【python】seleniumスクレイピングでcsvをダウンロードする方法

pip install selenium

import time
import glob
import shutil
from pathlib import Path
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options

############### ダウンロード機能の追加 ###############
# ダウンロードファイルの一時保存フォルダを作成(カレントディレクトリに「tmp」フォルダを作成)
tmp_dir = Path(Path.cwd(), "tmp")
tmp_dir.mkdir(exist_ok=True, parents=True)

# webdriverにオプションを追加
options = Options()
prefs = {"download.default_directory": str(tmp_dir)}
options.add_experimental_option("prefs", prefs)

# chromedriverのパスを指定
driver_path = "/Users/「PCのユーザ名」/Downloads/chromedriver"
chrome_service = Service(executable_path=driver_path)

# 追加したオプションを設定してwebdriverを起動
driver = webdriver.Chrome(service=chrome_service, options=options)

import time
import glob
import shutil
from pathlib import Path
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options

tmp_dir = Path(Path.cwd(), "tmp")
tmp_dir.mkdir(exist_ok=True, parents=True)
options = Options()
prefs = {"download.default_directory": str(tmp_dir)}
options.add_experimental_option("prefs", prefs)

driver_path = "/Users/「PCのユーザ名」/Downloads/chromedriver"
chrome_service = Service(executable_path=driver_path)
driver = webdriver.Chrome(service=chrome_service, options=options)

############### ここからWebページへのアクセス処理 ###############
# e-Statsのcsvダウンロードページにアクセス
url = "https://www.e-stat.go.jp/stat-search/files?page=1&layout=datalist&toukei=00200521&tstat=000001011777&cycle=0&tclass1=000001094741&tclass2val=0"
driver.get(url=url)

import time
import glob
import shutil
from pathlib import Path
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service

tmp_dir = Path(Path.cwd(), "tmp")
tmp_dir.mkdir(exist_ok=True, parents=True)
options = Options()
prefs = {"download.default_directory": str(tmp_dir)}
options.add_experimental_option("prefs", prefs)

driver_path = "/Users/「PCのユーザ名」/Downloads/chromedriver"
chrome_service = Service(executable_path=driver_path)
driver = webdriver.Chrome(service=chrome_service, options=options)

url = "https://www.e-stat.go.jp/stat-search/files?page=1&layout=datalist&toukei=00200521&tstat=000001011777&cycle=0&tclass1=000001094741&tclass2val=0"
driver.get(url=url)

##################### ここからWeb要素の探索 #####################
# コピーしたCSSセレクタを文字列に格納
selector = "body > div.dialog-off-canvas-main-canvas > div > main > div.row.l-estatRow > section > div.region.region-content > div > div > div.stat-content.fix > section > section > div > div.stat-dataset_list > div > article:nth-child(1) > div > ul > li:nth-child(2) > div > div:nth-child(4) > div > a"
element = driver.find_element(by=By.CSS_SELECTOR, value=selector)
# 取得したWeb要素のHTMLを表示
print(element.get_attribute("outerHTML"))

'<a href="/stat-search/file-download?statInfId=000031524010&fileKind=1" class="stat-dl_icon stat-icon_1 stat-icon_format js-dl stat-download_icon_left" data-file_id="000007847517" data-release_count="2" data-file_type="CSV" tabindex="22">\n<span class="stat-dl_text">CSV</span>\n</a>'

import time
import glob
import shutil
from pathlib import Path
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service

tmp_dir = Path(Path.cwd(), "tmp")
tmp_dir.mkdir(exist_ok=True, parents=True)
options = Options()
prefs = {"download.default_directory": str(tmp_dir)}
options.add_experimental_option("prefs", prefs)

driver_path = "/Users/「PCのユーザ名」/Downloads/chromedriver"
chrome_service = Service(executable_path=driver_path)
driver = webdriver.Chrome(service=chrome_service, options=options)

url = "https://www.e-stat.go.jp/stat-search/files?page=1&layout=datalist&toukei=00200521&tstat=000001011777&cycle=0&tclass1=000001094741&tclass2val=0"
driver.get(url=url)

selector = "body > div.dialog-off-canvas-main-canvas > div > main > div.row.l-estatRow > section > div.region.region-content > div > div > div.stat-content.fix > section > section > div > div.stat-dataset_list > div > article:nth-child(1) > div > ul > li:nth-child(2) > div > div:nth-child(4) > div > a"
element = driver.find_element(by=By.CSS_SELECTOR, value=selector)

##################### ダウンロード処理の実行 #####################
#ダウンロードボタンをクリック
element.click()

# 一時保存フォルダ内に".crdownload"の拡張子ファイルがある場合は待機
timeout_sec = 3
success_flg = True
while glob.glob(str(tmp_dir) + "/*.crdownload") != []:
    time.sleep(1)
    timeout_sec -= 1
    if timeout_sec < 0:
        # ダウンロード失敗タイムアウト
        shutil.rmtree(tmp_dir)
        success_flg = False
        break

if success_flg:
    time.sleep(1)
    # 正常にダウンロード成功したら、正規保存フォルダを作成して
    # ダウンロードしたすべてのファイルを一時保存フォルダから正規保存へ移動
    download_dir = Path(Path.cwd(), "download")
    download_dir.mkdir(exist_ok=True, parents=True)

    for file in glob.glob(str(tmp_dir) + "/*.*"):
        shutil.move(file, Path.cwd())
    # 一時保存フォルダを削除
    shutil.rmtree(tmp_dir)

driver.quit()