ScrapeSocialMediaPage

#Scrape all /any webpage from social media,FB,Twitter,etc




from time import sleep
from random import randint
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.common.exceptions import NoSuchElementException

chrome_options = Options()
chrome_options.add_argument("--start-maximized")
chrome_options.add_argument("--disable-infobars")
chrome_options.add_argument("--disable-extensions")
chrome_options.add_argument("--disable-popup-blocking")

# disable the banner "Chrome is being controlled by automated test software"
chrome_options.add_experimental_option("useAutomationExtension", False)
chrome_options.add_experimental_option("excludeSwitches", ['enable-automation'])

# global driver
driver = webdriver.Chrome('/usr/bin/chromedriver', options=chrome_options)

driver.get('https://www.facebook.com/allegianceflagsupply/posts/pfbid0dTkrvzyLdHUnGibKxwWDG1ytPK7HKShFJm5AXEK4XmhYGgGbbSbKAKNRYkNjdumRl?notif_id=1662404244196067&notif_t=comment_mention&ref=notif')

driver.implicitly_wait(20)

driver.find_element_by_id("email").send_keys("USRName")
driver.find_element_by_id("pass").send_keys("PssWRD")

driver.implicitly_wait(10)

driver.find_element_by_xpath(("//button[text()='Log In']")).click()


# this function checks for a standard username tag
def user_element_exist():
    try:
        if driver.find_element_by_xpath("//h4[@id][@class][./span[./a]]/span/a"):
            return True
    except NoSuchElementException:
        return False


# this function looks for username linked to Facebook Groups at the top of your feed
def group_element():
    try:
        if driver.find_element_by_xpath("//*[starts-with(@id, 'jsc_c_')]/span[1]/span/span/a/b"):
            poster_name = driver.find_element_by_xpath("//*[starts-with(@id, 'jsc_c_')]/span[1]/span/span/a/b").text
            return poster_name

        if driver.find_element_by_xpath("//*[starts-with(@id, 'jsc_c_')]/strong[1]/span/a/span/span"):
            poster_name = driver.find_element_by_xpath("//*[starts-with(@id, 'jsc_c_')]/strong["
                                                       "1]/span/a/span/span").text
            return poster_name

    except NoSuchElementException:
        return "No user information found"


while True:
    element_exists = user_element_exist()
    if not element_exists:
        user_name = group_element()
        print(user_name)
        driver.refresh()
    elif element_exists:
        user_name = driver.find_element_by_xpath("//h4[@id][@class][./span[./a]]/span/a").text
        print(user_name)
        driver.refresh()

    # set the sleep timer to fit your needs
    sleep(300) # This sleeps for 300 seconds, which is 5 minutes.

    # I would likely use a random sleep function
    # sleep(randint(180, 360))