chore: add eslint-plugin-regexp (#22189)

* chore: add eslint-plugin-regexp

* chore: autofix

* chore: fix no-useless-flag

* chore: fix optimal-lookaround-quantifier

* chore: fix no-lazy-ends

* chore: fix no-contradiction-with-assertion

* chore: fix no-useless-assertions

* chore: fix no-useless-quantifier

* chore: fix remaining regexp issues

* fix: regex for WFU news link validation
This commit is contained in:
Tony 2026-06-05 20:04:39 +08:00 committed by GitHub
parent bedeb4edaa
commit 75d43dd086
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
208 changed files with 418 additions and 295 deletions

View File

@ -14,6 +14,7 @@
"jsPlugins": [
{ "name": "n", "specifier": "eslint-plugin-n" },
{ "name": "unicorn-js", "specifier": "eslint-plugin-unicorn" },
{ "name": "regexp", "specifier": "eslint-plugin-regexp" },
"@stylistic/eslint-plugin",
"eslint-plugin-simple-import-sort",
"oxlint-plugin-eslint",
@ -32,19 +33,19 @@
"no-const-assign": "error",
"no-constant-binary-expression": "error",
"no-constant-condition": "error",
// "no-control-regex": "error", -> off
"no-control-regex": "error",
"no-debugger": "error",
"no-dupe-class-members": "error",
"no-dupe-else-if": "error",
"no-dupe-keys": "error",
"no-duplicate-case": "error",
"no-empty-character-class": "error",
// "no-empty-character-class": "error", -> off, handled by eslint-plugin-regexp
"no-empty-pattern": "error",
"no-ex-assign": "error",
"no-fallthrough": "error",
"no-func-assign": "error",
"no-import-assign": "error",
"no-invalid-regexp": "error",
// "no-invalid-regexp": "error", -> off, handled by eslint-plugin-regexp
"no-irregular-whitespace": "error",
"no-loss-of-precision": "error",
"no-misleading-character-class": "error",
@ -65,7 +66,7 @@
"no-unsafe-optional-chaining": "error",
"no-unused-private-class-members": "error",
// "no-unused-vars": "error", -> off for @typescript-eslint/no-unused-vars
"no-useless-backreference": "error",
// "no-useless-backreference": "error", -> off, handled by eslint-plugin-regexp
"use-isnan": "error",
"valid-typeof": "error",
// #endregion
@ -289,12 +290,74 @@
"unicorn/throw-new-error": "error",
// #endregion
// #region --- regexp recommended ---
"regexp/confusing-quantifier": "warn",
"regexp/control-character-escape": "error",
"regexp/match-any": "error",
"regexp/negation": "error",
"regexp/no-contradiction-with-assertion": "error",
"regexp/no-dupe-characters-character-class": "error",
"regexp/no-dupe-disjunctions": "error",
"regexp/no-empty-alternative": "warn",
"regexp/no-empty-capturing-group": "error",
"regexp/no-empty-character-class": "error",
"regexp/no-empty-group": "error",
"regexp/no-empty-lookarounds-assertion": "error",
"regexp/no-empty-string-literal": "error",
"regexp/no-escape-backspace": "error",
"regexp/no-extra-lookaround-assertions": "error",
"regexp/no-invalid-regexp": "error",
"regexp/no-invisible-character": "error",
"regexp/no-lazy-ends": "warn",
"regexp/no-legacy-features": "error",
"regexp/no-misleading-capturing-group": "error",
"regexp/no-misleading-unicode-character": "error",
"regexp/no-missing-g-flag": "error",
"regexp/no-non-standard-flag": "error",
"regexp/no-obscure-range": "error",
"regexp/no-optional-assertion": "error",
"regexp/no-potentially-useless-backreference": "warn",
"regexp/no-super-linear-backtracking": "error",
"regexp/no-trivially-nested-assertion": "error",
"regexp/no-trivially-nested-quantifier": "error",
"regexp/no-unused-capturing-group": "error",
"regexp/no-useless-assertions": "error",
"regexp/no-useless-backreference": "error",
"regexp/no-useless-character-class": "error",
"regexp/no-useless-dollar-replacements": "error",
"regexp/no-useless-escape": "error",
"regexp/no-useless-flag": "warn",
"regexp/no-useless-lazy": "error",
"regexp/no-useless-non-capturing-group": "error",
"regexp/no-useless-quantifier": "error",
"regexp/no-useless-range": "error",
"regexp/no-useless-set-operand": "error",
"regexp/no-useless-string-literal": "error",
"regexp/no-useless-two-nums-quantifier": "error",
"regexp/no-zero-quantifier": "error",
"regexp/optimal-lookaround-quantifier": "warn",
"regexp/optimal-quantifier-concatenation": "error",
"regexp/prefer-character-class": "error",
"regexp/prefer-d": "error",
"regexp/prefer-plus-quantifier": "error",
"regexp/prefer-predefined-assertion": "error",
"regexp/prefer-question-quantifier": "error",
"regexp/prefer-range": "error",
"regexp/prefer-set-operation": "error",
"regexp/prefer-star-quantifier": "error",
"regexp/prefer-unicode-codepoint-escapes": "error",
"regexp/prefer-w": "error",
"regexp/simplify-set-operations": "error",
"regexp/sort-flags": "error",
"regexp/strict": "error",
"regexp/use-ignore-case": "error",
// #endregion
// --- custom rules ---
// #region --- possible problems ---
"array-callback-return": ["error", { "allowImplicit": true }],
"no-await-in-loop": "error",
"no-control-regex": "off",
"no-prototype-builtins": "off",
"no-undef": "off", // typescript/eslint-recommended, ts(2552)
// #endregion

View File

@ -6,7 +6,7 @@ import { config } from '@/config';
import type { Data } from '@/types';
import logger from '@/utils/logger';
const templateRegex = /\${([^{}]+)}/g;
const templateRegex = /\$\{([^{}]+)\}/g;
const allowedUrlProperties = new Set(['hash', 'host', 'hostname', 'href', 'origin', 'password', 'pathname', 'port', 'protocol', 'search', 'searchParams', 'username']);
// match path or sub-path
@ -150,7 +150,7 @@ const middleware: MiddlewareHandler = async (ctx, next) => {
if (item.enclosure_url && item.enclosure_type) {
if (item.enclosure_type.startsWith('image/')) {
item.enclosure_url = replaceUrl(imageHotlinkTemplate, item.enclosure_url);
} else if (/^(video|audio)\//.test(item.enclosure_type)) {
} else if (/^(?:video|audio)\//.test(item.enclosure_type)) {
item.enclosure_url = replaceUrl(multimediaHotlinkTemplate, item.enclosure_url);
}
}

View File

@ -28,7 +28,7 @@ const middleware: MiddlewareHandler = async (ctx, next) => {
return ctx.json(ctx.get('json') || { message: 'plugin does not set debug json' });
}
if (/(\d+)\.debug\.html$/.test(outputType)) {
if (/\d+\.debug\.html$/.test(outputType)) {
const index = Number.parseInt(outputType.match(/(\d+)\.debug\.html$/)?.[1] || '0');
return ctx.html(data?.item?.[index]?.description || `data.item[${index}].description not found`);
}
@ -58,7 +58,8 @@ const middleware: MiddlewareHandler = async (ctx, next) => {
// https://stackoverflow.com/questions/1497885/remove-control-characters-from-php-string/1497928#1497928
// remove unicode control characters
// see #14940 #14943 #15262
item.description = item.description.replaceAll(/[\u0000-\u0009\u000B\u000C\u000E-\u001F\u007F\u200B\uFFFF]/g, '');
// oxlint-disable-next-line no-control-regex
item.description = item.description.replaceAll(/[\u0000-\u0009\v\f\u000E-\u001F\u007F\u200B\uFFFF]/g, '');
}
if (typeof item.author === 'string') {

View File

@ -16,7 +16,7 @@ const handler = async (ctx) => {
const $ = cheerio.load(response.data);
const pattern = /item=(\[{.*?}]);/;
const pattern = /item=(\[\{.*?\}\]);/;
const newsList = JSON.parse($('script[language="javascript"]').text().match(pattern)?.[1].replaceAll("'", '"') || '[]');
const topNewsList = newsList.slice(0, limit).map((item) => ({

View File

@ -102,7 +102,7 @@ async function handler(ctx) {
const url = `https://3g.163.com/touch/reconstruct/article/list/${type}/0-20.html`;
const response = await got(url);
const data = response.data;
const matches = data.replaceAll(/\s/g, '').match(/artiList\((.*?)]}\)/);
const matches = data.replaceAll(/\s/g, '').match(/artiList\((.*?)\]\}\)/);
const articlelist0 = matches[1].replace(/".*?wangning/, '"articles') + ']}';
const articlelist = JSON.parse(articlelist0);
const articles = articlelist.articles;
@ -112,7 +112,7 @@ async function handler(ctx) {
let url = article.url;
if (url === null || article.skipType === 'video') {
const skipurl = article.skipURL;
const vid = skipurl.match(/vid=(.*?)$/);
const vid = skipurl.match(/vid=(.*)$/);
if (vid !== null) {
url = `https://3g.163.com/exclusive/video/${vid[1]}.html`;
}

View File

@ -65,7 +65,7 @@ async function handler() {
const initialState = JSON.parse(
$('script')
.text()
.match(/window\.__INITIAL_STATE__=(.*);\(function\(\){var/)[1]
.match(/window\.__INITIAL_STATE__=(.*);\(function\(\)\{var/)[1]
);
const list = Object.values(initialState.courseindex.myModules).flatMap((mod) =>

View File

@ -164,7 +164,7 @@ async function handler(ctx) {
}
}
if (!item.enclosure_url) {
const hashMatch = readTpcHtml.match(/哈希校验[^;]*;\s*([a-fA-F0-9]{40})\s*[;]/);
const hashMatch = readTpcHtml.match(/哈希校验[^;]*;\s*([a-f0-9]{40})\s*[;]/i);
const magnetFromHash = hashMatch ? `magnet:?xt=urn:btih:${hashMatch[1]}` : null;
const magnetFromText = magnetText.match(/magnet:\?xt=urn:btih:[^\s"'<>]+/)?.[0];
const magnetLink = magnetFromText ?? readTpcHtml.match(/magnet:\?xt=urn:btih:[^\s"'<>]+/)?.[0] ?? magnetFromHash ?? copyLink;

View File

@ -79,7 +79,7 @@ async function handler(ctx) {
},
});
const data = getProperty(JSON.parse(response.data.match(/window.initialState=({.*})/)[1]), categories[category].key);
const data = getProperty(JSON.parse(response.data.match(/window.initialState=(\{.*\})/)[1]), categories[category].key);
let items = data
.slice(0, ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit')) : 10)

View File

@ -48,7 +48,7 @@ async function handler(ctx) {
const $ = load(response.data);
const data = JSON.parse(response.data.match(/"itemList":(\[.*?])/)[1]);
const data = JSON.parse(response.data.match(/"itemList":(\[.*?\])/)[1]);
let items = data
.slice(0, ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit')) : 30)
@ -64,7 +64,7 @@ async function handler(ctx) {
};
});
if (!/^\/(search|newsflashes)/.test(path)) {
if (!/^\/(?:search|newsflashes)/.test(path)) {
items = await Promise.all(items.map((item) => ProcessItem(item, cache.tryGet)));
}

View File

@ -11,7 +11,7 @@ export const ProcessItem = (item, tryGet) =>
tryGet(item.link, async () => {
const detailResponse = await ofetch(item.link);
const cipherTextList = detailResponse.match(/{"state":"(.*)","isEncrypt":true}/) ?? [];
const cipherTextList = detailResponse.match(/\{"state":"(.*)","isEncrypt":true\}/) ?? [];
if (cipherTextList.length === 0) {
const $ = load(detailResponse);

View File

@ -11,7 +11,7 @@ const parseArticle = (item, tryGet) =>
if (item.link.startsWith('https://dl.3dmgame.com/')) {
const lis = $('.patchtop .lis');
const [, category, pubDate, author] = lis.text().match(/(.*?)\n.*(.*?)\n.*(.*?)\n/s);
const [, category, pubDate, author] = lis.text().match(/([^\n]*)\n.*([^\n]*)\n.*([^\n]*)\n/s);
item.description = lis.html() + $('.L_title').html() + $('.GmL_1').html();
item.category = category;

View File

@ -114,7 +114,7 @@ async function handler(ctx) {
const scriptUrl = new URL(scriptPath, rootUrl).href;
const scriptResponse = await ofetch(scriptUrl);
const key = scriptResponse.match(/{var key="(.*?)"/)?.[1];
const key = scriptResponse.match(/\{var key="(.*?)"/)?.[1];
const value = scriptResponse.match(/",value="(.*?)"/)?.[1];
const getPath = scriptResponse.match(/\.get\("(.*?&key=)"/)?.[1];

View File

@ -54,8 +54,8 @@ const createItem = (url: string) =>
cache.tryGet(url, async () => {
const html = await get(url);
const $ = load(html);
const { articleid, chapterid, chaptername } = parseObject(/bookinfo\s?=\s?{[\S\s]+?}/, $('head>script:not([src])').text());
const decryptionMap = parseObject(/_\d+\s?=\s?{[\S\s]+?}/, $('.txtnav+script').text());
const { articleid, chapterid, chaptername } = parseObject(/bookinfo\s?=\s?\{[\s\S]+?\}/, $('head>script:not([src])').text());
const decryptionMap = parseObject(/_\d+\s?=\s?\{[\s\S]+?\}/, $('.txtnav+script').text());
return {
title: chaptername,
@ -70,7 +70,7 @@ const parseObject = (reg: RegExp, str: string): Record<string, string> => {
const obj = {};
const match = reg.exec(str);
if (match) {
for (const line of match[0].matchAll(/(\w+):\s?["']?([\S\s]+?)["']?[\n,}]/g)) {
for (const line of match[0].matchAll(/(\w+):\s?["']?([\s\S]+?)["']?[\n,}]/g)) {
obj[line[1]] = line[2];
}
}

View File

@ -66,7 +66,7 @@ async function handler(ctx) {
const content = load(detailResponse.data);
item.title = content('title').text().replace(' -6park.com', '');
item.author = detailResponse.data.match(/送交者: .*>(.*)<.*\[/)[1];
item.author = detailResponse.data.match(/送交者:[^>]*>([^<]*)<\/a>/)[1].trim();
item.pubDate = timezone(parseDate(detailResponse.data.match(/于 (.*) 已读/)[1], 'YYYY-MM-DD h:m'), +8);
item.description = content('pre')
.html()

View File

@ -76,7 +76,7 @@ async function handler(ctx) {
const content = load(detailResponse.data);
const matches = detailResponse.data.match(/新闻来源:(.*?)于.*(\d{4}(?:-\d{2}){2} (?:\d{1,2}:){2}\d{1,2})/);
const matches = detailResponse.data.match(/新闻来源:([^于]*)于.*(\d{4}(?:-\d{2}){2} (?:\d{1,2}:){2}\d{1,2})/);
item.title = content('h2').text();
item.author = matches[1].trim();

