{"id":54933,"date":"2025-08-13T13:30:51","date_gmt":"2025-08-13T05:30:51","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/54933.html"},"modified":"2025-08-13T13:30:51","modified_gmt":"2025-08-13T05:30:51","slug":"node-js%e6%b5%8f%e8%a7%88%e5%99%a8%e5%bc%95%e6%93%8epython%e5%a4%a7%e8%84%91%e7%9a%84%e6%99%ba%e8%83%bd%e7%88%ac%e8%99%ab%e7%b3%bb%e7%bb%9f","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/54933.html","title":{"rendered":"Node.js\u6d4f\u89c8\u5668\u5f15\u64ce+Python\u5927\u8111\u7684\u667a\u80fd\u722c\u866b\u7cfb\u7edf"},"content":{"rendered":"

Node.js+Python\u6df7\u5408\u722c\u866b\u521b\u65b0\u6027\u5730\u7ed3\u5408\u4e86Playwright\u7684\u6d4f\u89c8\u5668\u63a7\u5236\u80fd\u529b\u4e0ePython\u7684\u8c03\u5ea6\u7ba1\u7406\u4f18\u52bf\u3002Node.js\u9a71\u52a8\u65e0\u5934Chromium\u5904\u7406\u52a8\u6001\u6e32\u67d3\u548c\u53cd\u722c\u673a\u5236，\u901a\u8fc7REST API\u8f93\u51fa\u6e32\u67d3\u540eHTML；Python\u4e3b\u63a7\u7aef\u5b9e\u73b0\u4efb\u52a1\u8c03\u5ea6\u3001\u6570\u636e\u89e3\u6790\u548c\u5b58\u50a8\u3002\u8fd9\u79cd\u67b6\u6784\u5b8c\u7f8e\u89e3\u51b3SPA\u7f51\u7ad9\u91c7\u96c6\u96be\u9898，\u7279\u522b\u9002\u7528\u4e8e\u7535\u5546\u4ef7\u683c\u76d1\u63a7\u3001\u793e\u4ea4\u5a92\u4f53\u6293\u53d6\u7b49\u9700\u4ea4\u4e92\u64cd\u4f5c\u7684\u573a\u666f\u3002<\/p>\n

\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\"<\/p>\n

\u4ee5\u4e0b\u5c31\u662f\u6211\u901a\u8fc7\u7ed3\u5408 Node.js (Playwright) \u548c Python \u7684\u722c\u866b\u5b9e\u73b0，\u4e13\u95e8\u5904\u7406\u9700\u8981\u6d4f\u89c8\u5668\u6e32\u67d3\u7684\u590d\u6742\u7f51\u7ad9：<\/p>\n

\u67b6\u6784\u601d\u8def<\/h4>\n

1\u3001Node.js \u90e8\u5206：\u4f7f\u7528 Playwright \u63a7\u5236\u6d4f\u89c8\u5668\u5904\u7406 JS \u6e32\u67d3\u548c\u53cd\u722c<\/p>\n

2\u3001Python \u90e8\u5206：\u4e3b\u8c03\u5ea6\u3001\u6570\u636e\u89e3\u6790\u3001\u5b58\u50a8\u548c\u4efb\u52a1\u7ba1\u7406<\/p>\n

3\u3001\u901a\u4fe1\u65b9\u5f0f：REST API + JSON<\/p>\n

Node.js \u6d4f\u89c8\u5668\u670d\u52a1 (browser_service.js)<\/h4>\n

const<\/span> express =<\/span> require<\/span>(<\/span>'express'<\/span>)<\/span>;<\/span>
\nconst<\/span> {<\/span> chromium }<\/span> =<\/span> require<\/span>(<\/span>'playwright'<\/span>)<\/span>;<\/span><\/p>\n

const<\/span> app =<\/span> express<\/span>(<\/span>)<\/span>;<\/span>
\napp.<\/span>use<\/span>(<\/span>express.<\/span>json<\/span>(<\/span>)<\/span>)<\/span>;<\/span>
\nconst<\/span> PORT<\/span> =<\/span> 3000<\/span>;<\/span><\/p>\n

\/\/ \u6d4f\u89c8\u5668\u5b9e\u4f8b\u6c60<\/span>
\nconst<\/span> browserPool =<\/span> {<\/span>}<\/span>;<\/span>
\nconst<\/span> MAX_BROWSERS<\/span> =<\/span> 5<\/span>;<\/span><\/p>\n

async<\/span> function<\/span> getBrowserInstance<\/span>(<\/span>id<\/span>)<\/span> {<\/span>
\n if<\/span> (<\/span>!<\/span>browserPool[<\/span>id]<\/span>)<\/span> {<\/span>
\n browserPool[<\/span>id]<\/span> =<\/span> await<\/span> chromium.<\/span>launch<\/span>(<\/span>{<\/span>
\n headless:<\/span> true<\/span>,<\/span>
\n args:<\/span> [<\/span>'–no-sandbox'<\/span>]<\/span>
\n }<\/span>)<\/span>;<\/span>
\n }<\/span>
\n return<\/span> browserPool[<\/span>id]<\/span>;<\/span>
\n}<\/span><\/p>\n

\/\/ \u6d4f\u89c8\u5668\u6e32\u67d3\u7aef\u70b9<\/span>
\napp.<\/span>post<\/span>(<\/span>'\/render'<\/span>,<\/span> async<\/span> (<\/span>req,<\/span> res<\/span>)<\/span> =><\/span> {<\/span>
\n const<\/span> {<\/span> url,<\/span> js_actions,<\/span> session_id =<\/span> 'default'<\/span> }<\/span> =<\/span> req.<\/span>body;<\/span><\/p>\n

try<\/span> {<\/span>
\n const<\/span> browser =<\/span> await<\/span> getBrowserInstance<\/span>(<\/span>session_id)<\/span>;<\/span>
\n const<\/span> context =<\/span> await<\/span> browser.<\/span>newContext<\/span>(<\/span>{<\/span>
\n userAgent:<\/span> 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/91.0.4472.124 Safari\/537.36'<\/span>
\n }<\/span>)<\/span>;<\/span><\/p>\n

const<\/span> page =<\/span> await<\/span> context.<\/span>newPage<\/span>(<\/span>)<\/span>;<\/span>
\n await<\/span> page.<\/span>goto<\/span>(<\/span>url,<\/span> {<\/span> waitUntil:<\/span> 'networkidle'<\/span>,<\/span> timeout:<\/span> 60000<\/span> }<\/span>)<\/span>;<\/span><\/p>\n

\/\/ \u6267\u884c\u81ea\u5b9a\u4e49JS\u64cd\u4f5c<\/span>
\n for<\/span> (<\/span>const<\/span> action of<\/span> js_actions ||<\/span> [<\/span>]<\/span>)<\/span> {<\/span>
\n if<\/span> (<\/span>action.<\/span>type ===<\/span> 'click'<\/span>)<\/span> {<\/span>
\n await<\/span> page.<\/span>click<\/span>(<\/span>action.<\/span>selector)<\/span>;<\/span>
\n await<\/span> page.<\/span>waitForTimeout<\/span>(<\/span>2000<\/span>)<\/span>;<\/span>
\n }<\/span> else<\/span> if<\/span> (<\/span>action.<\/span>type ===<\/span> 'scroll'<\/span>)<\/span> {<\/span>
\n await<\/span> page.<\/span>evaluate<\/span>(<\/span>(<\/span>)<\/span> =><\/span> window.<\/span>scrollTo<\/span>(<\/span>0<\/span>,<\/span> document.<\/span>body.<\/span>scrollHeight)<\/span>)<\/span>;<\/span>
\n await<\/span> page.<\/span>waitForTimeout<\/span>(<\/span>1000<\/span>)<\/span>;<\/span>
\n }<\/span>
\n }<\/span><\/p>\n

\/\/ \u83b7\u53d6\u6e32\u67d3\u540e\u5185\u5bb9<\/span>
\n const<\/span> content =<\/span> await<\/span> page.<\/span>content<\/span>(<\/span>)<\/span>;<\/span>
\n const<\/span> screenshot =<\/span> await<\/span> page.<\/span>screenshot<\/span>(<\/span>{<\/span> fullPage:<\/span> true<\/span> }<\/span>)<\/span>;<\/span><\/p>\n

await<\/span> context.<\/span>close<\/span>(<\/span>)<\/span>;<\/span><\/p>\n

res.<\/span>json<\/span>(<\/span>{<\/span>
\n success:<\/span> true<\/span>,<\/span>
\n html:<\/span> content,<\/span>
\n screenshot:<\/span> screenshot.<\/span>toString<\/span>(<\/span>'base64'<\/span>)<\/span>
\n }<\/span>)<\/span>;<\/span>
\n }<\/span> catch<\/span> (<\/span>error)<\/span> {<\/span>
\n res.<\/span>status<\/span>(<\/span>500<\/span>)<\/span>.<\/span>json<\/span>(<\/span>{<\/span>
\n success:<\/span> false<\/span>,<\/span>
\n error:<\/span> error.<\/span>message
\n }<\/span>)<\/span>;<\/span>
\n }<\/span>
\n}<\/span>)<\/span>;<\/span><\/p>\n

\/\/ \u6e05\u7406\u8d44\u6e90<\/span>
\nprocess.<\/span>on<\/span>(<\/span>'SIGINT'<\/span>,<\/span> async<\/span> (<\/span>)<\/span> =><\/span> {<\/span>
\n for<\/span> (<\/span>const<\/span> id in<\/span> browserPool)<\/span> {<\/span>
\n await<\/span> browserPool[<\/span>id]<\/span>.<\/span>close<\/span>(<\/span>)<\/span>;<\/span>
\n }<\/span>
\n process.<\/span>exit<\/span>(<\/span>)<\/span>;<\/span>
\n}<\/span>)<\/span>;<\/span><\/p>\n

app.<\/span>listen<\/span>(<\/span>PORT<\/span>,<\/span> (<\/span>)<\/span> =><\/span> console.<\/span>log<\/span>(<\/span>`<\/span>Browser service running on port <\/span>${<\/span>PORT<\/span>}<\/span><\/span>`<\/span><\/span>)<\/span>)<\/span>;<\/span><\/p>\n

Python \u4e3b\u8c03\u5ea6\u7a0b\u5e8f (main.py)<\/h4>\n

import<\/span> requests
\nfrom<\/span> bs4 import<\/span> BeautifulSoup
\nimport<\/span> csv
\nimport<\/span> time
\nfrom<\/span> urllib.<\/span>parse import<\/span> urlparse<\/p>\n

BROWSER_API =<\/span> "http:\/\/localhost:3000\/render"<\/span><\/p>\n

def<\/span> get_domain<\/span>(<\/span>url)<\/span>:<\/span>
\n """\u63d0\u53d6\u57df\u540d\u7528\u4e8e\u4f1a\u8bdd\u5206\u7ec4"""<\/span>
\n return<\/span> urlparse(<\/span>url)<\/span>.<\/span>netloc<\/p>\n

def<\/span> scrape_page<\/span>(<\/span>url,<\/span> actions=<\/span>None<\/span>)<\/span>:<\/span>
\n """\u8bf7\u6c42\u6d4f\u89c8\u5668\u6e32\u67d3\u670d\u52a1"""<\/span>
\n payload =<\/span> {<\/span>
\n "url"<\/span>:<\/span> url,<\/span>
\n "js_actions"<\/span>:<\/span> actions or<\/span> [<\/span>]<\/span>,<\/span>
\n "session_id"<\/span>:<\/span> get_domain(<\/span>url)<\/span> # \u76f8\u540c\u57df\u540d\u5171\u4eab\u6d4f\u89c8\u5668\u4f1a\u8bdd<\/span>
\n }<\/span><\/p>\n

