mirror of
https://github.com/hotyue/IP-Sentinel.git
synced 2026-07-21 20:52:54 +08:00
feat(data): 兵工厂重构，升级 2025 高保真多平台 UA 轮换池；扩容活体新闻至 30 发纯双栈(IPv4+IPv6)满编矩阵
This commit is contained in:
hotyue
@@ -7,7 +7,6 @@ import time
|
||||
import random
|
||||
|
||||
# ================== [路径防弹装甲] ==================
|
||||
# 无论在哪里执行该脚本，都能精准反推项目根目录
|
||||
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||
PROJECT_ROOT = os.path.dirname(SCRIPT_DIR)
|
||||
|
||||
@@ -15,27 +14,15 @@ MAP_JSON_PATH = os.path.join(PROJECT_ROOT, "data", "map.json")
|
||||
DATA_DIR = os.path.join(PROJECT_ROOT, "data", "keywords")
|
||||
# ====================================================
|
||||
|
||||
# 特殊战区代码映射 (Google Trends RSS 要求)
|
||||
GEO_FIX = {'UK': 'GB'}
|
||||
FALLBACK_MAP = {'LA': 'US', 'MN': 'US', 'MO': 'HK'}
|
||||
|
||||
# ================== [核心修复 1: 兜底机制] ==================
|
||||
# Google Trends 不支持的战区，降级抓取 US (美国) 通用流量
|
||||
FALLBACK_MAP = {
|
||||
'LA': 'US',
|
||||
'MN': 'US'
|
||||
,'MO': 'HK'
|
||||
}
|
||||
|
||||
# ================== [核心修复 2: 随机 UA 池] ==================
|
||||
USER_AGENTS = [
|
||||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
||||
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.2.1 Safari/605.1.15',
|
||||
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36',
|
||||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:121.0) Gecko/20100101 Firefox/121.0'
|
||||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36',
|
||||
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36'
|
||||
]
|
||||
|
||||
def get_active_regions():
|
||||
"""动态提取 map.json 中的战区 (适配 v3.5.0 大洲战区降维架构)"""
|
||||
try:
|
||||
with open(MAP_JSON_PATH, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
@@ -50,14 +37,9 @@ def get_active_regions():
|
||||
return []
|
||||
|
||||
def fetch_trends(region_code):
|
||||
"""从 Google Trends 抓取当日热搜"""
|
||||
geo = GEO_FIX.get(region_code, region_code)
|
||||
|
||||
# 触发兜底判定
|
||||
actual_geo = FALLBACK_MAP.get(geo, geo)
|
||||
url = f"https://trends.google.com/trending/rss?geo={actual_geo}"
|
||||
|
||||
# 随机抽取 User-Agent
|
||||
headers = {'User-Agent': random.choice(USER_AGENTS)}
|
||||
|
||||
try:
|
||||
@@ -65,10 +47,7 @@ def fetch_trends(region_code):
|
||||
with urllib.request.urlopen(req, timeout=10) as response:
|
||||
xml_data = response.read()
|
||||
root = ET.fromstring(xml_data)
|
||||
|
||||
# 如果触发了兜底，准备提示信息
|
||||
fallback_msg = f" (兜底降级至 {actual_geo})" if actual_geo != geo else ""
|
||||
|
||||
words = [re.sub(r'[\n\r\t]', ' ', item.find('title').text).strip()
|
||||
for item in root.findall('./channel/item')
|
||||
if item.find('title') is not None]
|
||||
@@ -78,7 +57,7 @@ def fetch_trends(region_code):
|
||||
return [], ""
|
||||
|
||||
def update_file(region, new_words, fallback_msg=""):
|
||||
"""滑动窗口更新，保留 200 条最热记录"""
|
||||
"""滑动窗口更新，严格保留最新 100 条最热记录"""
|
||||
os.makedirs(DATA_DIR, exist_ok=True)
|
||||
file_path = os.path.join(DATA_DIR, f"kw_{region}.txt")
|
||||
old_words = []
|
||||
@@ -86,13 +65,13 @@ def update_file(region, new_words, fallback_msg=""):
|
||||
with open(file_path, 'r', encoding='utf-8') as f:
|
||||
old_words = [l.strip() for l in f if l.strip()]
|
||||
|
||||
# 新词排在最前面，去重
|
||||
combined = new_words + [w for w in old_words if w not in new_words]
|
||||
final_list = combined[:200]
|
||||
# 【业务收敛】切片收紧至 100 条
|
||||
final_list = combined[:100]
|
||||
|
||||
with open(file_path, 'w', encoding='utf-8') as f:
|
||||
f.write('\n'.join(final_list) + '\n')
|
||||
print(f"✅ [同步完成] {region}: 注入 {len(new_words)} 条新热点{fallback_msg}")
|
||||
print(f"✅ [同步完成] {region}: 注入 {len(new_words)} 条新热点，维持总数 {len(final_list)} 条{fallback_msg}")
|
||||
|
||||
if __name__ == '__main__':
|
||||
regions = get_active_regions()
|
||||
@@ -106,8 +85,5 @@ if __name__ == '__main__':
|
||||
words, fallback_msg = fetch_trends(r)
|
||||
if words:
|
||||
update_file(r, words, fallback_msg)
|
||||
|
||||
# [核心修复 3: 流量削峰] 随机休眠 1.5 到 3.5 秒
|
||||
time.sleep(random.uniform(1.5, 3.5))
|
||||
|
||||
print("========== 热词抓取引擎执行完毕 ==========")
|
||||
@@ -4,61 +4,85 @@ import os
|
||||
import json
|
||||
import random
|
||||
|
||||
# ================== [路径防弹装甲] ==================
|
||||
# ====================================================
|
||||
# 脚本功能: 5+25 混合流量注入矩阵 (双栈 IPv4+IPv6 防风控版)
|
||||
# 核心指标: 5条基石 + 25条活体新闻 = 30条确保双栈机型完全可达的白名单
|
||||
# ====================================================
|
||||
|
||||
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||
PROJECT_ROOT = os.path.dirname(SCRIPT_DIR)
|
||||
REGIONS_DIR = os.path.join(PROJECT_ROOT, "data", "regions")
|
||||
|
||||
# ====================================================
|
||||
# 2025 年高保真多平台 UA 轮换池 (防风控装甲)
|
||||
# 包含 Windows, macOS, iOS, Android 的最新骨干指纹
|
||||
# ====================================================
|
||||
USER_AGENTS = [
|
||||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36',
|
||||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36 Edg/133.0.0.0',
|
||||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:135.0) Gecko/20100101 Firefox/135.0',
|
||||
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36',
|
||||
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/618.1.15 (KHTML, like Gecko) Version/18.3 Safari/618.1.15',
|
||||
'Mozilla/5.0 (iPhone; CPU iPhone OS 18_3_1 like Mac OS X) AppleWebKit/618.1.15 (KHTML, like Gecko) Version/18.3 Mobile/15E148 Safari/604.1',
|
||||
'Mozilla/5.0 (Linux; Android 15; Pixel 9 Pro) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Mobile Safari/537.36'
|
||||
]
|
||||
|
||||
HEADERS = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
|
||||
}
|
||||
|
||||
# 全球骨干新闻 RSS 监听矩阵
|
||||
# ====================================================
|
||||
# 全球骨干新闻 RSS 监听矩阵 (双栈强穿透版)
|
||||
# 全面采用 Google News 本土化入口，确保提取的链接支持 IPv4+IPv6
|
||||
# ====================================================
|
||||
RSS_FEEDS = {
|
||||
"US": ["http://rss.cnn.com/rss/cnn_topstories.rss", "https://feeds.npr.org/1001/rss.xml"],
|
||||
"UK": ["http://feeds.bbci.co.uk/news/rss.xml"],
|
||||
"AU": ["https://www.abc.net.au/news/feed/51120/rss.xml"],
|
||||
"CA": ["https://www.cbc.ca/cmlink/rss-topstories"],
|
||||
"DE": ["https://www.tagesschau.de/xml/rss2"],
|
||||
"FR": ["https://www.france24.com/fr/rss"],
|
||||
"ES": ["https://feeds.elpais.com/mrss-s/pages/ep/site/elpais.com/portada"],
|
||||
"JP": ["https://news.yahoo.co.jp/rss/topics/top-picks.xml"],
|
||||
"HK": ["https://hk.news.yahoo.com/rss/hong-kong"],
|
||||
"MO": ["https://macaudailytimes.com.mo/feed/"],
|
||||
"US": ["https://news.google.com/rss?hl=en-US&gl=US&ceid=US:en"],
|
||||
"UK": ["https://news.google.com/rss?hl=en-GB&gl=GB&ceid=GB:en"],
|
||||
"AU": ["https://news.google.com/rss?hl=en-AU&gl=AU&ceid=AU:en"],
|
||||
"CA": ["https://news.google.com/rss?hl=en-CA&gl=CA&ceid=CA:en"],
|
||||
"DE": ["https://news.google.com/rss?hl=de&gl=DE&ceid=DE:de"],
|
||||
"FR": ["https://news.google.com/rss?hl=fr&gl=FR&ceid=FR:fr"],
|
||||
"ES": ["https://news.google.com/rss?hl=es-419&gl=US&ceid=US:es_419"],
|
||||
"JP": ["https://news.google.com/rss?hl=ja&gl=JP&ceid=JP:ja"],
|
||||
"HK": ["https://news.google.com/rss?hl=zh-HK&gl=HK&ceid=HK:zh-Hant"],
|
||||
"MO": ["https://news.google.com/rss?hl=zh-HK&gl=HK&ceid=HK:zh-Hant"],
|
||||
"TW": ["https://news.google.com/rss?hl=zh-TW&gl=TW&ceid=TW:zh-Hant"],
|
||||
"KR": ["https://www.yonhapnewstv.co.kr/category/news/headline/feed/"],
|
||||
"SG": ["https://www.channelnewsasia.com/api/v1/rss-outbound-feed?_format=xml"],
|
||||
"NL": ["https://feeds.nos.nl/nosnieuwsalgemeen"],
|
||||
"VN": ["https://vnexpress.net/rss/tin-moi-nhat.rss"],
|
||||
"KR": ["https://news.google.com/rss?hl=ko&gl=KR&ceid=KR:ko"],
|
||||
"SG": ["https://news.google.com/rss?hl=en-SG&gl=SG&ceid=SG:en"],
|
||||
"NL": ["https://news.google.com/rss?hl=nl&gl=NL&ceid=NL:nl"],
|
||||
"VN": ["https://news.google.com/rss?hl=vi&gl=VN&ceid=VN:vi"],
|
||||
"MY": ["https://news.google.com/rss?hl=en-MY&gl=MY&ceid=MY:en"],
|
||||
"NG": ["https://punchng.com/feed/", "https://www.vanguardngr.com/feed/"],
|
||||
"TR": ["https://www.hurriyet.com.tr/rss/anasayfa"],
|
||||
# ====== 下方为 PR #47 亚洲与中东新战区扩充源 (已通过实机验证) ======
|
||||
"NG": ["https://news.google.com/rss?hl=en-NG&gl=NG&ceid=NG:en"],
|
||||
"TR": ["https://news.google.com/rss?hl=tr&gl=TR&ceid=TR:tr"],
|
||||
"PH": ["https://news.google.com/rss?hl=en-PH&gl=PH"],
|
||||
"TH": ["https://www.bangkokpost.com/rss/data/topstories.xml"],
|
||||
"ID": ["https://www.antaranews.com/rss/terkini.xml"],
|
||||
"IN": ["https://timesofindia.indiatimes.com/rssfeedstopstories.cms"],
|
||||
"TH": ["https://news.google.com/rss?hl=th&gl=TH&ceid=TH:th"],
|
||||
"ID": ["https://news.google.com/rss?hl=id&gl=ID&ceid=ID:id"],
|
||||
"IN": ["https://news.google.com/rss?hl=en-IN&gl=IN&ceid=IN:en"],
|
||||
"AE": ["https://news.google.com/rss?hl=en-AE&gl=AE"],
|
||||
"SA": ["https://news.google.com/rss?hl=ar-SA&gl=SA"],
|
||||
"BD": ["https://www.thedailystar.net/frontpage/rss.xml"],
|
||||
"BD": ["https://news.google.com/rss?hl=en-BD&gl=BD"],
|
||||
"NP": ["https://news.google.com/rss?hl=en-NP&gl=NP"],
|
||||
"KH": ["https://www.cambodiadaily.com/feed/"],
|
||||
"KH": ["https://news.google.com/rss?hl=en-KH&gl=KH"],
|
||||
"MM": ["https://news.google.com/rss?hl=en-MM&gl=MM"],
|
||||
"LA": ["https://news.google.com/rss?hl=en-LA&gl=LA"],
|
||||
"MN": ["https://news.google.com/rss?hl=en-MN&gl=MN"]
|
||||
}
|
||||
|
||||
def fetch_rss_links(region_code, max_items=15):
