♻️ 重写 wiki 模块和相关插件

1. 使用 `pydantic` 重写了 wiki 模块所使用的 model
2. 添加了 weapon_level.json 用于后续计算武器升级所需的经验
3. 修改了 wiki 插件，以适应新的 model

core/wiki/cache.py

@@ -1,5 +1,6 @@
-import ujson
+import ujson as json
 
+from models.wiki.base import Model
 from utils.redisdb import RedisDB
 
 
@@ -8,14 +9,22 @@ class WikiCache:
         self.client = redis.client
         self.qname = "wiki"
 
-    async def refresh_info_cache(self, key_name: str, info):
+    async def set(self, key: str, value):
-        qname = f"{self.qname}:{key_name}"
+        qname = f"{self.qname}:{key}"
-        await self.client.set(qname, ujson.dumps(info))
+        if isinstance(value, Model):
+            value = value.json()
+        elif isinstance(value, (dict, list)):
+            value = json.dumps(value)
+        await self.client.set(qname, value)
 
-    async def del_one(self, key_name: str):
+    async def delete(self, key: str):
-        qname = f"{self.qname}:{key_name}"
+        qname = f"{self.qname}:{key}"
         await self.client.delete(qname)
 
-    async def get_one(self, key_name: str) -> str:
+    async def get(self, key: str) -> dict:
-        qname = f"{self.qname}:{key_name}"
+        qname = f"{self.qname}:{key}"
-        return await self.client.get(qname)
+        result = json.loads(await self.client.get(qname))
+        if isinstance(result, list) and len(result) > 0:
+            for num, item in enumerate(result):
+                result[num] = json.loads(item)
+        return result

core/wiki/services.py

@@ -1,11 +1,9 @@
-import asyncio
+from typing import List, NoReturn, Optional
-
-import ujson
 
+from core.wiki.cache import WikiCache
 from logger import Log
-from models.wiki.characters import Characters
+from models.wiki.character import Character
-from models.wiki.weapons import Weapons
+from models.wiki.weapon import Weapon
-from .cache import WikiCache
 
 
 class WikiService:
@@ -13,58 +11,47 @@ class WikiService:
     def __init__(self, cache: WikiCache):
         self._cache = cache
         """Redis 在这里的作用是作为持久化"""
-        self.weapons = Weapons()
+        self._character_list = []
-        self.characters = Characters()
+        self._character_name_list = []
-        self._characters_list = []
+        self._weapon_name_list = []
-        self._characters_name_list = []
+        self._weapon_list = []
-        self._weapons_name_list = []
-        self._weapons_list = []
         self.first_run = True
 
-    async def refresh_weapon(self):
+    async def refresh_weapon(self) -> NoReturn:
-        weapon_url_list = await self.weapons.get_all_weapon_url()
+        weapon_name_list = await Weapon.get_name_list()
-        Log.info(f"一共找到 {len(weapon_url_list)} 把武器信息")
+        Log.info(f"一共找到 {len(weapon_name_list)} 把武器信息")
-        weapons_list = []
+
-        task_list = []
+        weapon_list = []
-        for index, weapon_url in enumerate(weapon_url_list):
+        num = 0
-            task_list.append(self.weapons.get_weapon_info(weapon_url))
+        async for weapon in Weapon.full_data_generator():
-            # weapon_info = await self.weapons.get_weapon_info(weapon_url)
+            weapon_list.append(weapon)
-            if index % 5 == 0:
+            num += 1
-                result_list = await asyncio.gather(*task_list)
+            if num % 10 == 0:
-                weapons_list.extend(result for result in result_list if isinstance(result, dict))
+                Log.info(f"现在已经获取到 {num} 把武器信息")
-                task_list.clear()
-            if index % 10 == 0 and index != 0:
-                Log.info(f"现在已经获取到 {index} 把武器信息")
-        result_list = await asyncio.gather(*task_list)
-        weapons_list.extend(result for result in result_list if isinstance(result, dict))
 
         Log.info("写入武器信息到Redis")
-        self._weapons_list = weapons_list
+        self._weapon_list = weapon_list
-        await self._cache.del_one("weapon")
+        await self._cache.delete("weapon")
-        await self._cache.refresh_info_cache("weapon", weapons_list)
+        await self._cache.set("weapon", [i.json() for i in weapon_list])
 
-    async def refresh_characters(self):
+    async def refresh_characters(self) -> NoReturn:
-        characters_url_list = await self.characters.get_all_characters_url()
+        character_name_list = await Character.get_name_list()
-        Log.info(f"一共找到 {len(characters_url_list)} 个角色信息")
+        Log.info(f"一共找到 {len(character_name_list)} 个角色信息")
-        characters_list = []
+
-        task_list = []
+        character_list = []
-        for index, characters_url in enumerate(characters_url_list):
+        num = 0
-            task_list.append(self.characters.get_characters(characters_url))
+        async for character in Character.full_data_generator():
-            if index % 5 == 0:
+            character_list.append(character)
-                result_list = await asyncio.gather(*task_list)
+            num += 1
-                characters_list.extend(result for result in result_list if isinstance(result, dict))
+            if num % 10 == 0:
-                task_list.clear()
+                Log.info(f"现在已经获取到 {num} 个角色信息")
-            if index % 10 == 0 and index != 0:
-                Log.info(f"现在已经获取到 {index} 个角色信息")
-        result_list = await asyncio.gather(*task_list)
-        characters_list.extend(result for result in result_list if isinstance(result, dict))
 
         Log.info("写入角色信息到Redis")
-        self._characters_list = characters_list
+        self._character_list = character_list
-        await self._cache.del_one("characters")
+        await self._cache.delete("characters")
-        await self._cache.refresh_info_cache("characters", characters_list)
+        await self._cache.set("characters", [i.json() for i in character_list])
 
-    async def refresh_wiki(self):
+    async def refresh_wiki(self) -> NoReturn:
         """
         用于把Redis的缓存全部加载进Python
         :return:
@@ -76,40 +63,39 @@ class WikiService:
         await self.refresh_characters()
         Log.info("刷新成功")
 
-    async def init(self):
+    async def init(self) -> NoReturn:
         """
         用于把Redis的缓存全部加载进Python
         :return:
         """
         if self.first_run:
-            weapon_dict = await self._cache.get_one("weapon")
+            weapon_dict = await self._cache.get("weapon")
-            self._weapons_list = ujson.loads(weapon_dict)
+            self._weapon_list = [Weapon.parse_obj(obj) for obj in weapon_dict]
-            for weapon in self._weapons_list:
+            self._weapon_name_list = await Weapon.get_name_list()
-                self._weapons_name_list.append(weapon["name"])
+            characters_dict = await self._cache.get("characters")
-            characters_dict = await self._cache.get_one("characters")
+            self._character_list = [Character.parse_obj(obj) for obj in characters_dict]
-            self._characters_list = ujson.loads(characters_dict)
+            self._character_name_list = await Character.get_name_list()
-            for characters in self._characters_list:
+
-                self._characters_name_list.append(characters["name"])
             self.first_run = False
 
-    async def get_weapons(self, name: str):
+    async def get_weapons(self, name: str) -> Optional[Weapon]:
         await self.init()
-        if len(self._weapons_list) == 0:
+        if len(self._weapon_list) == 0:
-            return {}
+            return None
-        return next((weapon for weapon in self._weapons_list if weapon["name"] == name), {})
+        return next((weapon for weapon in self._weapon_list if weapon.name == name), None)
 
-    async def get_weapons_name_list(self) -> list:
+    async def get_weapons_name_list(self) -> List[str]:
         await self.init()
-        return self._weapons_name_list
+        return self._weapon_name_list
 
-    async def get_weapons_list(self) -> list:
+    async def get_weapons_list(self) -> List[Weapon]:
         await self.init()
-        return self._weapons_list
+        return self._weapon_list
 
-    async def get_characters_list(self) -> list:
+    async def get_characters_list(self) -> List[Character]:
         await self.init()
-        return self._characters_list
+        return self._character_list
 
-    async def get_characters_name_list(self) -> list:
+    async def get_characters_name_list(self) -> List[str]:
         await self.init()
-        return self._characters_name_list
+        return self._character_name_list

metadata/shortname.py

@@ -1,67 +1,195 @@
+from typing import Optional
+
+# noinspection SpellCheckingInspection
 roles = {
-    10000003: ["琴", "Jean", "jean", "团长", "代理团长", "琴团长", "蒲公英骑士"],
+    10000002: [
-    10000006: ["丽莎", "Lisa", "lisa", "图书管理员", "图书馆管理员", "蔷薇魔女"],
+        "神里绫华", "Kamisato Ayaka", "Ayaka", "ayaka", "神里", "绫华", "神里凌华", "凌华", "白鹭公主", "神里大小姐"
-    10000005: ["空", "男主", "男主角", "龙哥", "空哥", "旅行者", "卑鄙的外乡人", "荣誉骑士", "爷", "风主", "岩主", "雷主", "履刑者", "抽卡不歪真君"],
+    ],
-    10000007: ["荧", "女主", "女主角", "莹", "萤", "黄毛阿姨", "荧妹"],
+    10000003: [
-    10000014: ["芭芭拉", "Barbara", "barbara", "巴巴拉", "拉粑粑", "拉巴巴", "内鬼", "加湿器", "闪耀偶像", "偶像"],
+        "琴", "Jean", "jean", "团长", "代理团长", "琴团长", "蒲公英骑士"
-    10000015: ["凯亚", "Kaeya", "kaeya", "盖亚", "凯子哥", "凯鸭", "矿工", "矿工头子", "骑兵队长", "凯子", "凝冰渡海真君"],
+    ],
-    10000016: ["迪卢克", "diluc", "Diluc", "卢姥爷", "姥爷", "卢老爷", "卢锅巴", "正义人", "正e人", "正E人", "卢本伟", "暗夜英雄", "卢卢伯爵",
+    10000005: [
-               "落魄了", "落魄了家人们"],
+        "空", "男主", "男主角", "龙哥", "空哥"
-    10000020: ["雷泽", "razor", "Razor", "狼少年", "狼崽子", "狼崽", "卢皮卡", "小狼", "小狼狗"],
+    ],
-    10000021: ["安柏", "Amber", "amber", "安伯", "兔兔伯爵", "飞行冠军", "侦查骑士", "点火姬", "点火机", "打火机", "打火姬", ],
+    10000006: [
-    10000022: ["温迪", "Venti", "venti", "温蒂", "风神", "卖唱的", "巴巴托斯", "巴巴脱丝", "芭芭托斯", "芭芭脱丝", "干点正事", "不干正事", "吟游诗人",
+        "丽莎", "Lisa", "lisa", "图书管理员", "图书馆管理员", "蔷薇魔女"
-               "诶嘿", "唉嘿", "摸鱼", ],
+    ],
-    10000023: ["香菱", "Xiangling", "xiangling", "香玲", "锅巴", "厨师", "万民堂厨师", "香师傅"],
+    10000007: [
-    10000024: ["北斗", "Beidou", "beidou", "大姐头", "大姐", "无冕的龙王", "龙王"],
+        "荧", "女主", "女主角", "莹", "萤", "黄毛阿姨", "荧妹"
-    10000025: ["行秋", "Xingqiu", "xingqiu", "秋秋人", "秋妹妹", "书呆子", "水神", "飞云商会二少爷"],
+    ],
-    10000026: ["魈", "Xiao", "xiao", "杏仁豆腐", "打桩机", "插秧", "三眼五显仙人", "三眼五显真人", "降魔大圣", "护法夜叉", "快乐风男", "无聊", "靖妖傩舞",
+    10000014: [
-               "矮子仙人", "三点五尺仙人", "跳跳虎"],
+        "芭芭拉", "Barbara", "barbara", "巴巴拉", "拉粑粑", "拉巴巴", "内鬼", "加湿器", "闪耀偶像", "偶像"
-    10000027: ["凝光", "Ningguang", "ningguang", "富婆", "天权星"],
+    ],
-    10000029: ["可莉", "Klee", "klee", "嘟嘟可", "火花骑士", "蹦蹦炸弹", "炸鱼", "放火烧山", "放火烧山真君", "蒙德最强战力", "逃跑的太阳", "啦啦啦", "哒哒哒",
+    10000015: [
-               "炸弹人", "禁闭室", ],
+        "凯亚", "Kaeya", "kaeya", "盖亚", "凯子哥", "凯鸭", "矿工", "矿工头子", "骑兵队长", "凯子", "凝冰渡海真君"
-    10000030: ["钟离", "Zhongli", "zhongli", "摩拉克斯", "岩王爷", "岩神", "钟师傅", "天动万象", "岩王帝君", "未来可期", "帝君", "拒收病婿"],
+    ],
-    10000031: ["菲谢尔", "Fischl", "fischl", "皇女", "小艾米", "小艾咪", "奥兹", "断罪皇女", "中二病", "中二少女", "中二皇女", "奥兹发射器"],
+    10000016: [
-    10000032: ["班尼特", "Bennett", "bennett", "点赞哥", "点赞", "倒霉少年", "倒霉蛋", "霹雳闪雷真君", "班神", "班爷", "倒霉", "火神", "六星真神"],
+        "迪卢克", "diluc", "Diluc", "卢姥爷", "姥爷", "卢老爷", "卢锅巴", "正义人", "正e人", "正E人", "卢本伟",
-    10000033: ["达达利亚", "Tartaglia", "tartaglia", "Childe", "childe", "Ajax", "ajax", "达达鸭", "达达利鸭", "公子", "玩具销售员",
+        "暗夜英雄", "卢卢伯爵", "落魄了", "落魄了家人们"
-               "玩具推销员", "钱包", "鸭鸭", "愚人众末席"],
+    ],
-    10000034: ["诺艾尔", "Noelle", "noelle", "女仆", "高达", "岩王帝姬"],
+    10000020: [
-    10000035: ["七七", "Qiqi", "qiqi", "僵尸", "肚饿真君", "度厄真君"],
+        "雷泽", "razor", "Razor", "狼少年", "狼崽子", "狼崽", "卢皮卡", "小狼", "小狼狗"
-    10000036: ["重云", "Chongyun", "chongyun", "纯阳之体", "冰棍"],
+    ],
-    10000037: ["甘雨", "Ganyu", "ganyu", "椰羊", "椰奶", "王小美"],
+    10000021: [
-    10000038: ["阿贝多", "Albedo", "albedo", "可莉哥哥", "升降机", "升降台", "电梯", "白垩之子", "贝爷", "白垩", "阿贝少", "花呗多", "阿贝夕",
+        "安柏", "Amber", "amber", "安伯", "兔兔伯爵", "飞行冠军", "侦查骑士", "点火姬", "点火机", "打火机", "打火姬"
-               "abd", "阿师傅"],
+    ],
-    10000039: ["迪奥娜", "Diona", "diona", "迪欧娜", "dio", "dio娜", "冰猫", "猫猫", "猫娘", "喵喵", "调酒师"],
+    10000022: [
-    10000041: ["莫娜", "Mona", "mona", "穷鬼", "穷光蛋", "穷", "莫纳", "占星术士", "占星师", "讨龙真君", "半部讨龙真君", "阿斯托洛吉斯·莫娜·梅姬斯图斯"],
+        "温迪", "Venti", "venti", "温蒂", "风神", "卖唱的", "巴巴托斯", "巴巴脱丝", "芭芭托斯", "芭芭脱丝", "干点正事",
-    10000042: ["刻晴", "Keqing", "keqing", "刻情", "氪晴", "刻师傅", "刻师父", "牛杂", "牛杂师傅", "斩尽牛杂", "免疫", "免疫免疫", "屁斜剑法",
+        "不干正事", "吟游诗人", "诶嘿", "唉嘿", "摸鱼"
-               "玉衡星", "阿晴", "啊晴"],
+    ],
-    10000043: ["砂糖", "Sucrose", "sucrose", "雷莹术士", "雷萤术士", "雷荧术士"],
+    10000023: [
-    10000044: ["辛焱", "Xinyan", "xinyan", "辛炎", "黑妹", "摇滚"],
+        "香菱", "Xiangling", "xiangling", "香玲", "锅巴", "厨师", "万民堂厨师", "香师傅"
-    10000045: ["罗莎莉亚", "Rosaria", "rosaria", "罗莎莉娅", "白色史莱姆", "白史莱姆", "修女", "罗莎利亚", "罗莎利娅", "罗沙莉亚", "罗沙莉娅", "罗沙利亚",
+    ],
-               "罗沙利娅", "萝莎莉亚", "萝莎莉娅", "萝莎利亚", "萝莎利娅", "萝沙莉亚", "萝沙莉娅", "萝沙利亚", "萝沙利娅"],
+    10000024: [
-    10000046: ["胡桃", "Hu Tao", "hu tao", "HuTao", "hutao", "Hutao", "胡淘", "往生堂堂主", "火化", "抬棺的", "蝴蝶", "核桃", "堂主",
+        "北斗", "Beidou", "beidou", "大姐头", "大姐", "无冕的龙王", "龙王"
-               "胡堂主", "雪霁梅香"],
+    ],
-    10000047: ["枫原万叶", "Kaedehara Kazuha", "Kazuha", "kazuha", "万叶", "叶天帝", "天帝", "叶师傅"],
+    10000025: [
-    10000048: ["烟绯", "Yanfei", "yanfei", "烟老师", "律师", "罗翔"],
+        "行秋", "Xingqiu", "xingqiu", "秋秋人", "秋妹妹", "书呆子", "水神", "飞云商会二少爷"
-    10000051: ["优菈", "Eula", "eula", "优拉", "尤拉", "尤菈", "浪花骑士", "记仇", "劳伦斯"],
+    ],
-    10000002: ["神里绫华", "Kamisato Ayaka", "Ayaka", "ayaka", "神里", "绫华", "神里凌华", "凌华", "白鹭公主", "神里大小姐"],
+    10000026: [
-    10000049: ["宵宫", "Yoimiya", "yoimiya", "霄宫", "烟花", "肖宫", "肖工", "绷带女孩"],
+        "魈", "Xiao", "xiao", "杏仁豆腐", "打桩机", "插秧", "三眼五显仙人", "三眼五显真人", "降魔大圣", "护法夜叉",
-    10000052: ["雷电将军", "Raiden Shogun", "Raiden", "raiden", "雷神", "将军", "雷军", "巴尔", "阿影", "影", "巴尔泽布", "煮饭婆", "奶香一刀",
+        "快乐风男", "无聊", "靖妖傩舞", "矮子仙人", "三点五尺仙人", "跳跳虎"
-               "无想一刀", "宅女"],
+    ],
-    10000053: ["早柚", "Sayu", "sayu", "小狸猫", "狸猫", "忍者"],
+    10000027: [
-    10000054: ["珊瑚宫心海", "Sangonomiya Kokomi", "Kokomi", "kokomi", "心海", "军师", "珊瑚宫", "书记", "观赏鱼", "水母", "鱼", "美人鱼"],
+        "凝光", "Ningguang", "ningguang", "富婆", "天权星"
-    10000056: ["九条裟罗", "Kujou Sara", "Sara", "sara", "九条", "九条沙罗", "裟罗", "沙罗", "天狗"],
+    ],
-    10000062: ["埃洛伊", "Aloy", "aloy"],
+    10000029: [
-    10000050: ["托马", "Thoma", "thoma", "家政官", "太郎丸", "地头蛇", "男仆", "拖马"],
+        "可莉", "Klee", "klee", "嘟嘟可", "火花骑士", "蹦蹦炸弹", "炸鱼", "放火烧山", "放火烧山真君", "蒙德最强战力",
-    10000055: ["五郎", "Gorou", "gorou", "柴犬", "土狗", "希娜", "希娜小姐"],
+        "逃跑的太阳", "啦啦啦", "哒哒哒", "炸弹人", "禁闭室"
-    10000057: ["荒泷一斗", "Arataki Itto", "Itto", "itto", "荒龙一斗", "荒泷天下第一斗", "一斗", "一抖", "荒泷", "1斗", "牛牛", "斗子哥", "牛子哥",
+    ],
-               "牛子", "孩子王", "斗虫", "巧乐兹", "放牛的"],
+    10000030: [
-    10000058: ["八重神子", "Yae Miko", "Miko", "miko", "八重", "神子", "狐狸", "想得美哦", "巫女", "屑狐狸", "骚狐狸", "八重宫司", "婶子", "小八"],
+        "钟离", "Zhongli", "zhongli", "摩拉克斯", "岩王爷", "岩神", "钟师傅", "天动万象", "岩王帝君", "未来可期",
-    10000059: ["鹿野院平藏", "shikanoin heizou", "Heizou", "heizou", "heizo", "鹿野苑", "鹿野院", "平藏", "鹿野苑平藏"],
+        "帝君", "拒收病婿"
-    10000060: ["夜兰", "Yelan", "yelan", "夜阑", "叶澜", "腋兰", "夜天后"],
+    ],
-    10000063: ["申鹤", "Shenhe", "shenhe", "神鹤", "小姨", "小姨子", "审鹤"],
+    10000031: [
-    10000064: ["云堇", "Yun Jin", "yunjin", "yun jin", "云瑾", "云先生", "云锦", "神女劈观"],
+        "菲谢尔", "Fischl", "fischl", "皇女", "小艾米", "小艾咪", "奥兹", "断罪皇女", "中二病", "中二少女", "中二皇女",
-    10000065: ["久岐忍", "Kuki Shinobu", "Kuki", "kuki", "Shinobu", "shinobu", "97忍", "小忍", "久歧忍", "97", "茄忍", "阿忍", "忍姐"],
+        "奥兹发射器"
-    10000066: ["神里绫人", "Kamisato Ayato", "Ayato", "ayato", "绫人", "神里凌人", "凌人", "0人", "神人", "零人", "大舅哥"],
+    ],
+    10000032: [
+        "班尼特", "Bennett", "bennett", "点赞哥", "点赞", "倒霉少年", "倒霉蛋", "霹雳闪雷真君", "班神", "班爷", "倒霉",
+        "火神", "六星真神"
+    ],
+    10000033: [
+        "达达利亚", "Tartaglia", "tartaglia", "Childe", "childe", "Ajax", "ajax", "达达鸭", "达达利鸭", "公子",
+        "玩具销售员", "玩具推销员", "钱包", "鸭鸭", "愚人众末席"
+    ],
+    10000034: [
+        "诺艾尔", "Noelle", "noelle", "女仆", "高达", "岩王帝姬"
+    ],
+    10000035: [
+        "七七", "Qiqi", "qiqi", "僵尸", "肚饿真君", "度厄真君", "77"
+    ],
+    10000036: [
+        "重云", "Chongyun", "chongyun", "纯阳之体", "冰棍"
+    ],
+    10000037: [
+        "甘雨", "Ganyu", "ganyu", "椰羊", "椰奶", "王小美"
+    ],
+    10000038: [
+        "阿贝多", "Albedo", "albedo", "可莉哥哥", "升降机", "升降台", "电梯", "白垩之子", "贝爷", "白垩", "阿贝少",
+        "花呗多", "阿贝夕", "abd", "阿师傅"
+    ],
+    10000039: [
+        "迪奥娜", "Diona", "diona", "迪欧娜", "dio", "dio娜", "冰猫", "猫猫", "猫娘", "喵喵", "调酒师"
+    ],
+    10000041: [
+        "莫娜", "Mona", "mona", "穷鬼", "穷光蛋", "穷", "莫纳", "占星术士", "占星师", "讨龙真君", "半部讨龙真君",
+        "阿斯托洛吉斯·莫娜·梅姬斯图斯", "梅姬斯图斯", "梅姬斯图斯卿"
+    ],
+    10000042: [
+        "刻晴", "Keqing", "keqing", "刻情", "氪晴", "刻师傅", "刻师父", "牛杂", "牛杂师傅", "斩尽牛杂", "免疫",
+        "免疫免疫", "屁斜剑法", "玉衡星", "阿晴", "啊晴"
+    ],
+    10000043: [
+        "砂糖", "Sucrose", "sucrose", "雷莹术士", "雷萤术士", "雷荧术士"
+    ],
+    10000044: [
+        "辛焱", "Xinyan", "xinyan", "辛炎", "黑妹", "摇滚"
+    ],
+    10000045: [
+        "罗莎莉亚", "Rosaria", "rosaria", "罗莎莉娅", "白色史莱姆", "白史莱姆", "修女", "罗莎利亚", "罗莎利娅",
+        "罗沙莉亚", "罗沙莉娅", "罗沙利亚", "罗沙利娅", "萝莎莉亚", "萝莎莉娅", "萝莎利亚", "萝莎利娅", "萝沙莉亚",
+        "萝沙莉娅", "萝沙利亚", "萝沙利娅"
+    ],
+    10000046: [
+        "胡桃", "Hu Tao", "hu tao", "HuTao", "hutao", "Hutao", "胡淘", "往生堂堂主", "火化", "抬棺的", "蝴蝶", "核桃",
+        "堂主", "胡堂主", "雪霁梅香"
+    ],
+    10000047: [
+        "枫原万叶", "Kaedehara Kazuha", "Kazuha", "kazuha", "万叶", "叶天帝", "天帝", "叶师傅"
+    ],
+    10000048: [
+        "烟绯", "Yanfei", "yanfei", "烟老师", "律师", "罗翔"
+    ],
+    10000049: [
+        "宵宫", "Yoimiya", "yoimiya", "霄宫", "烟花", "肖宫", "肖工", "绷带女孩"
+    ],
+    10000050: [
+        "托马", "Thoma", "thoma", "家政官", "太郎丸", "地头蛇", "男仆", "拖马"
+    ],
+    10000051: [
+        "优菈", "Eula", "eula", "优拉", "尤拉", "尤菈", "浪花骑士", "记仇", "劳伦斯"
+    ],
+    10000052: [
+        "雷电将军", "Raiden Shogun", "Raiden", "raiden", "雷神", "将军", "雷军", "巴尔", "阿影", "影", "巴尔泽布",
+        "煮饭婆", "奶香一刀", "无想一刀", "宅女"
+    ],
+    10000053: [
+        "早柚", "Sayu", "sayu", "小狸猫", "狸猫", "忍者"
+    ],
+    10000054: [
+        "珊瑚宫心海", "Sangonomiya Kokomi", "Kokomi", "kokomi", "心海", "军师", "珊瑚宫", "书记", "观赏鱼", "水母",
+        "鱼", "美人鱼"
+    ],
+    10000055: [
+        "五郎", "Gorou", "gorou", "柴犬", "土狗", "希娜", "希娜小姐"
+    ],
+    10000056: [
+        "九条裟罗", "Kujou Sara", "Sara", "sara", "九条", "九条沙罗", "裟罗", "沙罗", "天狗"
+    ],
+    10000057: [
+        "荒泷一斗", "Arataki Itto", "Itto", "itto", "荒龙一斗", "荒泷天下第一斗", "一斗", "一抖", "荒泷", "1斗", "牛牛",
+        "斗子哥", "牛子哥", "牛子", "孩子王", "斗虫", "巧乐兹", "放牛的"
+    ],
+    10000058: [
+        "八重神子", "Yae Miko", "Miko", "miko", "八重", "神子", "狐狸", "想得美哦", "巫女", "屑狐狸", "骚狐狸",
+        "八重宫司", "婶子", "小八"
+    ],
+    10000059: [
+        "鹿野院平藏", "shikanoin heizou", "Heizou", "heizou", "heizo", "鹿野苑", "鹿野院", "平藏", "鹿野苑平藏", "鹿野",
+        "小鹿"
+    ],
+    10000060: [
+        "夜兰", "Yelan", "yelan", "夜阑", "叶澜", "腋兰", "夜天后"
+    ],
+    10000062: [
+        "埃洛伊", "Aloy", "aloy"
+    ],
+    10000063: [
+        "申鹤", "Shenhe", "shenhe", "神鹤", "小姨", "小姨子", "审鹤"
+    ],
+    10000064: [
+        "云堇", "Yun Jin", "yunjin", "yun jin", "云瑾", "云先生", "云锦", "神女劈观"
+    ],
+    10000065: [
+        "久岐忍", "Kuki Shinobu", "Kuki", "kuki", "Shinobu", "shinobu", "97忍", "小忍", "久歧忍", "97", "茄忍", "阿忍",
+        "忍姐"
+    ],
+    10000066: [
+        "神里绫人", "Kamisato Ayato", "Ayato", "ayato", "绫人", "神里凌人", "凌人", "0人", "神人", "零人", "大舅哥"
+    ],
+    10000067: [
+        "柯莱", "Collei", "collei", "克莱", "科莱", "须弥飞行冠军"
+    ],
+    10000068: [
+        "多莉", "Dori", "dori", "多利", "多丽"
+    ],
+    10000069: [
+        "提纳里", "Tighnari", "tighnari", "巡林官", "小提", "缇娜里", "提哪里", "提那里"
+    ],
+    20000000: [
+        "主角", "旅行者", "卑鄙的外乡人", "荣誉骑士", "爷", "风主", "岩主", "雷主", "草主", "履刑者", "抽卡不歪真君"
+    ]
 }
 weapons = {
     "磐岩结绿": ["绿箭", "绿剑"],
@@ -145,14 +273,15 @@ weapons = {
 
