Markdown 文書の統計量を計算するスクリプト

calc_markdown_statistics.py

#!/usr/bin/env python
# -*- coding: utf-8 -*- 
import os

import markdown
from bs4 import BeautifulSoup
from markdown import markdown

CHARSET = 'utf-8'

MARKDOWN_STATS_FILE = "./check_results/markdown_stats.csv"
MARKDOWN_FILE_LIST = "./markdown_list.txt"

def main():
    results = [
        ["ファイル名", "文字数", "句読点数", "h1の数", "h2の数", "h3の数", "h4の数", "h5の数", "h6の数", "tableの数", "liの数", "dtの数", "imgの数",
         "aの数"]]
    # ヘッダの設定
    with open(MARKDOWN_FILE_LIST, encoding=CHARSET) as f:
        for line in f:
            line = line.rstrip('\n')
            with open(line, encoding=CHARSET) as markdown_file:
                elems = []
                source = markdown_file.read()
                html = markdown(source)
                soup = BeautifulSoup(html, 'html.parser')
                # 文章統計情報を取得
                # ファイル名
                elems.append(os.path.basename(line))
                # 文字数
                text = ''.join(soup.findAll(text=True))
                elems.append(len(text))
                elems.append(str(text.count("、") + text.count("。")))
                elems.append(len(soup.find_all('h1')))
                elems.append(len(soup.find_all('h2')))
                elems.append(len(soup.find_all('h3')))
                elems.append(len(soup.find_all('h4')))
                elems.append(len(soup.find_all('h5')))
                elems.append(len(soup.find_all('h6')))
                elems.append(len(soup.find_all('table')))
                elems.append(len(soup.find_all('li')))
                elems.append(len(soup.find_all('dt')))
                elems.append(len(soup.find_all('img')))
                elems.append(len(soup.find_all('a')))
                results.append(elems)

    import csv
    with open(MARKDOWN_STATS_FILE, "w+") as results_csv:
        csv_writer = csv.writer(results_csv, delimiter=',')
        csv_writer.writerows(results)


if __name__ == '__main__':
    main()

markdown_stats.csv