|
||||
"""抓取该战区最新的 RSS 新闻链接"""
|
||||
feeds = RSS_FEEDS.get(region_code, [])
|
||||
if not feeds:
|
||||
return []
|
||||
|
||||
def is_dual_stack_safe(url):
|
||||
"""网络可达性过滤: 阻断任何不支持双栈(IPv4+IPv6)的域名"""
|
||||
# 强制白名单：已被确认具有完备双栈 Anycast 防线的顶级骨干站群
|
||||
DUAL_STACK_SAFE_DOMAINS = [
|
||||
"google.com", "wikipedia.org", "apple.com", "microsoft.com",
|
||||
"wikimedia.org", "blogspot.com", "yahoo.com"
|
||||
]
|
||||
return any(domain in url for domain in DUAL_STACK_SAFE_DOMAINS)
|
||||
|
||||
def fetch_rss_links(region_code, max_items=25):
|
||||
"""拉取 25 条支持双栈访问的活体新闻链接"""
|
||||
feeds = RSS_FEEDS.get(region_code, RSS_FEEDS["US"])
|
||||
links = []
|
||||
|
||||
for url in feeds:
|
||||
try:
|
||||
req = urllib.request.Request(url, headers=HEADERS)
|
||||
# 动态抽取随机UA防风控
|
||||
dynamic_headers = {'User-Agent': random.choice(USER_AGENTS)}
|
||||
req = urllib.request.Request(url, headers=dynamic_headers)
|
||||
with urllib.request.urlopen(req, timeout=10) as response:
|
||||
xml_data = response.read()
|
||||
root = ET.fromstring(xml_data)
|
||||
@@ -66,13 +90,16 @@ def fetch_rss_links(region_code, max_items=15):
|
||||
link = item.find('link')
|
||||
if link is not None and link.text:
|
||||
clean_link = link.text.strip()
|
||||
if clean_link.startswith('http'):
|
||||
# 注入防断网熔断判定: 必须以 http 开头且具备双栈安全性
|
||||
if clean_link.startswith('http') and is_dual_stack_safe(clean_link):
|
||||
links.append(clean_link)
|
||||
except Exception as e:
|
||||
print(f"⚠️ [{region_code}] RSS 抓取异常 ({url}): {e}")
|
||||
|
||||
# 去重并截取最新
|
||||
return list(set(links))[:max_items]
|
||||
# 高度去重并随机打乱，精准截取 max_items
|
||||
unique_links = list(set(links))
|
||||
random.shuffle(unique_links)
|
||||
return unique_links[:max_items]
|
||||
|
||||
def process_json_file(file_path, region_code):
|
||||
"""融合静态基石与动态新闻"""
|
||||
@@ -81,39 +108,51 @@ def process_json_file(file_path, region_code):
|
||||
data = json.load(f)
|
||||
|
||||
trust_mod = data.get("trust_module", {})
|
||||
if not trust_mod or "static_urls" not in trust_mod:
|
||||
if not trust_mod:
|
||||
return
|
||||
|
||||
# 1. 基石处理：提取静态配额，确保双栈安全后精准截取 5 条
|
||||
static_urls = trust_mod.get("static_urls", [])
|
||||
static_urls = [u for u in static_urls if is_dual_stack_safe(u)]
|
||||
if len(static_urls) < 5:
|
||||
# 基础数据残缺时，进行高权重锚点动态扩容补齐
|
||||
static_urls += ["https://en.wikipedia.org/wiki/Special:Random", "https://www.apple.com/", "https://www.microsoft.com/"]
|
||||
random.shuffle(static_urls)
|
||||
final_static = list(set(static_urls))[:5]
|
||||
|
||||
# 抓取今日该战区的活体新闻流
|
||||
daily_news_urls = fetch_rss_links(region_code)
|
||||
# 2. 活体处理：拉取 25 条双栈活体新闻
|
||||
final_news = fetch_rss_links(region_code, max_items=25)
|
||||
|
||||
# 战术混合：基石(保证高权重) + 新闻(保证活体动态)
|
||||
combined_urls = static_urls + daily_news_urls
|
||||
# 3. 战术混合：5条基石 + 25条活体 = 30条
|
||||
combined_urls = list(set(final_static + final_news))
|
||||
|
||||
# 深度洗牌，打破机械顺序特征
|
||||
combined_urls = list(set(combined_urls))
|
||||
random.shuffle(combined_urls)
|
||||
# 如果依然不够 30 条，用完美支持双栈的维基百科随机锚点疯狂垫高充能
|
||||
while len(combined_urls) < 30:
|
||||
combined_urls.append(f"https://en.wikipedia.org/wiki/Special:Random?r={random.randint(1,100000)}")
|
||||
combined_urls = list(set(combined_urls))
|
||||
|
||||
# 精准切片为 30 条，彻底打碎机械顺序特征
|
||||
final_white_list = combined_urls[:30]
|
||||
random.shuffle(final_white_list)
|
||||
|
||||
# 覆写回供 Agent 拉取的 white_urls
|
||||
trust_mod["white_urls"] = combined_urls
|
||||
# 覆写固化回 white_urls 字段
|
||||
trust_mod["white_urls"] = final_white_list
|
||||
data["trust_module"] = trust_mod
|
||||
|
||||
with open(file_path, 'w', encoding='utf-8') as f:
|
||||
json.dump(data, f, ensure_ascii=False, indent=2)
|
||||
|
||||
print(f"✅ [信用融合] {os.path.basename(file_path)}: 骨干 {len(static_urls)} 条 + 活体 {len(daily_news_urls)} 条")
|
||||
print(f"✅ [信用融合] {os.path.basename(file_path)}: 固化基石 {len(final_static)} 条 + 活体新闻 {len(final_news)} 条 = 统合满编 {len(final_white_list)} 条")
|
||||
|
||||
except Exception as e:
|
||||
print(f"❌ [处理失败] {file_path}: {e}")
|
||||
|
||||
if __name__ == '__main__':
|
||||
print("========== 启动 IP-Sentinel 活体新闻流融合引擎 ==========")
|
||||
print("========== 启动 IP-Sentinel 活体新闻流融合引擎 (30轮大容量双栈版) ==========")
|
||||
for root_dir, _, files in os.walk(REGIONS_DIR):
|
||||
for file in files:
|
||||
if file.endswith(".json"):
|
||||
file_path = os.path.join(root_dir, file)
|
||||
region_code = os.path.relpath(file_path, REGIONS_DIR).split(os.sep)[0]
|
||||
process_json_file(file_path, region_code)
|
||||
print("========== 融合引擎执行完毕 ==========")
|
||||
print("========== 融合引擎执行完毕 ==========")
|
||||
@@ -1,37 +1,36 @@
|
||||
import random
|
||||
import os
|
||||
|
||||
# ==========================================
|
||||
# IP-Sentinel 超大型高保真指纹工厂 (V3.1.5)
|
||||
# 无需第三方库，直接生成千万级组合的真实指纹
|
||||
# ==========================================
|
||||
# ==========================================================
|
||||
# IP-Sentinel 超大型高保真指纹工厂 (V4.1.0 - 2025 年换代版)
|
||||
# 核心功能: 升级指纹生命周期至 2025 年骨干型号，确保探测指纹真实度
|
||||
# ==========================================================
|
||||
|
||||
def generate_chrome_version():
|
||||
# 模拟 2024 年主流 Chrome 内核号 (122 - 125)
|
||||
major = random.randint(122, 125)
|
||||
build = random.randint(5000, 6500)
|
||||
# 模拟 2025 年主流 Chrome 内核号 (133 - 136)
|
||||
major = random.randint(133, 136)
|
||||
build = random.randint(6900, 7200)
|
||||
patch = random.randint(10, 150)
|
||||
return f"{major}.0.{build}.{patch}"
|
||||
|
||||
def generate_windows_ua(count=1000):
|
||||
uas = set()
|
||||
while len(uas) < count:
|
||||
# 现代 Windows UA 已经固化为 Windows NT 10.0
|
||||
uas.add(f"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/{generate_chrome_version()} Safari/537.36")
|
||||
return list(uas)
|
||||
|
||||
def generate_macos_ua(count=1000):
|
||||
uas = set()
|
||||
while len(uas) < count:
|
||||
mac_os_minor = random.randint(11, 15)
|
||||
mac_os_patch = random.randint(1, 6)
|
||||
mac_os_minor = random.randint(15, 16)
|
||||
mac_os_patch = random.randint(0, 4)
|
||||
if random.choice([True, False]):
|
||||
# Chrome on Mac
|
||||
uas.add(f"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_{mac_os_minor}_{mac_os_patch}) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/{generate_chrome_version()} Safari/537.36")
|
||||
else:
|
||||
# Safari on Mac
|
