chinese-scraper-utils 0.1.0__tar.gz

chinese_scraper_utils-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 sixtdreanight
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

chinese_scraper_utils-0.1.0/PKG-INFO

@@ -0,0 +1,141 @@
+Metadata-Version: 2.4
+Name: chinese-scraper-utils
+Version: 0.1.0
+Summary: Chinese scraping utilities — date parsing, city extraction, SHA256 ID, UA pool, rate limiter, DeepSeek client
+License-Expression: MIT
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: httpx>=0.24
+Requires-Dist: openai>=1.0
+Dynamic: license-file
+
+# chinese-scraper-utils
+
+<p align="center">
+  <img src="https://img.shields.io/pypi/v/chinese-scraper-utils" alt="PyPI version">
+  <img src="https://img.shields.io/badge/python-3.11%2B-blue" alt="Python 3.11+">
+  <img src="https://img.shields.io/badge/license-MIT-green" alt="MIT License">
+</p>
+
+Shared Python utilities for Chinese-language web scraping — date parsing, city extraction, stable ID generation, UA rotation, rate limiting, and a DeepSeek API client. Extracted from [ComiRadar](https://github.com/sixtdreanight/ComiRadar) and `weekly-cli`, where these functions had diverged across two codebases.
+
+从 [ComiRadar](https://github.com/sixtdreanight/ComiRadar) 与 `weekly-cli` 中提取的共享 Python 工具集：中文日期解析、城市提取、稳定 ID 生成、UA 池、速率限制、DeepSeek 客户端。
+
+---
+
+## Installation / 安装
+
+```bash
+pip install chinese-scraper-utils
+```
+
+---
+
+## Usage / 使用示例
+
+### Stable ID / 稳定 ID
+
+```python
+from chinese_scraper_utils import stable_id
+
+uid = stable_id("北京国际动漫展", "北京", "2026-05-04")
+# => "3a8f1c9e2d4b6a05"  (SHA256 hex prefix, deterministic across restarts)
+```
+
+### Date Parsing / 日期解析
+
+```python
+from chinese_scraper_utils import parse_date, extract_date
+
+# Structured date parsing / 结构化日期解析
+parse_date("2026-05-04")           # => "2026-05-04"
+parse_date("2026/05/04 14:30:00")  # => "2026-05-04"
+
+# Chinese text date extraction / 中文文本日期提取
+extract_date("5月4日上海有漫展")       # => "2026-05-04"
+extract_date("2026年5月4日-6日")      # => "2026-05-04"
+```
+
+### City Extraction & Normalization / 城市提取与规范化
+
+```python
+from chinese_scraper_utils import extract_city, normalize_city, CITIES
+
+extract_city("活动在上海举办")      # => "上海"
+extract_city("广州天河区")         # => "广州"
+
+normalize_city("上海市")           # => "上海"
+normalize_city("  深圳市  ")       # => "深圳"
+```
+
+### Category Guessing / 类别猜测
+
+```python
+from chinese_scraper_utils import guess_category
+
+guess_category("五一漫展嘉年华")   # => "漫展"
+guess_category("初音未来演唱会")   # => "演唱会"
+guess_category("清明上河图展览")   # => "展览"
+```
+
+### Random User-Agent / 随机 UA
+
+```python
+from chinese_scraper_utils import random_ua, UA_POOL
+
+random_ua()  # => "Mozilla/5.0 (Windows NT 10.0; ..."
+```
+
+### Async Rate Limiter / 异步速率限制
+
+```python
+import asyncio
+from chinese_scraper_utils import RateLimiter
+
+limiter = RateLimiter(min_interval=1.0)
+
+async def fetch():
+    async with httpx.AsyncClient() as client:
+        resp = await limiter.fetch_with_retry(
+            lambda: client.get("https://example.com")
+        )
+        return resp.text
+```
+
+### DeepSeek AI Client / DeepSeek AI 客户端
+
+```python
+from chinese_scraper_utils import DeepSeekClient
+
+client = DeepSeekClient(api_key="sk-xxx")
+result = client.chat_json([
+    {"role": "user", "content": "提取活动信息：北京五一漫展"}
+])
+# => {"name": "...", "date": "...", "city": "..."}
+```
+
+---
+
+## API Reference / API 参考
+
+| Export / 导出项          | Type / 类型         | Description / 描述                                           |
+|--------------------------|---------------------|---------------------------------------------------------------|
+| `stable_id(*parts)`      | `str` → `str`       | Deterministic SHA256 short ID / 确定性 SHA256 短 ID           |
+| `parse_date(s)`          | `str` → `str`       | Structured date parsing / 结构化日期解析                      |
+| `extract_date(text)`     | `str` → `str`       | Chinese text date extraction / 中文文本日期提取                |
+| `CITIES`                 | `list[str]`         | 52 major Chinese cities / 52 个主要中国城市                    |
+| `extract_city(text)`     | `str` → `str`       | Chinese city name extraction / 城市名提取                      |
+| `normalize_city(city)`   | `str` → `str`       | City name normalization (strip suffix) / 城市名规范化          |
+| `CATEGORY_ALIASES`       | `dict[str, str]`    | Category alias mapping / 类别别名映射                          |
+| `guess_category(title)`  | `str` → `str`       | Category guessing from title / 根据标题猜测类别                |
+| `UA_POOL`                | `list[str]`         | User-Agent pool / User-Agent 池                                |
+| `random_ua()`            | ` → `str`           | Random UA selection / 随机返回 UA                              |
+| `RateLimiter`            | class               | Async rate limiter with retry / 异步速率限制器                  |
+| `DeepSeekClient`         | class               | DeepSeek API wrapper / DeepSeek API 封装客户端                  |
+
+---
+
+## License / 许可证
+
+[MIT](LICENSE)

chinese_scraper_utils-0.1.0/README.md

@@ -0,0 +1,129 @@
+# chinese-scraper-utils
+
+<p align="center">
+  <img src="https://img.shields.io/pypi/v/chinese-scraper-utils" alt="PyPI version">
+  <img src="https://img.shields.io/badge/python-3.11%2B-blue" alt="Python 3.11+">
+  <img src="https://img.shields.io/badge/license-MIT-green" alt="MIT License">
+</p>
+
+Shared Python utilities for Chinese-language web scraping — date parsing, city extraction, stable ID generation, UA rotation, rate limiting, and a DeepSeek API client. Extracted from [ComiRadar](https://github.com/sixtdreanight/ComiRadar) and `weekly-cli`, where these functions had diverged across two codebases.
+
+从 [ComiRadar](https://github.com/sixtdreanight/ComiRadar) 与 `weekly-cli` 中提取的共享 Python 工具集：中文日期解析、城市提取、稳定 ID 生成、UA 池、速率限制、DeepSeek 客户端。
+
+---
+
+## Installation / 安装
+
+```bash
+pip install chinese-scraper-utils
+```
+
+---
+
+## Usage / 使用示例
+
+### Stable ID / 稳定 ID
+
+```python
+from chinese_scraper_utils import stable_id
+
+uid = stable_id("北京国际动漫展", "北京", "2026-05-04")
+# => "3a8f1c9e2d4b6a05"  (SHA256 hex prefix, deterministic across restarts)
+```
+
+### Date Parsing / 日期解析
+
+```python
+from chinese_scraper_utils import parse_date, extract_date
+
+# Structured date parsing / 结构化日期解析
+parse_date("2026-05-04")           # => "2026-05-04"
+parse_date("2026/05/04 14:30:00")  # => "2026-05-04"
+
+# Chinese text date extraction / 中文文本日期提取
+extract_date("5月4日上海有漫展")       # => "2026-05-04"
+extract_date("2026年5月4日-6日")      # => "2026-05-04"
+```
+
+### City Extraction & Normalization / 城市提取与规范化
+
+```python
+from chinese_scraper_utils import extract_city, normalize_city, CITIES
+
+extract_city("活动在上海举办")      # => "上海"
+extract_city("广州天河区")         # => "广州"
+
+normalize_city("上海市")           # => "上海"
+normalize_city("  深圳市  ")       # => "深圳"
+```
+
+### Category Guessing / 类别猜测
+
+```python
+from chinese_scraper_utils import guess_category
+
+guess_category("五一漫展嘉年华")   # => "漫展"
+guess_category("初音未来演唱会")   # => "演唱会"
+guess_category("清明上河图展览")   # => "展览"
+```
+
+### Random User-Agent / 随机 UA
+
+```python
+from chinese_scraper_utils import random_ua, UA_POOL
+
+random_ua()  # => "Mozilla/5.0 (Windows NT 10.0; ..."
+```
+
+### Async Rate Limiter / 异步速率限制
+
+```python
+import asyncio
+from chinese_scraper_utils import RateLimiter
+
+limiter = RateLimiter(min_interval=1.0)
+
+async def fetch():
+    async with httpx.AsyncClient() as client:
+        resp = await limiter.fetch_with_retry(
+            lambda: client.get("https://example.com")
+        )
+        return resp.text
+```
+
+### DeepSeek AI Client / DeepSeek AI 客户端
+
+```python
+from chinese_scraper_utils import DeepSeekClient
+
+client = DeepSeekClient(api_key="sk-xxx")
+result = client.chat_json([
+    {"role": "user", "content": "提取活动信息：北京五一漫展"}
+])
+# => {"name": "...", "date": "...", "city": "..."}
+```
+
+---
+
+## API Reference / API 参考
+
+| Export / 导出项          | Type / 类型         | Description / 描述                                           |
+|--------------------------|---------------------|---------------------------------------------------------------|
+| `stable_id(*parts)`      | `str` → `str`       | Deterministic SHA256 short ID / 确定性 SHA256 短 ID           |
+| `parse_date(s)`          | `str` → `str`       | Structured date parsing / 结构化日期解析                      |
+| `extract_date(text)`     | `str` → `str`       | Chinese text date extraction / 中文文本日期提取                |
+| `CITIES`                 | `list[str]`         | 52 major Chinese cities / 52 个主要中国城市                    |
+| `extract_city(text)`     | `str` → `str`       | Chinese city name extraction / 城市名提取                      |
+| `normalize_city(city)`   | `str` → `str`       | City name normalization (strip suffix) / 城市名规范化          |
+| `CATEGORY_ALIASES`       | `dict[str, str]`    | Category alias mapping / 类别别名映射                          |
+| `guess_category(title)`  | `str` → `str`       | Category guessing from title / 根据标题猜测类别                |
+| `UA_POOL`                | `list[str]`         | User-Agent pool / User-Agent 池                                |
+| `random_ua()`            | ` → `str`           | Random UA selection / 随机返回 UA                              |
+| `RateLimiter`            | class               | Async rate limiter with retry / 异步速率限制器                  |
+| `DeepSeekClient`         | class               | DeepSeek API wrapper / DeepSeek API 封装客户端                  |
+
+---
+
+## License / 许可证
+
+[MIT](LICENSE)

chinese_scraper_utils-0.1.0/pyproject.toml

@@ -0,0 +1,19 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "chinese-scraper-utils"
+version = "0.1.0"
+description = "Chinese scraping utilities — date parsing, city extraction, SHA256 ID, UA pool, rate limiter, DeepSeek client"
+readme = "README.md"
+license = "MIT"
+license-files = ["LICENSE"]
+requires-python = ">=3.11"
+dependencies = [
+    "httpx>=0.24",
+    "openai>=1.0",
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]

chinese_scraper_utils-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils/__init__.py

@@ -0,0 +1,28 @@
+"""chinese-scraper-utils — 中文信息抓取共享工具集。
+
+提供中文日期解析、城市提取、SHA256 稳定 ID、UA 池、
+速率限制、DeepSeek API 客户端等。
+"""
+
+from chinese_scraper_utils._hash import stable_id
+from chinese_scraper_utils._date import parse_date, extract_date
+from chinese_scraper_utils._city import CITIES, extract_city, normalize_city
+from chinese_scraper_utils._category import CATEGORY_ALIASES, guess_category
+from chinese_scraper_utils._ua import UA_POOL, random_ua
+from chinese_scraper_utils._rate_limit import RateLimiter
+from chinese_scraper_utils._ai import DeepSeekClient
+
+__all__ = [
+    "stable_id",
+    "parse_date",
+    "extract_date",
+    "CITIES",
+    "extract_city",
+    "normalize_city",
+    "CATEGORY_ALIASES",
+    "guess_category",
+    "UA_POOL",
+    "random_ua",
+    "RateLimiter",
+    "DeepSeekClient",
+]

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils/_ai.py

@@ -0,0 +1,80 @@
+"""DeepSeek API 客户端 — 基于 OpenAI SDK，带 JSON mode + 回退。"""
+
+import json
+import re
+from openai import OpenAI
+
+
+class DeepSeekClient:
+    """DeepSeek API 的轻量封装，自动处理 JSON 输出和回退。"""
+
+    def __init__(
+        self,
+        api_key: str,
+        base_url: str = "https://api.deepseek.com",
+        model: str = "deepseek-chat",
+    ):
+        self.base_url = base_url
+        self.model = model
+        self.client = OpenAI(api_key=api_key, base_url=base_url)
+
+    def chat(
+        self,
+        messages: list[dict],
+        temperature: float = 0.3,
+        max_tokens: int = 8192,
+    ) -> str:
+        """发送聊天请求，返回纯文本回复。"""
+        response = self.client.chat.completions.create(
+            model=self.model,
+            messages=messages,
+            temperature=temperature,
+            max_tokens=max_tokens,
+        )
+        return response.choices[0].message.content.strip()
+
+    def chat_json(
+        self,
+        messages: list[dict],
+        temperature: float = 0.3,
+        max_tokens: int = 8192,
+    ) -> dict:
+        """发送聊天请求，要求 JSON 输出。解析失败时自动回退重试。"""
+        msgs = [dict(m) for m in messages]
+        json_hint = "\n请以JSON格式输出。"
+        if msgs and msgs[0]["role"] == "system":
+            msgs[0] = {**msgs[0], "content": msgs[0]["content"] + json_hint}
+        else:
+            msgs.insert(0, {"role": "system", "content": json_hint.strip()})
+
+        response = self.client.chat.completions.create(
+            model=self.model,
+            messages=msgs,
+            temperature=temperature,
+            max_tokens=max_tokens,
+            response_format={"type": "json_object"},
+        )
+        raw = response.choices[0].message.content.strip()
+        if raw.startswith("```"):
+            raw = re.sub(r"^```(?:json)?\s*\n", "", raw)
+            raw = re.sub(r"\n```\s*$", "", raw)
+
+        try:
+            return json.loads(raw)
+        except json.JSONDecodeError:
+            fallback = self.client.chat.completions.create(
+                model=self.model,
+                messages=msgs,
+                temperature=temperature,
+                max_tokens=max_tokens,
+            )
+            raw = fallback.choices[0].message.content.strip()
+            if raw.startswith("```"):
+                raw = re.sub(r"^```(?:json)?\s*\n", "", raw)
+                raw = re.sub(r"\n```\s*$", "", raw)
+            try:
+                return json.loads(raw)
+            except json.JSONDecodeError as e:
+                raise ValueError(
+                    f"两次尝试均无法解析为 JSON。原始响应前 200 字符: {raw[:200]}"
+                ) from e

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils/_category.py

@@ -0,0 +1,24 @@
+"""中文活动类别猜测。"""
+
+CATEGORY_ALIASES = {
+    "漫展": "漫展", "同人展": "同人展", "演唱会": "演唱会",
+    "舞台剧": "舞台剧", "音乐会": "音乐会", "展览": "展览",
+    "二次元": "漫展", "cosplay": "漫展", "动漫": "漫展",
+    "主题餐厅": "展览", "主题店": "展览", "授权店": "展览",
+    "咖啡": "展览", "快闪": "展览", "谷子": "展览",
+    "only": "同人展", "ONLY": "同人展", "同人": "同人展",
+    "画展": "展览", "纪念展": "展览", "原画展": "展览",
+    "声优": "演唱会", "见面会": "演唱会", "live": "演唱会", "Live": "演唱会",
+    "音乐节": "演唱会", "地下偶像": "演唱会", "mixup": "演唱会",
+    "游乐园": "漫展", "嘉年华": "漫展", "面基": "漫展",
+    "痛岛": "漫展", "cafe": "展览", "茶会": "展览", "玩偶": "展览",
+}
+
+
+def guess_category(title: str) -> str:
+    """根据标题猜测活动类别。"""
+    t = title.lower().replace(" ", "")
+    for alias, cat in CATEGORY_ALIASES.items():
+        if alias.lower() in t:
+            return cat
+    return "其他"

