1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
|
"""
IndexNow URL 提交脚本 — 自动从 sitemap.xml 提取 URL 并提交到 IndexNow API
用法:
python indexnow_submit.py # 从 sitemap 获取 URL 并提交
python indexnow_submit.py --urls URL1 URL2 # 手动指定 URL
python indexnow_submit.py --dry-run # 仅查看要提交的 URL，不实际提交
python indexnow_submit.py --batch 100 # 每批 100 条（默认 50）
python indexnow_submit.py --workers 4 # 4 个并发任务并行提交
python indexnow_submit.py --verbose # 显示详细请求/响应信息
环境变量:
INDEXNOW_HOST 域名（默认 your-site.com，请改成你自己的）
INDEXNOW_SITEMAP sitemap URL
INDEXNOW_KEY 直接指定密钥（跳过文件查找）
INDEXNOW_KEY_DIR 密钥文件所在目录（默认当前目录）
"""
from __future__ import annotations
import argparse
import glob
import io
import json
import logging
import os
import random
import re
import ssl
import sys
import time
import xml.etree.ElementTree as ET
from concurrent.futures import FIRST_EXCEPTION, ThreadPoolExecutor, wait
from dataclasses import dataclass, field
from typing import List, Optional, Set
from urllib.error import HTTPError, URLError
from urllib.parse import urlparse
from urllib.request import Request, urlopen
__all__ = ["main"]
if sys.platform == "win32" and sys.stdout.encoding and sys.stdout.encoding.lower() in ("gbk", "gb2312", "gb18030"):
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="replace")
log = logging.getLogger("indexnow")
SITEMAP_NS = {"sm": "http://www.sitemaps.org/schemas/sitemap/0.9"}
DEFAULT_USER_AGENT = "Mozilla/5.0 (compatible; IndexNowSubmitter/2.0)"
_SSL_CTX = ssl.create_default_context()
@dataclass
class Config:
"""全部配置，支持环境变量覆盖。"""
host: str = field(default_factory=lambda: os.getenv("INDEXNOW_HOST", "your-site.com"))
sitemap_url: str = field(default_factory=lambda: os.getenv(
"INDEXNOW_SITEMAP",
f"https://{os.getenv('INDEXNOW_HOST', 'your-site.com')}/sitemap.xml",
))
key: Optional[str] = field(default_factory=lambda: os.getenv("INDEXNOW_KEY"))
key_dir: str = field(default_factory=lambda: os.getenv("INDEXNOW_KEY_DIR", "."))
endpoint: str = "https://api.indexnow.org/IndexNow"
max_batch_size: int = 10000
max_url_length: int = 2048
batch_size: int = 50
workers: int = 1
dry_run: bool = False
verbose: bool = False
@property
def effective_batch_size(self) -> int:
return min(self.batch_size, self.max_batch_size)
def _sep(title: str = "", width: int = 56) -> None:
if title:
print(f"\n{'=' * width}\n {title}\n{'=' * width}")
else:
print(f"{'=' * width}")
def _step(num: int, total: int, label: str, detail: str = "") -> None:
line = f"[{num}/{total}] {label}" + (f" {detail}" if detail else "")
print(f"\n{line}\n{'-' * len(line)}")
KEY_HEX_RE = re.compile(r"^[a-zA-Z0-9-]{8,128}$")
def find_key_file(directory: str = ".") -> Optional[str]:
"""在当前目录查找 IndexNow 密钥文件（.txt）。"""
txt_files = sorted(glob.glob(os.path.join(directory, "*.txt")))
if not txt_files:
return None
seen: Set[str] = set()
def _read_key(path: str) -> Optional[str]:
try:
with open(path, "r", encoding="utf-8") as fh:
return fh.read().strip()
except OSError:
return None
for f in txt_files:
basename = os.path.splitext(os.path.basename(f))[0]
if KEY_HEX_RE.match(basename):
key = _read_key(f)
if key:
return key
seen.add(f)
for f in txt_files:
if f in seen:
continue
key = _read_key(f)
if key and not key.startswith("#"):
return key
return None
def fetch_xml(url: str, max_retries: int = 4) -> bytes:
"""获取 XML，对 TLS 中断 / 瞬时网络错误做指数退避重试。"""
print(f" [请求] {url}")
req = Request(url, headers={"User-Agent": DEFAULT_USER_AGENT})
last_err: Optional[Exception] = None
for attempt in range(1, max_retries + 1):
try:
with urlopen(req, timeout=30, context=_SSL_CTX) as resp:
return resp.read()
except HTTPError:
raise