||||
safari_build = f"605.1.{random.randint(10, 15)}"
|
||||
safari_version = f"17.{random.randint(1, 4)}"
|
||||
# Safari on Mac (2025 年对应 Safari 18 系列)
|
||||
safari_build = f"618.1.{random.randint(10, 15)}"
|
||||
safari_version = f"18.{random.randint(1, 4)}"
|
||||
uas.add(f"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_{mac_os_minor}_{mac_os_patch}) AppleWebKit/{safari_build} (KHTML, like Gecko) Version/{safari_version} Safari/{safari_build}")
|
||||
return list(uas)
|
||||
|
||||
@@ -40,10 +39,10 @@ def generate_ios_ua(count=1000):
|
||||
devices = ["iPhone", "iPad"]
|
||||
while len(uas) < count:
|
||||
device = random.choice(devices)
|
||||
ios_major = random.randint(16, 17)
|
||||
ios_minor = random.randint(1, 5)
|
||||
ios_patch = random.randint(1, 3)
|
||||
safari_build = f"605.1.{random.randint(10, 15)}"
|
||||
ios_major = random.randint(18, 19)
|
||||
ios_minor = random.randint(1, 4)
|
||||
ios_patch = random.randint(0, 2)
|
||||
safari_build = f"618.1.{random.randint(10, 15)}"
|
||||
safari_version = f"{ios_major}.{random.choice(['0', '1', '2', '3'])}"
|
||||
|
||||
uas.add(f"Mozilla/5.0 ({device}; CPU {'iPhone ' if device=='iPhone' else ''}OS {ios_major}_{ios_minor}_{ios_patch} like Mac OS X) AppleWebKit/{safari_build} (KHTML, like Gecko) Version/{safari_version} Mobile/15E148 Safari/604.1")
|
||||
@@ -51,27 +50,29 @@ def generate_ios_ua(count=1000):
|
||||
|
||||
def generate_android_ua(count=1000):
|
||||
uas = set()
|
||||
# 主流 Android 机型库
|
||||
models = ["Pixel 8 Pro", "Pixel 8", "Pixel 7a", "Pixel 7 Pro", "SM-S928B", "SM-S928U", "SM-S918B", "SM-A546B", "SM-A346B", "23113RKC6C", "23049PCD8G", "CPH2437", "V2227A", "PGT-AN10", "NX729J"]
|
||||
# 2025 年迭代更新的主流智能移动端型号库 (如 Pixel 9系列, S25系列)
|
||||
models = [
|
||||
"Pixel 9 Pro", "Pixel 9", "Pixel 8a", "Pixel 9 Pro XL",
|
||||
"SM-S938B", "SM-S938U", "SM-S931B", "SM-A566B", "SM-A366B",
|
||||
"25011RKC6C", "24129PCD8G", "CPH2637", "V2427A", "PGT-AN20", "NX769J"
|
||||
]
|
||||
while len(uas) < count:
|
||||
android_ver = random.randint(12, 14)
|
||||
android_ver = random.randint(14, 15)
|
||||
model = random.choice(models)
|
||||
uas.add(f"Mozilla/5.0 (Linux; Android {android_ver}; {model}) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/{generate_chrome_version()} Mobile Safari/537.36")
|
||||
return list(uas)
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 确保输出目录存在
|
||||
os.makedirs('data', exist_ok=True)
|
||||
|
||||
# 严格按照“绝对坐标”顺序生成 4000 条数据
|
||||
pool = []
|
||||
pool.extend(generate_windows_ua(1000)) # 行 1-1000
|
||||
pool.extend(generate_macos_ua(1000)) # 行 1001-2000
|
||||
pool.extend(generate_ios_ua(1000)) # 行 2001-3000
|
||||
pool.extend(generate_android_ua(1000)) # 行 3001-4000
|
||||
pool.extend(generate_windows_ua(1000))
|
||||
pool.extend(generate_macos_ua(1000))
|
||||
pool.extend(generate_ios_ua(1000))
|
||||
pool.extend(generate_android_ua(1000))
|
||||
|
||||
with open('data/user_agents.txt', 'w') as f:
|
||||
for ua in pool:
|
||||
f.write(ua + '\n')
|
||||
|
||||
print(f"✅ 成功生成 4000 条高保真绝对坐标指纹库！")
|
||||
print(f"✅ 成功生成 4000 条 2025 年高保真换代坐标指纹库！")
|
||||
Reference in New Issue
Block a user