Paijo commited on
update app/grabber/patterns.py
Browse files- app/grabber/patterns.py +71 -0
app/grabber/patterns.py
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
from typing import List, Tuple
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
class ProxyPatterns:
|
| 6 |
+
HTTP_IP_PORT = re.compile(
|
| 7 |
+
r"\b(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}"
|
| 8 |
+
r"(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)"
|
| 9 |
+
r":([0-9]{1,5})\b"
|
| 10 |
+
)
|
| 11 |
+
|
| 12 |
+
VMESS_URL = re.compile(r"vmess://[A-Za-z0-9+/=]+")
|
| 13 |
+
|
| 14 |
+
VLESS_URL = re.compile(r"vless://[a-zA-Z0-9-]+@[a-zA-Z0-9.-]+:[0-9]+[^\s]*")
|
| 15 |
+
|
| 16 |
+
TROJAN_URL = re.compile(r"trojan://[^@\s]+@[a-zA-Z0-9.-]+:[0-9]+[^\s]*")
|
| 17 |
+
|
| 18 |
+
SS_URL = re.compile(r"ss://[A-Za-z0-9+/=]+@[a-zA-Z0-9.-]+:[0-9]+")
|
| 19 |
+
|
| 20 |
+
@classmethod
|
| 21 |
+
def extract_http_proxies(cls, text: str) -> List[Tuple[str, str]]:
|
| 22 |
+
result = []
|
| 23 |
+
for match in cls.HTTP_IP_PORT.finditer(text):
|
| 24 |
+
ip_port = match.group(0)
|
| 25 |
+
ip, port = ip_port.rsplit(":", 1)
|
| 26 |
+
result.append((ip, port))
|
| 27 |
+
return result
|
| 28 |
+
|
| 29 |
+
@classmethod
|
| 30 |
+
def is_vmess(cls, url: str) -> bool:
|
| 31 |
+
return bool(cls.VMESS_URL.match(url))
|
| 32 |
+
|
| 33 |
+
@classmethod
|
| 34 |
+
def extract_vmess_urls(cls, text: str) -> List[str]:
|
| 35 |
+
return cls.VMESS_URL.findall(text)
|
| 36 |
+
|
| 37 |
+
@classmethod
|
| 38 |
+
def is_vless(cls, url: str) -> bool:
|
| 39 |
+
return bool(cls.VLESS_URL.match(url))
|
| 40 |
+
|
| 41 |
+
@classmethod
|
| 42 |
+
def extract_vless_urls(cls, text: str) -> List[str]:
|
| 43 |
+
return cls.VLESS_URL.findall(text)
|
| 44 |
+
|
| 45 |
+
@classmethod
|
| 46 |
+
def is_trojan(cls, url: str) -> bool:
|
| 47 |
+
return bool(cls.TROJAN_URL.match(url))
|
| 48 |
+
|
| 49 |
+
@classmethod
|
| 50 |
+
def extract_trojan_urls(cls, text: str) -> List[str]:
|
| 51 |
+
return cls.TROJAN_URL.findall(text)
|
| 52 |
+
|
| 53 |
+
@classmethod
|
| 54 |
+
def is_shadowsocks(cls, url: str) -> bool:
|
| 55 |
+
return bool(cls.SS_URL.match(url))
|
| 56 |
+
|
| 57 |
+
@classmethod
|
| 58 |
+
def extract_ss_urls(cls, text: str) -> List[str]:
|
| 59 |
+
return cls.SS_URL.findall(text)
|
| 60 |
+
|
| 61 |
+
@classmethod
|
| 62 |
+
def is_valid_ip(cls, ip: str) -> bool:
|
| 63 |
+
try:
|
| 64 |
+
octets = ip.split(".")
|
| 65 |
+
return len(octets) == 4 and all(0 <= int(o) <= 255 for o in octets)
|
| 66 |
+
except (ValueError, AttributeError):
|
| 67 |
+
return False
|
| 68 |
+
|
| 69 |
+
@classmethod
|
| 70 |
+
def is_valid_port(cls, port: int) -> bool:
|
| 71 |
+
return 1 <= port <= 65535
|