Python

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
import time

# chromedriver.exeがある場所
driver_path = "driver/chromedriver.exe"
# WebDriverの作成
service = Service(executable_path=driver_path)
driver = webdriver.Chrome(service=service)

# www.google.co.jpを開く
driver.get("https://www.google.co.jp")
print(driver.title, driver.current_url)
time.sleep(2)

# www.yahoo.co.jpを開く
driver.get("https://www.yahoo.co.jp")
print(driver.title, driver.current_url)
time.sleep(2)

# www.python.orgを開く
driver.get("https://www.python.org")
print(driver.title, driver.current_url)
time.sleep(2)

# www.yahoo.co.jpに戻る
driver.back()
print(driver.title, driver.current_url)
time.sleep(2)

# www.google.co.jpに戻る
driver.back()
print(driver.title, driver.current_url)
time.sleep(2)

# webdriverの終了（ブラウザを閉じる）
driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
import time

# chromedriver.exeがある場所
driver_path = "driver/chromedriver.exe"

# WebDriverの作成
service = Service(executable_path=driver_path)
driver = webdriver.Chrome(service=service)

# 要素が見つからない場合は10秒まつように設定
driver.implicitly_wait(10)

# www.google.co.jpを開く
driver.get("https://www.google.co.jp")

# 検索ボックスに「札幌天気」を入力して、Enterキーを押す
driver.find_element(By.NAME, "q").send_keys("札幌天気" + Keys.ENTER)

# [降水確率]のボタンをクリック
driver.find_element(By.ID, "wob_rain").click()

# 5秒待つ
time.sleep(5)

# ブラウザを閉じる
driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By

# chromedriver.exeがある場所
driver_path = "driver/chromedriver.exe"

# webdriverの作成
service = Service(executable_path=driver_path)
driver = webdriver.Chrome(service=service)

# sample.htmlを開く
driver.get("file:///C:/Users/user\OneDrive/ドキュメント/document/python/ExcelPython/ch08/sample.html")

# Python公式ページのa要素を含む親要素
id_python = driver.find_element(By.ID,"python")

# タグ名が「a」の要素を検索
links = id_python.find_elements(By.TAG_NAME,"a")

# 検索した要素のテキストとhref属性の値を表示
for link in links:
    print(link.text)
    print(link.get_attribute("href"))

# ブラウザを閉じる
driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By

# chromedriver.exeがある場所
driver_path = "driver/chromedriver.exe"

# webdriverの作成
service = Service(executable_path=driver_path)
driver = webdriver.Chrome(service=service)

# sample.htmlを開く
driver.get("file:///C:/Users/user\OneDrive/ドキュメント/document/python/ExcelPython/ch08/sample.html")

# Python公式ページのa要素を検索
links = driver.find_elements(By.CSS_SELECTOR, "#python a")

# 検索した要素のテキストとhref属性の値を表示
for link in links:
    print(link.text)
    print(link.get_attribute("href"))

# ブラウザを閉じる
driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
import openpyxl

# chromedriver.exeがある場所
driver_path = "driver/chromedriver.exe"

# webdriverの作成
service = Service(executable_path=driver_path)
driver = webdriver.Chrome(service=service)

# 要素が見つからない場合は10秒待つように設定
driver.implicitly_wait(10)

# 外務省トップを開く
driver.get("https://www.mofa.go.jp/mofaj/")

# 最新の日付
data_elm = driver.find_element(By.CSS_SELECTOR, "#news-whatsnew dt:nth-of-type(1)")
data_text = data_elm.text

# 最新の新着情報のa要素
links = driver.find_elements(By.CSS_SELECTOR, "#news-whatsnew dd:nth-of-type(1) li a")

# 読み取り結果のリスト
data_list = []

for link in links:
    # テキスト
    link_text = link.text
    # リンク先
    link_url = link.get_attribute("href")

    # リストに登録
    data_list.append([data_text, link_text, link_url])
    # 確認表示
    print(data_text, link_text, link_url)

# ブラウザを閉じる
driver.quit()

# 新しいブックに保存
wb_new = openpyxl.Workbook()
ws_new = wb_new.worksheets[0]

row_num = 1

for data in data_list:
    # 日付
    ws_new.cell(row_num, 1).value = data[0]
    # テキスト
    ws_new.cell(row_num, 2).value = data[1]
    # リンク先
    ws_new.cell(row_num, 3).value = data[2]

    row_num = row_num + 1

wb_new.save("外務省新着情報.xlsx")

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
import openpyxl

# URLリストの読み込み
wb = openpyxl.load_workbook("官庁新着情報URL.xlsx")
ws = wb["Sheet1"]

url_list = []

for row in ws.iter_rows(min_row=2):
    if row[0].value is None:
        break
    value_list = []
    for c in row:
        value_list.append(c.value)
    url_list.append(value_list)

# chromedriver.exeがる場所
driver_path = "driver/chromedriver.exe"

# webdriverの作成
service = Service(executable_path=driver_path)
driver = webdriver.Chrome(service=service)

# 要素が見つからない場合は10秒待つように設定
driver.implicitly_wait(10)

# 読み取り結果のリスト
data_list = []

for url in url_list:
    kancyo_name = url[0]
    kancyo_url = url[1]
    css_data = url[2]
    css_links = url[3]

    # 新着情報のページを開く
    driver.get(kancyo_url)

    # 最新の日付
    data_elm = driver.find_element(By.CSS_SELECTOR, css_data)
    data_text = data_elm.text

    # 最新の新着情報のa要素
    links = driver.find_elements(By.CSS_SELECTOR, css_links)

    # スクリーンショット撮影
    driver.save_screenshot("csreen_" + kancyo_name + ".png")

    for link in links:
        link_text = link.text
        link_url = link.get_attribute("href")
        data_list.append([kancyo_name, data_text, link_text, link_url])

# ブラウザを閉じる
driver.quit()

# 新しいブックに保存
wb_new = openpyxl.Workbook()
ws_new = wb_new.worksheets[0]

row_num = 1

for data in data_list:
    # 官庁名
    ws_new.cell(row_num, 1).value = data[0]
    # 日付
    ws_new.cell(row_num, 2).value = data[1]
    # テキスト
    ws_new.cell(row_num, 3).value = data[2]
    # リンク先
    ws_new.cell(row_num, 4).value = data[3]

    row_num = row_num + 1

wb_new.save("官庁新着情報.xlsx")