except (URLError, ssl.SSLError, ConnectionError, TimeoutError) as e:
last_err = e
if attempt >= max_retries:
break
delay = 2 ** attempt + random.uniform(0.5, 1.5)
print(f" [重试] 第 {attempt}/{max_retries} 次失败 ({type(e).__name__})，等待 {delay:.1f}s…")
time.sleep(delay)
raise last_err
def extract_urls_from_sitemap(url: str, seen: Optional[Set[str]] = None) -> List[str]:
"""递归提取 sitemap 中的所有 URL（支持 sitemapindex → urlset）。"""
if seen is None:
seen = set()
urls: List[str] = []
try:
data = fetch_xml(url)
except Exception as e:
print(f" [错误] 无法获取 {url}: {e}")
return urls
try:
root = ET.fromstring(data)
except ET.ParseError as e:
print(f" [错误] XML 解析失败 {url}: {e}")
return urls
tag = root.tag.rsplit("}", 1)[-1]
if tag == "sitemapindex":
for sitemap in root.findall("sm:sitemap", SITEMAP_NS):
loc = sitemap.find("sm:loc", SITEMAP_NS)
if loc is not None and loc.text and loc.text not in seen:
seen.add(loc.text)
urls.extend(extract_urls_from_sitemap(loc.text, seen))
elif tag == "urlset":
for url_elem in root.findall("sm:url", SITEMAP_NS):
loc = url_elem.find("sm:loc", SITEMAP_NS)
if loc is not None and loc.text:
urls.append(loc.text.strip())
return urls
@dataclass
class SubmitResult:
success: bool
status: int
reason: str
body: str
batch_index: int = 0
url_count: int = 0
def verify_key_location(key: str, key_location: str, max_retries: int = 3) -> tuple[bool, str]:
"""预检：访问 keyLocation，确认内容包含 key，避免提交后被 403 拒绝。"""
req = Request(key_location, headers={"User-Agent": DEFAULT_USER_AGENT})
last_err: Optional[Exception] = None
for attempt in range(1, max_retries + 1):
try:
with urlopen(req, timeout=20, context=_SSL_CTX) as resp:
content = resp.read().decode("utf-8", errors="replace").strip()
if key in content:
return True, f"已托管，内容匹配 ({len(content)} 字符)"
return False, f"文件已存在但内容不包含密钥（前 80 字符: {content[:80]!r})"
except HTTPError as e:
return False, f"HTTP {e.code} — keyLocation 不可访问 ({e.reason})"
except (URLError, ssl.SSLError, ConnectionError, TimeoutError) as e:
last_err = e
if attempt >= max_retries:
break
time.sleep(2 ** attempt + random.uniform(0.5, 1.0))
return False, f"网络错误，无法验证 keyLocation: {last_err}"
def send_request(host: str, key: str, key_location: str,
url_batch: List[str], endpoint: str) -> SubmitResult:
payload = {"host": host, "key": key, "keyLocation": key_location, "urlList": url_batch}
body = json.dumps(payload, ensure_ascii=False).encode("utf-8")
req = Request(
endpoint, data=body,
headers={"Content-Type": "application/json; charset=utf-8", "User-Agent": DEFAULT_USER_AGENT},
method="POST",
)
try:
with urlopen(req, timeout=60, context=_SSL_CTX) as resp:
return SubmitResult(True, resp.status, "OK",
resp.read().decode("utf-8", errors="replace"))
except HTTPError as e:
return SubmitResult(False, e.code, str(e.reason),
e.read().decode("utf-8", errors="replace"))
except URLError as e:
return SubmitResult(False, 0, f"网络错误: {e.reason}", "")
def submit_batch(host, key, key_location, url_batch, batch_index, total_batches, config) -> SubmitResult:
b = len(url_batch)
print()
_sep(f"批次 {batch_index}/{total_batches} —— 共 {b} 条 URL")
if config.verbose:
for idx, u in enumerate(url_batch, 1):
print(f" [{idx}/{b}] {u}")
else:
for idx, u in enumerate(url_batch[:3], 1):
print(f" [{idx}/{b}] {u}")
if b > 3:
print(f" ... 还有 {b - 3} 条")
print(f"\n POST {config.endpoint}")
if config.verbose:
payload_display = {"host": host, "key": key, "keyLocation": key_location, "urlList": url_batch}
print(f" Body: {json.dumps(payload_display, ensure_ascii=False)}")
if config.dry_run:
print(f"\n [DRY RUN] 模拟完成，未实际发送 ✓")
return SubmitResult(True, 0, "DRY RUN", "", batch_index, b)
max_retries = 3
