트위터 아이디 수집 (collecting twitter ID) - ver 0.1

from selenium import webdriver

from selenium.webdriver.common.keys import Keys

import numpy as np

import random

import pandas as pd

url = 'https://twitter.com/bbmpott'

options = webdriver.ChromeOptions()

options.add_argument("headless")

options.add_experimental_option("excludeSwitches", ["enable-logging"])

driver = webdriver.Chrome('chromedriver_4844.exe', options=options)

driver.get(url)

driver.implicitly_wait(10)

ID  = []

while True:

    driver.find_element_by_tag_name('body').send_keys(Keys.PAGE_DOWN)

    driver.find_element_by_tag_name('body').send_keys(Keys.PAGE_DOWN)

    try:

        for page in range(1, 10):

            xpath_id = '//*[@id="react-root"]/div/div/div[2]/main/div/div/div/div/div/div[2]/div/div/section/div/div/div[' + str(page) + ']'

            dd = driver.find_element_by_xpath(xpath_id)

            driver.implicitly_wait(5)

           

            tt = dd.text

           

            pos_1 = tt.find('@')

            pos_2 = tt.find('·')

            id = tt[pos_1+1:pos_2-1]

            if len(id) < 20:

                ID.append(id)

                id_uni = np.unique(ID)

           

            if len(id_uni)%10 == 0:

                id_idx = random.randint(1, len(id_uni))

                twitter_id = id_uni[id_idx]

                url = 'https://twitter.com/' + twitter_id

                print(url)

                driver.get(url)

                driver.implicitly_wait(10)

               

        print(len(id_uni))

    except:

        pass