 
 def roleToName(shortname: str) -> str:
-    if not shortname:
+    """讲角色昵称转为正式名"""
-        return shortname
+    return next((value[0] for value in roles.values() for name in value if name == shortname), shortname)
-    for value in roles.values():
+
-        for i in value:
+
-            if i == shortname:
+def roleToId(name: str) -> Optional[int]:
-                return value[0]
+    """获取角色ID"""
-    return shortname
+    return next((key for key, value in roles.items() for n in value if n == name), None)
 
 
 def weaponToName(shortname: str) -> str:
+    """讲武器昵称转为正式名"""
     return next((key for key, value in weapons.items() if shortname == key or shortname in value), shortname)

models/wiki/base.py

@@ -0,0 +1,247 @@
+import asyncio
+import re
+from abc import abstractmethod
+from asyncio import Queue
+from multiprocessing import Value
+from typing import AsyncIterator, ClassVar, List, Optional, Tuple, Union
+
+import anyio
+import ujson as json
+from bs4 import BeautifulSoup
+from httpx import AsyncClient, HTTPError, Response, URL
+from pydantic import (
+    BaseConfig as PydanticBaseConfig,
+    BaseModel as PydanticBaseModel,
+)
+from typing_extensions import Self
+
+__all__ = ['Model', 'WikiModel', 'SCRAPE_HOST']
+
+SCRAPE_HOST = URL("https://genshin.honeyhunterworld.com/")
+
+
+class Model(PydanticBaseModel):
+    """基类"""
+
+    def __new__(cls, *args, **kwargs):
+        # 让每次new的时候都解析
+        cls.update_forward_refs()
+        return super(Model, cls).__new__(cls)
+
+    class Config(PydanticBaseConfig):
+        # 使用 ujson 作为解析库
+        json_dumps = json.dumps
+        json_loads = json.loads
+
+
+class WikiModel(Model):
+    """wiki所用到的基类
+
+    Attributes:
+        id (:obj:`int`): ID
+        name (:obj:`str`): 名称
+        rarity (:obj:`int`): 星级
+
+        _client (:class:`httpx.AsyncClient`): 发起 http 请求的 client
+    """
+    _client: ClassVar[AsyncClient] = AsyncClient()
+
+    id: str
+    name: str
+    rarity: int
+
+    @staticmethod
+    @abstractmethod
+    def scrape_urls() -> List[URL]:
+        """爬取的目标网页集合
+
+        例如有关武器的页面有:
+        [单手剑](https://genshin.honeyhunterworld.com/fam_sword/?lang=CHS)
+        [双手剑](https://genshin.honeyhunterworld.com/fam_claymore/?lang=CHS)
+        [长柄武器](https://genshin.honeyhunterworld.com/fam_polearm/?lang=CHS)
+        。。。
+        这个函数就是返回这些页面的网址所组成的 List
+
+        """
+
+    @classmethod
+    async def _client_get(cls, url: Union[URL, str], retry_times: int = 5, sleep: float = 1) -> Response:
+        """用自己的 client 发起 get 请求的快捷函数
+
+        Args:
+            url: 发起请求的 url
+            retry_times: 发生错误时的重复次数。不能小于 0 .
+            sleep: 发生错误后等待重试的时间，单位为秒。
+        Returns:
+            返回对应的请求
+        Raises:
+            请求所需要的异常
+        """
+        for _ in range(retry_times):
+            try:
+                return await cls._client.get(url, follow_redirects=True)
+            except HTTPError:
+                await anyio.sleep(sleep)
+        return await cls._client.get(url, follow_redirects=True)  # 防止 retry_times 等于 0 的时候无法发生请求
+
+    @classmethod
+    @abstractmethod
+    async def _parse_soup(cls, soup: BeautifulSoup) -> Self:
+        """解析 soup 生成对应 WikiModel
+
+        Args:
+            soup: 需要解析的 soup
+        Returns:
+            返回对应的 WikiModel
+        """
+
+    @classmethod
+    async def _scrape(cls, url: Union[URL, str]) -> Self:
+        """从 url 中爬取数据，并返回对应的 Model
+
+        Args:
+            url: 目标 url. 可以为字符串 str , 也可以为 httpx.URL
+        Returns:
+            返回对应的 WikiModel
+        """
+        response = await cls._client_get(url)
+        return await cls._parse_soup(BeautifulSoup(response.text, 'lxml'))
+
+    @classmethod
+    async def get_by_id(cls, id_: str) -> Self:
+        """通过ID获取Model
+
+        Args:
+            id_: 目标 ID
+        Returns:
+            返回对应的 WikiModel
+        """
+        return await cls._scrape(await cls.get_url_by_id(id_))
+
+    @classmethod
+    async def get_by_name(cls, name: str) -> Optional[Self]:
+        """通过名称获取Model
+
+        Args:
+            name: 目标名
+        Returns:
+            返回对应的 WikiModel
+        """
+        url = await cls.get_url_by_name(name)
+        if url is None:
+            return None
+        else:
+            return await cls._scrape(url)
+
+    @classmethod
+    async def get_full_data(cls) -> List[Self]:
+        """获取全部数据的 Model
+
+        Returns:
+            返回能爬到的所有的 Model 所组成的 List
+        """
+        return [i async for i in cls.full_data_generator()]
+
+    @classmethod
+    async def full_data_generator(cls) -> AsyncIterator[Self]:
+        """Model 生成器
+
+        这是一个异步生成器，该函数在使用时会爬取所有数据，并将其转为对应的 Model，然后存至一个队列中
+        当有需要时，再一个一个地迭代取出
+
+        Returns:
+            返回能爬到的所有的 WikiModel 所组成的 List
+        """
+        queue: Queue[Self] = Queue()  # 存放 Model 的队列
+        signal = Value('i', 0)  # 一个用于异步任务同步的信号
+
+        async def task(u):
+            # 包装的爬虫任务
+            await queue.put(await cls._scrape(u))  # 爬取一条数据，并将其放入队列中
+            signal.value -= 1  # 信号量减少 1 ，说明该爬虫任务已经完成
+
+        for _, url in await cls.get_name_list(with_url=True):  # 遍历爬取所有需要爬取的页面
+            signal.value += 1  # 信号量增加 1 ，说明有一个爬虫任务被添加
+            asyncio.create_task(task(url))  # 创建一个爬虫任务
+
+        while signal.value > 0 or not queue.empty():  # 当还有未完成的爬虫任务或存放数据的队列不为空时
+            yield await queue.get()  # 取出并返回一个存放的 Model
+
+    def __str__(self) -> str:
+        return f"<{self.__class__.__name__} {super(WikiModel, self).__str__()}>"
+
+    def __repr__(self) -> str:
+        return self.__str__()
+
+    @staticmethod
+    async def get_url_by_id(id_: str) -> URL:
+        """根据 id 获取对应的 url
+
+        例如神里绫华的ID为 ayaka_002，对应的数据页url为 https://genshin.honeyhunterworld.com/ayaka_002/?lang=CHS
+
+        Args:
+            id_ : 实列ID
+        Returns:
+            返回对应的 url
+        """
+        return SCRAPE_HOST.join(f"{id_}/?lang=CHS")
+
+    @classmethod
+    async def _name_list_generator(cls, *, with_url: bool = False) -> AsyncIterator[Union[str, Tuple[str, URL]]]:
+        """一个 Model 的名称 和 其对应 url 的异步生成器
+
+        Args:
+            with_url: 是否返回相应的 url
+        Returns:
+            返回对应的名称列表 或者 名称与url 的列表
+        """
+        urls = cls.scrape_urls()
+        queue: Queue[Union[str, Tuple[str, URL]]] = Queue()  # 存放 Model 的队列
+        signal = Value('i', len(urls))  # 一个用于异步任务同步的信号，初始值为存放所需要爬取的页面数
+
+        async def task(page: URL, s: Value):
+            """包装的爬虫任务"""
+            response = await cls._client_get(page)
+            # 从页面中获取对应的 chaos data (未处理的json格式字符串)
+            chaos_data = re.findall(r'sortable_data\.push\((.*)\);\s*sortable_cur_page', response.text)[0]
+            json_data = json.loads(chaos_data)  # 转为 json
+            for data in json_data:  # 遍历 json
+                data_name = re.findall(r'>(.*)<', data[1])[0]  # 获取 Model 的名称
+                if with_url:  # 如果需要返回对应的 url
+                    data_url = SCRAPE_HOST.join(re.findall(r'\"(.*?)\"', data[0])[0])
+                    await queue.put((data_name, data_url))
+                else:
+                    await queue.put(data_name)
+            signal.value = signal.value - 1  # 信号量减少 1 ，说明该爬虫任务已经完成
+
+        for url in urls:  # 遍历需要爬出的页面
+            asyncio.create_task(task(url, signal))  # 添加爬虫任务
+        while signal.value > 0 or not queue.empty():  # 当还有未完成的爬虫任务或存放数据的队列不为空时
+            yield await queue.get()  # 取出并返回一个存放的 Model
+
+    @classmethod
+    async def get_name_list(cls, *, with_url: bool = False) -> List[Union[str, Tuple[str, URL]]]:
+        """获取全部 Model 的 名称
+
+        Returns:
+            返回能爬到的所有的 Model 的名称所组成的 List
+        """
+        return [i async for i in cls._name_list_generator(with_url=with_url)]
+
+    @classmethod
+    async def get_url_by_name(cls, name: str) -> Optional[URL]:
+        """通过 Model 的名称获取对应的 url
+
+        Args:
+            name: 实列名
+        Returns:
+            若有对应的实列，则返回对应的 url; 若没有, 则返回 None
+        """
+        async for n, url in cls._name_list_generator(with_url=True):
+            if name == n:
+                return url
+
+    @property
+    @abstractmethod
+    def icon(self):
+        """返回此 Model 的图标链接"""

models/wiki/character.py

@@ -0,0 +1,177 @@
+import re
+from typing import List, Optional
+
+from bs4 import BeautifulSoup
+from httpx import URL
+
+from models.wiki.base import Model, SCRAPE_HOST
+from models.wiki.base import WikiModel
+from models.wiki.other import Association, Element, WeaponType
+
+
+class Birth(Model):
+    """生日
+    Attributes:
+        day: 天
+        month: 月
+    """
+    day: int
+    month: int
+
+
+class CharacterAscension(Model):
+    """角色的突破材料
+
+    Attributes:
+        level: 等级突破材料
+        skill: 技能/天赋培养材料
+    """
+    level: List[str] = []
+    skill: List[str] = []
+
+
+class CharacterState(Model):
+    """角色属性值
+
+    Attributes:
+        level: 等级
+        HP: 生命
+        ATK: 攻击力
+        DEF: 防御力
+        CR: 暴击率
+        CD: 暴击伤害
+        bonus: 突破属性
+    """
+    level: str
+    HP: int
+    ATK: float
+    DEF: float
+    CR: str
+    CD: str
+    bonus: str
+
+
+class CharacterIcon(Model):
+    icon: str
+    side: str
+    gacha: str
+    splash: Optional[str]
+
+
+class Character(WikiModel):
+    """角色
+    Attributes:
+        title: 称号
+        occupation: 所属
+        association: 地区
+        weapon_type: 武器类型
+        element: 元素
+        birth: 生日
+        constellation: 命之座
+        cn_cv: 中配
+        jp_cv: 日配
+        en_cv: 英配
+        kr_cv: 韩配
+        description: 描述
+    """
+
+    id: str
+    title: str
+    occupation: str
+    association: Association
+    weapon_type: WeaponType
+    element: Element
+    birth: Optional[Birth]
+    constellation: str
+    cn_cv: str
+    jp_cv: str
+    en_cv: str
+    kr_cv: str
+    description: str
+    ascension: CharacterAscension
+
+    stats: List[CharacterState]
+
+    @classmethod
+    def scrape_urls(cls) -> List[URL]:
+        return [SCRAPE_HOST.join("fam_chars/?lang=CHS")]
+
+    @classmethod
+    async def _parse_soup(cls, soup: BeautifulSoup) -> 'Character':
+        """解析角色页"""
+        soup = soup.select('.wp-block-post-content')[0]
+        tables = soup.find_all('table')
+        table_rows = tables[0].find_all('tr')
+
+        def get_table_text(row_num: int) -> str:
+            """一个快捷函数，用于返回表格对应行的最后一个单元格中的文本"""
+            return table_rows[row_num].find_all('td')[-1].text.replace('\xa0', '')
+
+        id_ = re.findall(r'img/(.*?_\d+)_.*', table_rows[0].find('img').attrs['src'])[0]
+        name = get_table_text(0)
+        if name != '旅行者':  # 如果角色名不是 旅行者
+            title = get_table_text(1)
+            occupation = get_table_text(2)
+            association = Association.convert(get_table_text(3).lower().title())
+            rarity = len(table_rows[4].find_all('img'))
+            weapon_type = WeaponType[get_table_text(5)]
+            element = Element[get_table_text(6)]
+            birth = Birth(day=int(get_table_text(7)), month=int(get_table_text(8)))
+            constellation = get_table_text(10)
+            cn_cv = get_table_text(11)
+            jp_cv = get_table_text(12)
+            en_cv = get_table_text(13)
+            kr_cv = get_table_text(14)
+        else:
+            name = '空' if id_.endswith('5') else '荧'
+            title = get_table_text(0)
+            occupation = get_table_text(1)
+            association = Association.convert(get_table_text(2).lower().title())
+            rarity = len(table_rows[3].find_all('img'))
+            weapon_type = WeaponType[get_table_text(4)]
+            element = Element[get_table_text(5)]
+            birth = None
+            constellation = get_table_text(7)
+            cn_cv = get_table_text(8)
+            jp_cv = get_table_text(9)
+            en_cv = get_table_text(10)
+            kr_cv = get_table_text(11)
+        description = get_table_text(-3)
+        ascension = CharacterAscension(
+            level=[
+                target[0] for i in table_rows[-2].find_all('a')
+                if (target := re.findall(r'/(.*)/', i.attrs['href']))  # 过滤掉错误的材料(honey网页的bug)
+            ],
+            skill=[re.findall(r'/(.*)/', i.attrs['href'])[0] for i in table_rows[-1].find_all('a')]
+        )
+        stats = []
+        for row in tables[2].find_all('tr')[1:]:
+            cells = row.find_all('td')
+            stats.append(
+                CharacterState(
+                    level=cells[0].text, HP=cells[1].text, ATK=cells[2].text, DEF=cells[3].text,
+                    CR=cells[4].text, CD=cells[5].text, bonus=cells[6].text
+                )
+            )
+        return Character(
+            id=id_, name=name, title=title, occupation=occupation, association=association, weapon_type=weapon_type,
+            element=element, birth=birth, constellation=constellation, cn_cv=cn_cv, jp_cv=jp_cv, rarity=rarity,
+            en_cv=en_cv, kr_cv=kr_cv, description=description, ascension=ascension, stats=stats
+        )
+
+    @classmethod
+    async def get_url_by_name(cls, name: str) -> Optional[URL]:
+        # 重写此函数的目的是处理主角名字的 ID
+        _map = {'荧': "playergirl_007", '空': "playerboy_005"}
+        if (id_ := _map.get(name, None)) is not None:
+            return await cls.get_url_by_id(id_)
+        return await super(Character, cls).get_url_by_name(name)
+
+    @property
+    def icon(self) -> CharacterIcon:
+        return CharacterIcon(
+            icon=str(SCRAPE_HOST.join(f'/img/{self.id}_icon.png')),
+            side=str(SCRAPE_HOST.join(f'/img/{self.id}_side_icon.png')),
+            gacha=str(SCRAPE_HOST.join(f'/img/{self.id}_gacha_card.png')),
+            splash=str(SCRAPE_HOST.join(f'/img/{self.id}_gacha_splash.png'))
+        )

models/wiki/characters.py

@@ -1,189 +0,0 @@
-import re
-from typing import Optional
-
-import httpx
-from bs4 import BeautifulSoup
-
-from .helpers import get_headers
-
-
-class Characters:
-    CHARACTERS_LIST_URL = "https://genshin.honeyhunterworld.com/db/char/characters/?lang=CHS"
-    ROOT_URL = "https://genshin.honeyhunterworld.com"
-
-    def __init__(self):
-        self.client = httpx.AsyncClient(headers=get_headers())
-
-    async def _get_soup(self, url: str) -> Optional[BeautifulSoup]:
-        request = await self.client.get(url)
-        return BeautifulSoup(request.text, "lxml")
-
-    async def get_all_characters_url(self):
-        url_list = []
-        soup = await self._get_soup(self.CHARACTERS_LIST_URL)
-        character_list = soup.find_all('div', {'class': 'char_sea_cont'})
-        for character in character_list:
-            name = character.find("span", {"class": "sea_charname"}).text
-            if "旅行者" in name:
-                continue
-            character_link = self.ROOT_URL + character.a['href']
-            url_list.append(character_link)
-        return url_list
-
-    def get_characters_info_template(self):
-        characters_info_dict = {
-            "name": "",
-            "title": "",
-            "rarity": 0,
-            "element": {"name": "", "icon": ""},
-            "description": "",
-            "constellations": {},
-            "skills": {
-                "normal_attack": self.get_skills_info_template(),
-                "skill_e": self.get_skills_info_template(),
-                "skill_q": self.get_skills_info_template(),
-                "skill_replace": self.get_skills_info_template(),
-            },
-            "gacha_splash": ""
-        }
-        return characters_info_dict
-
-    @staticmethod
-    def get_skills_info_template():
-        skills_info_dict = {
-            "icon": "",
-            "name": "",
-            "description": ""
-        }
-        return skills_info_dict
-
-    async def get_characters(self, url: str):
-        characters_info_dict = self.get_characters_info_template()
-        soup = await self._get_soup(url)
-        main_content = soup.find("div", {'class': 'wrappercont'})
-        char_name = main_content.find('div', {'class': 'custom_title'}).text
-        characters_info_dict["name"] = char_name
-        # 基础信息
-        char_info_table = main_content.find('table', {'class': 'item_main_table'}).find_all('tr')
-        for char_info_item in char_info_table:
-            content = char_info_item.find_all('td')
-            if content[0].text == "Title":
-                char_title = content[1].text
-                characters_info_dict["title"] = char_title
-            if content[0].text == "Allegiance":
-                char_allegiance = content[1].text
-                characters_info_dict["allegiance"] = char_allegiance
-            if content[0].text == "Rarity":
-                char_rarity = len(content[1].find_all('div', {'class': 'sea_char_stars_wrap'}))
-                characters_info_dict["rarity"] = char_rarity
-            if content[0].text == "Element":
-                char_element_icon_url = self.ROOT_URL + content[1].find('img')['data-src'].replace("_35", "")
-                characters_info_dict["element"]["icon"] = char_element_icon_url
-            if content[0].text == "Astrolabe Name":
-                char_astrolabe_name = content[1].text
-            if content[0].text == "In-game Description":
-                char_description = content[1].text
-                characters_info_dict["description"] = char_description
-
-        # 角色属性表格 咕咕咕
-        skill_dmg_wrapper = main_content.find('div', {'class': 'skilldmgwrapper'}).find_all('tr')
-
-        # 命之座
-        constellations_title = main_content.find('span', {'class': 'item_secondary_title'}, string="Constellations")
-        constellations_table = constellations_title.findNext('table', {'class': 'item_main_table'}).find_all('tr')
-        constellations_list = []
-        constellations_list_index = 0
-        for index, value in enumerate(constellations_table):
-            # 判断第一行
-            if index % 2 == 0:
-                constellations_dict = {
-                    "icon": "",
-                    "name": "",
-                    "description": ""
-                }
-                constellations_list.append(constellations_dict)
-                icon_url = self.ROOT_URL + value.find_all('img', {'class': 'itempic'})[-1]['data-src']
-                constellations_name = value.find_all('a', href=re.compile("/db/skill"))[-1].text
-                constellations_list[constellations_list_index]["icon"] = icon_url
-                constellations_list[constellations_list_index]["name"] = constellations_name
-            if index % 2 == 1:
-                constellations_description = value.find('div', {'class': 'skill_desc_layout'}).text
-                constellations_list[constellations_list_index]["description"] = constellations_description
-                constellations_list_index += 1
-
-        characters_info_dict["constellations"] = constellations_list
-
-        # 技能
-        skills_title = main_content.find('span', string='Attack Talents')
-
-        # 普攻
-        normal_attack_area = skills_title.find_next_sibling()
-        normal_attack_info = normal_attack_area.find_all('tr')
-        normal_attack_icon = self.ROOT_URL + normal_attack_info[0].find('img', {'class': 'itempic'})['data-src']
-        normal_attack_name = normal_attack_info[0].find('a', href=re.compile('/db/skill/')).text
-        normal_attack_desc = normal_attack_info[1].find('div', {'class': 'skill_desc_layout'}).text.replace(" ", "\n")
-        normal_attack = characters_info_dict["skills"]["normal_attack"]
-        normal_attack["icon"] = normal_attack_icon
-        normal_attack["name"] = normal_attack_name
-        normal_attack["description"] = normal_attack_desc
-
-        normal_attack_table_area = normal_attack_area.find_next_sibling()
-        # normal_attack_table = normal_attack_table_area.find_all('tr')
-
-        skill_e_area = normal_attack_table_area.find_next_sibling()
-        skill_e_info = skill_e_area.find_all('tr')
-        skill_e_icon = self.ROOT_URL + skill_e_info[0].find('img', {'class': 'itempic'})['data-src']
-        skill_e_name = skill_e_info[0].find('a', href=re.compile('/db/skill/')).text
-        skill_e_desc = skill_e_info[1].find('div', {'class': 'skill_desc_layout'}).text.replace(" ", "\n")
-        skill_e = characters_info_dict["skills"]["skill_e"]
-        skill_e["icon"] = skill_e_icon
-        skill_e["name"] = skill_e_name
-        skill_e["description"] = skill_e_desc
-
-        skill_e_table_area = skill_e_area.find_next_sibling()
-        # skillE_table = skillE_table_area.find_all('tr')
-
-        load_another_talent_q: bool = False
-        if char_name in ("神里绫华", "莫娜"):
-            load_another_talent_q = True
-
-        skill_q_area = skill_e_table_area.find_next_sibling()
-        skill_q_info = skill_q_area.find_all('tr')
-        skill_q_icon = self.ROOT_URL + skill_q_info[0].find('img', {'class': 'itempic'})['data-src']
-        skill_q_name = skill_q_info[0].find('a', href=re.compile('/db/skill/')).text
-        skill_q_desc = skill_q_info[1].find('div', {'class': 'skill_desc_layout'}).text.replace(" ", "\n")
-        skill_q_table_area = skill_q_area.find_next_sibling()
-        # skill_q_table = skill_q_table_area.find_all('tr')
-
-        if load_another_talent_q:
-            skill_replace = characters_info_dict["skills"]["skill_replace"]
-            skill_replace["icon"] = skill_q_icon
-            skill_replace["name"] = skill_q_name
-            skill_replace["description"] = skill_q_desc
-        else:
-            skill_q = characters_info_dict["skills"]["skill_q"]
-            skill_q["icon"] = skill_q_icon
-            skill_q["name"] = skill_q_name
-            skill_q["description"] = skill_q_desc
-
-        if load_another_talent_q:
-            skill_q2_area = skill_q_table_area.find_next_sibling()
-            skill_q2_info = skill_q2_area.find_all('tr')
-            skill_q2_icon = self.ROOT_URL + skill_q2_info[0].find('img', {'class': 'itempic'})['data-src']
-            skill_q2_name = skill_q2_info[0].find('a', href=re.compile('/db/skill/')).text
-            skill_q2_desc = skill_q2_info[1].find('div', {'class': 'skill_desc_layout'}).text.replace(" ", "\n")
-            skill_q2 = characters_info_dict["skills"]["skill_q"]
-            skill_q2["icon"] = skill_q2_icon
-            skill_q2["name"] = skill_q2_name
-            skill_q2["description"] = skill_q2_desc
-
-        # 角色图片
-        char_pic_area = main_content.find('span', string='Character Gallery').find_next_sibling()
-        all_char_pic = char_pic_area.find("div", {"class": "gallery_cont"})
-
-        gacha_splash_text = all_char_pic.find("span", {"class": "gallery_cont_span"}, string="Gacha Splash")
-        gacha_splash_pic_url = self.ROOT_URL + gacha_splash_text.previous_element.previous_element["data-src"].replace(
-            "_70", "")
-        characters_info_dict["gacha_splash"] = gacha_splash_pic_url
-
-        return characters_info_dict

models/wiki/helpers.py

@@ -1,27 +0,0 @@
-import re
-
-ID_RGX = re.compile(r"/db/[^.]+_(?P<id>\d+)")
-
-
-def get_headers():
-    headers = {
-        "accept": "text/html,application/xhtml+xml,application/xml;"
-                  "q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
-                      "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.5005.63 Safari/537.36",
-        "referer": "https://genshin.honeyhunterworld.com/db/char/hutao/?lang=CHS",
-    }
-    return headers
-
-
-def get_id_form_url(url: str):
-    matches = ID_RGX.search(url)
-    if matches is None:
-        return -1
-    entries = matches.groupdict()
-    if entries is None:
-        return -1
-    try:
-        return int(entries.get('id'))
-    except (IndexError, ValueError, TypeError):
-        return -1

models/wiki/material.py

@@ -0,0 +1,57 @@
+import re
+from typing import List
+
+from bs4 import BeautifulSoup
+from httpx import URL
+from typing_extensions import Self
+
+from models.wiki.base import SCRAPE_HOST, WikiModel
+
+__all__ = ['Material']
+
+
+class Material(WikiModel):
+    """材料
+
+    Attributes:
+        type: 类型
+        source: 获取方式
+        description: 描述
+        serise: 材料系列
+    """
+
+    type: str
+    source: List[str]
+    description: str
+
+    @staticmethod
+    def scrape_urls() -> List[URL]:
+        return [SCRAPE_HOST.join(f'fam_wep_{i}/?lang=CHS') for i in ['primary', 'secondary', 'common']]
+
+    @classmethod
+    async def _parse_soup(cls, soup: BeautifulSoup) -> Self:
+        """解析材料页"""
+        soup = soup.select('.wp-block-post-content')[0]
+        tables = soup.find_all('table')
+        table_rows = tables[0].find_all('tr')
+
+        def get_table_text(row_num: int) -> str:
+            """一个快捷函数，用于返回表格对应行的最后一个单元格中的文本"""
+            return table_rows[row_num].find_all('td')[-1].text.replace('\xa0', '')
+
+        id_ = re.findall(r'/img/(.*?)\.webp', str(table_rows[0]))[0]
+        name = get_table_text(0)
+        rarity = len(table_rows[3].find_all('img'))
+        type_ = get_table_text(1)
+        source = list(
+            filter(
+                lambda x: x,  # filter 在这里的作用是过滤掉为空的数据
+                table_rows[-2].find_all('td')[-1].encode_contents().decode().split('<br/>')
+            )
+        )
+        description = get_table_text(-1)
+        return Material(id=id_, name=name, rarity=rarity, type=type_, source=source, description=description)
+
+    @property
+    def icon(self) -> str:
+        return str(SCRAPE_HOST.join(f'/img/{self.id}.png'))

models/wiki/metadata/weapon_level.json

@@ -0,0 +1,362 @@
+[
+    {
+        "level": 1,
+        "requiredExps": [125, 175, 275, 400, 600]
+    },
+    {
+        "level": 2,
+        "requiredExps": [200, 275, 425, 625, 950]
+    },
+    {
+        "level": 3,
+        "requiredExps": [275, 400, 600, 900, 1350]
+    },
+    {
+        "level": 4,
+        "requiredExps": [350, 550, 800, 1200, 1800]
+    },
+    {
+        "level": 5,
+        "requiredExps": [475, 700, 1025, 1550, 2325]
+    },
+    {
+        "level": 6,
+        "requiredExps": [575, 875, 1275, 1950, 2925]
+    },
+    {
+        "level": 7,
+        "requiredExps": [700, 1050, 1550, 2350, 3525]
+    },
+    {
+        "level": 8,
+        "requiredExps": [850, 1250, 1850, 2800, 4200]
+    },
+    {
+        "level": 9,
+        "requiredExps": [1000, 1475, 2175, 3300, 4950]
+    },
+    {
+        "level": 10,
+        "requiredExps": [1150, 1700, 2500, 3800, 5700]
+    },
+    {
+        "level": 11,
+        "requiredExps": [1300, 1950, 2875, 4350, 6525]
+    },
+    {
+        "level": 12,
+        "requiredExps": [1475, 2225, 3250, 4925, 7400]
+    },
+    {
+        "level": 13,
+        "requiredExps": [1650, 2475, 3650, 5525, 8300]
+    },
+    {
+        "level": 14,
+        "requiredExps": [1850, 2775, 4050, 6150, 9225]
+    },
+    {
+        "level": 15,
+        "requiredExps": [2050, 3050, 4500, 6800, 10200]
+    },
+    {
+        "level": 16,
+        "requiredExps": [2250, 3375, 4950, 7500, 11250]
+    },
+    {
+        "level": 17,
+        "requiredExps": [2450, 3700, 5400, 8200, 12300]
+    },
+    {
+        "level": 18,
+        "requiredExps": [2675, 4025, 5900, 8950, 13425]
+    },
+    {
+        "level": 19,
+        "requiredExps": [2925, 4375, 6425, 9725, 14600]
+    },
+    {
+        "level": 20,
+        "requiredExps": [3150, 4725, 6925, 10500, 15750]
+    },
+    {
+        "level": 21,
+        "requiredExps": [3575, 5350, 7850, 11900, 17850]
+    },
+    {
+        "level": 22,
+        "requiredExps": [3825, 5750, 8425, 12775, 19175]
+    },
+    {
+        "level": 23,
+        "requiredExps": [4100, 6175, 9050, 13700, 20550]
+    },
+    {
+        "level": 24,
+        "requiredExps": [4400, 6600, 9675, 14650, 21975]
+    },
+    {
+        "level": 25,
+        "requiredExps": [4700, 7025, 10325, 15625, 23450]
+    },
+    {
+        "level": 26,
+        "requiredExps": [5000, 7475, 10975, 16625, 24950]
+    },
+    {
+        "level": 27,
+        "requiredExps": [5300, 7950, 11650, 17650, 26475]
+    },
+    {
+        "level": 28,
+        "requiredExps": [5600, 8425, 12350, 18700, 28050]
+    },
+    {
+        "level": 29,
+        "requiredExps": [5925, 8900, 13050, 19775, 29675]
+    },
+    {
+        "level": 30,
+        "requiredExps": [6275, 9400, 13800, 20900, 31350]
+    },
+    {
+        "level": 31,
+        "requiredExps": [6600, 9900, 14525, 22025, 33050]
+    },
+    {
+        "level": 32,
+        "requiredExps": [6950, 10450, 15300, 23200, 34800]
+    },
+    {
+        "level": 33,
+        "requiredExps": [7325, 10975, 16100, 24375, 36575]
+    },
+    {
+        "level": 34,
+        "requiredExps": [7675, 11525, 16900, 25600, 38400]
+    },
+    {
+        "level": 35,
+        "requiredExps": [8050, 12075, 17700, 26825, 40250]
+    },
+    {
+        "level": 36,
+        "requiredExps": [8425, 12650, 18550, 28100, 42150]
+    },
+    {
+        "level": 37,
+        "requiredExps": [8825, 13225, 19400, 29400, 44100]
+    },
+    {
+        "level": 38,
+        "requiredExps": [9225, 13825, 20275, 30725, 46100]
+    },
+    {
+        "level": 39,
+        "requiredExps": [9625, 14425, 21175, 32075, 48125]
+    },
+    {
+        "level": 40,
+        "requiredExps": [10025, 15050, 22050, 33425, 50150]
+    },
+    {
+        "level": 41,
+        "requiredExps": [10975, 16450, 24150, 36575, 54875]
+    },
+    {
+        "level": 42,
+        "requiredExps": [11425, 17125, 25125, 38075, 57125]
+    },
+    {
+        "level": 43,
+        "requiredExps": [11875, 17825, 26125, 39600, 59400]
+    },
+    {
+        "level": 44,
+        "requiredExps": [12350, 18525, 27150, 41150, 61725]
+    },
+    {
+        "level": 45,
+        "requiredExps": [12825, 19225, 28200, 42725, 64100]
+    },
+    {
+        "level": 46,
+        "requiredExps": [13300, 19950, 29250, 44325, 66500]
+    },
+    {
+        "level": 47,
+        "requiredExps": [13775, 20675, 30325, 45950, 68925]
+    },
+    {
+        "level": 48,
+        "requiredExps": [14275, 21425, 31425, 47600, 71400]
+    },
+    {
+        "level": 49,
+        "requiredExps": [14800, 22175, 32550, 49300, 73950]
+    },
+    {
+        "level": 50,
+        "requiredExps": [15300, 22950, 33650, 51000, 76500]
+    },
+    {
+        "level": 51,
+        "requiredExps": [16625, 24925, 36550, 55375, 83075]
+    },
+    {
+        "level": 52,
+        "requiredExps": [17175, 25750, 37775, 57225, 85850]
+    },
+    {
+        "level": 53,
+        "requiredExps": [17725, 26600, 39000, 59100, 88650]
+    },
+    {
+        "level": 54,
+        "requiredExps": [18300, 27450, 40275, 61025, 91550]
+    },
+    {
+        "level": 55,
+        "requiredExps": [18875, 28325, 41550, 62950, 94425]
+    },
+    {
+        "level": 56,
+        "requiredExps": [19475, 29225, 42850, 64925, 97400]
+    },
+    {
+        "level": 57,
+        "requiredExps": [20075, 30100, 44150, 66900, 100350]
+    },
+    {
+        "level": 58,
+        "requiredExps": [20675, 31025, 45500, 68925, 103400]
+    },
+    {
+        "level": 59,
+        "requiredExps": [21300, 31950, 46850, 70975, 106475]
+    },
+    {
+        "level": 60,
+        "requiredExps": [21925, 32875, 48225, 73050, 109575]
+    },
+    {
+        "level": 61,
+        "requiredExps": [23675, 35500, 52075, 78900, 118350]
+    },
+    {
+        "level": 62,
+        "requiredExps": [24350, 36500, 53550, 81125, 121700]
+    },
+    {
+        "level": 63,
+        "requiredExps": [25025, 37525, 55050, 83400, 125100]
+    },
+    {
+        "level": 64,
+        "requiredExps": [25700, 38575, 56550, 85700, 128550]
+    },
+    {
+        "level": 65,
+        "requiredExps": [26400, 39600, 58100, 88025, 132050]
+    },
+    {
+        "level": 66,
+        "requiredExps": [27125, 40675, 59650, 90375, 135575]
+    },
+    {
+        "level": 67,
+        "requiredExps": [27825, 41750, 61225, 92750, 139125]
+    },
+    {
+        "level": 68,
+        "requiredExps": [28550, 42825, 62800, 95150, 142725]
+    },
+    {
+        "level": 69,
+        "requiredExps": [29275, 43900, 64400, 97575, 146375]
+    },
+    {
+        "level": 70,
+        "requiredExps": [30025, 45025, 66025, 100050, 150075]
+    },
+    {
+        "level": 71,
+        "requiredExps": [32300, 48450, 71075, 107675, 161525]
+    },
+    {
+        "level": 72,
+        "requiredExps": [33100, 49650, 72825, 110325, 165500]
+    },
+    {
+        "level": 73,
+        "requiredExps": [33900, 50850, 74575, 113000, 169500]
+    },
+    {
+        "level": 74,
+        "requiredExps": [34700, 52075, 76350, 115700, 173550]
+    },
+    {
+        "level": 75,
+        "requiredExps": [35525, 53300, 78150, 118425, 177650]
+    },
+    {
+        "level": 76,
+        "requiredExps": [36350, 54550, 80000, 121200, 181800]
+    },
+    {
+        "level": 77,
+        "requiredExps": [37200, 55800, 81850, 124000, 186000]
+    },
+    {
+        "level": 78,
+        "requiredExps": [38050, 57075, 83700, 126825, 190250]
+    },
+    {
+        "level": 79,
+        "requiredExps": [38900, 58350, 85575, 129675, 194525]
+    },
+    {
+        "level": 80,
+        "requiredExps": [39775, 59650, 87500, 132575, 198875]
+    },
+    {
+        "level": 81,
+        "requiredExps": [46950, 70425, 103275, 156475, 234725]
+    },
+    {
+        "level": 82,
+        "requiredExps": [52775, 79150, 116075, 175875, 263825]
+    },
+    {
+        "level": 83,
+        "requiredExps": [59275, 88925, 130425, 197600, 296400]
+    },
+    {
+        "level": 84,
+        "requiredExps": [66600, 99900, 146500, 221975, 332975]
+    },
+    {
+        "level": 85,
+        "requiredExps": [74800, 112175, 164550, 249300, 373950]
+    },
+    {
+        "level": 86,
+        "requiredExps": [83975, 125975, 184775, 279950, 419925]
+    },
+    {
+        "level": 87,
+        "requiredExps": [94275, 141425, 207400, 314250, 471375]
+    },
+    {
+        "level": 88,
+        "requiredExps": [105800, 158725, 232775, 352700, 529050]
+    },
+    {
+        "level": 89,
+        "requiredExps": [118725, 178100, 261200, 395775, 593675]
+    },
+    {
+        "level": 90,
+        "requiredExps": [133200, 199800, 293050, 444025, 666050]
+    }
+]

models/wiki/other.py

@@ -0,0 +1,132 @@
+from enum import Enum
+from typing import Optional
+
+from typing_extensions import Self
+
+from models.wiki.base import SCRAPE_HOST
+
+__all__ = [
+    'Element',
+    'WeaponType',
+    'AttributeType',
+    'Association',
+]
+
+
+class Element(Enum):
+    """元素"""
+    Pyro = '火'
+    Hydro = '水'
+    Electro = '雷'
+    Cryo = '冰'
+    Dendro = '草'
+    Anemo = '风'
+    Geo = '岩'
+    Multi = '无'  # 主角
+
+
+_WEAPON_ICON_MAP = {
+    'Sword': SCRAPE_HOST.join('img/s_23101.png'),
+    'Claymore': SCRAPE_HOST.join('img/s_163101.png'),
+    'Polearm': SCRAPE_HOST.join('img/s_233101.png'),
+    'Catalyst': SCRAPE_HOST.join('img/s_43101.png'),
+    'Bow': SCRAPE_HOST.join('img/s_213101.png'),
+}
+
+
+class WeaponType(Enum):
+    """武器类型"""
+    Sword = '单手剑'
+    Claymore = '双手剑'
+    Polearm = '长柄武器'
+    Catalyst = '法器'
+    Bow = '弓'
+
+    def icon_url(self) -> str:
+        return str(_WEAPON_ICON_MAP.get(self.name))
+
+
+_ATTR_TYPE_MAP = {
+    # 这个字典用于将 Honey 页面中遇到的 属性的缩写的字符 转为 AttributeType 的字符
+    # 例如 Honey 页面上写的 HP% 则对应 HP_p
+    "HP": ['Health'],
+    "HP_p": ['HP%', 'Health %'],
+    "ATK": ['Attack'],
+    "ATK_p": ['Atk%', 'Attack %'],
+    "DEF": ['Defense'],
+    "DEF_p": ['Def%', 'Defense %'],
+    "EM": ['Elemental Mastery'],
+    "ER": ['ER%', 'Energy Recharge %'],
+    "CR": ['CrR%', 'Critical Rate %', 'CritRate%'],
+    "CD": ['Crd%', 'Critical Damage %', 'CritDMG%'],
+    "PD": ['Phys%', 'Physical Damage %'],
+    "HB": [],
+    "Pyro": [],
+    "Hydro": [],
+    "Electro": [],
+    "Cryo": [],
+    "Dendro": [],
+    "Anemo": [],
+    "Geo": [],
+}
+
+
+class AttributeType(Enum):
+    """属性枚举类。包含了武器和圣遗物的属性。"""
+    HP = "生命"
+    HP_p = "生命%"
+    ATK = "攻击力"
+    ATK_p = "攻击力%"
+    DEF = "防御力"
+    DEF_p = "防御力%"
+    EM = "元素精通"
+    ER = "元素充能效率"
+    CR = "暴击率"
+    CD = "暴击伤害"
+    PD = "物理伤害加成"
+    HB = "治疗加成"
+    Pyro = '火元素伤害加成'
+    Hydro = '水元素伤害加成'
+    Electro = '雷元素伤害加成'
+    Cryo = '冰元素伤害加成'
+    Dendro = '草元素伤害加成'
+    Anemo = '风元素伤害加成'
+    Geo = '岩元素伤害加成'
+
+    @classmethod
+    def convert(cls, string: str) -> Optional[Self]:
+        string = string.strip()
+        for k, v in _ATTR_TYPE_MAP.items():
+            if string == k or string in v or string.upper() == k:
+                return cls[k]
+
+
+_ASSOCIATION_MAP = {
+    'Other': ['Mainactor', 'Ranger', 'Fatui'],
+    'Snezhnaya': [],
+    'Sumeru': [],
+    'Inazuma': [],
+    'Liyue': [],
+    'Mondstadt': [],
+}
+
+
+class Association(Enum):
+    """角色所属地区"""
+    Other = '其它'
+    Snezhnaya = '至冬'
+    Sumeru = '须弥'
+    Inazuma = '稻妻'
+    Liyue = '璃月'
+    Mondstadt = '蒙德'
+
+    @classmethod
+    def convert(cls, string: str) -> Optional[Self]:
+        string = string.strip()
+        for k, v in _ASSOCIATION_MAP.items():
+            if string == k or string in v:
+                return cls[k]
+            string = string.lower().title()
+            if string == k or string in v:
+                return cls[k]
+        return cls[string]