result = SubmitResult(False, 0, "", "", batch_index, b)
for attempt in range(1, max_retries + 1):
if attempt > 1:
delay = 2 ** attempt + random.uniform(1, 2)
print(f"\n [重试] 第 {attempt}/{max_retries} 次，等待 {delay:.0f} 秒…")
time.sleep(delay)
else:
print(f" 发送中…")
result = send_request(host, key, key_location, url_batch, config.endpoint)
result.batch_index = batch_index
result.url_count = b
print(f" HTTP {result.status}" + (f" {result.reason}" if result.reason else ""))
if config.verbose and result.body:
try:
print(f" 响应: {json.dumps(json.loads(result.body), ensure_ascii=False)}")
except json.JSONDecodeError:
print(f" 响应: {result.body}")
if result.success:
print(f" ✓ 成功")
return result
should_retry = False
if result.status == 429 and attempt < max_retries:
should_retry = True
print(f" ⚠ 触发频率限制")
elif result.status == 403 and "UserForbiddedToAccessSite" in result.body and attempt < max_retries:
should_retry = True
print(f" ⚠ 密钥验证未通过")
if not should_retry:
print(f" ✗ 失败 (HTTP {result.status})")
return result
print(f" ✗ 重试 {max_retries} 次后仍失败")
return result
def validate_urls(urls: List[str], max_length: int = 2048) -> List[str]:
valid: List[str] = []
seen: Set[str] = set()
for u in urls:
u = u.strip()
if not u.startswith("https://"):
continue
if len(u) > max_length:
print(f" [跳过] URL 过长 ({len(u)} 字符): {u[:80]}…")
continue
if u not in seen:
seen.add(u)
valid.append(u)
dup_or_skip = len(urls) - len(valid)
print(f" ✓ 有效 URL: {len(valid)} 条" + (f"，跳过/去重: {dup_or_skip} 条" if dup_or_skip else ""))
return valid
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(
description="IndexNow URL 提交工具",
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog=__doc__,
)
parser.add_argument("--urls", nargs="+", help="手动指定要提交的 URL 列表")
parser.add_argument("--dry-run", action="store_true", help="模拟运行，不实际提交")
parser.add_argument("--batch", type=int, default=50, help="每批提交的 URL 数量（默认 50）")
parser.add_argument("--workers", type=int, default=1, help="并发工作数（默认 1）")
parser.add_argument("--sitemap", type=str, default=None, help="sitemap URL")
parser.add_argument("--host", type=str, default=None, help="网站域名（默认 your-site.com 或 INDEXNOW_HOST）")
parser.add_argument("--key", type=str, default=None, help="直接指定密钥（跳过文件查找）")
parser.add_argument("--key-dir", type=str, default=".", help="密钥文件所在目录（默认当前目录）")
parser.add_argument("--verbose", "-v", action="store_true", help="显示每个 URL 和请求/响应详情")
return parser
def build_config(args: argparse.Namespace) -> Config:
cfg = Config()
if args.host:
cfg.host = args.host
if args.sitemap:
cfg.sitemap_url = args.sitemap
elif args.host or not os.getenv("INDEXNOW_SITEMAP"):
cfg.sitemap_url = f"https://{cfg.host}/sitemap.xml"
if args.key:
cfg.key = args.key
if args.key_dir:
cfg.key_dir = args.key_dir
cfg.batch_size = args.batch
cfg.workers = max(1, args.workers)
cfg.dry_run = args.dry_run
cfg.verbose = args.verbose
return cfg
def setup_logging(verbose: bool = False) -> None:
logging.basicConfig(
level=logging.DEBUG if verbose else logging.WARNING,
format="%(message)s", stream=sys.stdout,
)
def main(argv: Optional[List[str]] = None) -> int:
parser = build_parser()
args = parser.parse_args(argv)
config = build_config(args)
setup_logging(config.verbose)
_sep("IndexNow URL 提交工具")
_step(1, 4, "读取密钥")
key = config.key or find_key_file(config.key_dir)
if not key:
print(" [错误] 未找到有效的密钥文件。")
print(f" 请将 .txt 密钥文件放在 {config.key_dir} 目录下，")
print(" 或通过 --key / INDEXNOW_KEY 环境变量指定。")
return 1
print(f" ✓ 密钥: {key}")
_step(2, 4, "获取 URL")
if args.urls:
raw_urls = args.urls
print(f" ✓ 命令行提供 {len(raw_urls)} 个 URL")
detected_hosts: Set[str] = set()
for u in raw_urls:
