-
-
Save YuniqueUnic/e8efce7b256cca783770e456e104ec4c to your computer and use it in GitHub Desktop.
Save .mhtml web archive using playwright
This file contains hidden or 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
| from playwright.sync_api import sync_playwright | |
| def save_mhtml(path: str, text: str): | |
| with open(path, mode='w', encoding='UTF-8', newline='\n') as file: | |
| file.write(text) | |
| def save_page(url: str, path: str): | |
| with sync_playwright() as playwright: | |
| browser = playwright.chromium.launch(headless=False) | |
| page = browser.new_page() | |
| page.goto(url) | |
| client = page.context.new_cdp_session(page) | |
| mhtml = client.send("Page.captureSnapshot")['data'] | |
| save_mhtml(path, mhtml) | |
| browser.close() | |
| if __name__ == '__main__': | |
| save_page('https://example.com/', 'example.mhtml') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment