0.0.3

spider/work.py

@@ -0,0 +1,333 @@
+import random
+import time
+from datetime import date, timedelta
+from typing import Optional, Dict
+
+import requests
+
+
+CA_PROVINCE_ABBR = {
+    "Alberta": "AB",
+    "British Columbia": "BC",
+    "Manitoba": "MB",
+    "New Brunswick": "NB",
+    "Newfoundland and Labrador": "NL",
+    "Nova Scotia": "NS",
+    "Ontario": "ON",
+    "Prince Edward Island": "PE",
+    "Quebec": "QC",
+    "Saskatchewan": "SK",
+    "Northwest Territories": "NT",
+    "Nunavut": "NU",
+    "Yukon": "YT",
+}
+
+
+CA_COORDS = {
+    "AB": [(51.044733, -114.071883, "Calgary"), (53.546124, -113.493823, "Edmonton")],
+    "BC": [(49.282729, -123.120738, "Vancouver"), (48.428421, -123.365644, "Victoria")],
+    "MB": [(49.895137, -97.138374, "Winnipeg"), (50.445211, -96.823611, "East St Paul")],
+    "NB": [(45.963589, -66.643115, "Fredericton"), (46.510712, -67.255044, "Woodstock")],
+    "NL": [(53.135509, -57.660435, "Labrador City"), (47.561510, -52.712585, "St. John's")],
+    "NS": [(44.648862, -63.575320, "Halifax"), (45.010474, -63.416817, "Truro")],
+    "ON": [(43.653225, -79.383186, "Toronto"), (45.421532, -75.697189, "Ottawa")],
+    "PE": [(46.238240, -63.131074, "Charlottetown"), (46.392410, -63.787629, "Summerside")],
+    "QC": [(45.501689, -73.567256, "Montreal"), (46.813878, -71.207980, "Quebec City")],
+    "SK": [(52.133214, -106.670046, "Saskatoon"), (50.445211, -104.618896, "Regina")],
+    "NT": [(62.4540, -114.3725, "Yellowknife"), (61.251955, -114.352482, "Yellowknife")],
+    "NU": [(63.7467, -68.5167, "Iqaluit"), (64.282327, -76.614813, "Nunavut")],
+    "YT": [(60.7212, -135.0568, "Whitehorse"), (64.000000, -138.000000, "Yukon")],
+}
+
+
+CA_AREA_CODES = {
+    "AB": ["403", "587", "825"],
+    "BC": ["236", "250", "604", "672", "778"],
+    "MB": ["204", "431"],
+    "NB": ["506"],
+    "NL": ["709"],
+    "NS": ["782", "902"],
+    "ON": ["226", "249", "289", "343", "365", "416", "437", "519", "548", "613", "639", "647", "705", "807", "905"],
+    "PE": ["902"],
+    "QC": ["418", "438", "450", "514", "579", "581", "819", "873"],
+    "SK": ["306", "639"],
+    "NT": ["867"],
+    "NU": ["867"],
+    "YT": ["867"],
+}
+
+
+REMOTE_PROVINCES = {"NL", "NT", "NU", "YT"}
+
+
+def _normalize_province(province: str) -> str:
+    """
+    省份入参规范化，支持全称或缩写，返回缩写
+
+    参数:
+        province (str): 省份，可为全称或缩写（如 "Alberta" 或 "AB"）
+
+    返回值:
+        str: 省份缩写（如 "AB"）
+    """
+    if not province:
+        raise ValueError("province 不能为空")
+    p = province.strip()
+    if len(p) == 2:
+        return p.upper()
+    return CA_PROVINCE_ABBR.get(p, p)
+
+
+def _pick_coords(province_abbr: str, city: Optional[str]) -> tuple[float, float, str]:
+    """
+    按省份与可选城市选择一个坐标点
+
+    参数:
+        province_abbr (str): 省份缩写
+        city (Optional[str]): 城市名（如 "Calgary"），可为空
+
+    返回值:
+        (lat, lon, city_name): 选中的基础坐标及城市名
+    """
+    coords = CA_COORDS.get(province_abbr)
+    if not coords:
+        # 默认回退至 Calgary
+        return 51.044733, -114.071883, "Calgary"
+    if city:
+        c = city.strip().lower()
+        for lat, lon, cname in coords:
+            if cname.lower() == c:
+                return lat, lon, cname
+    return random.choice(coords)
+
+
+def _random_near(lat: float, lon: float) -> tuple[float, float]:
+    """
+    在给定坐标附近生成一个随机偏移坐标
+
+    参数:
+        lat (float): 基准纬度
+        lon (float): 基准经度
+
+    返回值:
+        (new_lat, new_lon): 随机偏移后的坐标
+    """
+    return lat + (random.random() - 0.5) * 0.1, lon + (random.random() - 0.5) * 0.1
+
+
+def _reverse_geocode(lat: float, lon: float) -> Dict:
+    """
+    使用 Nominatim 反向地理编码，返回地址字典
+
+    参数:
+        lat (float): 纬度
+        lon (float): 经度
+
+    返回值:
+        dict: 包含 address 字段的响应数据
+    """
+    url = f"https://nominatim.openstreetmap.org/reverse?format=json&lat={lat}&lon={lon}&zoom=18&addressdetails=1"
