Created
August 18, 2022 06:19
-
-
Save Alyetama/80434842b831b3cabdfb6143fdea4b07 to your computer and use it in GitHub Desktop.
Stable Diffusion Scraper
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
python-dotenv>=0.20.0 | |
selenium>=4.3.0 |
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
#!/usr/bin/env python | |
# coding: utf-8 | |
import json | |
import os | |
import re | |
import time | |
from datetime import datetime | |
from discord.ext import commands | |
from dotenv import load_dotenv | |
from selenium import webdriver | |
from selenium.common.exceptions import StaleElementReferenceException, NoSuchElementException # noqa | |
from selenium.webdriver.chrome.service import Service | |
from selenium.webdriver.common.by import By | |
load_dotenv() | |
CHANNEL_LINK = os.environ['CHANNEL_LINK'] | |
CHROME_BIN = os.environ['CHROME_BIN'] | |
CHROMEDRIVER_EXEC = os.environ['CHROMEDRIVER_EXEC'] | |
HELPER_TOKEN = os.environ['HELPER_TOKEN'] | |
options = webdriver.ChromeOptions() | |
options.add_argument('--headless') | |
options.add_argument('--mute-audio') | |
options.add_argument('--start-maximized') | |
options.add_argument('--no-sandbox') | |
options.add_argument('--disable-dev-shm-usage') | |
options.binary_location = CHROME_BIN | |
service = Service(CHROMEDRIVER_EXEC) | |
driver = webdriver.Chrome(options=options, service=service) | |
driver.get('https://discord.com/login') | |
driver.execute_script("let token =\"" + HELPER_TOKEN + """\"; | |
function login(token) { | |
setInterval(() => { | |
document.body.appendChild( | |
document.createElement `iframe` | |
).contentWindow.localStorage.token = `"${token}"` | |
}, 50); | |
setTimeout(() => { | |
location.reload(); | |
}, 2500); | |
} | |
login(token);""") | |
time.sleep(8) | |
driver.get(CHANNEL_LINK) | |
time.sleep(5) | |
elms = driver.find_elements(By.TAG_NAME, 'li') | |
try: | |
inbox_button = driver.find_element( | |
By.XPATH, | |
'/html/body/div[1]/div[2]/div/div[1]/div/div[2]/div/div[1]/div/div/' | |
'div[3]/section/div[2]/div[6]').click() | |
except NoSuchElementException: | |
elms = driver.find_elements(By.TAG_NAME, 'div') | |
inbox_button = [ | |
e for e in elms if e.get_attribute('aria-label') == 'Inbox' | |
][0].click() | |
time.sleep(1) | |
inbox = driver.find_element( | |
By.XPATH, '/html/body/div[1]/div[2]/div/div[3]/div/div/div/div[2]/div[1]') | |
inbox.find_element( | |
By.XPATH, | |
'/html/body/div[1]/div[2]/div/div[3]/div/div/div/div[1]/div[2]/div').click( | |
) | |
inbox_filter = inbox.find_element( | |
By.XPATH, '/html/body/div[1]/div[2]/div/div[3]/div[2]') | |
include_everyone = inbox_filter.find_element(By.ID, 'mentions-filter-Everyone') | |
if include_everyone.get_attribute('aria-checked') == 'true': | |
include_everyone.click() | |
time.sleep(1) | |
include_all_servers = inbox_filter.find_element(By.ID, | |
'mentions-filter-All Servers') | |
if include_all_servers.get_attribute('aria-checked') == 'true': | |
include_all_servers.click() | |
time.sleep(1) | |
inbox_messages = [ | |
e for e in inbox.find_elements(By.TAG_NAME, 'div') | |
if e.get_attribute('role') == 'article' | |
] | |
output = [] | |
for message in inbox_messages: | |
image_container = message.find_elements(By.TAG_NAME, 'div') | |
if 'DreamBotMothership' not in message.text: | |
continue | |
for e in image_container: | |
try: | |
url = e.find_element(By.TAG_NAME, 'a').get_attribute('href') | |
filler = 'Message could not be loaded.\n' | |
output.append([message.text.replace(filler, ''), url]) | |
except NoSuchElementException: | |
continue | |
data = [] | |
for response, url in output: | |
out = response.split('\n') | |
now = datetime.now() | |
try: | |
timestamp = datetime.strptime(' '.join(out[2].split(' ')[2:]), | |
'%I:%M %p').replace(year=now.year, | |
month=now.month, | |
day=now.day) | |
except ValueError: | |
timestamp = datetime.strptime(out[2], '%m/%d/%Y') | |
took = re.search(r'\d+.\d+s', out[3])[0] | |
prompt = '!dream '.join(out[3].split('!dream')[1:]).strip() | |
commands = out[5:] | |
d = { | |
'timestamp': str(timestamp), | |
'took': took, | |
'prompt': prompt, | |
'commands': commands, | |
'url': url | |
} | |
data.append(d) | |
# Export as JSON | |
with open('data.json', 'w') as j: | |
json.dump(data, j, indent=4) | |
driver.quit() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment