Update api/validate.py
Browse files- api/validate.py +27 -32
api/validate.py
CHANGED
|
@@ -2,66 +2,61 @@ import requests
|
|
| 2 |
import re
|
| 3 |
import time
|
| 4 |
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
"User-Agent": (
|
| 8 |
-
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
|
| 9 |
-
"AppleWebKit/537.36 (KHTML, like Gecko) "
|
| 10 |
-
"Chrome/91.0.4472.124 Safari/537.36"
|
| 11 |
-
)
|
| 12 |
}
|
| 13 |
|
| 14 |
# Cache variables
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
CACHE_DURATION = 36000 # Cache duration in seconds (10
|
| 18 |
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
global _cached_hid, _cache_time
|
| 22 |
current_time = time.time()
|
| 23 |
|
| 24 |
-
#
|
| 25 |
-
if not force_refresh and
|
| 26 |
-
print("
|
| 27 |
-
return
|
| 28 |
|
| 29 |
try:
|
| 30 |
-
#
|
| 31 |
-
response = requests.get(
|
| 32 |
response.raise_for_status()
|
| 33 |
content = response.text
|
| 34 |
|
| 35 |
-
#
|
| 36 |
pattern = r"static/chunks/app/layout-[a-zA-Z0-9]+\.js"
|
| 37 |
match = re.search(pattern, content)
|
| 38 |
|
| 39 |
if match:
|
| 40 |
-
#
|
| 41 |
js_path = match.group()
|
| 42 |
-
full_url = f"{
|
| 43 |
|
| 44 |
-
#
|
| 45 |
-
js_response = requests.get(full_url, headers=
|
| 46 |
js_response.raise_for_status()
|
| 47 |
|
| 48 |
-
#
|
| 49 |
h_pattern = r'h="([0-9a-f-]+)"'
|
| 50 |
h_match = re.search(h_pattern, js_response.text)
|
| 51 |
|
| 52 |
if h_match:
|
| 53 |
h_value = h_match.group(1)
|
| 54 |
-
print("
|
| 55 |
-
#
|
| 56 |
-
|
| 57 |
-
|
| 58 |
return h_value
|
| 59 |
else:
|
| 60 |
-
print("h-value
|
| 61 |
return None
|
| 62 |
else:
|
| 63 |
-
print("
|
| 64 |
return None
|
| 65 |
except requests.exceptions.RequestException as e:
|
| 66 |
-
print(f"
|
| 67 |
return None
|
|
|
|
| 2 |
import re
|
| 3 |
import time
|
| 4 |
|
| 5 |
+
base_url = "https://www.blackbox.ai"
|
| 6 |
+
headers = {
|
| 7 |
+
"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"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
| 9 |
|
| 10 |
# Cache variables
|
| 11 |
+
cached_hid = None
|
| 12 |
+
cache_time = 0
|
| 13 |
+
CACHE_DURATION = 36000 # Cache duration in seconds (10 hour)
|
| 14 |
|
| 15 |
+
def getHid(force_refresh=False):
|
| 16 |
+
global cached_hid, cache_time
|
|
|
|
| 17 |
current_time = time.time()
|
| 18 |
|
| 19 |
+
# 检查是否强制刷新或缓存值是否仍然有效
|
| 20 |
+
if not force_refresh and cached_hid and (current_time - cache_time) < CACHE_DURATION:
|
| 21 |
+
print("using cached_hid:", cached_hid)
|
| 22 |
+
return cached_hid
|
| 23 |
|
| 24 |
try:
|
| 25 |
+
# 获取初始 HTML 内容
|
| 26 |
+
response = requests.get(base_url, headers=headers)
|
| 27 |
response.raise_for_status()
|
| 28 |
content = response.text
|
| 29 |
|
| 30 |
+
# 使用正则表达式查找特定的 static/chunks 路径
|
| 31 |
pattern = r"static/chunks/app/layout-[a-zA-Z0-9]+\.js"
|
| 32 |
match = re.search(pattern, content)
|
| 33 |
|
| 34 |
if match:
|
| 35 |
+
# 构造 JS 文件的完整 URL
|
| 36 |
js_path = match.group()
|
| 37 |
+
full_url = f"{base_url}/_next/{js_path}"
|
| 38 |
|
| 39 |
+
# 请求 JS 文件内容
|
| 40 |
+
js_response = requests.get(full_url, headers=headers)
|
| 41 |
js_response.raise_for_status()
|
| 42 |
|
| 43 |
+
# 在 JS 内容中使用正则表达式搜索 h-value
|
| 44 |
h_pattern = r'h="([0-9a-f-]+)"'
|
| 45 |
h_match = re.search(h_pattern, js_response.text)
|
| 46 |
|
| 47 |
if h_match:
|
| 48 |
h_value = h_match.group(1)
|
| 49 |
+
print("找到 h-value:", h_value)
|
| 50 |
+
# 更新缓存
|
| 51 |
+
cached_hid = h_value
|
| 52 |
+
cache_time = current_time
|
| 53 |
return h_value
|
| 54 |
else:
|
| 55 |
+
print("在 JS 内容中未找到 h-value")
|
| 56 |
return None
|
| 57 |
else:
|
| 58 |
+
print("在 HTML 内容中未找到指定的 JS 文件路径")
|
| 59 |
return None
|
| 60 |
except requests.exceptions.RequestException as e:
|
| 61 |
+
print(f"发生错误: {e}")
|
| 62 |
return None
|