Files
emo-grab/src/test/java/EmoneyScraper.java
Administrator 6a5e13974c First Commit
2025-05-12 12:04:42 +08:00

69 lines
3.6 KiB
Java

import com.microsoft.playwright.*;
import com.microsoft.playwright.BrowserType.LaunchOptions;
import com.microsoft.playwright.Route.ResumeOptions;
import com.microsoft.playwright.options.HttpHeader;
import com.microsoft.playwright.options.Proxy;
import com.microsoft.playwright.options.WaitUntilState;
import java.util.*;
public class EmoneyScraper {
public static void main(String[] args) {
try (Playwright playwright = Playwright.create()) {
// 设置浏览器上下文选项,包括 User-Agent
Proxy proxy = new Proxy("http://127.0.0.1:8888");
LaunchOptions launchOptions = new BrowserType.LaunchOptions()
.setHeadless(true)
.setProxy(proxy);
Browser browser = playwright.chromium().launch(launchOptions);
BrowserContext context = browser.newContext(new Browser.NewContextOptions()
.setUserAgent("Mozilla/5.0 (Linux; Android 9; PCRT00 Build/PQ3B.190801.11191547; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/91.0.4472.114 Mobile Safari/537.36"));
// 设置全局请求头
Map<String, String> headers = new HashMap<>();
headers.put("Upgrade-Insecure-Requests", "1");
headers.put("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9");
headers.put("X-Requested-With", "cn.emoney.emstock");
headers.put("Sec-Fetch-Site", "none");
headers.put("Sec-Fetch-Mode", "navigate");
headers.put("Sec-Fetch-User", "?1");
headers.put("Sec-Fetch-Dest", "document");
headers.put("Accept-Encoding", "gzip, deflate");
headers.put("Accept-Language", "zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7");
context.setExtraHTTPHeaders(headers);
context.route("**/*", route -> {
Request request = route.request();
List<HttpHeader> requestHeaderList = request.headersArray();
Map<String, String> requestHeaders = new HashMap<>();
for (HttpHeader header : requestHeaderList) {
requestHeaders.put(header.name, header.value);
}
requestHeaders.remove("sec-ch-ua");
requestHeaders.remove("sec-ch-ua-mobile");
requestHeaders.remove("sec-ch-ua-platform");
route.resume(new ResumeOptions().setHeaders(requestHeaders));
});
Page page = context.newPage();
page.onResponse(handler -> {
String url = handler.request().url();
if (url.endsWith(".js")) {
String str = handler.request().response().text();
System.out.println(str);
}
});
String url = "https://appstatic.emoney.cn/html/emapp/stock/note/?name=10003001&emoneyScaleType=0&emoneyLandMode=0&token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCIsImN0eSI6IkpXVCJ9.eyJ1dWQiOjEwMTA2NjAwNDcsInVpZCI6MjQ3NjY5MDIsImRpZCI6IjdmOTA3N2VjZTlmMWIxMjQ4NmZmYjRmNDhjMzdkODJhIiwidHlwIjoxLCJhY2MiOiJlbXkxNzMwOTc4Iiwic3d0IjoxLCJsZ3QiOjE3NDQ1OTY2NTY3MTgsIm5iZiI6MTc0NDU5NjY1NiwiZXhwIjoxNzQ2MzI0NjU2LCJpYXQiOjE3NDQ1OTY2NTZ9.SHLqiavrzkwtLfxaWbA6GfnF7iBqbjnv86PTOhumiGc";
page.navigate(url, new Page.NavigateOptions().setWaitUntil(WaitUntilState.NETWORKIDLE));
String html = page.content();
System.out.println(html);
browser.close();
}
}
}