mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-06-09 03:17:25 +08:00
feat: 支持playwright通过cdp协议连接本地chrome浏览器
docs: 增加uv来管理python依赖的文档
This commit is contained in:
@@ -15,7 +15,7 @@ import random
|
||||
from asyncio import Task
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
from playwright.async_api import (BrowserContext, BrowserType, Page,
|
||||
from playwright.async_api import (BrowserContext, BrowserType, Page, Playwright,
|
||||
async_playwright)
|
||||
|
||||
import config
|
||||
@@ -23,6 +23,7 @@ from base.base_crawler import AbstractCrawler
|
||||
from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
|
||||
from store import douyin as douyin_store
|
||||
from tools import utils
|
||||
from tools.cdp_browser import CDPBrowserManager
|
||||
from var import crawler_type_var, source_keyword_var
|
||||
|
||||
from .client import DOUYINClient
|
||||
@@ -35,9 +36,11 @@ class DouYinCrawler(AbstractCrawler):
|
||||
context_page: Page
|
||||
dy_client: DOUYINClient
|
||||
browser_context: BrowserContext
|
||||
cdp_manager: Optional[CDPBrowserManager]
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.index_url = "https://www.douyin.com"
|
||||
self.cdp_manager = None
|
||||
|
||||
async def start(self) -> None:
|
||||
playwright_proxy_format, httpx_proxy_format = None, None
|
||||
@@ -47,14 +50,23 @@ class DouYinCrawler(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,
|
||||
user_agent=None,
|
||||
headless=config.HEADLESS
|
||||
)
|
||||
# 根据配置选择启动模式
|
||||
if config.ENABLE_CDP_MODE:
|
||||
utils.logger.info("[DouYinCrawler] 使用CDP模式启动浏览器")
|
||||
self.browser_context = await self.launch_browser_with_cdp(
|
||||
playwright, playwright_proxy_format, None,
|
||||
headless=config.CDP_HEADLESS
|
||||
)
|
||||
else:
|
||||
utils.logger.info("[DouYinCrawler] 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,
|
||||
playwright_proxy_format,
|
||||
user_agent=None,
|
||||
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")
|
||||
self.context_page = await self.browser_context.new_page()
|
||||
@@ -282,7 +294,41 @@ class DouYinCrawler(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
|
||||
)
|
||||
|
||||
# 添加反检测脚本
|
||||
await self.cdp_manager.add_stealth_script()
|
||||
|
||||
# 显示浏览器信息
|
||||
browser_info = await self.cdp_manager.get_browser_info()
|
||||
utils.logger.info(f"[DouYinCrawler] CDP浏览器信息: {browser_info}")
|
||||
|
||||
return browser_context
|
||||
|
||||
except Exception as e:
|
||||
utils.logger.error(f"[DouYinCrawler] 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) -> None:
|
||||
"""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("[DouYinCrawler.close] Browser context closed ...")
|
||||
|
||||
Reference in New Issue
Block a user