Created
August 19, 2020 16:03
-
-
Save DipanshKhandelwal/f7acfded1b547fbd76c2b7d7810e6dd9 to your computer and use it in GitHub Desktop.
Scraping Verified Twitter Usernames using Selenium
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import time | |
from bs4 import BeautifulSoup | |
from selenium import webdriver | |
from selenium.webdriver.chrome.options import Options | |
chrome_options = Options() | |
chrome_options.add_argument("--headless") | |
driver = webdriver.Chrome('/usr/lib/chromium-browser/chromedriver', chrome_options=chrome_options) | |
driver.get('https://www.twitter.com/login') | |
search_box = driver.find_element_by_class_name('js-username-field') | |
search_box.send_keys('your_email_address') # <--- your email goes here | |
driver.implicitly_wait(1) | |
search_box = driver.find_element_by_class_name('js-password-field') | |
search_box.send_keys('your_password') # <--- your password goes here | |
driver.implicitly_wait(1) | |
search_box.submit() | |
textContent = [] | |
driver.get('https://www.twitter.com/verified/following') | |
for d in range(100): | |
for times in range(210): | |
file = open('twitter_names_scroll_again_wow'+str(d), 'w+') | |
print("process : " + str(d) + " time : " + str(times)) | |
driver.execute_script("window.scrollTo(0, document.body.scrollHeight)") | |
time.sleep(2) | |
page_source = driver.page_source | |
page_content = BeautifulSoup(page_source, "html.parser") | |
some = page_content.find_all(class_="ProfileCard-screennameLink") | |
for i in some[len(textContent):]: | |
name = i.get('href')[1:] | |
if name not in textContent: | |
textContent.append(name) | |
file.write(name+'\n') | |
driver.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment