Files
proxy-scraper-checker/proxy_scraper_checker/parsers.py
T
monosansandGitHub e4047e16ae Huge update
- Drop support for Python 3.7.
- Use offline geolocation database instead of ip-api.com.
- Add support for proxy authentication.
- Add pre-compiled binaries.
- Refactor the code by a lot.
- Simplify config.
- Add automatic text encoding detection.
- Use TOML instead of INI for configuration.
- Add support for using httpbin-compatible services and services which return plain IP address for getting proxy's exit node.
- Add support for reading proxy lists from local files.
- Add support for saving to json.
- Remove support for saving geolocation to txt, use json instead.
- Improve parser.
- Improve config validation.
- Use poetry instead of requirements.txt.
- Use venv in start scripts.
2024-01-21 17:45:01 +00:00

20 lines
840 B
Python

from __future__ import annotations
import re
PROXY_REGEX = re.compile(
r"(?:^|[^\.\/\d:@A-Za-z])(?:(?P<protocol>https?|socks[45]):\/\/)?(?:(?P<username>[\dA-Za-z]*):(?P<password>[\dA-Za-z]*)@)?(?P<host>(?:\d|[1-9]\d|1\d{2}|2[0-4]\d|25[0-5])(?:\.(?:\d|[1-9]\d|1\d{2}|2[0-4]\d|25[0-5])){3}):(?P<port>\d|[1-9]\d{1,3}|[1-5]\d{4}|6[0-4]\d{3}|65[0-4]\d{2}|655[0-2]\d|6553[0-5])(?=[^\.\/\d:@A-Za-z]|$)",
flags=re.MULTILINE | re.IGNORECASE,
)
IPV4_REGEX = re.compile(
r"^\s*(?P<host>(?:\d|[1-9]\d|1\d{2}|2[0-4]\d|25[0-5])(?:\.(?:\d|[1-9]\d|1\d{2}|2[0-4]\d|25[0-5])){3})(?::(?:\d|[1-9]\d{1,3}|[1-5]\d{4}|6[0-4]\d{3}|65[0-4]\d{2}|655[0-2]\d|6553[0-5]))?\s*$"
)
def parse_ipv4(s: str, /) -> str:
"""Parse ip from ip:port."""
match = IPV4_REGEX.match(s)
if not match:
raise ValueError
return match.group("host")