models/wiki/weapon.py

@@ -0,0 +1,143 @@
+import itertools
+import re
+from typing import List, Optional, Tuple, Union
+
+from bs4 import BeautifulSoup
+from httpx import URL
+
+from models.wiki.base import Model, SCRAPE_HOST, WikiModel
+from models.wiki.other import AttributeType, WeaponType
+
+__all__ = ['Weapon', 'WeaponAffix', 'WeaponAttribute']
+
+
+class WeaponAttribute(Model):
+    """武器词条"""
+    type: AttributeType
+    value: str
+
+
+class WeaponAffix(Model):
+    """武器技能
+
+    Attributes:
+        name: 技能名
+        description: 技能描述
+
+    """
+    name: str
+    description: List[str]
+
+
+class WeaponState(Model):
+    level: str
+    ATK: float
+    bonus: Optional[str]
+
+
+class WeaponIcon(Model):
+    icon: str
+    awakened: str
+    gacha: str
+
+
+class Weapon(WikiModel):
+    """武器
+
+    Attributes:
+        type: 武器类型
+        attack: 基础攻击力
+        attribute:
+        affix: 武器技能
+        description: 描述
+        ascension: 突破材料
+        story: 武器故事
+    """
+
+    weapon_type: WeaponType
+    attack: float
+    attribute: Optional[WeaponAttribute]
+    affix: Optional[WeaponAffix]
+    description: str
+    ascension: List[str]
+    story: Optional[str]
+
+    stats: List[WeaponState]
+
+    @staticmethod
+    def scrape_urls() -> List[URL]:
+        return [SCRAPE_HOST.join(f"fam_{i.lower()}/?lang=CHS") for i in WeaponType.__members__]
+
+    @classmethod
+    async def _parse_soup(cls, soup: BeautifulSoup) -> 'Weapon':
+        """解析武器页"""
+        soup = soup.select('.wp-block-post-content')[0]
+        tables = soup.find_all('table')
+        table_rows = tables[0].find_all('tr')
+
+        def get_table_text(row_num: int) -> str:
+            """一个快捷函数，用于返回表格对应行的最后一个单元格中的文本"""
+            return table_rows[row_num].find_all('td')[-1].text.replace('\xa0', '')
+
+        def find_table(select: str):
+            """一个快捷函数，用于寻找对应表格头的表格"""
+            return list(filter(lambda x: select in ' '.join(x.attrs['class']), tables))
+
+        id_ = re.findall(r'/img/(.*?)_gacha', str(table_rows[0]))[0]
+        weapon_type = WeaponType[get_table_text(1).split(',')[-1].strip()]
+        name = get_table_text(0)
+        rarity = len(table_rows[2].find_all('img'))
+        attack = float(get_table_text(4))
+        ascension = [re.findall(r'/(.*)/', tag.attrs['href'])[0] for tag in table_rows[-1].find_all('a')]
+        if rarity > 2:  # 如果是 3 星及其以上的武器
+            attribute = WeaponAttribute(
+                type=AttributeType.convert(
+                    tables[2].find('thead').find('tr').find_all('td')[2].text.split(' ')[1]
+                ),
+                value=get_table_text(6)
+            )
+            affix = WeaponAffix(name=get_table_text(7), description=[
+                i.find_all('td')[1].text for i in tables[3].find_all('tr')[1:]
+            ])
+            if len(tables) < 11:
+                description = get_table_text(-1)
+            else:
+                description = get_table_text(9)
+            if story_table := find_table('quotes'):
+                story = story_table[0].text.strip()
+            else:
+                story = None
+        else:  # 如果是 2 星及其以下的武器
+            attribute = affix = None
+            description = get_table_text(5)
+            story = tables[-1].text.strip()
+        stats = []
+        for row in tables[2].find_all('tr')[1:]:
+            cells = row.find_all('td')
+            if rarity > 2:
+                stats.append(WeaponState(level=cells[0].text, ATK=cells[1].text, bonus=cells[2].text))
+            else:
+                stats.append(WeaponState(level=cells[0].text, ATK=cells[1].text))
+        return Weapon(
+            id=id_, name=name, rarity=rarity, attack=attack, attribute=attribute, affix=affix, weapon_type=weapon_type,
+            story=story, stats=stats, description=description, ascension=ascension
+        )
+
+    @classmethod
+    async def get_name_list(cls, *, with_url: bool = False) -> List[Union[str, Tuple[str, URL]]]:
+        # 重写此函数的目的是名字去重，例如单手剑页面中有三个 “「一心传」名刀”
+        name_list = [i async for i in cls._name_list_generator(with_url=with_url)]
+        if with_url:
+            return [
+                (i[0], list(i[1])[0][1]) for i in itertools.groupby(name_list, lambda x: x[0])
+            ]
+        else:
+            return [i[0] for i in itertools.groupby(name_list, lambda x: x)]
+
+    @property
+    def icon(self) -> WeaponIcon:
+        return WeaponIcon(
+            icon=str(SCRAPE_HOST.join(f'/img/{self.id}.png')),
+            awakened=str(SCRAPE_HOST.join(f'/img/{self.id}_awaken_icon.png')),
+            gacha=str(SCRAPE_HOST.join(f'/img/{self.id}_gacha_icon.png')),
+        )

models/wiki/weapons.py

@@ -1,210 +0,0 @@
-import os
-from enum import Enum
-from typing import Optional
-
-import httpx
-import ujson
-from bs4 import BeautifulSoup
-
-from .helpers import get_headers, get_id_form_url
-
-
-class WeaponType(Enum):
-    Sword = "sword"  # 单手剑
-    Claymore = "claymore"  # 双手剑
-    PoleArm = "polearm"  # 长柄武器
-    Bow = "bow"  # 弓
-    Catalyst = "catalyst"  # 法器
-
-
-class Weapons:
-    IGNORE_WEAPONS_ID = [
-        "1001", "1101", "1406",
-        "2001", "2101", "2204", "2406", "2407",
-        "3001", "3101", "3204", "3404",
-        "4001", "4101", "4201", "4403", "4405", "4406",
-        "5001", "5101", "5201", "5404", "5404", "5405",
-    ]  # 忽略的武器包括一星、二星武器，beta表格内无名武器，未上架到正服的武器
-
-    # 根地址
-    ROOT_URL = "https://genshin.honeyhunterworld.com"
-
-    TEXT_MAPPING = {
-        "Type": "类型",
-        "Rarity": "Rarity",
-        "Base Attack": "基础攻击力"
-    }
-
-    WEAPON_TYPE_MAPPING = {
-        "Sword": "https://genshin.honeyhunterworld.com/img/skills/s_33101.png",  # 单手剑
-        "Claymore": "https://genshin.honeyhunterworld.com/img/skills/s_163101.png",  # 双手剑
-        "Polearm": "https://genshin.honeyhunterworld.com/img/skills/s_233101.png",  # 长枪
-        "Bow": "https://genshin.honeyhunterworld.com/img/skills/s_213101.png",  # 弓箭
-        "Catalyst": "https://genshin.honeyhunterworld.com/img/skills/s_43101.png",  # 法器
-    }
-
-    def __init__(self):
-        self.client = httpx.AsyncClient(headers=get_headers())
-        project_path = os.path.dirname(__file__)
-        characters_file = os.path.join(project_path, "metadata", "ascension.json")
-        monster_file = os.path.join(project_path, "metadata", "monster.json")
-        elite_file = os.path.join(project_path, "metadata", "elite.json")
-        with open(characters_file, "r", encoding="utf-8") as f:
-            self._ascension_json: dict = ujson.load(f)
-        with open(monster_file, "r", encoding="utf-8") as f:
-            self._monster_json: dict = ujson.load(f)
-        with open(elite_file, "r", encoding="utf-8") as f:
-            self._elite_json: dict = ujson.load(f)
-
-    async def _get_soup(self, url: str) -> Optional[BeautifulSoup]:
-        request = await self.client.get(url)
-        return BeautifulSoup(request.text, "lxml")
-
-    async def get_weapon_url_list(self, weapon_type: WeaponType):
-        weapon_url_list = []
-        url = self.ROOT_URL + f"/db/weapon/{weapon_type.value}/?lang=CHS"
-        soup = await self._get_soup(url)
-        weapon_table = soup.find("span", {"class": "item_secondary_title"},
-                                 string="Released (Codex) Weapons").find_next_sibling()
-        weapon_table_rows = weapon_table.find_all("tr")
-        for weapon_table_row in weapon_table_rows:
-            content = weapon_table_row.find_all("td")[2]
-            if content.find("a") is not None:
-                weapon_url = self.ROOT_URL + content.find("a")["href"]
-                weapon_id = str(get_id_form_url(weapon_url))
-                if weapon_id not in self.IGNORE_WEAPONS_ID:
-                    weapon_url_list.append(weapon_url)
-        return weapon_url_list
-
-    async def get_all_weapon_url(self):
-        all_weapon_url = []
-        temp_data = await self.get_weapon_url_list(WeaponType.Bow)
-        all_weapon_url.extend(temp_data)
-        temp_data = await self.get_weapon_url_list(WeaponType.Sword)
-        all_weapon_url.extend(temp_data)
-        temp_data = await self.get_weapon_url_list(WeaponType.PoleArm)
-        all_weapon_url.extend(temp_data)
-        temp_data = await self.get_weapon_url_list(WeaponType.Catalyst)
-        all_weapon_url.extend(temp_data)
-        temp_data = await self.get_weapon_url_list(WeaponType.Claymore)
-        all_weapon_url.extend(temp_data)
-        return all_weapon_url
-
-    @staticmethod
-    def get_weapon_info_template():
-        weapon_info_dict = {
-            "name": "",
-            "description": "",
-            "source_img": "",
-            "atk":
-                {
-                    "min": 0,
-                    "max": 999999,
-                    "name": "基础攻击力"
-                },
-            "secondary":
-                {
-                    "min": 0.1,
-                    "max": 999999.9,
-                    "name": ""
-                },
-            "star":
-                {
-                    "value": -1,
-                    "icon": ""
-                },
-            "type":
-                {
-                    "name": "",
-                    "icon": ""
-                },
-            "passive_ability":
-                {
-                    "name": "",
-                    "description": ""
-                }
-        }
-        materials_dict = {
-            "name": "",
-            "star": {
-                "value": 0,
-                "icon": ""
-            },
-            "city": "",
-            "icon": ""
-        }
-        weapon_info_dict["materials"] = {
-            "ascension": materials_dict,
-            "elite": materials_dict,
-            "monster": materials_dict,
-        }
-        return weapon_info_dict
-
-    async def get_weapon_info(self, url: str):
-        weapon_info_dict = self.get_weapon_info_template()
-        soup = await self._get_soup(url)
-        weapon_content = soup.find("div", {"class": "wrappercont"})
-        data = weapon_content.find("div", {"class": "data_cont_wrapper", "style": "display: block"})
-        weapon_info = data.find("table", {"class": "item_main_table"})
-        weapon_name = weapon_content.find("div", {"class": "custom_title"}).text.replace("-", "").replace(" ", "")
-        weapon_info_dict["name"] = weapon_name
-        weapon_info_row = weapon_info.find_all("tr")
-        for weapon_info_ in weapon_info_row:
-            content = weapon_info_.find_all("td")
-            if len(content) == 3:  # 第一行会有三个td，其中一个td是武器图片
-                weapon_info_dict["source_img"] = self.ROOT_URL + content[0].find("img",
-                                                                                 {"class": "itempic lazy"})["data-src"]
-                weapon_info_dict["type"]["name"] = content[2].text
-                weapon_info_dict["type"]["icon"] = self.get_weapon_type(content[2].text)
-            elif len(content) == 2:
-                if content[0].text == "Rarity":
-                    weapon_info_dict["star"]["value"] = len(
-                        content[1].find_all("div", {"class": "sea_char_stars_wrap"}))
-                elif content[0].text == "Special (passive) Ability":
-                    weapon_info_dict["passive_ability"]["name"] = content[1].text
-                elif content[0].text == "Special (passive) Ability Description":
-                    weapon_info_dict["passive_ability"]["description"] = content[1].text
-                elif content[0].text == "In-game Description":
-                    weapon_info_dict["description"] = content[1].text
-                elif content[0].text == "Secondary Stat":
-                    weapon_info_dict["secondary"]["name"] = content[1].text
-
-        stat_table = data.find("span", {"class": "item_secondary_title"},
-                               string=" Stat Progression ").find_next_sibling()
-        stat_table_row = stat_table.find_all("tr")
-        for stat_table_ in stat_table_row:
-            content = stat_table_.find_all("td")
-            # 通过等级判断
-            if content[0].text == "1":
-                weapon_info_dict["atk"]["min"] = int(content[1].text)
-                weapon_info_dict["secondary"]["min"] = float(content[2].text)
-            elif content[0].text == "80+":
-                item_hrefs = content[3].find_all("a")
-                for item_href in item_hrefs:
-                    item_id = get_id_form_url(item_href["href"])
-                    ascension = self.get_ascension(str(item_id))
-                    if ascension.get("name") is not None:
-                        weapon_info_dict["materials"]["ascension"] = ascension
-                    monster = self.get_monster(str(item_id))
-                    if monster.get("name") is not None:
-                        weapon_info_dict["materials"]["monster"] = monster
-                    elite = self.get_elite(str(item_id))
-                    if elite.get("name") is not None:
-                        weapon_info_dict["materials"]["elite"] = elite
-            elif content[0].text == "90":
-                weapon_info_dict["atk"]["max"] = int(content[1].text)
-                weapon_info_dict["secondary"]["max"] = float(content[2].text)
-
-        return weapon_info_dict
-
-    def get_ascension(self, item_id: str):
-        return self._ascension_json.get(item_id, {})
-
-    def get_monster(self, item_id: str):
-        return self._monster_json.get(item_id, {})
-
-    def get_elite(self, item_id: str):
-        return self._elite_json.get(item_id, {})
-
-    def get_weapon_type(self, weapon_type: str):
-        return self.WEAPON_TYPE_MAPPING.get(weapon_type, "")

plugins/genshin/weapon.py

@@ -1,11 +1,13 @@
-from telegram import Update, InlineKeyboardButton, InlineKeyboardMarkup
+from telegram import InlineKeyboardButton, InlineKeyboardMarkup, Update
 from telegram.constants import ChatAction
-from telegram.ext import filters, CommandHandler, MessageHandler, CallbackContext
+from telegram.ext import CallbackContext, CommandHandler, MessageHandler, filters
 
 from core.template.services import TemplateService
 from core.wiki.services import WikiService
 from logger import Log
 from metadata.shortname import weaponToName
+from models.wiki.base import SCRAPE_HOST
+from models.wiki.weapon import Weapon
 from plugins.base import BasePlugins
 from utils.bot import get_all_args
 from utils.decorators.error import error_callable
@@ -16,10 +18,12 @@ from utils.service.inject import inject
 
