用于 AI 训练数据和大型语言模型网络语料库的代理

import urllib.robotparser
from urllib.parse import urlsplit

import requests

PROXY = "http://USERNAME:[email protected]:7777"
PROXIES = {"http": PROXY, "https": PROXY}
USER_AGENT = "ExampleDataBot/1.0 (+https://example.com/bot)"
_rules = {}


def site_rules(url):
    """Robots rules and Content-Signal values for the site of url (cache them for 24 h at most)."""
    scheme, host = urlsplit(url)[:2]
    root = "%s://%s" % (scheme, host)
    if root not in _rules:
        try:
            r = requests.get(root + "/robots.txt", proxies=PROXIES, timeout=(10, 30),
                             headers={"User-Agent": USER_AGENT})
            status, text = r.status_code, r.text
        except requests.RequestException:
            status, text = 599, ""
        if 400 <= status < 500:
            lines = []  # RFC 9309: unavailable, crawling allowed
        elif status >= 500:
            lines = ["User-agent: *", "Disallow: /"]  # unreachable: assume complete disallow
        else:
            lines = text.splitlines()
        parser = urllib.robotparser.RobotFileParser()
        parser.parse(lines)
        signals = {}
        for line in lines:
            if line.lower().startswith("content-signal:"):
                for part in line.split(":", 1)[1].split(","):
                    key, _, value = part.strip().partition("=")
                    signals[key.strip().lower()] = value.strip().lower()
        _rules[root] = (parser, signals)
    return _rules[root]


def may_collect_for_training(url):
    parser, signals = site_rules(url)
    return parser.can_fetch(USER_AGENT, url) and signals.get("ai-train") != "no"


print(may_collect_for_training("https://example.com/some/page"))