Created
September 2, 2022 16:20
-
-
Save dgtlmoon/6f306e321200af521f82843bd4bc9901 to your computer and use it in GitHub Desktop.
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/python3 | |
""" | |
DOES NOT WORK because requests (and requests_cache) are blocking, if you have some ideas.. | |
https://stackoverflow.com/questions/52246796/await-a-method-and-assign-a-variable-to-the-returned-value-with-asyncio | |
""" | |
import asyncio | |
import re | |
import time | |
import requests_cache | |
from playwright.async_api import async_playwright | |
async def fetcher(): | |
async def handle(route, request): | |
print("handler called at {} {}".format(str(time.time()), request.url)) | |
session = requests_cache.CachedSession('demo_cache') | |
response = session.get(request.url, headers=request.headers) | |
print (response.from_cache) | |
await route.fulfill( | |
status=response.status_code, | |
content_type=response.headers.get('content-type'), | |
body=response.content, | |
headers=dict(response.headers)) | |
async with async_playwright() as p: | |
browser = await p.chromium.connect_over_cdp('ws://127.0.0.1:3000') | |
page = await browser.new_page() | |
await page.route(re.compile(r"\.(png|jpg|jpeg|css|js|webp|gif|mov|mpg|avi|mpeg|txt|ttf|woff)", re.IGNORECASE), handle) | |
await page.goto('https://theguardian.co.uk', timeout=300000) | |
print(f'title:{await page.title()}') | |
async def main(): | |
print("Calling async") | |
await fetcher() | |
print("Running in the asyncio") | |
asyncio.run(main()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment