scrape_peers_mastodon_ai/peer_instances.py

# import libraries
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import os
import time
import datetime
from pprint import pprint
import requests
import multiprocessing
from mastodon import Mastodon

with open('token.txt','r') as token:
    print(token.read())
    mastodon = Mastodon(access_token=token.read(),api_base_url="https://todon.nl")

peers = mastodon.instance_peers()

today = datetime.date.today()
text_file = open("scrape/results.txt", "a+")
text_file.write("Data collected on : "+str(today)+"\n"+"\n")


for n, peer in enumerate(peers):
    if n < 200:
        time.sleep(0.5)
        # get the url from the terminal
        # url ("Enter instance.social url (include https:// ): ")
        url = "https://"+(str(peer))
        print(peer)

        # Tell Selenium to open a new Firefox session
        # and specify the path to the driver
        driver = webdriver.Firefox(executable_path=os.path.dirname(os.path.realpath(__file__)) + '/geckodriver')

        # Implicit wait tells Selenium how long it should wait before it throws an exception
        driver.implicitly_wait(5)
        driver.get(url)
        time.sleep(3)

        print ('Instance: ', "\n", peer)
        text_file.write("Instance:"+"\n"+(peer)+"\n")

        try:
            about = driver.find_element_by_css_selector('.landing-page__short-description')
            print ('About:')
            print(about.text)
            text_file.write("About:"+"\n"+about.text+"\n"+"\n")
            time.sleep(1)

            try:
                # get the image source
                img = driver.find_element_by_xpath('/html/body/div[1]/div/div/div[3]/div[1]/img')
                src = img.get_attribute('src')
                # download the image
                Picture_request = requests.get(src)
                if Picture_request.status_code == 200:
                    with open("scrape/{}.jpg".format(peer), 'wb') as f:
                        f.write(Picture_request.content)
                        print("Printed Image")

            except:
                print("Impossible to print image")
                text_file.write("Impossible to print image"+"\n"+"\n")
                time.sleep(0.5)

        except:
            text_file.write("Impossible to check instance"+"\n"+"\n")
            print("Status:"+"\n"+"Impossible to check instance")
            time.sleep(1)

        # close new tab
        driver.close()
        print("Closing Window")

text_file.close()
# close the browser
driver.close()