 
 @listener_plugins_class()
-class Weapon(BasePlugins):
+class WeaponPlugin(BasePlugins):
     """武器查询"""
 
-    KEYBOARD = [[InlineKeyboardButton(text="查看武器列表并查询", switch_inline_query_current_chat="查看武器列表并查询")]]
+    KEYBOARD = [[
+        InlineKeyboardButton(text="查看武器列表并查询", switch_inline_query_current_chat="查看武器列表并查询")
+    ]]
 
     @inject
     def __init__(self, template_service: TemplateService, wiki_service: WikiService):
@@ -52,7 +56,7 @@ class Weapon(BasePlugins):
         weapon_name = weaponToName(weapon_name)
         weapons_list = await self.wiki_service.get_weapons_list()
         for weapon in weapons_list:
-            if weapon["name"] == weapon_name:
+            if weapon.name == weapon_name:
                 weapon_data = weapon
                 break
         else:
@@ -65,27 +69,44 @@ class Weapon(BasePlugins):
         Log.info(f"用户 {user.full_name}[{user.id}] 查询武器命令请求 || 参数 {weapon_name}")
         await message.reply_chat_action(ChatAction.TYPING)
 
-        async def input_template_data(_weapon_data):
+        async def input_template_data(_weapon_data: Weapon):
-            _template_data = {
+            if weapon.rarity > 2:
-                "weapon_name": _weapon_data["name"],
+                bonus = _weapon_data.stats[-1].bonus
-                "weapon_info_type_img": await url_to_file(_weapon_data["type"]["icon"]),
+                if '%' in bonus:
-                "progression_secondary_stat_value": _weapon_data["secondary"]["max"],
+                    bonus = str(round(float(bonus.rstrip('%')))) + '%'
-                "progression_secondary_stat_name": _weapon_data["secondary"]["name"],
+                else:
-                "weapon_info_source_img": await url_to_file(_weapon_data["source_img"]),
+                    bonus = str(round(float(bonus)))
-                "progression_base_atk": _weapon_data["atk"]["max"],
+                _template_data = {
-                "weapon_info_source_list": [],
+                    "weapon_name": _weapon_data.name,
-                "special_ability_name": _weapon_data["passive_ability"]["name"],
+                    "weapon_info_type_img": await url_to_file(_weapon_data.weapon_type.icon_url()),
-                "special_ability_info": _weapon_data["passive_ability"]["description"],
+                    "progression_secondary_stat_value": bonus,
-            }
+                    "progression_secondary_stat_name": _weapon_data.attribute.type.value,
-            _template_data["weapon_info_source_list"].append(
+                    "weapon_info_source_img": await url_to_file(_weapon_data.icon.icon),
-                await url_to_file(_weapon_data["materials"]["ascension"]["icon"])
+                    "weapon_info_max_level": _weapon_data.stats[-1].level,
-            )
+                    "progression_base_atk": round(_weapon_data.stats[-1].ATK),
-            _template_data["weapon_info_source_list"].append(
+                    "weapon_info_source_list": [
-                await url_to_file(_weapon_data["materials"]["elite"]["icon"])
+                        await url_to_file(str(SCRAPE_HOST.join(f'/img/{mid}.png')))
-            )
+                        for mid in _weapon_data.ascension[-3:]
-            _template_data["weapon_info_source_list"].append(
+                    ],
-                await url_to_file(_weapon_data["materials"]["monster"]["icon"])
+                    "special_ability_name": _weapon_data.affix.name,
-            )
+                    "special_ability_info": _weapon_data.affix.description[0],
+                }
+            else:
+                _template_data = {
+                    "weapon_name": _weapon_data.name,
+                    "weapon_info_type_img": await url_to_file(_weapon_data.weapon_type.icon_url()),
+                    "progression_secondary_stat_value": ' ',
+                    "progression_secondary_stat_name": '无其它属性加成',
+                    "weapon_info_source_img": await url_to_file(_weapon_data.icon.icon),
+                    "weapon_info_max_level": _weapon_data.stats[-1].level,
+                    "progression_base_atk": round(_weapon_data.stats[-1].ATK),
+                    "weapon_info_source_list": [
+                        await url_to_file(str(SCRAPE_HOST.join(f'/img/{mid}.png')))
+                        for mid in _weapon_data.ascension[-3:]
+                    ],
+                    "special_ability_name": '',
+                    "special_ability_info": _weapon_data.description,
+                }
             return _template_data
 
         template_data = await input_template_data(weapon_data)

resources/genshin/weapon/weapon.html

@@ -33,7 +33,7 @@
     <div class="stat-progression-2 flex py-2">
         <div class="flex-grow m-2">
             <div class="stat-progression-level text-base font-semibold">
-                <h1>Lv.90</h1>
+                <h1>Lv.{{ weapon_info_max_level }}</h1>
             </div>
             <div class="stat-progression-base-atk text-base">
                 <h2>攻击力 {{progression_base_atk}}</h2>

test/model/wiki/test_wiki.py

@@ -1,53 +1,94 @@
 import unittest
 from unittest import IsolatedAsyncioTestCase
 
-from models.wiki.characters import Characters
+from models.wiki.character import Character
-from models.wiki.weapons import Weapons
+from models.wiki.material import Material
-
+from models.wiki.weapon import Weapon
-weapons = Weapons()
 
 
-class TestWiki(IsolatedAsyncioTestCase):
+class TestWeapon(IsolatedAsyncioTestCase):
-    TEST_WEAPONS_URL = "https://genshin.honeyhunterworld.com/db/weapon/w_3405/?lang=CHS"
+    async def test_get_by_id(self):
-    TEST_CHARACTERS_URL = "https://genshin.honeyhunterworld.com/db/char/hutao/?lang=CHS"
+        weapon = await Weapon.get_by_id('11417')
+        self.assertEqual(weapon.name, '原木刀')
+        self.assertEqual(weapon.rarity, 4)
+        self.assertEqual(weapon.attack, 43.73)
+        self.assertEqual(weapon.attribute.type.value, '元素充能效率')
+        self.assertEqual(weapon.affix.name, '森林的瑞佑')
 
-    def setUp(self):
+    async def test_get_by_name(self):
-        self.weapons = Weapons()
+        weapon = await Weapon.get_by_name('风鹰剑')
-        self.characters = Characters()
+        self.assertEqual(weapon.id, 11501)
+        self.assertEqual(weapon.rarity, 5)
+        self.assertEqual(weapon.attack, 47.54)
+        self.assertEqual(weapon.attribute.type.value, '物理伤害加成')
+        self.assertEqual(weapon.affix.name, '西风之鹰的抗争')
+        self.assertTrue('听凭风引，便是正义与自由之风' in weapon.story)
 
-    async def test_get_weapon(self):
+    async def test_get_full_gen(self):
-        weapon_info = await self.weapons.get_weapon_info(self.TEST_WEAPONS_URL)
+        async for weapon in Weapon.full_data_generator():
-        self.assertEqual(weapon_info["name"], "护摩之杖")
+            self.assertIsInstance(weapon, Weapon)
-        self.assertEqual(weapon_info["description"], "在早已失落的古老祭仪中，使用的朱赤「柴火杖」。")
-        self.assertEqual(weapon_info["atk"]["name"], "基础攻击力")
-        self.assertEqual(weapon_info["atk"]["min"], 46)
-        self.assertEqual(weapon_info["atk"]["max"], 608)
-        self.assertEqual(weapon_info["secondary"]["name"], "暴击伤害")
-        self.assertEqual(weapon_info["secondary"]["min"], 14.4)
-        self.assertEqual(weapon_info["secondary"]["max"], 66.2)
-        self.assertEqual(weapon_info["star"]["value"], 5)
-        self.assertEqual(weapon_info["type"]["name"], "Polearm")
-        self.assertEqual(weapon_info["passive_ability"]["name"], "无羁的朱赤之蝶")
-        self.assertEqual(weapon_info["passive_ability"]["description"], "生命值提升20%。"
-                                                                        "此外，基于装备该武器的角色生命值上限的0.8%，"
-                                                                        "获得攻击力加成。当装备该武器的角色生命值低于50%时，"
-                                                                        "进一步获得1%基于生命值上限的攻击力提升。")
 
-    async def test_get_all_weapon_url(self):
+    async def test_get_full(self):
-        url_list = await self.weapons.get_all_weapon_url()
+        full_data = await Weapon.get_full_data()
-        self.assertEqual(True, len(url_list) >= 123)
+        for weapon in full_data:
+            self.assertIsInstance(weapon, Weapon)
 
-    async def test_get_characters(self):
+    async def test_name_list(self):
-        characters_info = await self.characters.get_characters(self.TEST_CHARACTERS_URL)
+        from httpx import URL
-        self.assertEqual(characters_info["name"], "胡桃")
+        async for name in Weapon._name_list_generator(with_url=True):
-        self.assertEqual(characters_info["title"], "雪霁梅香")
+            self.assertIsInstance(name[0], str)
-        self.assertEqual(characters_info["rarity"], 5)
+            self.assertIsInstance(name[1], URL)
-        self.assertEqual(characters_info["description"], "「往生堂」七十七代堂主，年纪轻轻就已主掌璃月的葬仪事务。")
-        self.assertEqual(characters_info["allegiance"], "往生堂")
 
-    async def test_get_all_characters_url(self):
+
-        url_list = await self.characters.get_all_characters_url()
+class TestCharacter(IsolatedAsyncioTestCase):
-        self.assertEqual(True, len(url_list) >= 49)
+    async def test_get_by_id(self):
+        character = await Character.get_by_id('ayaka_002')
+        self.assertEqual(character.name, '神里绫华')
+        self.assertEqual(character.title, '白鹭霜华')
+        self.assertEqual(character.occupation, '社奉行')
+        self.assertEqual(character.association.value, '稻妻')
+        self.assertEqual(character.cn_cv, '小N')
+
+    async def test_get_by_name(self):
+        character = await Character.get_by_name('神里绫华')
+        self.assertEqual(character.id, 'ayaka_002')
+        self.assertEqual(character.title, '白鹭霜华')
+        self.assertEqual(character.occupation, '社奉行')
+        self.assertEqual(character.association.value, '稻妻')
+        self.assertEqual(character.cn_cv, '小N')
+
+        main_character = await Character.get_by_name('荧')
+        self.assertEqual(main_character.constellation, '旅人座')
+        self.assertEqual(main_character.cn_cv, '宴宁&多多poi')
+
+    async def test_get_full(self):
+        async for character in Character.full_data_generator():
+            self.assertIsInstance(character, Character)
+
+
+class TestMaterial(IsolatedAsyncioTestCase):
+    async def test_get_full_gen(self):
+        async for material in Material.full_data_generator():
+            self.assertIsInstance(material, Material)
+
+    async def test_get_full(self):
+        material_list = await Material.get_full_data()
+        for material in material_list:
+            self.assertIsInstance(material, Material)
+
+
+class TestAll(IsolatedAsyncioTestCase):
+    async def test_all_get_full(self):
+        import asyncio
+        materials, weapons, characters = tuple(await asyncio.gather(
+            Material.get_full_data(),
+            Weapon.get_full_data(),
+            Character.get_full_data(),
+            return_exceptions=True
+        ))
+        self.assertEqual(len(materials), 120)
+        self.assertEqual(len(weapons), 151)
+        self.assertEqual(len(characters), 58)
 
 
 if __name__ == "__main__":