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils/_city.py

@@ -0,0 +1,26 @@
+"""中国城市提取与规范化。"""
+
+# 52 个主要城市（从 ComiRadar 合并）
+CITIES = [
+    "上海", "北京", "广州", "深圳", "成都", "杭州", "南京", "武汉", "重庆",
+    "西安", "长沙", "苏州", "天津", "郑州", "东莞", "青岛", "沈阳", "宁波",
+    "昆明", "大连", "厦门", "合肥", "佛山", "无锡", "福州", "济南", "哈尔滨",
+    "长春", "石家庄", "南宁", "贵阳", "南昌", "太原", "乌鲁木齐", "兰州",
+    "海口", "银川", "西宁", "拉萨", "珠海", "常州", "南通", "徐州", "温州",
+    "绍兴", "嘉兴", "金华", "泉州", "漳州", "三亚",
+]
+
+
+def extract_city(text: str) -> str:
+    """从文本中提取第一个匹配的城市名。"""
+    for city in CITIES:
+        if city in text:
+            return city
+    return ""
+
+
+def normalize_city(city: str) -> str:
+    """统一城市名：去空格、去'市'后缀、处理别名。"""
+    c = city.strip().rstrip("市")
+    aliases = {"中国": "", "全国": ""}
+    return aliases.get(c, c)

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils/_date.py

@@ -0,0 +1,60 @@
+"""中文日期解析 — 支持结构化字符串和自由文本提取。"""
+
+import re
+from datetime import datetime
+
+
+# 自由文本日期正则
+_DATE_PATTERNS = [
+    re.compile(r"(\d{4})[年.\-](\d{1,2})[月.\-](\d{1,2})[日号]?"),
+    re.compile(r"(\d{1,2})月(\d{1,2})[日号]"),
+    re.compile(r"(\d{1,2})月(\d{1,2})[日号]?\s*[-–—至到]\s*(\d{1,2})[日号]?"),
+]
+
+
+def parse_date(s: str) -> str:
+    """解析结构化日期字符串，返回 YYYY-MM-DD 格式。
+
+    支持: 2026-05-04, 2026/05/04, 2026.05.04, 2026-05-04 14:30:00, 20260504, ISO 格式。
+    缺失时返回今天。
+    """
+    if not s:
+        return datetime.now().strftime("%Y-%m-%d")
+    s = str(s).strip()
+    for fmt in ("%Y-%m-%d", "%Y/%m/%d", "%Y.%m.%d", "%Y-%m-%d %H:%M:%S", "%Y%m%d"):
+        try:
+            return datetime.strptime(s[:len(fmt)], fmt).strftime("%Y-%m-%d")
+        except (ValueError, IndexError):
+            continue
+    try:
+        return datetime.fromisoformat(s.replace("Z", "+00:00")).strftime("%Y-%m-%d")
+    except (ValueError, TypeError):
+        pass
+    return s[:10] if len(s) >= 10 else s
+
+
+def extract_date(text: str) -> str:
+    """从中文自由文本中提取日期，返回 YYYY-MM-DD 格式。
+
+    支持: '2026年5月4日', '5月4日', '5月4日-6日'。
+    无法提取时返回空字符串。
+    """
+    year = datetime.now().year
+    for pat in _DATE_PATTERNS:
+        m = pat.search(text)
+        if m:
+            groups = m.groups()
+            if len(groups) == 2:
+                mth, day = int(groups[0]), int(groups[1])
+                y = year
+            elif len(str(groups[0])) == 4:
+                y, mth, day = int(groups[0]), int(groups[1]), int(groups[2])
+            else:
+                mth, day = int(groups[0]), int(groups[1])
+                y = year
+            try:
+                dt = datetime(y, mth, day)
+                return dt.strftime("%Y-%m-%d")
+            except ValueError:
+                continue
+    return ""

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils/_hash.py

@@ -0,0 +1,11 @@
+"""确定性的 SHA256 稳定 ID 生成，替代 Python 不稳定的 hash()。"""
+
+import hashlib
+
+
+def stable_id(*parts: str) -> str:
+    """生成确定性的短 ID，跨进程重启不变。
+
+    用 '|' 连接输入片段，SHA256 哈希后取前 16 位 hex。
+    """
+    return hashlib.sha256("|".join(parts).encode()).hexdigest()[:16]