+    headers = {"User-Agent": "ca_auto_table/1.0"}
+    r = requests.get(url, headers=headers, timeout=15)
+    r.raise_for_status()
+    return r.json()
+
+
+def _format_address(address: Dict, province_abbr: str) -> str:
+    """
+    将 Nominatim 的 address 格式化为完整地址字符串
+
+    参数:
+        address (dict): Nominatim 返回的 address 字段
+        province_abbr (str): 省份缩写（如 "AB"）
+
+    返回值:
+        str: 格式化后的地址字符串
+    """
+    house = address.get("house_number")
+    road = address.get("road") or address.get("residential") or address.get("footway")
+    city = address.get("city") or address.get("town") or address.get("village")
+    postcode = address.get("postcode") or ""
+    if house and road and city:
+        return f"{house} {road}, {city}, {province_abbr} {postcode}, Canada"
+    # 远端省份允许部分地址
+    return f"{city or ''}, {province_abbr} {postcode}, Canada".strip(", ")
+
+
+def _random_name() -> tuple[str, str]:
+    """
+    生成随机英文名（Firstname, Lastname），组合空间可达数百万以上
+
+    实现策略:
+    - 60% 概率使用常见英文名与姓氏列表（更自然）
+    - 40% 概率使用音节组合算法动态生成（数量级远超百万）
+
+    返回值:
+        (firstname, lastname)
+    """
+    common_first = [
+        "James", "Mary", "Robert", "Patricia", "John", "Jennifer", "Michael", "Linda", "William", "Elizabeth",
+        "David", "Barbara", "Richard", "Susan", "Joseph", "Jessica", "Thomas", "Sarah", "Charles", "Karen",
+        "Christopher", "Nancy", "Daniel", "Lisa", "Matthew", "Betty", "Anthony", "Margaret", "Mark", "Sandra",
+        "Donald", "Ashley", "Steven", "Kimberly", "Paul", "Emily", "Andrew", "Donna", "Joshua", "Michelle",
+        "Kenneth", "Dorothy", "Kevin", "Carol", "Brian", "Amanda", "George", "Melissa", "Edward", "Deborah",
+        "Ronald", "Stephanie", "Timothy", "Rebecca", "Jason", "Laura", "Jeffrey", "Sharon", "Ryan", "Cynthia",
+        "Jacob", "Kathleen", "Gary", "Amy", "Nicholas", "Shirley", "Eric", "Angela", "Stephen", "Helen",
+        "Jonathan", "Anna", "Larry", "Brenda", "Justin", "Pamela", "Scott", "Nicole", "Brandon", "Samantha",
+        "Frank", "Katherine", "Benjamin", "Christine", "Gregory", "Emma", "Raymond", "Ruth", "Samuel", "Julie",
+        "Patrick", "Olivia", "Alexander", "Victoria"
+    ]
+    common_last = [
+        "Smith", "Johnson", "Williams", "Brown", "Jones", "Garcia", "Miller", "Davis", "Rodriguez", "Martinez",
+        "Hernandez", "Lopez", "Gonzalez", "Wilson", "Anderson", "Thomas", "Taylor", "Moore", "Jackson", "Martin",
+        "Lee", "Perez", "Thompson", "White", "Harris", "Sanchez", "Clark", "Ramirez", "Lewis", "Robinson",
+        "Walker", "Young", "Allen", "King", "Wright", "Scott", "Torres", "Nguyen", "Hill", "Flores",
+        "Green", "Adams", "Nelson", "Baker", "Hall", "Rivera", "Campbell", "Mitchell", "Carter", "Roberts",
+        "Turner", "Phillips", "Parker", "Evans", "Edwards", "Collins", "Stewart", "Sanchez", "Morris", "Rogers",
+        "Reed", "Cook", "Morgan", "Bell", "Murphy", "Bailey", "Cooper", "Richardson", "Cox", "Howard",
+        "Ward", "Torres", "Peterson", "Gray", "Ramirez", "James", "Watson", "Brooks", "Kelly", "Sanders",
+        "Price", "Bennett", "Wood", "Barnes", "Ross", "Henderson", "Coleman", "Jenkins", "Perry", "Powell",
+        "Long", "Patterson", "Hughes", "Flores"
+    ]
+
+    if random.random() < 0.6:
+        return random.choice(common_first), random.choice(common_last)
+
+    # 动态音节组合生成，支持数百万组合
+    f_beg = [
+        "al", "ben", "car", "dan", "el", "fran", "ge", "har", "isa", "jo", "ka", "li", "mar", "no",
+        "ol", "pa", "qui", "ra", "sa", "ta", "ul", "vi", "wil", "xa", "ya", "zo"
+    ]
+    f_mid = [
+        "a", "e", "i", "o", "u", "ae", "ai", "ia", "ie", "oa", "ou"
+    ]
+    f_end = [
+        "n", "ne", "na", "son", "ton", "la", "ra", "rie", "ry", "ley", "ly", "ah"
+    ]
+
+    l_beg = [
+        "sm", "john", "dav", "wil", "and", "tho", "tay", "mo", "jack", "mar", "lee", "tho", "whi", "har",
