feat: other platfrom support the cdp mode

This commit is contained in:
程序员阿江(Relakkes)
2025-07-03 17:13:32 +08:00
parent c892c3324c
commit 848df2b491
9 changed files with 565 additions and 102 deletions

View File

@@ -16,7 +16,7 @@ import random
from asyncio import Task
from typing import Dict, List, Optional, Tuple, cast
from playwright.async_api import (BrowserContext, BrowserType, Page,
from playwright.async_api import (BrowserContext, BrowserType, Page, Playwright,
async_playwright)
import config
@@ -26,6 +26,7 @@ from model.m_zhihu import ZhihuContent, ZhihuCreator
from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
from store import zhihu as zhihu_store
from tools import utils
from tools.cdp_browser import CDPBrowserManager
from var import crawler_type_var, source_keyword_var
from .client import ZhiHuClient
@@ -38,12 +39,14 @@ class ZhihuCrawler(AbstractCrawler):
context_page: Page
zhihu_client: ZhiHuClient
browser_context: BrowserContext
cdp_manager: Optional[CDPBrowserManager]
def __init__(self) -> None:
self.index_url = "https://www.zhihu.com"
# self.user_agent = utils.get_user_agent()
self.user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36"
self._extractor = ZhihuExtractor()
self.cdp_manager = None
async def start(self) -> None:
"""
@@ -58,14 +61,23 @@ class ZhihuCrawler(AbstractCrawler):
playwright_proxy_format, httpx_proxy_format = self.format_proxy_info(ip_proxy_info)
async with async_playwright() as playwright:
# Launch a browser context.
chromium = playwright.chromium
self.browser_context = await self.launch_browser(
chromium,
None,
self.user_agent,
headless=config.HEADLESS
)
# 根据配置选择启动模式
if config.ENABLE_CDP_MODE:
utils.logger.info("[ZhihuCrawler] 使用CDP模式启动浏览器")
self.browser_context = await self.launch_browser_with_cdp(
playwright, playwright_proxy_format, self.user_agent,
headless=config.CDP_HEADLESS
)
else:
utils.logger.info("[ZhihuCrawler] 使用标准模式启动浏览器")
# Launch a browser context.
chromium = playwright.chromium
self.browser_context = await self.launch_browser(
chromium,
None,
self.user_agent,
headless=config.HEADLESS
)
# stealth.min.js is a js script to prevent the website from detecting the crawler.
await self.browser_context.add_init_script(path="libs/stealth.min.js")
@@ -365,7 +377,38 @@ class ZhihuCrawler(AbstractCrawler):
)
return browser_context
async def launch_browser_with_cdp(self, playwright: Playwright, playwright_proxy: Optional[Dict],
user_agent: Optional[str], headless: bool = True) -> BrowserContext:
"""
使用CDP模式启动浏览器
"""
try:
self.cdp_manager = CDPBrowserManager()
browser_context = await self.cdp_manager.launch_and_connect(
playwright=playwright,
playwright_proxy=playwright_proxy,
user_agent=user_agent,
headless=headless
)
# 显示浏览器信息
browser_info = await self.cdp_manager.get_browser_info()
utils.logger.info(f"[ZhihuCrawler] CDP浏览器信息: {browser_info}")
return browser_context
except Exception as e:
utils.logger.error(f"[ZhihuCrawler] CDP模式启动失败回退到标准模式: {e}")
# 回退到标准模式
chromium = playwright.chromium
return await self.launch_browser(chromium, playwright_proxy, user_agent, headless)
async def close(self):
"""Close browser context"""
await self.browser_context.close()
# 如果使用CDP模式需要特殊处理
if self.cdp_manager:
await self.cdp_manager.cleanup()
self.cdp_manager = None
else:
await self.browser_context.close()
utils.logger.info("[ZhihuCrawler.close] Browser context closed ...")