from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.chrome.options import Options from selenium.webdriver.chrome.service import Service from webdriver_manager.chrome import ChromeDriverManager from selenium.webdriver.support.ui import Select from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support import expected_conditions as EC import pandas as pd import time import urllib.request import requests from fake_useragent import UserAgent options = Options() # options.add_argument('--headless') # options.add_argument('--no-sandbox') options.add_argument('--disable-dev-shm-usage') driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=options) driver.get("https://admin.wls.eims.co.kr/WattageState/Report") input_id = driver.find_element(By.CLASS_NAME, 'login-userid') input_password = driver.find_element(By.CLASS_NAME, 'login-password') login_button = driver.find_element(By.CSS_SELECTOR, "div.col-sm-7.text-right button") input_id.clear() input_password.clear() input_id.send_keys("wl00002") input_password.send_keys("2666##") login_button.click() did_it_logged_in = EC.presence_of_element_located((By.ID, 'data-select2')) time.sleep(2) driver.get("https://admin.wls.eims.co.kr/WattageState/Report") time.sleep(2) # ---------- gather the data from the website, by company, time_interval, and date starting_date_input_box = driver.find_element(By.NAME, "from") end_date_input_box = driver.find_element(By.NAME, "to") starting_date_input_box.clear() end_date_input_box.clear() starting_date_input_box.send_keys("2023-01-01") end_date_input_box.send_keys("2023-01-31") drop_down_customer = driver.find_element(By.XPATH, '//select[@data-placeholder="참여고객명"]') customer_list = drop_down_customer.text.split("\n")[1:] drop_down_time_interval = driver.find_element(By.XPATH, '//select[@data-placeholder="검침기종류"]') time_interval_list = drop_down_time_interval.text.split("\n")[1:3] select = Select(drop_down_customer) select.select_by_visible_text(customer_list[5]) df = pd.DataFrame(customer_list) df.to_csv("customer_list.csv", index=False) df = pd.DataFrame(time_interval_list) df.to_csv("time_interval_list.csv", index=False) select = Select(drop_down_time_interval) select.select_by_visible_text(time_interval_list[0].replace(' ','')) the_red_button = driver.find_element(By.XPATH, '//button[@ng-click="ctrl.getContractWattageStatistics(ctrl.req)"]') the_red_button.click() the_download_button = driver.find_element(By.XPATH, '//a[@class="btn btn-default btn-outline pull-right btn-sm"]') # time.sleep(3) wait = WebDriverWait(driver, 10) href = wait.until( lambda driver: the_download_button.get_attribute('href') ) the_download_button.click() time.sleep(10) # this is an attemp to download files with requests, but did not worked... # print(href) # # time.sleep(10) # # # urllib.request.urlretrieve(href, "test/test.xlsx") # # USER_AGENT = UserAgent() # # fake_browser = USER_AGENT.firefox # header = { # 'User-Agent': USER_AGENT.firefox # } # # with open("test/test.xlsx", "wb") as file: # r = requests.get(href, headers=header) # file.write(r.content) # # time.sleep(10000) # WebDriverWait(driver, 10).until(lambda d: d.find_element(By.CSS_SELECTOR, "div.span.span.select2-selection select2-selection--single")) print(driver.title) # driver.close()