+        "san", "cla", "ram", "lew", "rob", "walk", "young", "all", "king", "wri", "scott", "tor", "nguy",
+        "hil", "flo", "gre", "ada", "nel", "bak", "hal", "riv", "camp", "mit", "car", "rob"
+    ]
+    l_mid = [
+        "a", "e", "i", "o", "u", "ar", "er", "or", "an", "en", "in", "on", "un"
+    ]
+    l_suf = [
+        "son", "ton", "man", "ley", "ford", "wood", "well", "er", "ers", "ing", "s", "son", "es"
+    ]
+
+    def build_name(beg, mid, end, syllables=(2, 3)) -> str:
+        parts = [random.choice(beg)]
+        for _ in range(random.choice(syllables) - 1):
+            parts.append(random.choice(mid))
+        parts.append(random.choice(end))
+        name = "".join(parts)
+        return name.capitalize()
+
+    first = build_name(f_beg, f_mid, f_end)
+    last = build_name(l_beg, l_mid, l_suf)
+    return first, last
+
+
+def _random_birthday() -> str:
+    """
+    生成随机生日，格式为 yyyy-mm-dd
+
+    返回值:
+        str: 生日字符串
+    """
+    start = date(1950, 1, 1)
+    end = date(2000, 12, 31)
+    delta_days = (end - start).days
+    d = start + timedelta(days=random.randint(0, delta_days))
+    return f"{d.year}-{d.month:02d}-{d.day:02d}"
+
+
+def _random_phone(province_abbr: str) -> str:
+    """
+    生成随机加拿大电话号码，带区号
+
+    参数:
+        province_abbr (str): 省份缩写
+
+    返回值:
+        str: 电话，例如 "(403) 555-1234"
+    """
+    codes = CA_AREA_CODES.get(province_abbr, ["000"])
+    area = random.choice(codes)
+    exchange = str(random.randint(200, 899)).zfill(3)
+    line = str(random.randint(1000, 9999)).zfill(4)
+    return f"({area}) {exchange}-{line}"
+
+
+def generate_canada_info(province: str, city: Optional[str] = None, max_attempts: int = 15, sleep_sec: float = 0.6) -> Dict[str, str]:
+    """
+    随机生成加拿大个人与地址信息，可指定省份（全称或缩写）与可选城市
+
+    参数:
+        province (str): 省份（如 "Alberta" 或 "AB"）
+        city (Optional[str]): 城市（如 "Calgary"），不传则在省内随机
+        max_attempts (int): 反向地理编码最大尝试次数
+        sleep_sec (float): 每次失败后的等待秒数，用于尊重 Nominatim 频率限制
+
+    返回值:
+        dict: 包含 Firstname、Lastname、全名、生日、街道地址、城市、电话、邮编、州全称
+    """
+    prov_abbr = _normalize_province(province)
+    base_lat, base_lon, chosen_city = _pick_coords(prov_abbr, city)
+
+    address_str = ""
+    city_name = ""
+    postcode = ""
+    for _ in range(max_attempts):
+        lat, lon = _random_near(base_lat, base_lon)
+        data = _reverse_geocode(lat, lon)
+        addr = data.get("address", {})
+        city_name = addr.get("city") or addr.get("town") or addr.get("village") or chosen_city
+        postcode = addr.get("postcode") or ""
+        address_str = _format_address(addr, prov_abbr)
+        if prov_abbr in REMOTE_PROVINCES:
+            break
+        if addr.get("house_number") and (addr.get("road") or addr.get("residential") or addr.get("footway")) and city_name:
+            break
+        time.sleep(sleep_sec)
+
+    firstname, lastname = _random_name()
+    full_name = f"{firstname} {lastname}"
+    birthday = _random_birthday()
+    phone = _random_phone(prov_abbr)
+
+    return {
+        "firstname": firstname,
+        "lastname": lastname,
+        "full_name": full_name,
+        "birthday": birthday,
+        "address_str": address_str.split(",")[0],
+        "city_name": city_name,
+        "phone": phone,
+        "postcode": postcode,
+        "province": next((k for k, v in CA_PROVINCE_ABBR.items() if v == prov_abbr), prov_abbr),
+    }
+
+
+def get_random_canada_info(province, city) -> Dict[str, str]:
+    """
+    随机生成加拿大个人与地址信息，省份随机选择，城市随机选择
+
+    返回值:
+        dict: 包含 Firstname、Lastname、全名、生日、街道地址、城市、电话、邮编、州全称
+    """
+    return generate_canada_info(province, city)
+
+
+def main() -> None:
+    """
+    演示：生成 Alberta 省 Calgary 的随机信息；可修改为其他省/城市
+    """
+    info = generate_canada_info("Alberta", "Calgary")
+    print(info)
+
+
+if __name__ == "__main__":
+    main()