try<\/span>:<\/span>
\n response =<\/span> requests.<\/span>post(<\/span>BROWSER_API,<\/span> json=<\/span>payload,<\/span> timeout=<\/span>120<\/span>)<\/span>
\n data =<\/span> response.<\/span>json(<\/span>)<\/span><\/p>\n

if<\/span> data[<\/span>'success'<\/span>]<\/span>:<\/span>
\n return<\/span> data[<\/span>'html'<\/span>]<\/span>
\n else<\/span>:<\/span>
\n print<\/span>(<\/span>f"\u6e32\u67d3\u5931\u8d25 <\/span>{<\/span>url}<\/span><\/span>: <\/span>{<\/span>data[<\/span>'error'<\/span>]<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span>
\n return<\/span> None<\/span>
\n except<\/span> Exception as<\/span> e:<\/span>
\n print<\/span>(<\/span>f"API\u8bf7\u6c42\u9519\u8bef <\/span>{<\/span>url}<\/span><\/span>: <\/span>{<\/span>str<\/span>(<\/span>e)<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span>
\n return<\/span> None<\/span><\/p>\n

def<\/span> parse_product<\/span>(<\/span>html,<\/span> url)<\/span>:<\/span>
\n """\u89e3\u6790\u4ea7\u54c1\u9875\u9762\u6570\u636e"""<\/span>
\n soup =<\/span> BeautifulSoup(<\/span>html,<\/span> 'lxml'<\/span>)<\/span><\/p>\n

# \u793a\u4f8b\u89e3\u6790\u903b\u8f91（\u6839\u636e\u5b9e\u9645\u7f51\u7ad9\u7ed3\u6784\u8c03\u6574）<\/span>
\n return<\/span> {<\/span>
\n 'url'<\/span>:<\/span> url,<\/span>
\n 'title'<\/span>:<\/span> soup.<\/span>find(<\/span>'h1'<\/span>)<\/span>.<\/span>get_text(<\/span>strip=<\/span>True<\/span>)<\/span> if<\/span> soup.<\/span>find(<\/span>'h1'<\/span>)<\/span> else<\/span> ''<\/span>,<\/span>
\n 'price'<\/span>:<\/span> (<\/span>soup.<\/span>select_one(<\/span>'.price'<\/span>)<\/span> or<\/span> soup.<\/span>select_one(<\/span>'[itemprop="price"]'<\/span>)<\/span>)<\/span>.<\/span>get_text(<\/span>strip=<\/span>True<\/span>)<\/span> if<\/span> soup.<\/span>select_one(<\/span>'.price'<\/span>)<\/span> else<\/span> ''<\/span>,<\/span>
\n 'description'<\/span>:<\/span> soup.<\/span>select_one(<\/span>'.description'<\/span>)<\/span>.<\/span>get_text(<\/span>strip=<\/span>True<\/span>)<\/span>[<\/span>:<\/span>200<\/span>]<\/span> if<\/span> soup.<\/span>select_one(<\/span>'.description'<\/span>)<\/span> else<\/span> ''<\/span>,<\/span>
\n 'rating'<\/span>:<\/span> soup.<\/span>select_one(<\/span>'[data-rating]'<\/span>)<\/span>.<\/span>attrs.<\/span>get(<\/span>'data-rating'<\/span>,<\/span> ''<\/span>)<\/span> if<\/span> soup.<\/span>select_one(<\/span>'[data-rating]'<\/span>)<\/span> else<\/span> ''<\/span>
\n }<\/span><\/p>\n

