Created
April 26, 2019 07:28
-
-
Save gteissier/acff20a3d3ef8d71574da5c4468b2652 to your computer and use it in GitHub Desktop.
Take web screenshots
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 | |
from selenium import webdriver | |
import selenium | |
import sys | |
import re | |
def take_screenshot(url, png): | |
options = webdriver.ChromeOptions() | |
options.add_argument('headless') | |
options.add_argument('--ignore-certificate-errors') | |
driver = webdriver.Chrome(chrome_options=options) | |
driver.set_page_load_timeout(10) | |
driver.set_window_size(1024, 768) | |
driver.get(url) | |
driver.save_screenshot(png) | |
driver.quit() | |
urls = sys.stdin.read().split('\n') | |
n_urls = len(urls) | |
for i in range(n_urls): | |
url = urls[i] | |
url = url.rstrip('\n') | |
if not url: continue | |
m = re.search(r'//(.*)/', url) | |
assert(m) | |
png = 'pngs/%s.png' % m.group(1) | |
try: | |
take_screenshot(url, png) | |
except: | |
pass | |
sys.stdout.write('\r %2.2f%% %30s' % ((100.0*i)/n_urls, url)) | |
sys.stdout.flush() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment