selenium_phantomjs_custom_user_agent_click_export_csv.py

# r'https://pypi.python.org/pypi/selenium
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
import os, time, errno, sys
import lxml
def main():
    if len(sys.argv) < 2:
        sys.exit(0)
    else:
        url = r'https://www.esios.ree.es/en/analysis/600?vis=1&start_date=04-12-2016T00%3A00&end_date=04-12-2016T23%3A00&compare_start_date=03-12-2016T00%3A00&groupby=hour'
        url = sys.argv[1]
        # use chrome webdriver
        #w = webdriver.Chrome()
        
        # use default phantom
        # w = webdriver.PhantomJS()
        
        # USE phantom set custom user-agent
        dcap = dict(DesiredCapabilities.PHANTOMJS)
        dcap["phantomjs.page.settings.userAgent"] = ('Mozilla/5.0 (Linux; Android 6.0.1; Nexus 6P Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.83 Mobile Safari/537.36')
        w = webdriver.PhantomJS(desired_capabilities=dcap)

        # get url
        w.get(url)
        
        # display w.page_source using BS
        soup = BeautifulSoup(w.page_source, "lxml")
        print(soup.prettify)
        time.sleep(5)

        # click the export button using xpath
        xpath_export = r'//*[@id="dashboardView"]/form/div[7]/div'
        w.find_element_by_xpath(xpath_export).click()

        # click the csv button using xpath
        xpath_export_csv = '//*[@id="dashboardView"]/form/div[7]/div/ul/li[1]/a'
        w.find_element_by_xpath(xpath_export_csv).click()

if __name__ == '__main__':
    # python selium_click_export_csv.py 'url of webpage'
    main()