メインコンテンツまでスキップ

Scraping Template

· 約1分

GAS​

取得​

API​

const res = UrlFetchApp.fetch('https://example.com');
status = res.getResponseCode();
const json = JSON.parse(res.getContentText());

保存​

Spreadsheet​

複数行を追加

const sheet = SpreadsheetApp.getActiveSpreadsheet().getSheetByName('シート名');

sheet
  .getRange(sheet.getLastRow() + 1, 1, values.length, values[0].length)
  .setValues(values);

Python​

取得​

HTML：requests​

def download_html(url, file_path):
    res = requests.get(url)
    html = res.text
    os.makedirs(os.path.dirname(file_path), exist_ok=True)
    with open(file_path, 'w') as f:
        f.write(html)
    return html

def get_html(url, force_download=False):
    file_path = f"html/{convert_url_to_filename(url)}.html"

    if os.path.isfile(file_path) and not force_download:
        with open(file_path, 'r') as f:
            html = f.read()
    else:
        html = download_html(url, file_path)

    return html

def convert_url_to_filename(url):
    return re.sub(r'/', '_', url)

requests​

import requests

res = requests.get('https://example.com')
status = res.status_code
json = res.json()

保存​

csv​

import csv
with open(f'hoge.csv', 'w', newline='', encoding='utf-8') as f:
    writer = csv.writer(f)
    writer.writerow([
        'id',                   # id
        'name',                 # プロジェクト名
    ])
    writer.writerows(dataList)