連盟の入力欄に入力するよくん

entory_robo.py

# -*- coding: utf-8 -*-
import lxml.html as lh
import argparse
import datetime
from urllib import request


def CALC_OLD(birth_year):
    today = datetime.date.today()
    year = today.year
    if 1 <= today.month and 3 >= today.month:
        year -= 1
    return str(year - int(birth_year))


class DataReader():
    def __init__(self, path):
        self.path = path

    def read_data(self):
        with open(self.path, 'r') as f:
            str = f.read()
        return [s.split(',') for s in str.split('\n')][:-1]


class EntryEditor():
    def __init__(self, url):
        self.url = url

    def retrieve_html(self):
        with request.urlopen(self.url) as f:
            self.html = f.read().decode('cp932')
            return self

    def inject_data(self, data_list):
        row = lh.fromstring(self.html).xpath('//tr')[3:]
        for i, tr in enumerate(row):
            inputs = tr.xpath('./td//input')
            try:
                print(data_list[i])
                if i == 0 or i == 1:
                    inputs[0].value = data_list[i][1]
                    inputs[1].value = CALC_OLD(data_list[i][2])
                else:
                    inputs[0].value = data_list[i][0]
                    inputs[1].value = data_list[i][1]
                    inputs[2].value = CALC_OLD(data_list[i][2])
            except:
                continue
            root = tr.getroottree()
            self.html = lh.tostring(root).decode('cp932')
        return self

    def write_html(self):
        with open('result.html', 'w', encoding='cp932') as f:
            f.write(self.html)

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='urlのフォームをdataの内容で入力します')
    parser.add_argument('-d', '--data', dest='data', required=True, help='データcsvファイルのパス')
    parser.add_argument('-u', '--url', dest='url', required=True, help='フォームhtmlのurl')
    args = parser.parse_args()
    # print(args.data)
    # print(args.url)
    data_list = DataReader(args.data).read_data()
    EntryEditor(args.url).retrieve_html().inject_data(data_list).write_html()

nenkan.py

def inject_data(self, data_list):
        row = lh.fromstring(self.html).xpath('//tr')[6:]
        for i, tr in enumerate(row):
            inputs = tr.xpath('./td//input')
            try:
                print(data_list[i])
                if i == 0 or i == 1:
                    inputs[0].value = data_list[i][1]
                    inputs[1].value = CALC_OLD(data_list[i][2])
                    inputs[2].value = data_list[i][3]
                    inputs[3].value = data_list[i][4]
                    inputs[4].value = data_list[i][5]
                else:
                    inputs[0].value = data_list[i][0]
                    inputs[1].value = data_list[i][1]
                    inputs[2].value = CALC_OLD(data_list[i][2])
                    inputs[3].value = data_list[i][3]
                    inputs[4].value = data_list[i][4]
                    inputs[5].value = data_list[i][5]
            except:
                continue
            root = tr.getroottree()
            self.html = lh.tostring(root).decode('cp932')
        return self