CMD帶入引數 利用BS4爬出表格內容 並輸出CSV

html_table_import_csv.py

import codecs
import argparse
from bs4 import BeautifulSoup

#在CMD取得引數
parser = argparse.ArgumentParser()
parser.add_argument("-name")                            #<file_name.py> -name "html檔名"
args = parser.parse_args()

#讀取 HTML 靜態頁
data_list = []
file = codecs.open(args.name+".htm", 'r','utf-8')
soup = BeautifulSoup(file.read(),"html.parser")         #使用BS4解析HTML
table = soup.find("tbody")                              #利用BS4找到Table

#取出表格內容
for row in table.findAll("tr"):
    cells = row.findAll("td")
    data_list.append([
        cells[0].contents[0],
        cells[1].contents[0],
        cells[2].contents[0],
        cells[3].contents[0],
        cells[4].contents[0],
        cells[5].contents[0]
    ])

#輸出CSV
with open(args.name+".csv",'w') as file:                #CSV檔名其實就是來源html的檔名
    for line in data_list:
        for text in line:
            file.write(text)
            file.write(',')
        file.write('\n')