Compare commits
4
Commits
f83ea3e29a
..
master
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
1407fa9fb6 | ||
|
|
d4e5c611b0 | ||
|
|
6dc33604d1 | ||
|
|
5823b5fbb3 |
@@ -41,6 +41,8 @@ README — TamaBox 站内信群发工具(mail-broadcast)
|
||||
to = ; 可选:默认测试收件邮箱
|
||||
delay = 1.0
|
||||
group_pause = 3.0
|
||||
smtp_idle_reconnect = 30 ; SMTP 空闲超时秒数,超时就重连
|
||||
batch_size = 0 ; 合并信封:内容相同的收件人每 N 人一封(0=逐封)
|
||||
|
||||
[bounce] ; 退信核查 / 发送中限流巡检(见下节)
|
||||
watch_bounces = 1 ; 发送中巡检限流退信,发现即中止
|
||||
@@ -247,9 +249,61 @@ conf/app.ini 路径的解析优先级:
|
||||
- 用的是 conf/app.ini [mail] 的账号与密码(需邮箱已开启 IMAP,密码为邮箱登录密码)
|
||||
- 交互模式的运行方式「4) 退信核查」里同样三选一:仅核查 / 仅剔除 / 剔除并补发,
|
||||
选择「仅剔除 / 剔除并补发」时会再问一次是否连未分类的一起补发
|
||||
- 已核查过的退信(按 Message-ID)记录在 broadcast_bounces_seen.json,
|
||||
重复核查不会重复报告/重复剔除
|
||||
- 每次核查另写一份明细报告 broadcast_bounce_report.json(含每个收件人的类别与判定依据)
|
||||
- 已核查过的退信(按 Message-ID)与**上次扫描位置**(INBOX UID 游标 +
|
||||
UIDVALIDITY)都记录在 broadcast_bounces_seen.json:
|
||||
默认从上次位置续扫(UID n+1:*),只拉新邮件的头部,重复核查不会
|
||||
重复报告/重复剔除,也不会随邮箱邮件增多越扫越慢
|
||||
- 以下情况自动回退为按日期窗口从头扫(扫完位置照常更新):
|
||||
首次核查(无位置记录)、邮箱 UIDVALIDITY 变化(换号/重建邮箱)、
|
||||
显式指定 --since、加 --full-scan
|
||||
- 发送中巡检不推进扫描位置(它只看本次运行之后新到的退信,
|
||||
范围内的历史邮件不标记「已扫」),位置只由 --check-bounces 推进
|
||||
- 每次核查另写一份明细报告 broadcast_bounce_report.json(含每个收件人的
|
||||
类别与判定依据,以及 scan_mode / scan_cursor)
|
||||
|
||||
发信账号来源:app.ini / 程序自带 SMTP
|
||||
------------------------------------
|
||||
默认用 conf/app.ini [mail] 的 SMTP(站内信跟随站点自己的邮箱)。切到程序
|
||||
自带的一套后,发信与退信核查(IMAP)都走这套账号:
|
||||
|
||||
[mail]
|
||||
source = app ; app(默认)= conf/app.ini [mail];own = 下面这套
|
||||
account = bot@other.com
|
||||
password = env:MY_SMTP_PASSWORD ; 支持 env:变量名,推荐
|
||||
smtp = smtp.other.com
|
||||
port = 465
|
||||
skip_tls_verify = 0
|
||||
|
||||
临时切换(优先级高于 params.ini):`--mail-source own` / `--mail-source app`
|
||||
交互模式里若 [mail] 配齐了,会多问一次选哪个来源。
|
||||
|
||||
安全提醒:
|
||||
- params.ini 会被 git 跟踪,**不要把密码明文写进去**;用 `env:变量名`
|
||||
从环境变量读取,或把 params.ini 加入 .gitignore
|
||||
- 明文写死时脚本会打印警告,但不会阻止运行
|
||||
- 切到 own 但 [mail] 缺 smtp/account/password 时直接 FATAL,不会用半套配置
|
||||
|
||||
合并信封批量发送(可选)
|
||||
------------------------
|
||||
默认逐人一封(一个 SMTP 信封 = 1 个 RCPT TO)。开启 batch_size 后,
|
||||
「渲染后内容完全相同」的收件人合并发送:一个信封 = 1×MAIL FROM +
|
||||
N×RCPT TO + 1×DATA,发送次数从「人数」降到「信封数」(如 305 人、
|
||||
每 50 人一封 → 约 7 次发信)。
|
||||
|
||||
开启方式(0=关闭):
|
||||
broadcast.py --send --single --batch-size 25
|
||||
或 params.ini [send] batch_size = 25
|
||||
|
||||
与限流的关系(要点):
|
||||
- 服务商按「发信次数」计频率 → 合并后成倍降低触发概率(主要收益)
|
||||
- 服务商按「单位时间收件人总数」计数 → 无缓解,仍靠 delay/pause 控制节奏
|
||||
- 单封收件人数上限常见 50~100:超限的 RCPT 会被 452 拒收,脚本自动把
|
||||
batch_size 砍半、被拒者重试,不会中止也不会误判为限流
|
||||
- 信封收件人对其他收件人不可见;批量信封的 To: 头显示为「站点名+发件邮箱」
|
||||
|
||||
适用的前提是内容逐字相同:模板含 {{name}}/{{box_link}} 等个人化占位符时,
|
||||
渲染结果逐人不同,会自动落回逐封,不会错合。断点续发按人记录(DATA 被
|
||||
服务器接收即整批入账,被拒的除外);发送中限流巡检照常按收件人数计数。
|
||||
|
||||
安全机制
|
||||
--------
|
||||
@@ -257,7 +311,12 @@ conf/app.ini 路径的解析优先级:
|
||||
- 发送前打印数据库统计与语言分布,人工核对
|
||||
- 每封间隔 --delay 秒(默认 1.0);--pause-every/--pause-for 防限流
|
||||
- 按语言分群发送,组间 --group-pause 秒(默认 3.0)
|
||||
- SMTP 断线自动重连:服务器会掐掉空闲连接,--delay 调大(如 60s/封)时
|
||||
必现「Server not connected / please run connect() first」,整批失败。
|
||||
连接空闲超过 `smtp_idle_reconnect` 秒(默认 30,0 关闭)就主动重连;
|
||||
仍遇到断线则立即重试最多 3 次(间隔 2s/4s),失败才会记为该收件人失败
|
||||
- SMTP 拒收(refused)计入失败并写入报告
|
||||
- 批量信封遇 452「收件人数超限」自动砍半拆批重试;限流类拒收仍立即中止
|
||||
- From/Subject 头自动做 RFC2047 编码(中文显示名不会被 QQ 邮箱 550 拒收)
|
||||
- 自动定位 users 表所在 schema(避免 psql 命中别的同名空表)
|
||||
- 语言列自动试跑探测(language → lang → NULL 兜底),老库没有该列也能发
|
||||
|
||||
+557
-97
@@ -62,6 +62,7 @@ TamaBox 站内信群发工具(独立项目,零依赖,不依赖、不修改
|
||||
import argparse
|
||||
import configparser
|
||||
import email.utils
|
||||
import hashlib
|
||||
import imaplib
|
||||
import json
|
||||
import os
|
||||
@@ -82,7 +83,7 @@ from email.mime.text import MIMEText
|
||||
from email.utils import formataddr, make_msgid, parsedate_to_datetime
|
||||
from urllib.parse import quote_plus
|
||||
|
||||
SCRIPT_VERSION = "2026-09-07.bounceclass.v3"
|
||||
SCRIPT_VERSION = "2026-09-08.mailsource.v5"
|
||||
|
||||
DEFAULT_STATE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "broadcast_state.json")
|
||||
DEFAULT_REPORT = os.path.join(os.path.dirname(os.path.abspath(__file__)), "broadcast_report.json")
|
||||
@@ -599,24 +600,43 @@ def resolve_lang(lang_field, default_lang, available):
|
||||
return lang
|
||||
|
||||
|
||||
def build_message(cfg, to_addr, ctx, subject, html, plain):
|
||||
subject, miss1 = render_strict(subject, ctx)
|
||||
html, miss2 = render_strict(html, ctx)
|
||||
plain, miss3 = render_strict(plain, ctx)
|
||||
def render_content(subject, html, plain, ctx):
|
||||
"""渲染 subject/html/plain 三段;返回 (渲染结果三元组, 缺失占位符列表)。
|
||||
|
||||
拆出来是为了批量发送:先渲染、按内容指纹分桶,内容完全相同的收件人
|
||||
才共用一个 SMTP 信封;逐封路径与批量路径共用同一份渲染结果。
|
||||
"""
|
||||
subject, m1 = render_strict(subject, ctx)
|
||||
html, m2 = render_strict(html, ctx)
|
||||
plain, m3 = render_strict(plain, ctx)
|
||||
return subject, html, plain, sorted(set(m1 + m2 + m3))
|
||||
|
||||
|
||||
def build_message_from(cfg, to_header, subject, html, plain):
|
||||
"""用已渲染好的内容构造 MIME 邮件(不再做占位符替换)。
|
||||
|
||||
to_header 只影响收件人看到的「收件人」显示,与实际投递无关:
|
||||
批量信封的真实收件人走 SMTP 信封(RCPT TO),互相不可见。
|
||||
"""
|
||||
msg = MIMEMultipart("alternative")
|
||||
from_user = cfg.get("app_title") or ""
|
||||
from_addr = cfg["mail_account"]
|
||||
# RFC5322/RFC2047:非 ASCII 显示名必须先编码再放进 From,
|
||||
# 否则 QQ 邮箱等会以 "From header is missing or invalid" 550 拒收。
|
||||
msg["From"] = formataddr((str(Header(from_user, "utf-8")), from_addr))
|
||||
msg["To"] = to_addr
|
||||
msg["To"] = to_header
|
||||
msg["Subject"] = Header(subject, "utf-8")
|
||||
msg["Date"] = email.utils.formatdate(localtime=True)
|
||||
msg["Message-ID"] = make_msgid(domain=from_addr.split("@")[-1])
|
||||
msg.attach(MIMEText(plain, "plain", "utf-8"))
|
||||
msg.attach(MIMEText(html, "html", "utf-8"))
|
||||
return msg, sorted(set(miss1 + miss2 + miss3))
|
||||
return msg
|
||||
|
||||
|
||||
def build_message(cfg, to_addr, ctx, subject, html, plain):
|
||||
subject, html, plain, missing = render_content(subject, html, plain, ctx)
|
||||
msg = build_message_from(cfg, to_addr, subject, html, plain)
|
||||
return msg, missing
|
||||
|
||||
|
||||
def smtp_login(cfg):
|
||||
@@ -637,6 +657,118 @@ def smtp_login(cfg):
|
||||
return server
|
||||
|
||||
|
||||
# 断线重连需要重试的异常:连接被服务器掐掉 / 压根没连上 / 网络层故障。
|
||||
# 注意 SMTP 拒收(SMTPRecipientsRefused / SMTPDataError 等)不在其中——
|
||||
# 那是服务器明确回了话,重试同样会失败,还会重复投递。
|
||||
SMTP_TRANSIENT_ERRORS = (smtplib.SMTPServerDisconnected, smtplib.SMTPConnectError, OSError)
|
||||
|
||||
|
||||
class SmtpSession:
|
||||
"""维持一条 SMTP 连接,断线自动重连。
|
||||
|
||||
为什么必须有:服务器会掐掉空闲连接(QQ/163/阿里云常见 5~15 分钟,
|
||||
有的更短)。群发一旦把 --delay 调大(比如 60s/封),两封之间连接空闲
|
||||
整整一分钟,第一封就报「Server not connected」,之后每封都是
|
||||
「please run connect() first」——脚本此前只在开头登录一次,从不重连。
|
||||
|
||||
策略:
|
||||
- 发送前若距上次活动超过 idle_reconnect 秒,主动断开重连(省得每次
|
||||
都先吃一发失败)
|
||||
- 仍遇到断线类异常则立即重连重试,最多 max_retries 次(重试间隔
|
||||
2s/4s,给服务器喘息)
|
||||
"""
|
||||
|
||||
def __init__(self, cfg, max_retries=3, idle_reconnect=30):
|
||||
self.cfg = cfg
|
||||
self.max_retries = max(1, max_retries)
|
||||
self.idle_reconnect = max(0, idle_reconnect)
|
||||
self.server = None
|
||||
self.last_used = 0.0
|
||||
self.reconnects = 0
|
||||
self.server = self._connect() # 启动时就连,账号/网络问题第一时间暴露
|
||||
|
||||
def _connect(self):
|
||||
self.server = smtp_login(self.cfg)
|
||||
self.last_used = time.time()
|
||||
return self.server
|
||||
|
||||
def close(self):
|
||||
if self.server is not None:
|
||||
try:
|
||||
self.server.quit()
|
||||
except Exception: # noqa: BLE001
|
||||
pass
|
||||
self.server = None
|
||||
|
||||
def send_to(self, msg, rcpt_addrs=None):
|
||||
"""带重连的发送;rcpt_addrs 给定时做批量信封(1×MAIL FROM + N×RCPT TO + 1×DATA)。
|
||||
|
||||
- rcpt_addrs=None:按邮件头解析收件人(等价旧的逐封 send_message)
|
||||
- rcpt_addrs=[...]:信封收件人列表,To: 头仅作显示(互相不可见)
|
||||
返回 refused dict {地址: (码, 错误)}。整信封全部被拒时
|
||||
SMTPRecipientsRefused 也转为 dict 返回——那是服务器明确回话,
|
||||
不属于连接故障,不重试。连接类异常仍走重连重试,耗尽后抛原始异常。
|
||||
"""
|
||||
if (self.idle_reconnect and self.server is not None
|
||||
and time.time() - self.last_used > self.idle_reconnect):
|
||||
self.close()
|
||||
last_err = None
|
||||
for attempt in range(1, self.max_retries + 1):
|
||||
try:
|
||||
if self.server is None:
|
||||
self.reconnects += 1
|
||||
print(f" [重连] SMTP 连接已断开,正在重新登录"
|
||||
f"(第 {self.reconnects} 次)...")
|
||||
self._connect()
|
||||
if rcpt_addrs is None:
|
||||
refused = self.server.send_message(msg)
|
||||
else:
|
||||
refused = self.server.send_message(
|
||||
msg, from_addr=self.cfg["mail_account"],
|
||||
to_addrs=list(rcpt_addrs))
|
||||
self.last_used = time.time()
|
||||
return refused
|
||||
except smtplib.SMTPRecipientsRefused as e:
|
||||
self.last_used = time.time()
|
||||
return dict(e.recipients or {})
|
||||
except SMTP_TRANSIENT_ERRORS as e: # noqa: PERF203
|
||||
last_err = e
|
||||
self.close()
|
||||
if attempt < self.max_retries:
|
||||
wait = 2 * attempt
|
||||
print(f" [重试] SMTP 连接异常({e}),{wait}s 后重试"
|
||||
f"({attempt}/{self.max_retries - 1})")
|
||||
time.sleep(wait)
|
||||
raise last_err
|
||||
|
||||
def send_message(self, msg):
|
||||
"""逐封发送(兼容旧调用),委托给 send_to。"""
|
||||
return self.send_to(msg, None)
|
||||
|
||||
|
||||
def _is_too_many_rcpts(err):
|
||||
"""判断拒收是否为「单封收件人数超限」类(452 / too many recipients)。
|
||||
|
||||
这类拒绝可以砍小批次重试解决,不能按限流中止、也不能按硬退信处理。
|
||||
"""
|
||||
low = str(err).strip().lower()
|
||||
if low.startswith("452"):
|
||||
return True
|
||||
if "too many recipients" in low:
|
||||
return True
|
||||
if "收件人" in low and ("上限" in low or "超" in low or "过多" in low):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _fmt_smtp_result(item):
|
||||
"""把 smtplib refused dict 的值 (code, msg_bytes) 规整成可读字符串。"""
|
||||
code, err = item
|
||||
if isinstance(err, bytes):
|
||||
err = err.decode("utf-8", "replace").strip()
|
||||
return f"{code} {err}".strip()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 断点续发状态(JSONL 追加写,崩溃安全)
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -1117,18 +1249,59 @@ def _parse_mail_date(value):
|
||||
return dt
|
||||
|
||||
|
||||
def _load_bounce_seen():
|
||||
"""读取已核查记录文件(DEFAULT_BOUNCE_SEEN)。
|
||||
|
||||
旧格式:Message-ID 列表;新格式:{"seen": [...], "cursor": {...}}。
|
||||
返回 (seen 集合, cursor dict 或 None)。
|
||||
cursor = {"uidvalidity": int, "last_uid": int},即上次扫描在 INBOX 里
|
||||
扫到的位置;UIDVALIDITY 对不上(邮箱重建/换号)时游标作废回退全扫。
|
||||
"""
|
||||
if not os.path.isfile(DEFAULT_BOUNCE_SEEN):
|
||||
return set(), None
|
||||
try:
|
||||
with open(DEFAULT_BOUNCE_SEEN, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
except Exception: # noqa: BLE001
|
||||
return set(), None
|
||||
if isinstance(data, dict):
|
||||
seen = set(data.get("seen") or [])
|
||||
cur = data.get("cursor")
|
||||
if (isinstance(cur, dict)
|
||||
and isinstance(cur.get("uidvalidity"), int)
|
||||
and isinstance(cur.get("last_uid"), int)):
|
||||
return seen, cur
|
||||
return seen, None
|
||||
return set(data or []), None
|
||||
|
||||
|
||||
def _save_bounce_seen(seen, cursor=None):
|
||||
try:
|
||||
with open(DEFAULT_BOUNCE_SEEN, "w", encoding="utf-8") as f:
|
||||
json.dump({"seen": sorted(seen), "cursor": cursor}, f, ensure_ascii=False)
|
||||
except Exception as e: # noqa: BLE001
|
||||
print(f"[警告] 记录已核查邮件/扫描位置失败(不影响本次结果):{e}")
|
||||
|
||||
|
||||
def _scan_imap_bounces(cfg, args, start_dt, skip_ids=None, not_before=None,
|
||||
start_desc="", verbose=True):
|
||||
start_desc="", verbose=True, resume=None):
|
||||
"""连 IMAP 扫描退信并逐收件人分类(check_bounces 与发送中巡检共用)。
|
||||
|
||||
skip_ids 已处理过的 Message-ID(seen 文件 / 本次运行内已见过),跳过不重复报
|
||||
not_before 只统计 Date 头晚于该时刻的退信(发送中巡检用:只看本次运行之后
|
||||
新到的退信,避免拿历史退信误触发中止);Date 解析不了则放行
|
||||
返回 dict:bounced / new_ids / scanned / touched_ids
|
||||
resume 上次扫描位置 {"uidvalidity": int, "last_uid": int};UIDVALIDITY
|
||||
一致时从 last_uid 之后续扫(UID 检索),否则回退按日期窗口全扫
|
||||
(全新 / 邮箱 UID 代际变更 / 显式 --since / --full-scan)。
|
||||
只由 check_bounces 传入推进——发送中巡检的 not_before 会过滤掉
|
||||
范围内的历史邮件,若推进游标会把没处理过的邮件标记成「已扫」。
|
||||
返回 dict:bounced / new_ids / scanned / touched_ids / last_uid / uidvalidity
|
||||
bounced {email: {"subject","date","category","reason","detail"}}
|
||||
new_ids 本次计入的退信 Message-ID(是否落盘由调用方决定)
|
||||
touched_ids 本次扫到的所有退信 Message-ID(含被 not_before 过滤掉的),
|
||||
供巡检做运行期去重,避免每轮重复拉取同一封全文
|
||||
last_uid 本次检查到的最大 UID(供调用方更新扫描位置)
|
||||
uidvalidity 当前邮箱的 UIDVALIDITY(读不到为 None,调用方据此不落游标)
|
||||
"""
|
||||
smtp_host = cfg["mail_smtp"] or ""
|
||||
imap_host = (args.imap_host or "").strip()
|
||||
@@ -1148,33 +1321,58 @@ def _scan_imap_bounces(cfg, args, start_dt, skip_ids=None, not_before=None,
|
||||
try:
|
||||
conn.login(account, password)
|
||||
conn.select("INBOX", readonly=True)
|
||||
typ, data = conn.search(None, f'(SINCE "{since}")')
|
||||
try:
|
||||
uv = int(conn.response("UIDVALIDITY")[1][0])
|
||||
except Exception: # noqa: BLE001
|
||||
uv = None
|
||||
resume_uid = None
|
||||
if resume:
|
||||
if uv is not None and uv == resume.get("uidvalidity"):
|
||||
resume_uid = int(resume["last_uid"])
|
||||
if verbose:
|
||||
print(f" [扫描位置] 续扫:从 UID {resume_uid} 之后开始"
|
||||
f"(uidvalidity {uv})")
|
||||
elif verbose:
|
||||
print(" [扫描位置] 邮箱 UIDVALIDITY 已变化(或无法读取),"
|
||||
"本次回退按日期窗口全量扫描")
|
||||
if resume_uid is not None:
|
||||
typ, data = conn.uid("SEARCH", None, f"UID {resume_uid + 1}:*")
|
||||
else:
|
||||
typ, data = conn.uid("SEARCH", None, f'(SINCE "{since}")')
|
||||
if typ != "OK":
|
||||
raise RuntimeError("IMAP search 失败")
|
||||
ids = data[0].split()
|
||||
if verbose:
|
||||
print(f" [IMAP] 扫描范围内共 {len(ids)} 封待扫描")
|
||||
print(f" [IMAP] 扫描范围内共 {len(ids)} 封"
|
||||
f"({'续扫' if resume_uid is not None else '日期窗口'})")
|
||||
|
||||
skip_ids = skip_ids or set()
|
||||
bounced, new_ids, touched, scanned = {}, [], [], 0
|
||||
last_uid = resume_uid or 0
|
||||
for i, mid in enumerate(ids, 1):
|
||||
uid = mid.decode() if isinstance(mid, bytes) else str(mid)
|
||||
uid = int(mid)
|
||||
if uid <= last_uid:
|
||||
# 防御:UID n:* 在 n 超过邮箱最大 UID 时会返回最后一封
|
||||
continue
|
||||
last_uid = uid
|
||||
ustr = str(uid)
|
||||
# 两段式:先取头部(省流量),命中退信特征再取全文
|
||||
typ, hdata = conn.fetch(
|
||||
mid, "(BODY.PEEK[HEADER.FIELDS (SUBJECT MESSAGE-ID FROM CONTENT-TYPE)])")
|
||||
typ, hdata = conn.uid(
|
||||
"fetch", ustr,
|
||||
"(BODY.PEEK[HEADER.FIELDS (SUBJECT MESSAGE-ID FROM CONTENT-TYPE)])")
|
||||
if typ != "OK" or not hdata or hdata[0] is None:
|
||||
continue
|
||||
try:
|
||||
head = email.message_from_bytes(hdata[0][1])
|
||||
except Exception: # noqa: BLE001
|
||||
continue
|
||||
msg_id = (head.get("Message-ID") or "").strip() or f"uid:{uid}"
|
||||
msg_id = (head.get("Message-ID") or "").strip() or f"uid:{ustr}"
|
||||
if msg_id in skip_ids:
|
||||
continue
|
||||
scanned += 1
|
||||
if not is_bounce_message(head):
|
||||
continue
|
||||
typ, fdata = conn.fetch(mid, "(RFC822)")
|
||||
typ, fdata = conn.uid("fetch", ustr, "(RFC822)")
|
||||
if typ != "OK" or not fdata or fdata[0] is None:
|
||||
continue
|
||||
try:
|
||||
@@ -1201,7 +1399,8 @@ def _scan_imap_bounces(cfg, args, start_dt, skip_ids=None, not_before=None,
|
||||
for r in rcpts) if rcpts else "(未解析出收件人)"
|
||||
print(f" [退信 {i}/{len(ids)}] {subject[:40]} → {desc}")
|
||||
return {"bounced": bounced, "new_ids": new_ids,
|
||||
"scanned": scanned, "touched_ids": touched}
|
||||
"scanned": scanned, "touched_ids": touched,
|
||||
"last_uid": last_uid, "uidvalidity": uv}
|
||||
finally:
|
||||
try:
|
||||
conn.logout()
|
||||
@@ -1210,29 +1409,43 @@ def _scan_imap_bounces(cfg, args, start_dt, skip_ids=None, not_before=None,
|
||||
|
||||
|
||||
def check_bounces(cfg, args):
|
||||
"""登录发件邮箱 IMAP,扫描近 N 天的退信并解析失败收件人。
|
||||
"""登录发件邮箱 IMAP,扫描退信并解析失败收件人。
|
||||
|
||||
返回 {email: {"subject","date","category","reason","detail"}};已处理过的
|
||||
邮件(Message-ID)记录在 broadcast_bounces_seen.json,重复核查不会重复报告。
|
||||
邮件(Message-ID)与上次扫描位置(UID 游标)都记录在
|
||||
broadcast_bounces_seen.json:默认从上次位置续扫,只查新到的邮件,
|
||||
游标不存在/作废、显式 --since 或 --full-scan 时才按日期窗口从头扫。
|
||||
category 见 CAT_RATE / CAT_HARD / CAT_UNKNOWN。"""
|
||||
start_dt, start_desc = resolve_scan_start(args)
|
||||
|
||||
seen = set()
|
||||
if os.path.isfile(DEFAULT_BOUNCE_SEEN):
|
||||
try:
|
||||
with open(DEFAULT_BOUNCE_SEEN, "r", encoding="utf-8") as f:
|
||||
seen = set(json.load(f))
|
||||
except Exception: # noqa: BLE001
|
||||
seen = set()
|
||||
seen, cursor = _load_bounce_seen()
|
||||
since_explicit = ((getattr(args, "since", "auto") or "auto").strip().lower()
|
||||
not in ("", "auto"))
|
||||
full_scan = bool(getattr(args, "full_scan", False))
|
||||
resume = None
|
||||
if full_scan:
|
||||
print("[扫描位置] --full-scan:忽略上次扫描位置,从头全量扫描")
|
||||
elif since_explicit:
|
||||
print("[扫描位置] 显式 --since 指定窗口,本次忽略上次扫描位置")
|
||||
elif cursor is None:
|
||||
print("[扫描位置] 全新扫描(尚无上次位置记录),按日期窗口全扫")
|
||||
else:
|
||||
resume = cursor
|
||||
print(f"[扫描位置] 从上次扫到的 UID {cursor['last_uid']} 之后续扫"
|
||||
f"(uidvalidity {cursor['uidvalidity']})")
|
||||
|
||||
try:
|
||||
res = _scan_imap_bounces(cfg, args, start_dt, skip_ids=seen, start_desc=start_desc)
|
||||
res = _scan_imap_bounces(cfg, args, start_dt, skip_ids=seen,
|
||||
start_desc=start_desc, resume=resume)
|
||||
except Exception as e: # noqa: BLE001
|
||||
sys.exit(f"[FATAL] IMAP 扫描失败(请确认邮箱已开启 IMAP,密码用邮箱登录密码): {e}")
|
||||
|
||||
bounced = res["bounced"]
|
||||
newly_seen, scanned = res["new_ids"], res["scanned"]
|
||||
bounce_cnt = len(newly_seen)
|
||||
scan_mode = "resume" if resume is not None else "full"
|
||||
scan_cursor = ({"uidvalidity": res["uidvalidity"], "last_uid": res["last_uid"]}
|
||||
if res.get("uidvalidity") is not None and res.get("last_uid") else None)
|
||||
|
||||
# ---- 按类别分组处理:只有「可重试」的才剔除补发 ----
|
||||
groups = {CAT_RATE: [], CAT_HARD: [], CAT_UNKNOWN: []}
|
||||
@@ -1296,6 +1509,8 @@ def check_bounces(cfg, args):
|
||||
"script_version": SCRIPT_VERSION,
|
||||
"scan_from": start_dt.strftime("%Y-%m-%d %H:%M:%S"),
|
||||
"scan_from_desc": start_desc,
|
||||
"scan_mode": scan_mode,
|
||||
"scan_cursor": scan_cursor,
|
||||
"scanned": scanned,
|
||||
"bounce_messages": bounce_cnt,
|
||||
"counts": {c: len(groups.get(c, [])) for c in (CAT_RATE, CAT_HARD, CAT_UNKNOWN)},
|
||||
@@ -1305,12 +1520,10 @@ def check_bounces(cfg, args):
|
||||
except Exception as e: # noqa: BLE001
|
||||
print(f"[警告] 写入退信报告失败(不影响本次结果):{e}")
|
||||
|
||||
if newly_seen:
|
||||
try:
|
||||
with open(DEFAULT_BOUNCE_SEEN, "w", encoding="utf-8") as f:
|
||||
json.dump(sorted(set(newly_seen) | seen), f, ensure_ascii=False)
|
||||
except Exception as e: # noqa: BLE001
|
||||
print(f"[警告] 记录已核查邮件失败(不影响本次结果):{e}")
|
||||
# 落盘:已核查 Message-ID + 新的扫描位置
|
||||
# (本次读不到 uidvalidity 时沿用旧游标:只可能往回多扫几封头部,不会漏)
|
||||
if newly_seen or scan_cursor or cursor:
|
||||
_save_bounce_seen(set(newly_seen) | seen, scan_cursor or cursor)
|
||||
return bounced
|
||||
|
||||
|
||||
@@ -1353,7 +1566,8 @@ def load_params(path):
|
||||
sys.exit(f"[FATAL] 解析参数文件失败: {e}")
|
||||
|
||||
data = {"config": "", "site_url": "", "box_prefix": "", "vars": {}, "to": "",
|
||||
"limit": None, "delay": None, "group_pause": None,
|
||||
"limit": None, "delay": None, "group_pause": None, "smtp_idle_reconnect": None,
|
||||
"batch_size": None, "mail": {},
|
||||
"watch_bounces": None, "watch_every": None, "prune_unknown": None,
|
||||
"no_invalid_list": None, "invalid_file": "", "bounce_report": "",
|
||||
"imap_host": "", "imap_port": None, "since": "", "since_days": None}
|
||||
@@ -1363,7 +1577,8 @@ def load_params(path):
|
||||
if cp.has_section("vars"):
|
||||
data["vars"] = {k: v.strip() for k, v in cp.items("vars")}
|
||||
data["to"] = cp.get("send", "to", fallback="").strip()
|
||||
for key, cast in (("limit", int), ("delay", float), ("group_pause", float)):
|
||||
for key, cast in (("limit", int), ("delay", float), ("group_pause", float),
|
||||
("smtp_idle_reconnect", float), ("batch_size", int)):
|
||||
raw = cp.get("send", key, fallback="").strip()
|
||||
if raw:
|
||||
try:
|
||||
@@ -1385,9 +1600,77 @@ def load_params(path):
|
||||
data[key] = cast(raw)
|
||||
except ValueError:
|
||||
print(f"[警告] params.ini [bounce] {key}={raw!r} 不是合法整数,已忽略")
|
||||
|
||||
# [mail] 程序自带 SMTP(source=own 时取代 conf/app.ini 的 [mail])
|
||||
if cp.has_section("mail"):
|
||||
m = {}
|
||||
m["source"] = cp.get("mail", "source", fallback="").strip().lower() or "app"
|
||||
for key in ("account", "password", "smtp"):
|
||||
m[key] = cp.get("mail", key, fallback="").strip()
|
||||
m["skip_tls_verify"] = bool(_parse_bool(
|
||||
cp.get("mail", "skip_tls_verify", fallback="").strip(), "skip_tls_verify"))
|
||||
raw = cp.get("mail", "port", fallback="").strip()
|
||||
try:
|
||||
m["port"] = int(raw) if raw else 465
|
||||
except ValueError:
|
||||
print(f"[警告] params.ini [mail] port={raw!r} 不是合法整数,已忽略")
|
||||
m["port"] = 465
|
||||
data["mail"] = m
|
||||
return data
|
||||
|
||||
|
||||
def resolve_mail_password(raw):
|
||||
"""SMTP 密码:支持 env:变量名 从环境变量取值,避免明文写进配置文件。"""
|
||||
raw = (raw or "").strip()
|
||||
if raw.lower().startswith("env:"):
|
||||
name = raw[4:].strip()
|
||||
if not name:
|
||||
return ""
|
||||
return (os.environ.get(name) or "").strip()
|
||||
return raw
|
||||
|
||||
|
||||
def apply_mail_source(cfg, args, params, verbose=True):
|
||||
"""发信账号来源切换:app(conf/app.ini [mail],默认)/ own(params.ini [mail])。
|
||||
|
||||
就地覆盖 cfg 的 mail_* 键,后续 SMTP 发信与 IMAP 退信核查都跟着走这套。
|
||||
优先级:命令行 --mail-source > params.ini [mail] source > app。
|
||||
返回实际生效的来源。
|
||||
"""
|
||||
m = (params or {}).get("mail") or {}
|
||||
src = (getattr(args, "mail_source", None) or "").strip().lower()
|
||||
if src not in ("app", "own"):
|
||||
src = (m.get("source") or "app").strip().lower()
|
||||
if src != "own":
|
||||
if verbose:
|
||||
print(f"[发信账号] 来源 = conf/app.ini [mail]"
|
||||
f"({cfg['mail_smtp']} / {cfg['mail_account']})")
|
||||
return "app"
|
||||
|
||||
smtp = (m.get("smtp") or "").strip()
|
||||
account = (m.get("account") or "").strip()
|
||||
raw_pw = (m.get("password") or "").strip()
|
||||
password = resolve_mail_password(raw_pw)
|
||||
missing = [k for k, v in (("smtp", smtp), ("account", account), ("password", password))
|
||||
if not v]
|
||||
if missing:
|
||||
sys.exit(f"[FATAL] params.ini [mail] 缺少或不完整:{', '.join(missing)}。"
|
||||
f"补全后重试,或改用 --mail-source app(用 conf/app.ini 的 SMTP)")
|
||||
if raw_pw and not raw_pw.lower().startswith("env:"):
|
||||
print("[警告] [mail] password 以明文写在 params.ini(该文件通常会被 git 跟踪),"
|
||||
"建议改成 env:变量名 从环境变量读取,或把 params.ini 加入 .gitignore")
|
||||
|
||||
cfg["mail_smtp"] = smtp
|
||||
cfg["mail_account"] = account
|
||||
cfg["mail_password"] = password
|
||||
cfg["mail_port"] = int(m.get("port") or 465)
|
||||
cfg["mail_skip_tls_verify"] = bool(m.get("skip_tls_verify"))
|
||||
if verbose:
|
||||
print(f"[发信账号] 来源 = 程序自带 params.ini [mail]"
|
||||
f"({smtp}:{cfg['mail_port']} / {account})")
|
||||
return "own"
|
||||
|
||||
|
||||
def _parse_bool(raw, key=""):
|
||||
"""解析 1/0、yes/no、true/false、on/off;空串返回 None(表示未配置)。"""
|
||||
low = (raw or "").strip().lower()
|
||||
@@ -1402,7 +1685,27 @@ def _parse_bool(raw, key=""):
|
||||
return None
|
||||
|
||||
|
||||
def _preserve_extra_sections(path, managed=("path", "site", "vars", "send", "bounce")):
|
||||
def _read_mail_section(path):
|
||||
"""读取已有 params.ini 的 [mail] 小节(保存时回写,避免被覆盖丢弃)。"""
|
||||
out = {}
|
||||
if not path or not os.path.isfile(path):
|
||||
return out
|
||||
cp = configparser.ConfigParser(comment_prefixes=(";", "#"),
|
||||
inline_comment_prefixes=(";", "#"),
|
||||
interpolation=None, strict=False)
|
||||
cp.optionxform = str
|
||||
try:
|
||||
cp.read(path, encoding="utf-8")
|
||||
except Exception: # noqa: BLE001
|
||||
return out
|
||||
if not cp.has_section("mail"):
|
||||
return out
|
||||
for k in ("source", "account", "password", "smtp", "port", "skip_tls_verify"):
|
||||
out[k] = cp.get("mail", k, fallback="").strip()
|
||||
return {k: v for k, v in out.items() if v}
|
||||
|
||||
|
||||
def _preserve_extra_sections(path, managed=("path", "site", "vars", "send", "bounce", "mail")):
|
||||
"""读取已有 params.ini 里非托管的小节,原样保留(避免保存时丢掉手写的配置)。"""
|
||||
if not path or not os.path.isfile(path):
|
||||
return []
|
||||
@@ -1426,9 +1729,11 @@ def _preserve_extra_sections(path, managed=("path", "site", "vars", "send", "bou
|
||||
|
||||
|
||||
def save_params(path, config, site_url, box_prefix, extra_vars, lang_labels=None,
|
||||
bounce=None):
|
||||
bounce=None, batch_size=0, smtp_idle_reconnect=30.0, mail=None):
|
||||
"""把参数写回 params.ini(覆盖写;vars 逐行 key = value)。
|
||||
bounce:当前生效的退信/巡检设置,回写进 [bounce] 小节以便下次直接沿用。"""
|
||||
bounce:当前生效的退信/巡检设置,回写进 [bounce] 小节以便下次直接沿用。
|
||||
batch_size / smtp_idle_reconnect / mail:同属 [send]/[mail] 小节,必须回写,
|
||||
否则覆盖写会把手工加的键抹掉(mail 的小节值从原文件读回,只覆盖传入项)。"""
|
||||
lines = ["; broadcast.py 参数文件:每次运行自动读取;命令行参数优先级更高",
|
||||
"; 注意:本文件不控制 --send/--yes,正式发送仍需命令行显式指定", ""]
|
||||
lines.append("[path]")
|
||||
@@ -1448,6 +1753,10 @@ def save_params(path, config, site_url, box_prefix, extra_vars, lang_labels=None
|
||||
lines.append("; to = 可选:默认测试收件邮箱(正式群发用命令行 --send,不加 --to)")
|
||||
lines.append("delay = 1.0")
|
||||
lines.append("group_pause = 3.0")
|
||||
lines.append("; SMTP 连接空闲超过该秒数就主动重连再发(delay 调大时必开,0 关闭)")
|
||||
lines.append(f"smtp_idle_reconnect = {float(smtp_idle_reconnect):g}")
|
||||
lines.append("; 合并信封批量发送:渲染内容完全相同的收件人每 N 人共用一个信封(0=逐封)")
|
||||
lines.append(f"batch_size = {int(batch_size)}")
|
||||
lines.append("")
|
||||
lines.append("; 退信核查 / 发送中限流巡检(均可用同名命令行参数临时覆盖)")
|
||||
lines.append("[bounce]")
|
||||
@@ -1470,6 +1779,24 @@ def save_params(path, config, site_url, box_prefix, extra_vars, lang_labels=None
|
||||
lines.append("; since = auto 表示从断点清单最早一条记录的时间开始扫描")
|
||||
lines.append(f"since = {b.get('since', 'auto')}")
|
||||
lines.append(f"since_days = {b.get('since_days', 3)}")
|
||||
lines.append("")
|
||||
# [mail]:值从原文件读回(含 env: 形式的密码),再用传入的覆盖项更新
|
||||
mv = {"source": "app", "account": "", "password": "", "smtp": "", "port": "465",
|
||||
"skip_tls_verify": "0"}
|
||||
mv.update(_read_mail_section(path))
|
||||
for k, v in (mail or {}).items():
|
||||
if v not in (None, ""):
|
||||
mv[k] = str(v)
|
||||
lines.append("; 发信账号来源:app = 用 conf/app.ini [mail] 的 SMTP(默认);")
|
||||
lines.append("; own = 用下面这套程序自带 SMTP(--mail-source 可临时覆盖)")
|
||||
lines.append("[mail]")
|
||||
lines.append(f"source = {mv['source'] or 'app'}")
|
||||
lines.append(f"account = {mv['account']}")
|
||||
lines.append("; password 支持 env:变量名(推荐),避免明文写进会被 git 跟踪的文件")
|
||||
lines.append(f"password = {mv['password']}")
|
||||
lines.append(f"smtp = {mv['smtp']}")
|
||||
lines.append(f"port = {mv['port'] or 465}")
|
||||
lines.append(f"skip_tls_verify = {mv['skip_tls_verify'] or 0}")
|
||||
lines.extend(_preserve_extra_sections(path))
|
||||
with open(path, "w", encoding="utf-8") as f:
|
||||
f.write("\n".join(lines) + "\n")
|
||||
@@ -1514,6 +1841,15 @@ def run_interactive(cfg, templates, extra_vars, args, config_path):
|
||||
f"(每 {args.watch_every} 封一次)"
|
||||
f" 来源:params.ini [bounce] / 命令行,改值请编辑 params.ini")
|
||||
|
||||
# 发信账号来源:只有 params.ini [mail] 配齐了才提供切换
|
||||
if getattr(args, "_own_mail_ready", False):
|
||||
cur = (getattr(args, "mail_source", None) or "").strip().lower()
|
||||
default_src = cur if cur in ("app", "own") else "app"
|
||||
src = ask("发信账号来源(app = conf/app.ini 的 SMTP;own = 程序自带 params.ini [mail])",
|
||||
default_src).strip().lower()
|
||||
args.mail_source = "own" if src == "own" else "app"
|
||||
print(f" 发信账号 = {'程序自带 params.ini [mail]' if args.mail_source == 'own' else 'conf/app.ini [mail]'}")
|
||||
|
||||
# 站点地址:只有完全没值时才问(值链已在 main 里兜底过 external_url)
|
||||
if not site_url:
|
||||
site_url = ask("站点地址 site_url(如 https://box.shiroko.one)", "")
|
||||
@@ -1605,6 +1941,9 @@ def run_interactive(cfg, templates, extra_vars, args, config_path):
|
||||
save_ans = ""
|
||||
if save_ans in ("y", "yes"):
|
||||
save_params(DEFAULT_PARAMS, config_path, site_url, box_prefix, extra_vars,
|
||||
batch_size=getattr(args, "batch_size", 0) or 0,
|
||||
smtp_idle_reconnect=getattr(args, "smtp_idle_reconnect", 30.0) or 30.0,
|
||||
mail={"source": getattr(args, "mail_source", None) or "app"},
|
||||
bounce={
|
||||
"watch_bounces": args.watch_bounces,
|
||||
"watch_every": args.watch_every,
|
||||
@@ -1662,6 +2001,16 @@ def build_arg_parser():
|
||||
help="--pause-every 触发时的长暂停秒数,默认 15.0")
|
||||
parser.add_argument("--group-pause", type=float, default=3.0,
|
||||
help="不同语言分组之间的额外暂停秒数,默认 3.0(0 关闭)")
|
||||
parser.add_argument("--smtp-idle-reconnect", type=float, default=None, metavar="SEC",
|
||||
help="SMTP 连接空闲超过该秒数就主动重连再发(默认 30)。"
|
||||
"--delay 调大时(如 60s/封)服务器会掐掉空闲连接,"
|
||||
"不重连的话每封都会先吃一发 Server not connected")
|
||||
parser.add_argument("--batch-size", type=int, default=None, metavar="N",
|
||||
help="合并信封批量发送(0=逐封,默认):渲染内容完全相同的收件人"
|
||||
"每 N 人共用一个 SMTP 信封,发送次数从「人数」降到「信封数」,"
|
||||
"可显著减少触发「外发频率超过限制」类限流(服务商按收件人计数"
|
||||
"则无效)。单封收件人有上限(常见 50~100),被 452 拒收时脚本"
|
||||
"自动砍半拆批重试,不会中止")
|
||||
parser.add_argument("--db-driver", default="auto",
|
||||
choices=["auto", "psql", "mysql", "psycopg2", "pymysql"],
|
||||
help="DB 驱动:auto(默认,优先系统 psql/mysql 客户端)/ psycopg2 / pymysql")
|
||||
@@ -1681,6 +2030,12 @@ def build_arg_parser():
|
||||
help=f"参数文件路径(默认自动读取脚本同目录 params.ini,不存在则跳过;CLI 参数优先级更高)")
|
||||
parser.add_argument("--no-params", action="store_true",
|
||||
help="不读取 params.ini 参数文件")
|
||||
parser.add_argument("--mail-source", default=None, choices=["app", "own"],
|
||||
help="发信账号来源:app = conf/app.ini [mail](默认);"
|
||||
"own = 程序自带 SMTP(读 params.ini [mail] 的"
|
||||
" account/password/smtp/port,password 支持 env:变量名)。"
|
||||
"命令行优先于 params.ini [mail] source。切换后发信与"
|
||||
"退信核查(IMAP)都走这套账号")
|
||||
parser.add_argument("--interactive", "-i", action="store_true", default=None,
|
||||
help="交互模式(默认开启:不带任何运行参数运行脚本时自动进入)。"
|
||||
"运行后逐项询问参数,并直接选择运行方式(演练/测试一封/群发)")
|
||||
@@ -1699,6 +2054,9 @@ def build_arg_parser():
|
||||
parser.add_argument("--prune-unknown", action="store_true", default=None,
|
||||
help="配合 --check-bounces:无法分类的退信也按「可重试」处理,一并剔除补发"
|
||||
"(默认不剔除,避免给死信地址反复重发;也可在 params.ini [bounce] 设置)")
|
||||
parser.add_argument("--full-scan", action="store_true",
|
||||
help="退信核查忽略上次扫描位置,按日期窗口从头全量扫描"
|
||||
"(默认记住上次扫到的位置只查新邮件;显式 --since 也会忽略位置)")
|
||||
parser.add_argument("--invalid-file", default=None, metavar="FILE",
|
||||
help=f"无效地址清单(硬退信地址)路径;默认脚本同目录 broadcast_invalid.json。"
|
||||
f"清单里的地址每次运行都会跳过,即使 --reset-state")
|
||||
@@ -1788,6 +2146,11 @@ def main():
|
||||
args.delay = params["delay"]
|
||||
if args.group_pause == 3.0 and params.get("group_pause") is not None:
|
||||
args.group_pause = params["group_pause"]
|
||||
if args.smtp_idle_reconnect is None:
|
||||
args.smtp_idle_reconnect = (30.0 if params.get("smtp_idle_reconnect") is None
|
||||
else params["smtp_idle_reconnect"])
|
||||
if args.batch_size is None:
|
||||
args.batch_size = params.get("batch_size") or 0
|
||||
|
||||
# 退信核查 / 发送中巡检:命令行没给(None)时才用 params.ini [bounce]
|
||||
if args.watch_bounces is None:
|
||||
@@ -1836,10 +2199,20 @@ def main():
|
||||
elif not args.interactive:
|
||||
print("[警告] site_url 为空:{{site}} 与无个性域名用户的 {{box_link}} 将为空串")
|
||||
|
||||
# 程序自带 SMTP 是否已配齐(交互模式据此提供来源切换)
|
||||
_m = params.get("mail") or {}
|
||||
args._own_mail_ready = bool((_m.get("smtp") or "").strip()
|
||||
and (_m.get("account") or "").strip()
|
||||
and (_m.get("password") or "").strip())
|
||||
|
||||
if args.interactive:
|
||||
site_url, args.box_prefix, extra_vars = run_interactive(
|
||||
cfg, templates, extra_vars, args, config_path)
|
||||
|
||||
# ---- 发信账号来源切换(app.ini / 程序自带 params.ini [mail])----
|
||||
# 必须在交互模式之后(交互里可能改选)、退信核查与发信之前(两者都用 cfg)
|
||||
