File size: 2,131 Bytes
901a13f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
import requests
import re
import time
base_url = "https://www.blackbox.ai"
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
}
# Cache variables
cached_hid = None
cache_time = 0
CACHE_DURATION = 36000 # Cache duration in seconds (10 hour)
def getHid(force_refresh=False):
global cached_hid, cache_time
current_time = time.time()
# 检查是否强制刷新或缓存值是否仍然有效
if not force_refresh and cached_hid and (current_time - cache_time) < CACHE_DURATION:
print("using cached_hid:", cached_hid)
return cached_hid
try:
# 获取初始 HTML 内容
response = requests.get(base_url, headers=headers)
response.raise_for_status()
content = response.text
# 使用正则表达式查找特定的 static/chunks 路径
pattern = r"static/chunks/app/layout-[a-zA-Z0-9]+\.js"
match = re.search(pattern, content)
if match:
# 构造 JS 文件的完整 URL
js_path = match.group()
full_url = f"{base_url}/_next/{js_path}"
# 请求 JS 文件内容
js_response = requests.get(full_url, headers=headers)
js_response.raise_for_status()
# 在 JS 内容中使用正则表达式搜索 h-value
h_pattern = r'h="([0-9a-f-]+)"'
h_match = re.search(h_pattern, js_response.text)
if h_match:
h_value = h_match.group(1)
print("找到 h-value:", h_value)
# 更新缓存
cached_hid = h_value
cache_time = current_time
return h_value
else:
print("在 JS 内容中未找到 h-value")
return None
else:
print("在 HTML 内容中未找到指定的 JS 文件路径")
return None
except requests.exceptions.RequestException as e:
print(f"发生错误: {e}")
return None
|