def<\/span> save_to_csv<\/span>(<\/span>data,<\/span> filename)<\/span>:<\/span>
\n """\u4fdd\u5b58\u7ed3\u679c\u5230CSV"""<\/span>
\n with<\/span> open<\/span>(<\/span>filename,<\/span> 'a'<\/span>,<\/span> newline=<\/span>''<\/span>,<\/span> encoding=<\/span>'utf-8'<\/span>)<\/span> as<\/span> f:<\/span>
\n writer =<\/span> csv.<\/span>DictWriter(<\/span>f,<\/span> fieldnames=<\/span>data.<\/span>keys(<\/span>)<\/span>)<\/span>
\n if<\/span> f.<\/span>tell(<\/span>)<\/span> ==<\/span> 0<\/span>:<\/span>
\n writer.<\/span>writeheader(<\/span>)<\/span>
\n writer.<\/span>writerow(<\/span>data)<\/span><\/p>\n

def<\/span> main<\/span>(<\/span>)<\/span>:<\/span>
\n # \u4efb\u52a1\u961f\u5217（\u5b9e\u9645\u9879\u76ee\u53ef\u4ece\u6570\u636e\u5e93\/\u961f\u5217\u83b7\u53d6）<\/span>
\n tasks =<\/span> [<\/span>
\n {<\/span>
\n 'url'<\/span>:<\/span> 'https:\/\/example.com\/products\/1'<\/span>,<\/span>
\n 'actions'<\/span>:<\/span> [<\/span>{<\/span>'type'<\/span>:<\/span> 'scroll'<\/span>}<\/span>,<\/span> {<\/span>'type'<\/span>:<\/span> 'click'<\/span>,<\/span> 'selector'<\/span>:<\/span> '.show-more'<\/span>}<\/span>]<\/span>
\n }<\/span>,<\/span>
\n {<\/span>
\n 'url'<\/span>:<\/span> 'https:\/\/example.com\/products\/2'<\/span>,<\/span>
\n 'actions'<\/span>:<\/span> [<\/span>{<\/span>'type'<\/span>:<\/span> 'click'<\/span>,<\/span> 'selector'<\/span>:<\/span> '.load-reviews'<\/span>}<\/span>]<\/span>
\n }<\/span>
\n ]<\/span><\/p>\n

for<\/span> task in<\/span> tasks:<\/span>
\n print<\/span>(<\/span>f"\u5904\u7406: <\/span>{<\/span>task[<\/span>'url'<\/span>]<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span>
\n html =<\/span> scrape_page(<\/span>task[<\/span>'url'<\/span>]<\/span>,<\/span> task.<\/span>get(<\/span>'actions'<\/span>)<\/span>)<\/span><\/p>\n

if<\/span> html:<\/span>
\n product_data =<\/span> parse_product(<\/span>html,<\/span> task[<\/span>'url'<\/span>]<\/span>)<\/span>
\n save_to_csv(<\/span>product_data,<\/span> 'products.csv'<\/span>)<\/span>
\n print<\/span>(<\/span>f"\u5df2\u4fdd\u5b58: <\/span>{<\/span>product_data[<\/span>'title'<\/span>]<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

time.<\/span>sleep(<\/span>3<\/span>)<\/span> # \u793c\u8c8c\u6027\u5ef6\u8fdf<\/span><\/p>\n

if<\/span> __name__ ==<\/span> "__main__"<\/span>:<\/span>
\n main(<\/span>)<\/span><\/p>\n

\u7cfb\u7edf\u8fd0\u884c\u6d41\u7a0b<\/h4>\n

1\u3001\u542f\u52a8\u6d4f\u89c8\u5668\u670d\u52a1：<\/p>\n

node browser_service.js<\/p>\n

2\u3001\u8fd0\u884c\u722c\u866b\u8c03\u5ea6：<\/p>\n

python main.py<\/p>\n

\u6838\u5fc3\u529f\u80fd\u8bf4\u660e<\/h4>\n

1\u3001\u6d4f\u89c8\u5668\u6e32\u67d3\u5c42 (Node.js)：<\/p>\n