mail_source = apply_mail_source(cfg, args, params)
|
||||
|
||||
# ---- 退信核查模式:不查数据库、不发信;扫描(含可选剔除)后结束,
|
||||
# 除非同时指定 --send(剔除并补发),此时继续走正常发送流程 ----
|
||||
if args.check_bounces:
|
||||
@@ -1870,6 +2243,8 @@ def main():
|
||||
print(f" [db] host:port = {cfg['db_host']}:{cfg['db_port']} db={cfg['db_name'] or '(空)'}")
|
||||
print(f" [mail] smtp:port = {cfg['mail_smtp']}:{cfg['mail_port']}")
|
||||
print(f" [mail] account = {cfg['mail_account'] or '(空)'}")
|
||||
print(f" [mail] 来源 = "
|
||||
f"{'程序自带 params.ini [mail]' if mail_source == 'own' else 'conf/app.ini [mail]'}")
|
||||
print(f" [断点续发] state_file = {args.state}")
|
||||
print("=" * 56)
|
||||
|
||||
@@ -2081,6 +2456,9 @@ def main():
|
||||
attempted = 0
|
||||
total = len(recipients)
|
||||
all_missing = set()
|
||||
batch_size = max(0, int(getattr(args, "batch_size", 0) or 0))
|
||||
envelopes = 0 # SMTP 信封数(批量模式下 < 发送人数)
|
||||
watch_mark = 0
|
||||
|
||||
# 发送中巡检:限流退信是异步投到发件箱的,边发边看才能及时止损
|
||||
watch_active = bool(getattr(args, "watch_bounces", True)) and not args.to
|
||||
@@ -2089,9 +2467,48 @@ def main():
|
||||
known_ids, watch_fails = set(), 0
|
||||
watch_rate, watch_hard, abort_reason = {}, {}, ""
|
||||
|
||||
def note_smtp_err(email, err_str, subject_label):
|
||||
"""SMTP 拒收按退信分类处理:硬退信记无效清单;返回限流中止理由(否则空串)。"""
|
||||
cat, why = classify_bounce("", err_str, "")
|
||||
if cat == CAT_HARD and not args.no_invalid_list:
|
||||
record_invalid(args.invalid_file, {email: {
|
||||
"reason": why, "detail": err_str[:160], "subject": subject_label,
|
||||
"date": datetime.now().strftime("%Y-%m-%d %H:%M:%S")}})
|
||||
if cat == CAT_RATE:
|
||||
return f"SMTP 返回疑似限流({why}):{err_str[:100]}"
|
||||
return ""
|
||||
|
||||
def run_patrol():
|
||||
"""周期巡检收件箱:命中限流退信则给出中止理由,连续两轮失败则关巡检。"""
|
||||
nonlocal watch_fails, watch_active, watch_hard, abort_reason
|
||||
nb, ok = watch_bounces(cfg, args, watch_start, known_ids)
|
||||
if not ok:
|
||||
watch_fails += 1
|
||||
if watch_fails >= 2:
|
||||
print(" [退信巡检] IMAP 连续不可用,本次已关闭巡检"
|
||||
"(不影响发送;发完请手动跑一次 --check-bounces)")
|
||||
watch_active = False
|
||||
return
|
||||
watch_fails = 0
|
||||
for em, info in nb.items():
|
||||
if info["category"] == CAT_RATE:
|
||||
watch_rate[em] = info
|
||||
elif info["category"] == CAT_HARD:
|
||||
watch_hard[em] = info
|
||||
if watch_hard:
|
||||
if not args.no_invalid_list:
|
||||
record_invalid(args.invalid_file, watch_hard)
|
||||
watch_hard = {}
|
||||
if watch_rate and not abort_reason:
|
||||
abort_reason = (
|
||||
f"收件箱出现 {len(watch_rate)} 条限流退信"
|
||||
f"(如 {sorted(watch_rate)[0]}:"
|
||||
f"{watch_rate[sorted(watch_rate)[0]]['reason']})")
|
||||
|
||||
print(f"\n[发送中] 目标 {total} 封,每封间隔 {args.delay}s"
|
||||
+ (f",每组间隔 {args.group_pause}s" if args.group_pause > 0 else "")
|
||||
+ (f",每 {args.pause_every} 封暂停 {args.pause_for}s" if args.pause_every > 0 else "")
|
||||
+ (f",合并信封每 {batch_size} 人/封" if batch_size > 0 else "")
|
||||
+ (f",每 {watch_every} 封巡检一次退信" if watch_active else "") + " ...")
|
||||
|
||||
if args.single:
|
||||
@@ -2106,7 +2523,7 @@ def main():
|
||||
group_order = [lg for lg in lang_list if lg in groups] + [lg for lg in groups if lg not in lang_list]
|
||||
|
||||
try:
|
||||
server = smtp_login(cfg)
|
||||
session = SmtpSession(cfg, idle_reconnect=getattr(args, "smtp_idle_reconnect", 30))
|
||||
except Exception as e: # noqa: BLE001
|
||||
sys.exit(f"[FATAL] SMTP 登录失败: {e}")
|
||||
|
||||
@@ -2120,6 +2537,15 @@ def main():
|
||||
label = LANG_LABEL.get(lg, lg)
|
||||
tpl = templates[lg]
|
||||
print(f"\n[语言分组 {gi}/{len(group_order)}] {lg} ({label}) : 本组 {len(grp)} 封")
|
||||
|
||||
subject_raw = args.subject if args.subject else tpl["subject"]
|
||||
html_raw = override_html if override_html is not None else tpl["html"]
|
||||
plain_raw = override_plain if override_plain is not None else tpl["plain"]
|
||||
|
||||
# 渲染并按内容指纹分桶:只有渲染结果完全相同的收件人才共用信封。
|
||||
# 模板含 {{name}}/{{box_link}} 等个人化占位符时结果逐人不同,
|
||||
# 自然落回逐人一封,不会错合。
|
||||
buckets, bucket_map = [], {}
|
||||
for r in grp:
|
||||
box_link = f"{site_url}{args.box_prefix}{r['domain']}" if r["domain"] else site_url
|
||||
ctx = {
|
||||
@@ -2132,68 +2558,103 @@ def main():
|
||||
"year": datetime.now().strftime("%Y"),
|
||||
**extra_vars,
|
||||
}
|
||||
subject = args.subject if args.subject else tpl["subject"]
|
||||
html = override_html if override_html is not None else tpl["html"]
|
||||
plain = override_plain if override_plain is not None else tpl["plain"]
|
||||
msg, missing = build_message(cfg, r["email"], ctx, subject, html, plain)
|
||||
s, h, p, missing = render_content(subject_raw, html_raw, plain_raw, ctx)
|
||||
if missing:
|
||||
all_missing.update(missing)
|
||||
smtp_err = ""
|
||||
try:
|
||||
refused = server.send_message(msg)
|
||||
if refused:
|
||||
refused_desc = "; ".join(f"{a} {c}:{err}" for a, (c, err) in refused.items())
|
||||
smtp_err = refused_desc
|
||||
failed.append((r["email"], f"SMTP 拒收 {refused_desc}"))
|
||||
smtp_rejected += 1
|
||||
print(f" [SMTP 拒收] {r['email']}: {refused_desc}")
|
||||
digest = hashlib.sha256(
|
||||
"\x00".join((s, h, p)).encode("utf-8", "replace")).hexdigest()
|
||||
bkt = bucket_map.get(digest)
|
||||
if bkt is None:
|
||||
bkt = {"content": (s, h, p), "queue": []}
|
||||
bucket_map[digest] = bkt
|
||||
buckets.append(bkt)
|
||||
bkt["queue"].append(r)
|
||||
del bucket_map
|
||||
|
||||
for bkt in buckets:
|
||||
subj_r, html_r, plain_r = bkt["content"]
|
||||
queue = bkt["queue"]
|
||||
while queue and not abort_reason:
|
||||
take = batch_size if batch_size > 0 else 1
|
||||
batch, queue = queue[:take], queue[take:]
|
||||
rcpts = [r["email"] for r in batch]
|
||||
|
||||
if len(batch) == 1:
|
||||
to_header = batch[0]["email"]
|
||||
else:
|
||||
# 批量信封:To: 头只作显示(站点名+发件邮箱),真实收件人
|
||||
# 走 RCPT TO 信封,互相不可见
|
||||
to_header = formataddr((str(Header(cfg.get("app_title") or "", "utf-8")),
