Boris-code
playwright方式报错
问题 运行示例test_playwright.py 报错playwright._impl._errors.Error: It looks like you are using Playwright Sync API inside the asyncio loop.\nPlease use the Async API instead.
python环境 conda python 3.10 feapder[render] 1.9.0
截图
代码
import time
from playwright.sync_api import Page
import feapder
from feapder.utils.webdriver import PlaywrightDriver
class TestPlaywright(feapder.AirSpider):
__custom_setting__ = dict(
RENDER_DOWNLOADER="feapder.network.downloader.PlaywrightDownloader",
)
def start_requests(self):
yield feapder.Request("https://www.baidu.com", render=True)
def parse(self, reqeust, response):
driver: PlaywrightDriver = response.driver
page: Page = driver.page
page.type("#kw", "feapder")
page.click("#su")
page.wait_for_load_state("networkidle")
time.sleep(1)
html = page.content()
response.text = html # 使response加载最新的页面
for data_container in response.xpath("//div[@class='c-container']"):
print(data_container.xpath("string(.//h3)").extract_first())
if __name__ == "__main__":
TestPlaywright(thread_count=1).run()
你好, 解决了吗
还没有🥹
storage_state_path=None, # 保存浏览器状态的路径
我把这个设为None后, 不报错了
哇，这么厉害，我明天试试😎
你好, 解决了吗
还没有🥹
storage_state_path=None, # 保存浏览器状态的路径 我把这个设为None后, 不报错了
这样吗，我测试还是报错 class TestPlaywright(feapder.AirSpider): custom_setting = dict( RENDER_DOWNLOADER="feapder.network.downloader.PlaywrightDownloader", PLAYWRIGHT=dict( storage_state_path=None ) )
__custom_setting__ = dict(
PLAYWRIGHT=dict(
user_agent=None, # 字符串 或 无参函数，返回值为user_agent
proxy=None, # xxx.xxx.xxx.xxx:xxxx 或 无参函数，返回值为代理地址
headless=False, # 是否为无头浏览器
driver_type="chromium", # chromium、firefox、webkit
args=["--lang=zh-CN"],
timeout=60, # 请求超时时间
window_size=(1024, 800), # 窗口大小
executable_path=None, # 浏览器路径，默认为默认路径
download_path=None, # 下载文件的路径
render_time=0, # 渲染时长，即打开网页等待指定时间后再获取源码
wait_until="networkidle",
use_stealth_js=True, # 使用stealth.min.js隐藏浏览器特征
storage_state_path=None, # 保存浏览器状态的路径
page_on_event_callback=dict(response=on_response),
save_all=False,
),
)
我是这样的, 没报错, wsl2大便环境
__custom_setting__ = dict( PLAYWRIGHT=dict( user_agent=None, # 字符串 或 无参函数，返回值为user_agent proxy=None, # xxx.xxx.xxx.xxx:xxxx 或 无参函数，返回值为代理地址 headless=False, # 是否为无头浏览器 driver_type="chromium", # chromium、firefox、webkit args=["--lang=zh-CN"], timeout=60, # 请求超时时间 window_size=(1024, 800), # 窗口大小 executable_path=None, # 浏览器路径，默认为默认路径 download_path=None, # 下载文件的路径 render_time=0, # 渲染时长，即打开网页等待指定时间后再获取源码 wait_until="networkidle", use_stealth_js=True, # 使用stealth.min.js隐藏浏览器特征 storage_state_path=None, # 保存浏览器状态的路径 page_on_event_callback=dict(response=on_response), save_all=False, ), )我是这样的, 没报错, wsl2大便环境 确实 按你的配置我也好了 3Q
Author
可以使用 download_path 吗? download_path 好像用到了异步环境, 报错也与异步环境有关, 不使用download_path后即正常, 我这边是这样