Created
November 5, 2023 03:57
-
-
Save vane/76aa72737809e091bc5732015c1867f3 to your computer and use it in GitHub Desktop.
python save page mhtml and screenshot using selenium webdriver
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 argparse | |
import base64 | |
import os.path | |
import selenium.webdriver.chrome.webdriver | |
from selenium import webdriver | |
from selenium.webdriver.chrome.options import Options | |
def save_screenshot(driver: selenium.webdriver.chrome.webdriver.WebDriver, fname: str): | |
page_rect = driver.execute_cdp_cmd("Page.getLayoutMetrics", {}) | |
src = driver.execute_cdp_cmd('Page.captureScreenshot', { | |
"format": "png", | |
"captureBeyondViewport": True, | |
"clip": { | |
"width": page_rect["cssContentSize"]["width"], | |
"height": page_rect["cssContentSize"]["height"], | |
"x": 0, | |
"y": 0, | |
"scale": 1 | |
} | |
}) | |
with open(fname, 'wb+') as f: | |
f.write(base64.urlsafe_b64decode(src['data'])) | |
def save_mhtml(driver: selenium.webdriver.chrome.webdriver.WebDriver, fname: str): | |
with open(fname, 'w+') as f: | |
page_source = driver.execute_cdp_cmd('Page.captureSnapshot', {}) | |
f.write(page_source['data']) | |
def driver_save(url: str, path: str, mhtml: str, screenshot: str): | |
chrome_options = Options() | |
chrome_options.add_argument("--headless") | |
driver = webdriver.Chrome(options=chrome_options) | |
try: | |
driver.get(url) | |
if mhtml: | |
save_mhtml(driver, fname=os.path.join(path, f'{mhtml}.mhtml')) | |
if screenshot: | |
save_screenshot(driver, fname=os.path.join(path, f'{screenshot}.jpg')) | |
finally: | |
driver.quit() | |
if __name__ == '__main__': | |
parser = argparse.ArgumentParser('Selenium scrap') | |
parser.add_argument('-u', '--url', required=True, help='page url') | |
parser.add_argument('-p', '--path', default='', help='save path') | |
parser.add_argument('-m', '--mhtml', default='page', help='mhtml file name') | |
parser.add_argument('-s', '--screenshot', default='page', help='screenshot file name') | |
args = parser.parse_args() | |
driver_save(args.url, args.path, args.mhtml, args.screenshot) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment