[中文]

用途:

• 返回用户搜这个词之前和之后还会搜什么，对应内容广场的「相关灵感」卡片
• 典型用法是选题扩词：拿一个核心词跑出一批关联词，再用 /get_keyword_stat 逐个比热度， 挑出竞争小但搜索量不低的词

请求体参数:

• search_word: 关键词，如 "面膜"

返回:

• upSearchWords[]（上游词）与 downSearchWords[]（下游词）
• 每个词自带 searchScore 搜索指数、readTotalCount 阅读总量、noteNum 笔记数、 relevanceRank 相关度排名、brandTag 是否品牌词

响应结构（取数要剥两层）:

• resp["data"] 是蒲公英原样信封（含 code/msg/success），业务数据还在它里面一层
• 正确取法：data = resp["data"]["data"]；下面「返回」列的字段都在这一层下

计费:

• HTTP 200 → 计费。包含「查无结果」（data 为 null，如 ID 不存在或筛选无命中）—— 请求已送达蒲公英，同样扣费，不要因为拿不到数据就重试
• HTTP 400 → 不计费（参数格式非法，或上游资源不足/异常）

[English]

Purpose:

• What users search before and after this keyword ("Related Inspiration" card)
• Typical use: expand one seed keyword into a candidate list, then compare each with /get_keyword_stat to find low-competition but decent-volume terms

Request Body Parameters:

• search_word: keyword, e.g. "面膜"

Return:

• upSearchWords[] (upstream terms) and downSearchWords[] (downstream terms)
• Each term carries searchScore, readTotalCount, noteNum, relevanceRank, brandTag

Response shape (two layers):

• resp["data"] is PGY's raw envelope (with code/msg/success); the payload is one level deeper
• Correct access: data = resp["data"]["data"] — every field listed under "Return" lives here

Billing:

• HTTP 200 → charged, including "no result" (data is null, e.g. ID not found or filters matched nothing): the request did reach PGY, so retrying on empty data just burns quota
• HTTP 400 → not charged (malformed params, or upstream unavailable/error)

[示例/Example]

{"search_word": "面膜"}

返回的 upSearchWords[]（上游词）与 downSearchWords[]（下游词）就是扩词的种子， 拿去逐个跑 /get_keyword_stat 比热度，挑竞争小的。

upSearchWords[] / downSearchWords[] are your expansion seeds — score them with /get_keyword_stat.

{
  "search_word": "面膜"
}