docs: 联网搜索服务架构方案全套(plan-final/design-arch/选型决策/整合导览/MCP文档/部署预设/联调手册) bench: 5 方案 + 代理 + 站点矩阵本机实测工程(无密钥) 部署目标:primary mgr1 先行测试(待批准后执行)
21 lines
851 B
Bash
Executable file
21 lines
851 B
Bash
Executable file
#!/usr/bin/env bash
|
|
# request.sh t2|t2-once [idx]
|
|
set -euo pipefail
|
|
unset HTTP_PROXY HTTPS_PROXY ALL_PROXY http_proxy https_proxy all_proxy NO_PROXY no_proxy
|
|
|
|
ROOT="$(cd "$(dirname "$0")" && pwd)"
|
|
SCHEME="trafilatura-http"
|
|
TARGET_URL="${T2_URL:-https://www.gov.cn/zhengce/2021-03/13/content_5592681.htm}"
|
|
idx="${2:-1}"
|
|
mode="${1:-t2}"
|
|
raw_dir="${RAW_DIR:-$ROOT/raw}"
|
|
mkdir -p "$raw_dir/bodies"
|
|
|
|
export BODY_OUT="${BODY_OUT:-$raw_dir/bodies/${mode}-${idx}.json}"
|
|
export SCHEME TEMPLATE="T2" IDX="$idx" METHOD="POST" MAX_TIME="${MAX_TIME:-30}"
|
|
export URL="http://127.0.0.1:18881/v1/read"
|
|
export TARGET_URL
|
|
export DATA
|
|
DATA=$(TARGET_URL="$TARGET_URL" python3 -c "import json,os; print(json.dumps({'url': os.environ['TARGET_URL'], 'formats': ['markdown'], 'max_chars': 20000}, ensure_ascii=False))")
|
|
export NOTE="${NOTE:-}"
|
|
bash "$ROOT/lib/curl_time.sh"
|