parsed = urlparse(u)
if parsed.hostname:
detected_hosts.add(parsed.hostname)
actual_host = detected_hosts.pop() if len(detected_hosts) == 1 else config.host
if len(detected_hosts) > 1:
print(f" ℹ 检测到多个域名，使用 --host 指定的: {actual_host}")
else:
sitemap = config.sitemap_url
print(f" 从 sitemap 获取: {sitemap}")
raw_urls = extract_urls_from_sitemap(sitemap)
if not raw_urls:
print(" [错误] 未能从 sitemap 获取任何 URL")
return 1
print(f" ✓ 提取 {len(raw_urls)} 个 URL")
if config.verbose:
for u in raw_urls[:5]:
print(f" {u}")
if len(raw_urls) > 5:
print(f" … 共 {len(raw_urls)} 条")
actual_host = urlparse(raw_urls[0]).hostname or config.host
key_location = f"https://{actual_host}/{key}.txt"
print(f" ✓ 域名: {actual_host}")
print(f" ✓ keyLocation: {key_location}")
print(f" 验证 keyLocation 可访问…")
ok, detail = verify_key_location(key, key_location)
if ok:
print(f" ✓ {detail}")
else:
print(f" ✗ keyLocation 预检失败：{detail}")
print(f" 提交后会被搜索引擎以 403 拒绝，已中止。")
print(f" 请把 {key}.txt（内容为密钥）上传到站点根目录：")
print(f" {key_location}")
return 1
_step(3, 4, "验证 URL")
valid_urls = validate_urls(raw_urls, config.max_url_length)
if not valid_urls:
print(" [错误] 没有有效的 URL 可提交")
return 1
batch_size = config.effective_batch_size
_step(4, 4, f"提交到 IndexNow", f"每批 {batch_size} 条 × {config.workers} 个并发")
if config.dry_run:
print(" [模式] DRY RUN —— 不会实际发送请求")
batches = [valid_urls[i:i + batch_size] for i in range(0, len(valid_urls), batch_size)]
total_batches = len(batches)
print(f" 共 {len(valid_urls)} 条 URL，分为 {total_batches} 批{'，开始提交…' if not config.dry_run else ''}")
success_count = 0
fail_count = 0
interrupted = False
first_error: Optional[SubmitResult] = None
if config.workers > 1 and not config.dry_run:
print(f"\n 并行模式：{config.workers} 个 worker 同时工作\n")
with ThreadPoolExecutor(max_workers=config.workers) as executor:
future_map = {
executor.submit(submit_batch, actual_host, key, key_location,
batch, i, total_batches, config): (i, batch)
for i, batch in enumerate(batches, 1)
}
done, _ = wait(future_map.keys(), return_when=FIRST_EXCEPTION)
for fut in done:
try:
result = fut.result()
if result.success:
success_count += result.url_count
else:
fail_count += result.url_count
first_error = result
break
except KeyboardInterrupt:
interrupted = True
break
except Exception as exc:
log.error("并发任务异常: %s", exc)
fail_count += 1
first_error = SubmitResult(False, 0, str(exc), "", url_count=1)
if interrupted or fail_count:
executor.shutdown(wait=False, cancel_futures=True)
else:
for i, batch in enumerate(batches, 1):
result = submit_batch(actual_host, key, key_location, batch, i, total_batches, config)
if result.success:
success_count += result.url_count
else:
fail_count += result.url_count
first_error = result
break
if not config.dry_run and i < total_batches:
delay = random.uniform(1.5, 3)
print(f"\n --- 等待 {delay:.1f} 秒后提交下一批 ---")
time.sleep(delay)
if fail_count and first_error and not config.dry_run:
_sep("提交失败")
print(f" 批次: {first_error.batch_index}")
print(f" 原因: HTTP {first_error.status} {first_error.reason}")
if first_error.body:
try:
print(f" 详情: {json.dumps(json.loads(first_error.body), ensure_ascii=False)}")
except json.JSONDecodeError:
print(f" 响应: {first_error.body}")
print(f" 已成功: {success_count} 条 ✓")
print(f" 已失败: {fail_count} 条 ✗")
_sep()
else:
_sep("提交报告")
print(f" 总计: {success_count + fail_count} 条")
print(f" 成功: {success_count} 条 ✓")
if config.dry_run:
print(f" 模式: DRY RUN（未实际提交）")
if interrupted:
print(f" 状态: 用户中断")
_sep()
if fail_count and first_error and first_error.status > 0:
return first_error.status
return 1 if fail_count else 0
if __name__ == "__main__":
exit(main())
|