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils/_rate_limit.py

@@ -0,0 +1,41 @@
+"""异步速率限制器 — 请求间最小间隔 + 指数退避重试。"""
+
+import time
+import asyncio
+
+
+class RateLimiter:
+    """异步速率限制器，保证两次请求之间至少间隔 min_interval 秒。"""
+
+    def __init__(self, min_interval: float = 2.0):
+        self.min_interval = min_interval
+        self._last_request = 0.0
+
+    async def wait(self):
+        """等待直到可以发起下一次请求。"""
+        now = time.monotonic()
+        elapsed = now - self._last_request
+        if elapsed < self.min_interval:
+            await asyncio.sleep(self.min_interval - elapsed)
+        self._last_request = time.monotonic()
+
+    async def fetch_with_retry(self, fetch_fn, max_retries: int = 3):
+        """带指数退避的请求包装器。
+
+        fetch_fn: 无参异步函数，返回响应对象。
+        """
+        last_exc = None
+        for attempt in range(max_retries):
+            try:
+                await self.wait()
+                resp = await fetch_fn()
+                if hasattr(resp, "status_code") and resp.status_code in (429, 503):
+                    wait_s = 2 ** attempt
+                    await asyncio.sleep(wait_s)
+                    continue
+                return resp
+            except Exception as e:
+                last_exc = e
+                if attempt < max_retries - 1:
+                    await asyncio.sleep(2 ** attempt)
+        raise last_exc or RuntimeError("max retries exceeded")

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils/_ua.py

@@ -0,0 +1,16 @@
+"""User-Agent 池与随机选择。"""
+
+import random
+
+UA_POOL = [
+    "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",
+    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:133.0) Gecko/20100101 Firefox/133.0",
+    "Mozilla/5.0 (iPhone; CPU iPhone OS 18_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.0 Mobile/15E148 Safari/604.1",
+]
+
+
+def random_ua() -> str:
+    """随机返回一个 User-Agent 字符串。"""
+    return random.choice(UA_POOL)

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils.egg-info/PKG-INFO

@@ -0,0 +1,141 @@
+Metadata-Version: 2.4
+Name: chinese-scraper-utils
+Version: 0.1.0
+Summary: Chinese scraping utilities — date parsing, city extraction, SHA256 ID, UA pool, rate limiter, DeepSeek client
+License-Expression: MIT
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: httpx>=0.24
+Requires-Dist: openai>=1.0
+Dynamic: license-file
+
+# chinese-scraper-utils
+
+<p align="center">
+  <img src="https://img.shields.io/pypi/v/chinese-scraper-utils" alt="PyPI version">
+  <img src="https://img.shields.io/badge/python-3.11%2B-blue" alt="Python 3.11+">
+  <img src="https://img.shields.io/badge/license-MIT-green" alt="MIT License">
+</p>
+
+Shared Python utilities for Chinese-language web scraping — date parsing, city extraction, stable ID generation, UA rotation, rate limiting, and a DeepSeek API client. Extracted from [ComiRadar](https://github.com/sixtdreanight/ComiRadar) and `weekly-cli`, where these functions had diverged across two codebases.
+
+从 [ComiRadar](https://github.com/sixtdreanight/ComiRadar) 与 `weekly-cli` 中提取的共享 Python 工具集：中文日期解析、城市提取、稳定 ID 生成、UA 池、速率限制、DeepSeek 客户端。
+
+---
+
+## Installation / 安装
+
+```bash
+pip install chinese-scraper-utils
+```
+
+---
+
+## Usage / 使用示例
+
+### Stable ID / 稳定 ID
+
+```python
+from chinese_scraper_utils import stable_id
+
+uid = stable_id("北京国际动漫展", "北京", "2026-05-04")
+# => "3a8f1c9e2d4b6a05"  (SHA256 hex prefix, deterministic across restarts)
+```
+
+### Date Parsing / 日期解析
+
+```python
+from chinese_scraper_utils import parse_date, extract_date
+
+# Structured date parsing / 结构化日期解析
+parse_date("2026-05-04")           # => "2026-05-04"
+parse_date("2026/05/04 14:30:00")  # => "2026-05-04"
+
+# Chinese text date extraction / 中文文本日期提取
+extract_date("5月4日上海有漫展")       # => "2026-05-04"
+extract_date("2026年5月4日-6日")      # => "2026-05-04"
+```
+
+### City Extraction & Normalization / 城市提取与规范化
+
+```python
+from chinese_scraper_utils import extract_city, normalize_city, CITIES
+
+extract_city("活动在上海举办")      # => "上海"
+extract_city("广州天河区")         # => "广州"
+
+normalize_city("上海市")           # => "上海"
+normalize_city("  深圳市  ")       # => "深圳"
+```
+
+### Category Guessing / 类别猜测
+
+```python
+from chinese_scraper_utils import guess_category
+
+guess_category("五一漫展嘉年华")   # => "漫展"
+guess_category("初音未来演唱会")   # => "演唱会"
+guess_category("清明上河图展览")   # => "展览"
+```
+
+### Random User-Agent / 随机 UA
+
+```python
+from chinese_scraper_utils import random_ua, UA_POOL
+
+random_ua()  # => "Mozilla/5.0 (Windows NT 10.0; ..."
+```
+
+### Async Rate Limiter / 异步速率限制
+
+```python
+import asyncio
+from chinese_scraper_utils import RateLimiter
+
+limiter = RateLimiter(min_interval=1.0)
+
+async def fetch():
+    async with httpx.AsyncClient() as client:
+        resp = await limiter.fetch_with_retry(
+            lambda: client.get("https://example.com")
+        )
+        return resp.text
+```
+
+### DeepSeek AI Client / DeepSeek AI 客户端
+
+```python
+from chinese_scraper_utils import DeepSeekClient
+
+client = DeepSeekClient(api_key="sk-xxx")
+result = client.chat_json([
+    {"role": "user", "content": "提取活动信息：北京五一漫展"}
+])
+# => {"name": "...", "date": "...", "city": "..."}
+```
+
+---
+
+## API Reference / API 参考
+
+| Export / 导出项          | Type / 类型         | Description / 描述                                           |
+|--------------------------|---------------------|---------------------------------------------------------------|
+| `stable_id(*parts)`      | `str` → `str`       | Deterministic SHA256 short ID / 确定性 SHA256 短 ID           |
+| `parse_date(s)`          | `str` → `str`       | Structured date parsing / 结构化日期解析                      |
+| `extract_date(text)`     | `str` → `str`       | Chinese text date extraction / 中文文本日期提取                |
+| `CITIES`                 | `list[str]`         | 52 major Chinese cities / 52 个主要中国城市                    |
+| `extract_city(text)`     | `str` → `str`       | Chinese city name extraction / 城市名提取                      |
+| `normalize_city(city)`   | `str` → `str`       | City name normalization (strip suffix) / 城市名规范化          |
+| `CATEGORY_ALIASES`       | `dict[str, str]`    | Category alias mapping / 类别别名映射                          |
+| `guess_category(title)`  | `str` → `str`       | Category guessing from title / 根据标题猜测类别                |
+| `UA_POOL`                | `list[str]`         | User-Agent pool / User-Agent 池                                |
+| `random_ua()`            | ` → `str`           | Random UA selection / 随机返回 UA                              |
+| `RateLimiter`            | class               | Async rate limiter with retry / 异步速率限制器                  |
+| `DeepSeekClient`         | class               | DeepSeek API wrapper / DeepSeek API 封装客户端                  |
+
+---
+
+## License / 许可证
+
+[MIT](LICENSE)

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils.egg-info/SOURCES.txt

@@ -0,0 +1,16 @@
+LICENSE
+README.md
+pyproject.toml
+src/chinese_scraper_utils/__init__.py
+src/chinese_scraper_utils/_ai.py
+src/chinese_scraper_utils/_category.py
+src/chinese_scraper_utils/_city.py
+src/chinese_scraper_utils/_date.py
+src/chinese_scraper_utils/_hash.py
+src/chinese_scraper_utils/_rate_limit.py
+src/chinese_scraper_utils/_ua.py
+src/chinese_scraper_utils.egg-info/PKG-INFO
+src/chinese_scraper_utils.egg-info/SOURCES.txt
+src/chinese_scraper_utils.egg-info/dependency_links.txt
+src/chinese_scraper_utils.egg-info/requires.txt
+src/chinese_scraper_utils.egg-info/top_level.txt

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils.egg-info/requires.txt

@@ -0,0 +1,2 @@
+httpx>=0.24
+openai>=1.0

chinese_scraper_utils-0.1.0/src/chinese_scraper_utils.egg-info/top_level.txt

@@ -0,0 +1 @@
+chinese_scraper_utils