容摘录'])
            content_cell.style.alignment.wrap_text = True
            ws.append([cata['序号'], cata['起始页'], cata['Topic'], content_cell])
        wb.save(path)

if __name__ == "__main__":
    cat = Catloger()
    # Root ICIS2017 Proceedings
    root_dir = os.getcwd()
    cat.clear_cache_file(root_dir)
    for f_root in os.listdir(root_dir):
        topic_dir = os.path.join(root_dir, f_root)
        if os.path.isdir(topic_dir):
            # => Topic 0 Keynote and Invited Presentations
            os.chdir(topic_dir)
            cat.clear_cache_file(topic_dir)
            cat.topic_name = f_root
            print(f_root)     
            for f_topic in os.listdir(topic_dir):
                sub_dir = os.path.join(topic_dir, f_topic)
                if os.path.isdir(sub_dir):
                    # => Sub 5100001
                    os.chdir(os.path.join(topic_dir, sub_dir))
                    cat.clear_cache_file(topic_dir)
                    new_name = cat.regular_name(sub_dir)
                    # print (f_topic, '=>', new_name)
                    os.chdir(topic_dir)
                    os.rename(f_topic, new_name)
                    # for f_sub in os.listdir(sub_dir):
                    #     del_prefix(f_sub)
    print('Total page:', cat.page_count)
    cat.save2xlsx(root_dir)