Files
searxng-use-cli/scripts/common.py
T
thzxx f983a9377e feat(v1.7.0): AI 友好度增强 + 测试补全 (155→309)
核心新增(面向 AI Agent 程序化使用):
- 结构化错误码体系:E_CONFIG/E_AUTH/E_NETWORK/E_RATE_LIMIT/E_PARSE/E_EMPTY/E_INPUT/E_INTERNAL
  classify_error() 自动分类异常,JSON 错误输出含 error_code 字段
- JSON Lines 流式输出 (--stream):每条结果独立一行,AI 可增量处理
- 进度事件 (--progress):JSON Lines 事件流到 stderr(start/cache_hit/fetch_ok/done 等)

测试补全(+154 例,覆盖全部高风险盲区):
- HTML 回退搜索路径 (19)
- --fetch 自动抓取 (21)
- --verify 健康检查 (15)
- 输出格式化 (15)
- 实例解析链 (20)
- 并行多实例搜索 (10)
- CLI 入口与端到端 (17)
- 错误码分类 (27)
- 流式输出与进度事件 (10)

源码改进:
- search.py: h3 内 a 标签 href 作为 url fallback,提升 SearXNG 主题兼容性
- common.py: 新增 classify_error/emit_progress/set_progress_enabled

文档同步:SKILL.md 新增 AI Agent Integration Guide 章节,README.md 更新参数与错误码表
2026-08-01 17:40:14 +08:00

395 lines
15 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""Shared utilities for searxng-cli scripts.
This module centralizes code that was previously duplicated across
``search.py`` and ``fetch.py``:
* ``build_auth_headers`` — construct an Authorization header from CLI flags
* ``resolve_auth_basic`` — resolve basic-auth credentials from file/env/CLI
(avoids leaving passwords in shell history)
* ``detect_charset`` — guess a response's text encoding
* ``is_retryable_error`` — unified transient-error policy (urllib + requests)
* ``FALLBACK_UAS`` — browser-like User-Agents used when blocked
* retry constants — ``RETRYABLE_STATUS``, ``RETRY_BACKOFF_BASE``, etc.
* ``setup_logging`` — shared logging configuration (--verbose/--quiet)
Centralizing the retry policy guarantees that both scripts treat 429/5xx
as retryable and connection errors as transient, eliminating the previous
inconsistency where ``search.py`` ignored 5xx.
"""
import logging
import sys
import urllib.error
# Root logger for the searxng-cli package. All modules create child loggers
# via ``logging.getLogger("searxng.<module>")`` so a single setup_logging()
# call controls them all.
_LOG = logging.getLogger("searxng")
def setup_logging(verbose: bool = False, quiet: bool = False) -> None:
"""Configure the ``searxng`` logger hierarchy.
* Default (no flags): ``INFO`` — progress messages, warnings, retry notices.
Matches the previous ``print(..., file=sys.stderr)`` behavior so existing
scripts and agents see no change.
* ``--verbose`` / ``-v``: ``DEBUG`` — also shows HTTP request URLs, response
status codes, cache keys, and other diagnostic detail.
* ``--quiet`` / ``-q``: ``WARNING`` — suppresses progress and retry noise;
only warnings and errors reach stderr.
All log output goes to stderr; stdout is reserved for data (JSON/CSV/etc.).
"""
if verbose:
level = logging.DEBUG
elif quiet:
level = logging.WARNING
else:
level = logging.INFO
_LOG.setLevel(level)
# Avoid duplicate handlers if setup_logging() is called twice (e.g. tests).
if not _LOG.handlers:
handler = logging.StreamHandler(sys.stderr)
handler.setFormatter(logging.Formatter("%(message)s"))
_LOG.addHandler(handler)
# Don't let root logger add its own handler — we own the searxng namespace.
_LOG.propagate = False
# Retry settings (shared by both scripts)
MAX_RETRIES = 3
RETRY_BACKOFF_BASE = 1.5 # seconds; exponential backoff + jitter
# HTTP status codes that are worth retrying (rate limit + gateway errors)
RETRYABLE_STATUS = frozenset({429, 502, 503, 504})
# Browser-like UA strings for fallback when the searxng-cli UA is blocked
FALLBACK_UAS = [
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
]
def build_auth_headers(bearer_token: str = None, basic_auth: str = None) -> dict:
"""Build an Authorization header dict from CLI auth flags.
``bearer_token``: raw Bearer token string.
``basic_auth``: ``"username:password"`` string (base64-encoded).
If both are provided, Bearer takes precedence (more common for APIs).
Returns a dict to merge into request headers, or an empty dict.
"""
import base64
headers = {}
if bearer_token:
headers["Authorization"] = f"Bearer {bearer_token}"
elif basic_auth:
encoded = base64.b64encode(basic_auth.encode("utf-8")).decode("ascii")
headers["Authorization"] = f"Basic {encoded}"
return headers
def _warn_file_perms(path: str) -> None:
"""Warn if a credentials file is readable by group/other (POSIX only).
On Windows the Unix permission bits in ``st_mode`` do not reflect the
actual ACL, so the check is skipped to avoid false alarms.
"""
import os
if os.name != "posix":
return
log = logging.getLogger("searxng.common")
try:
mode = os.stat(path).st_mode & 0o777
if mode & 0o077:
log.warning(
f"Warning: credentials file '{path}' has permissions {oct(mode)} "
f"(accessible by group/other); recommend 'chmod 600' for security."
)
except OSError:
pass
def resolve_auth_basic(cli_value: str = None, file_path: str = None,
env_var: str = "SEARXNG_BASIC_AUTH") -> str:
"""Resolve basic-auth credentials without leaking them via shell history.
Priority (highest wins):
1. ``cli_value`` — explicit ``--auth-basic "user:pass"`` (convenient
but leaks into shell history; discouraged)
2. ``file_path`` — ``--auth-basic-file FILE``; first non-empty line
is read as ``user:pass``. Recommended for shells.
3. ``env_var`` — ``SEARXNG_BASIC_AUTH`` environment variable.
Returns ``"user:pass"`` or ``None`` if no source provides credentials.
Raises ``RuntimeError`` if a file is specified but cannot be read.
"""
if cli_value:
return cli_value
if file_path:
try:
from pathlib import Path
text = Path(file_path).read_text(encoding="utf-8")
_warn_file_perms(file_path)
for line in text.splitlines():
line = line.strip()
if line and not line.startswith("#"):
return line
raise RuntimeError(f"auth file '{file_path}' contains no credentials")
except OSError as e:
raise RuntimeError(f"cannot read auth file '{file_path}': {e}") from e
import os
return os.environ.get(env_var)
def resolve_auth_bearer(cli_value: str = None, file_path: str = None,
env_var: str = "SEARXNG_BEARER_TOKEN") -> str:
"""Resolve a Bearer token from CLI flag, file, or environment variable.
Mirrors :func:`resolve_auth_basic` for token-style auth. Useful for
long-lived API tokens that should not appear in shell history.
"""
if cli_value:
return cli_value
if file_path:
try:
from pathlib import Path
text = Path(file_path).read_text(encoding="utf-8")
_warn_file_perms(file_path)
for line in text.splitlines():
line = line.strip()
if line and not line.startswith("#"):
return line
raise RuntimeError(f"token file '{file_path}' contains no token")
except OSError as e:
raise RuntimeError(f"cannot read token file '{file_path}': {e}") from e
import os
return os.environ.get(env_var)
def apply_proxy(proxy_url: str) -> None:
"""Configure proxy via environment variables.
Sets ``HTTP_PROXY`` and ``HTTPS_PROXY`` so both urllib (which reads
them via :func:`urllib.request.getproxies`) and ``requests`` (which
honors them when ``trust_env=True``, the default) pick up the proxy
without any changes to call sites.
``NO_PROXY`` is set to ``localhost,127.0.0.1,::1`` (if not already set)
so local traffic stays direct — matters for self-hosted SearXNG on
localhost behind a corporate proxy.
Pass an empty string to clear the proxy env vars (rarely needed; the
default unset state already means "no proxy").
"""
import os
if not proxy_url:
return
os.environ["HTTP_PROXY"] = proxy_url
os.environ["HTTPS_PROXY"] = proxy_url
# Keep local traffic direct unless the user has explicitly set NO_PROXY
os.environ.setdefault("NO_PROXY", "localhost,127.0.0.1,::1")
def detect_charset(raw: bytes, content_type: str) -> str:
"""Detect charset from the Content-Type header, then an HTML meta tag.
Falls back to UTF-8 (with replacement) if nothing reliable is found.
"""
import re
# 1. HTTP header
if "charset=" in content_type:
charset = content_type.split("charset=")[-1].split(";")[0].strip()
try:
raw.decode(charset)
return charset
except (UnicodeDecodeError, LookupError):
pass
# 2. HTML <meta charset> or <meta http-equiv>
try:
head = raw[:4096].decode("ascii", errors="replace")
m = re.search(r'<meta[^>]+charset=["\']?([a-zA-Z0-9_-]+)', head, re.IGNORECASE)
if m:
charset = m.group(1).strip()
try:
raw.decode(charset)
return charset
except (UnicodeDecodeError, LookupError):
pass
except Exception:
pass
# 3. Fallback: UTF-8 with replacement
return "utf-8"
def is_retryable_error(exc: BaseException) -> bool:
"""Return True if ``exc`` is a transient error worth retrying.
Handles both the stdlib ``urllib`` errors and ``requests`` errors via
duck-typing (so this module does not need to import ``requests``):
* ``urllib.error.HTTPError`` → retry iff status in ``RETRYABLE_STATUS``
* ``urllib.error.URLError`` / ``OSError`` / ``TimeoutError`` → retry
(connection refused, DNS failure, timeout — all transient)
* ``requests.exceptions.HTTPError`` → retry iff ``response.status_code``
is in ``RETRYABLE_STATUS``
* ``requests`` connection/timeout errors (no ``.response``) → retry
"""
if isinstance(exc, urllib.error.HTTPError):
return exc.code in RETRYABLE_STATUS
if isinstance(exc, (urllib.error.URLError, OSError, TimeoutError)):
return not isinstance(exc, urllib.error.HTTPError)
# requests.exceptions.HTTPError / RequestException (duck-typed)
resp = getattr(exc, "response", None)
status = getattr(resp, "status_code", None)
if status is not None:
return status in RETRYABLE_STATUS
if resp is None:
# requests connection/timeout error without a response -> transient
return True
return False
# ----- Structured error classification -----
#
# 错误码体系:让 AI Agent 程序化地判断错误类型并采取恢复策略。
# 所有错误码以 E_ 前缀,在 --format json 模式下随 error_code 字段输出。
#
# AI 可根据 error_code 决策:
# E_CONFIG → 检查实例配置/环境变量,提示用户设置
# E_AUTH → 检查 token/凭证,提示用户重新认证
# E_NETWORK → 重试或切换实例/代理
# E_RATE_LIMIT → 等待后重试,降低请求频率
# E_PARSE → 检查实例是否支持 JSON,尝试 HTML 回退
# E_EMPTY → 调整查询词或时间范围
# E_INPUT → 修正参数/文件路径
# E_INTERNAL → 报告 bug,附带完整错误信息
# 错误码常量(供 search.py / fetch.py 引用)
E_CONFIG = "E_CONFIG"
E_AUTH = "E_AUTH"
E_NETWORK = "E_NETWORK"
E_RATE_LIMIT = "E_RATE_LIMIT"
E_PARSE = "E_PARSE"
E_EMPTY = "E_EMPTY"
E_INPUT = "E_INPUT"
E_INTERNAL = "E_INTERNAL"
def classify_error(exc: BaseException) -> str:
"""将异常分类为结构化错误码,供 AI Agent 程序化处理。
分类逻辑(按优先级):
1. 429 → E_RATE_LIMIT
2. 401/403 → E_AUTH
3. 4xx(非上述)→ E_INPUT(请求参数问题)
4. 5xx / URLError / OSError / TimeoutError → E_NETWORK
5. json.JSONDecodeError / ValueError → E_PARSE
6. FileNotFoundError → E_INPUT
7. RuntimeError → 尝试从消息中提取线索,否则 E_INTERNAL
8. 其他 → E_INTERNAL
"""
import json as _json
# HTTP 错误(urllib 和 requests 都有 .code 或 .status_code
status = None
if isinstance(exc, urllib.error.HTTPError):
status = exc.code
else:
resp = getattr(exc, "response", None)
status = getattr(resp, "status_code", None)
if status is not None:
if status == 429:
return E_RATE_LIMIT
if status in (401, 403):
return E_AUTH
if 400 <= status < 500:
return E_INPUT
if 500 <= status < 600:
return E_NETWORK
# 文件/输入错误(FileNotFoundError 是 OSError 子类,必须先于 OSError 检查)
if isinstance(exc, FileNotFoundError):
return E_INPUT
# 连接级错误
if isinstance(exc, (urllib.error.URLError, OSError, TimeoutError)):
return E_NETWORK
if isinstance(exc, ConnectionError):
return E_NETWORK
# 解析错误
if isinstance(exc, (ValueError, _json.JSONDecodeError)):
return E_PARSE
# RuntimeError:从消息中推断(search_multi 的 "All N instances failed" 等)
msg = str(exc).lower()
if isinstance(exc, RuntimeError):
if "auth" in msg or "403" in msg or "401" in msg:
return E_AUTH
if "rate" in msg or "429" in msg:
return E_RATE_LIMIT
if "all" in msg and "instance" in msg and "fail" in msg:
return E_NETWORK
if "parse" in msg or "json" in msg or "html" in msg:
return E_PARSE
if "not found" in msg or "no " in msg and "instance" in msg:
return E_CONFIG
return E_INTERNAL
return E_INTERNAL
# ----- Progress event emitter (for --progress flag) -----
#
# 当 --progress 启用时,search.py 会调用 emit_progress() 发射结构化事件到
# stderrJSON Lines 格式)。AI Agent 可解析这些事件来跟踪执行进度。
#
# 事件类型:
# {"event": "start", "query": "...", "instances": N}
# {"event": "instance_try", "url": "...", "attempt": 1}
# {"event": "instance_ok", "url": "...", "latency": 0.5, "results": 10}
# {"event": "instance_fail", "url": "...", "error": "...", "error_code": "E_*"}
# {"event": "cache_hit", "query": "...", "ttl": 30}
# {"event": "cache_store", "query": "...", "ttl": 30}
# {"event": "fetch_start", "count": 3}
# {"event": "fetch_ok", "url": "...", "chars": 1234}
# {"event": "fetch_fail", "url": "...", "error": "..."}
# {"event": "done", "results": N, "query": "..."}
# {"event": "error", "error": "...", "error_code": "E_*", "query": "..."}
_progress_enabled = False
def set_progress_enabled(enabled: bool) -> None:
"""全局开关:是否向 stderr 输出 JSON Lines 格式的进度事件。"""
global _progress_enabled
_progress_enabled = enabled
def emit_progress(event: str, **kwargs) -> None:
"""向 stderr 输出一行 JSON 格式的进度事件。
仅当 --progress 启用时才输出。``event`` 是事件类型字符串,
``kwargs`` 是事件的附加字段。输出格式为 JSON Lines(每行一个 JSON 对象)。
"""
if not _progress_enabled:
return
import json as _json
payload = {"event": event}
payload.update(kwargs)
print(_json.dumps(payload, ensure_ascii=False), file=sys.stderr, flush=True)