| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117 |
- import { processLine } from './lib/process-line';
- import { normalizeDomain } from './lib/normalize-domain';
- import { createTrie } from './lib/trie';
- import { Readable } from 'stream';
- import { parse } from 'csv-parse';
- import { readFileByLine } from './lib/fetch-text-by-line';
- import path from 'path';
- export const parseGfwList = async () => {
- const whiteSet = new Set<string>();
- const blackSet = new Set<string>();
- const text = await (await fetch('https://raw.githubusercontent.com/gfwlist/gfwlist/master/gfwlist.txt')).text();
- for (const l of atob(text).split('\n')) {
- const line = processLine(l);
- if (!line) continue;
- if (line[0] === '[') {
- continue;
- }
- if (line.includes('.*')) {
- continue;
- }
- if (line.includes('*')) {
- continue;
- }
- if (line.startsWith('@@||')) {
- whiteSet.add(line.slice(4));
- continue;
- }
- if (line.startsWith('@@|http://')) {
- whiteSet.add(line.slice(8));
- continue;
- }
- if (line.startsWith('@@|https://')) {
- whiteSet.add(line.slice(9));
- continue;
- }
- if (line.startsWith('||')) {
- blackSet.add(line.slice(2));
- continue;
- }
- if (line.startsWith('|')) {
- blackSet.add(line.slice(1));
- continue;
- }
- if (line.startsWith('.')) {
- blackSet.add(line.slice(1));
- continue;
- }
- const d = normalizeDomain(line);
- if (d) {
- blackSet.add(d);
- continue;
- }
- }
- const top500Gfwed = new Set<string>();
- const res = await fetch('https://radar.cloudflare.com/charts/LargerTopDomainsTable/attachment?id=843&top=1000');
- const stream = Readable.fromWeb(res.body!).pipe(parse());
- const trie = createTrie(blackSet);
- for await (const [domain] of stream) {
- if (trie.has(domain)) {
- top500Gfwed.add(domain);
- }
- }
- const notIncludedTop500Gfwed = new Set<string>(top500Gfwed);
- const runAgainstRuleset = async (ruleset: string) => {
- for await (const l of readFileByLine(ruleset)) {
- const line = processLine(l);
- if (!line) continue;
- const [type, domain] = line.split(',');
- if (type === 'DOMAIN-SUFFIX') {
- if (top500Gfwed.has(domain)) {
- notIncludedTop500Gfwed.delete(domain);
- }
- } else if (type === 'DOMAIN-KEYWORD') {
- for (const d of top500Gfwed) {
- if (d.includes(domain)) {
- notIncludedTop500Gfwed.delete(d);
- }
- }
- }
- }
- };
- await Promise.all([
- runAgainstRuleset(path.resolve(import.meta.dir, '../Source/non_ip/global_plus.conf')),
- runAgainstRuleset(path.resolve(import.meta.dir, '../List/non_ip/stream.conf'))
- ]);
- // for await (const l of readFileByLine(path.resolve(import.meta.dir, '../List/non_ip/stream.conf'))) {
- // const line = processLine(l);
- // if (!line) continue;
- // const domain = line[0] === '.' ? line.slice(1) : line;
- // if (top500Gfwed.has(domain)) {
- // notIncludedTop500Gfwed.delete(domain);
- // }
- // }
- console.log(notIncludedTop500Gfwed);
- return [
- whiteSet,
- blackSet,
- trie,
- top500Gfwed
- ] as const;
- };
- if (import.meta.main) {
- parseGfwList();
- }
|