"""排查:list.json 分页响应中每个职位的字段结构,找招聘者职位(猎头顾问)字段""" import json import time from pathlib import Path from client.browser.cdp_lite import LiteCDP, CDPSession from client.browser.manager import BrowserManager OUT = Path(__file__).resolve().parent / "data" / "debug" / "猎头字段排查.txt" _lines: list[str] = [] def log(*a): s = " ".join(str(x) for x in a) _lines.append(s) OUT.write_text("\n".join(_lines), encoding="utf-8") def main(): BrowserManager().ensure_browser_started() lite = LiteCDP() tab = lite.open_tab("https://www.zhipin.com/web/geek/jobs?query=java&city=101010100") time.sleep(8) s = CDPSession(tab["webSocketDebuggerUrl"]) s.call("Network.enable") # 触发一次滚动,让站点请求分页/列表接口 s.eval_js("window.scrollBy(0, 600)") time.sleep(2) s.eval_js("window.scrollBy(0, 600)") dumped = 0 for msg in s.pump(6): if msg.get("method") != "Network.responseReceived": continue url = msg["params"]["response"]["url"] if not any(k in url for k in ("joblist", "job/list", "search", "recommend")): continue rid = msg["params"]["requestId"] try: body = s.call("Network.getResponseBody", {"requestId": rid}).get("body", "") jobs = json.loads(body).get("zpData", {}).get("jobList") or [] except Exception as e: log(f"响应解析失败:{e}") continue log(f"接口:{url[:120]},职位数:{len(jobs)}") for j in jobs[:6]: log("----- 职位字段 -----") log(json.dumps(j, ensure_ascii=False)[:1200]) dumped += 1 if dumped >= 2: break s.close() lite.close_tab(tab["id"]) log("完成") print("排查完成 ->", OUT) if __name__ == "__main__": main()