61 lines
3.8 KiB
SQL
61 lines
3.8 KiB
SQL
/*
|
||
MIP Query Task Table
|
||
用于存储查询词任务,抓取需要自动点击的网址
|
||
|
||
Date: 2026-01-19
|
||
*/
|
||
|
||
SET NAMES utf8mb4;
|
||
SET FOREIGN_KEY_CHECKS = 0;
|
||
|
||
-- ----------------------------
|
||
-- Table structure for ai_mip_query_task
|
||
-- ----------------------------
|
||
DROP TABLE IF EXISTS `ai_mip_query_task`;
|
||
CREATE TABLE `ai_mip_query_task` (
|
||
`id` int NOT NULL AUTO_INCREMENT COMMENT '主键ID',
|
||
`query_word` varchar(512) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NOT NULL COMMENT '查询词/关键词',
|
||
`query_type` enum('keyword','phrase','long_tail') CHARACTER SET utf8mb4 COLLATE utf8mb4_general_ci NOT NULL DEFAULT 'keyword' COMMENT '查询类型:关键词/短语/长尾词',
|
||
`task_date` char(8) CHARACTER SET utf8mb4 COLLATE utf8mb4_general_ci NOT NULL COMMENT '任务日期,格式:YYYYMMDD',
|
||
`threshold_max` int NOT NULL DEFAULT 100 COMMENT '最大抓取数量阈值',
|
||
`current_count` int NOT NULL DEFAULT 0 COMMENT '当前已抓取数量',
|
||
`status` enum('ready','doing','failed','finished','closed') CHARACTER SET utf8mb4 COLLATE utf8mb4_general_ci NOT NULL DEFAULT 'ready' COMMENT '任务状态:准备中/执行中/失败/完成/已关闭',
|
||
`priority` tinyint NOT NULL DEFAULT 5 COMMENT '优先级(1-10,数字越小优先级越高)',
|
||
`category` varchar(64) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '分类标签(如:医疗、教育、法律等)',
|
||
`source_platform` varchar(64) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT 'baidu' COMMENT '来源平台:baidu/sogou/360等',
|
||
`crawl_url_count` int NOT NULL DEFAULT 0 COMMENT '已爬取URL数量',
|
||
`valid_url_count` int NOT NULL DEFAULT 0 COMMENT '有效URL数量(带广告)',
|
||
`error_message` text CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL COMMENT '错误信息',
|
||
`started_at` timestamp NULL DEFAULT NULL COMMENT '开始执行时间',
|
||
`finished_at` timestamp NULL DEFAULT NULL COMMENT '完成时间',
|
||
`closed_at` timestamp NULL DEFAULT NULL COMMENT '达到阈值关闭时间',
|
||
`created_at` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT '创建时间',
|
||
`updated_at` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP COMMENT '更新时间',
|
||
`created_by` varchar(64) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT 'system' COMMENT '创建人',
|
||
`remark` varchar(512) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '备注信息',
|
||
PRIMARY KEY (`id`) USING BTREE,
|
||
UNIQUE INDEX `uniq_query_date`(`query_word`(191) ASC, `task_date` ASC) USING BTREE COMMENT '同一查询词每天只有一个任务',
|
||
INDEX `idx_date_status`(`task_date` ASC, `status` ASC) USING BTREE COMMENT '按日期和状态查询',
|
||
INDEX `idx_status_priority`(`status` ASC, `priority` ASC) USING BTREE COMMENT '按状态和优先级查询',
|
||
INDEX `idx_category`(`category` ASC) USING BTREE COMMENT '按分类查询',
|
||
INDEX `idx_threshold`(`threshold_max` ASC, `current_count` ASC) USING BTREE COMMENT '阈值监控',
|
||
INDEX `idx_closed`(`closed_at` ASC) USING BTREE COMMENT '关闭时间索引'
|
||
) ENGINE = InnoDB
|
||
AUTO_INCREMENT = 1
|
||
CHARACTER SET = utf8mb4
|
||
COLLATE = utf8mb4_general_ci
|
||
COMMENT = 'MIP查询任务表 - 用于存储查询词抓取网址任务'
|
||
ROW_FORMAT = DYNAMIC;
|
||
|
||
-- ----------------------------
|
||
-- 示例数据
|
||
-- ----------------------------
|
||
INSERT INTO `ai_mip_query_task`
|
||
(`query_word`, `query_type`, `task_date`, `threshold_max`, `priority`, `category`, `source_platform`, `remark`)
|
||
VALUES
|
||
('糖尿病治疗', 'keyword', '20260119', 50, 3, '医疗', 'baidu', '医疗类关键词测试'),
|
||
('在线教育平台', 'phrase', '20260119', 30, 5, '教育', 'baidu', '教育类短语测试'),
|
||
('法律咨询免费在线', 'long_tail', '20260119', 20, 7, '法律', 'baidu', '法律类长尾词测试');
|
||
|
||
SET FOREIGN_KEY_CHECKS = 1;
|