|
||||
cfg["mail_account"]))
|
||||
msg = build_message_from(cfg, to_header, subj_r, html_r, plain_r)
|
||||
|
||||
envelopes += 1
|
||||
try:
|
||||
refused = session.send_to(msg, rcpts if len(batch) > 1 else None)
|
||||
except Exception as e: # noqa: BLE001
|
||||
# 整信封异常(重连耗尽 / DATA 被拒等):多收件人时无法
|
||||
# 区分到人,只记失败;若像限流(DATA 4xx/552)则立即中止。
|
||||
for r in batch:
|
||||
failed.append((r["email"], str(e)))
|
||||
attempted += len(batch)
|
||||
print(f" [失败] 本信封 {len(batch)} 人: {e}")
|
||||
if len(batch) == 1:
|
||||
ab = note_smtp_err(batch[0]["email"], str(e), subj_r)
|
||||
else:
|
||||
cat, why = classify_bounce("", str(e), "")
|
||||
ab = f"SMTP 返回疑似限流({why}):{str(e)[:100]}" if cat == CAT_RATE else ""
|
||||
if ab and not abort_reason:
|
||||
abort_reason = ab
|
||||
continue
|
||||
|
||||
err_map = {a.lower(): _fmt_smtp_result(v)
|
||||
for a, v in (refused or {}).items()}
|
||||
ok_n = 0
|
||||
for r in batch:
|
||||
if r["email"].lower() in err_map:
|
||||
continue
|
||||
ok_n += 1
|
||||
sent += 1
|
||||
if not args.to:
|
||||
record_sent(args.state, {"email": r["email"], "lang": lg, "ts": time.time()})
|
||||
record_sent(args.state, {"email": r["email"], "lang": lg,
|
||||
"ts": time.time()})
|
||||
attempted += len(batch)
|
||||
|
||||
# 「单封收件人数超限」的拒绝:砍半批次重试,被拒的人排回队首;
|
||||
# 未被拒的收件人已随本次 DATA 投出,照常入账
|
||||
oversized = [r for r in batch
|
||||
if _is_too_many_rcpts(err_map.get(r["email"].lower(), ""))]
|
||||
if oversized:
|
||||
batch_size = max(1, batch_size // 2)
|
||||
queue[:0] = oversized
|
||||
over_set = {r["email"].lower() for r in oversized}
|
||||
print(f" [拆批] {len(oversized)} 人被拒(单封收件人数超限),"
|
||||
f"batch_size 降为 {batch_size} 后重试")
|
||||
else:
|
||||
over_set = set()
|
||||
|
||||
for r in batch:
|
||||
em_low = r["email"].lower()
|
||||
e = err_map.get(em_low)
|
||||
if e is None or em_low in over_set:
|
||||
continue
|
||||
failed.append((r["email"], f"SMTP 拒收 {e}"))
|
||||
smtp_rejected += 1
|
||||
print(f" [SMTP 拒收] {r['email']}: {e}")
|
||||
ab = note_smtp_err(r["email"], e, subj_r)
|
||||
if ab and not abort_reason:
|
||||
abort_reason = ab
|
||||
|
||||
if len(batch) > 1:
|
||||
print(f" [信封] 一封投递 {len(batch)} 人:"
|
||||
f"接收 {ok_n},拒收 {len(err_map) - len(over_set)}")
|
||||
if sent % 25 == 0 or sent == total:
|
||||
print(f" 进度 {sent}/{total} 已成功 {sent}")
|
||||
except Exception as e: # noqa: BLE001
|
||||
smtp_err = str(e)
|
||||
failed.append((r["email"], smtp_err))
|
||||
print(f" [失败] {r['email']}: {e}")
|
||||
|
||||
attempted += 1
|
||||
# SMTP 当场就返回限流信号 → 继续发只会更糟,立即中止
|
||||
if smtp_err:
|
||||
cat, why = classify_bounce("", smtp_err, "")
|
||||
if cat == CAT_HARD and not args.no_invalid_list:
|
||||
record_invalid(args.invalid_file, {r["email"]: {
|
||||
"reason": why, "detail": smtp_err[:160], "subject": subject,
|
||||
"date": datetime.now().strftime("%Y-%m-%d %H:%M:%S")}})
|
||||
elif cat == CAT_RATE and not abort_reason:
|
||||
abort_reason = f"SMTP 返回疑似限流({why}):{smtp_err[:100]}"
|
||||
|
||||
# 周期巡检收件箱:异步退信才是限流最常见的表现
|
||||
if watch_active and not abort_reason and attempted % watch_every == 0:
|
||||
nb, ok = watch_bounces(cfg, args, watch_start, known_ids)
|
||||
if not ok:
|
||||
watch_fails += 1
|
||||
if watch_fails >= 2:
|
||||
print(" [退信巡检] IMAP 连续不可用,本次已关闭巡检"
|
||||
"(不影响发送;发完请手动跑一次 --check-bounces)")
|
||||
watch_active = False
|
||||
else:
|
||||
watch_fails = 0
|
||||
for em, info in nb.items():
|
||||
if info["category"] == CAT_RATE:
|
||||
watch_rate[em] = info
|
||||
elif info["category"] == CAT_HARD:
|
||||
watch_hard[em] = info
|
||||
if watch_hard:
|
||||
if not args.no_invalid_list:
|
||||
record_invalid(args.invalid_file, watch_hard)
|
||||
watch_hard = {}
|
||||
if watch_rate:
|
||||
abort_reason = (
|
||||
f"收件箱出现 {len(watch_rate)} 条限流退信"
|
||||
f"(如 {sorted(watch_rate)[0]}:"
|
||||
f"{watch_rate[sorted(watch_rate)[0]]['reason']})")
|
||||
# 周期巡检收件箱:按收件人计数,异步退信才是限流最常见表现
|
||||
if watch_active and not abort_reason and attempted >= watch_mark + watch_every:
|
||||
watch_mark = attempted
|
||||
run_patrol()
|
||||
|
||||
if abort_reason:
|
||||
break
|
||||
@@ -2208,14 +2669,13 @@ def main():
|
||||
if abort_reason:
|
||||
break
|
||||
finally:
|
||||
try:
|
||||
server.quit()
|
||||
except Exception: # noqa: BLE001
|
||||
pass
|
||||
session.close()
|
||||
|
||||
report["sent"] = sent
|
||||
report["failed"] = len(failed)
|
||||
report["smtp_rejected"] = smtp_rejected
|
||||
report["batch_size"] = batch_size
|
||||
report["envelopes"] = envelopes
|
||||
report["aborted"] = abort_reason or None
|
||||
report["abort_rate_bounces"] = sorted(watch_rate)
|
||||
report["watch_bounces"] = watch_active
|
||||
|
||||
+25
@@ -18,6 +18,31 @@ old_domain = box.tama.guru
|
||||
; to = 可选:默认测试收件邮箱(正式群发用命令行 --send,不加 --to)
|
||||
delay = 1.0
|
||||
group_pause = 3.0
|
||||
; SMTP 连接空闲超过该秒数就主动重连再发。
|
||||
; delay 调大时(比如 60s/封)服务器会掐掉空闲连接,出现整批
|
||||
; 「please run connect() first」;保持默认 30 即可自动重连,设 0 关闭
|
||||
smtp_idle_reconnect = 30
|
||||
|
||||
; 合并信封批量发送(0=逐封)。渲染内容完全相同的收件人每 N 人共用一个
|
||||
; SMTP 信封:发送次数从「人数」降到「信封数」(如 305 人、每 50 人一封
|
||||
; → 约 7 次发信),可显著降低触发「外发频率超过邮件系统限制」类限流的
|
||||
; 概率;若服务商按收件人计数则无缓解。
|
||||
; 注意:单封收件人有服务商上限(常见 50~100),超限被 452 拒收时脚本会
|
||||
; 自动砍半拆批重试,不会中止;delay 在批量模式下的语义是「每批之间」间隔。
|
||||
; 模板含 {{name}} 等个人化占位符时内容逐人不同,自动回退逐封,不会错合。
|
||||
batch_size = 0
|
||||
|
||||
; 发信账号来源:app = 用 conf/app.ini [mail] 的 SMTP(默认,站内信跟随站点邮箱)
|
||||
; own = 用下面这套程序自带 SMTP(命令行 --mail-source own 可临时覆盖)
|
||||
; 切到 own 后,发信与退信核查(IMAP)都走这套账号
|
||||
[mail]
|
||||
source = app
|
||||
account =
|
||||
; password 支持 env:变量名(推荐),避免明文写进会被 git 跟踪的文件
|
||||
password =
|
||||
smtp =
|
||||
port = 465
|
||||
skip_tls_verify = 0
|
||||
|
||||
; 退信核查 / 发送中限流巡检开关
|
||||
; 这些都能在 params.ini 里长期配置,命令行同名参数可临时覆盖
|
||||
|
||||
Reference in New Issue
Block a user