Playwright python 同步客户端出于某种原因使用异步上下文

Question

我正在尝试使用 Playwright Python 库编写一个简单的剪贴器

这是我如何使用它的基本示例：

from contextlib import contextmanager

from playwright.sync_api import sync_playwright


import asyncio

def is_async():
    return asyncio.get_event_loop().is_running()


class BaseScrapper(object):
    
    @property
    @contextmanager
    def playwright(self):
        print(f'BaseScrapper.playwright - is_async={is_async()}')
        with sync_playwright() as p:
            print(f'BaseScrapper.playwright with - is_async={is_async()}')
            yield p
    
    @property
    @contextmanager
    def browser(self):
        print(f'BaseScrapper.browser - is_async={is_async()}')
        with self.playwright as p:
            print(f'BaseScrapper.browser with - is_async={is_async()}')
            yield p.chromium.launch(headless=True)
    
    @contextmanager
    def open_page(self, url):
        print(f'BaseScrapper.open_page - is_async={is_async()}')
        with self.browser as browser:
            print(f'BaseScrapper.open_page.with - is_async={is_async()}')
            new_page = browser.new_page()
            
            # attach response listener
            new_page.on("response", self.intercept_response)
            
            new_page.goto(url, wait_until="domcontentloaded")
            yield new_page
    
    def intercept_response(self, response):
        pass



class ScrapeTest(BaseScrapper):
    @contextmanager
    def run(self):
        print(f'ScrapeTest.run - is_async={is_async()}')
        with self.open_page(url='www.google.com') as page:
            print(f'ScrapeTest.run - is_async={is_async()}')
            yield page


def run():
    print(f'running ... is_async={is_async()}')
    s = ScrapeTest()
    with s.run() as p:
        print(f'run.with is_async={is_async()}')

我希望它在同步上下文中运行，但它尝试切换到异步。运行 run 函数会产生以下输出：

>>> run()
running ... is_async=False
ScrapeTest.run - is_async=False
BaseScrapper.open_page - is_async=False
BaseScrapper.browser - is_async=False
BaseScrapper.playwright - is_async=False
BaseScrapper.playwright with - is_async=True
BaseScrapper.browser with - is_async=True
BaseScrapper.open_page.with - is_async=True

为什么“playwright”函数会切换到上下文管理器块内的异步上下文？我正在尝试在其中运行一些 django ORM 调用，但失败了

django.core.exceptions.SynchronousOnlyOperation: You cannot call this from an async context - use a thread or sync_to_async.

但我正在尝试在同步上下文中运行它......

我错过了什么？

非常感谢！

更简单的例子：

from playwright.sync_api import sync_playwright

import asyncio


class BaseScrapper(object):
    @property
    def playwright(self):
        print('basescrapper.playwright')
        return sync_playwright().start()
    
    @property
    def browser(self):
        print('basescrapper.browser')
        return self.playwright.chromium.launch(headless=True)
    
    def open_page(self, url):
        print('basescrapper.open page')
        page = self.browser.new_page()
        page.goto(url)
        return page



class SampleScrapper(BaseScrapper):
    def run(self):
        print(f'before - {"async" if asyncio.get_event_loop().is_running() else "sync"}')
        page = self.open_page(url='https://www.google.com')
        print(f'after - {"async" if asyncio.get_event_loop().is_running() else "sync"}')


def run():
    print(f'run 1 - {"async" if asyncio.get_event_loop().is_running() else "sync"}')
    s = SampleScrapper()
    print(f'run 2 - {"async" if asyncio.get_event_loop().is_running() else "sync"}')
    s.run()
    print(f'run 3 - {"async" if asyncio.get_event_loop().is_running() else "sync"}')

结果：

>>> run()
run 1 - sync
run 2 - sync
before - sync
basescrapper.open page
basescrapper.browser
basescrapper.playwright
after - async
run 3 - async

Answer 1

Playwright for Python 使用 asyncio 来执行其任务，但它有一个包装器来使 API 同步。

注意：我不精通Python。如果我错了请纠正我。