View File

@ -22,7 +22,7 @@ const ProcessFeed = (data) => {
content.find('div').each((i, e) => {
if ($(e)[0].attribs.class) {
const classes = $(e)[0].attribs.class;
if (/\w{10}\s\w{10}/g.test(classes)) {
if (/\w{10}\s\w{10}/.test(classes)) {
$(e).remove();
}
}

View File

@ -49,7 +49,7 @@ async function handler(ctx) {
const feedUrl = new URL(`news/feed/${documentId}/rss.xml`, rootUrl).href;
const feedResponse = await ofetch(feedUrl);
currentUrl = feedResponse.match(/<link>([\w-./:?]+)<\/link>/)[1];
currentUrl = feedResponse.match(/<link>([\w./:?-]+)<\/link>/)[1];
}
const currentResponse = await ofetch(currentUrl);
@ -124,7 +124,7 @@ async function handler(ctx) {
item.title = content('meta[property="og:title"]').prop('content');
item.description = '';
const enclosurePattern = String.raw`"(?:MIME|content)?Type":"([\w]+/[\w]+)".*?"(?:fileS|s)?ize":(\d+),.*?"url":"([\w-.:/?]+)"`;
const enclosurePattern = String.raw`"(?:MIME|content)?Type":"(\w+/\w+)".*?"(?:fileS|s)?ize":(\d+),.*?"url":"([\w.:/?-]+)"`;
const enclosureMatches = detailResponse.match(new RegExp(enclosurePattern, 'g'));

View File

@ -40,7 +40,7 @@ async function handler(ctx) {
const list = $('#ac-space-video-list a').toArray();
const image = $('head style:contains("user-photo")')
.text()
.match(/.user-photo{\n\s*background:url\((.*)\) 0% 0% \/ 100% no-repeat;/)?.[1];
.match(/.user-photo\{\n\s*background:url\((.*)\) 0% 0% \/ 100% no-repeat;/)?.[1];
return {
title,

View File

@ -43,7 +43,7 @@ async function handler(ctx) {
const $ = load(response);
const jrnlName = $('meta[property="og:title"]')
.attr('content')
.match(/(?:[^=]*=)?\s*([^>]+)\s*/)[1];
.match(/(?:[^=]*=)?\s*([^>]+)/)[1];
const publication = $('.al-article-item-wrap.al-normal');
const list = publication.toArray().map((item) => {

View File

@ -71,7 +71,7 @@ function extractItem(a: Cheerio<any>, language: string) {
const descEl = a.find('p').first();
const description = descEl.text().trim();
const dateMatch = language === 'fr' ? description.match(/(\d{1,2} [a-zéû]+[.]? \d{4})/i) : description.match(/([A-Z][a-z]+[.]? \d{1,2}, \d{4})/);
const dateMatch = language === 'fr' ? description.match(/(\d{1,2} [a-zéû]+\.? \d{4})/i) : description.match(/([A-Z][a-z]+\.? \d{1,2}, \d{4})/);
const pubDateStr = dateMatch ? dateMatch[1].trim() : '';
const pubDate = parseDate(pubDateStr);

View File

@ -47,7 +47,7 @@ async function handler() {
}
}
const partRegex = /^([0-9a-zA-Z]+):([0-9a-zA-Z]+)?(\[.*)$/;
const partRegex = /^([0-9a-z]+):([0-9a-z]+)?(\[.*)$/i;
const fd = textList
.join('')
.split('\n')

View File

@ -23,7 +23,7 @@ async function handler(ctx) {
const $ = load(response);
let items = response
.match(/(parm\.newsTitle[\S\s]*?arr\.push\(parm\))/g)
.match(/(parm\.newsTitle[\s\S]*?arr\.push\(parm\))/g)
.slice(0, limit)
.map((item) => ({
title: item.match(/parm\.newsTitle = '(.*?)'/)[1],

View File

@ -42,7 +42,7 @@ async function handler() {
const data = response.data;
const $ = load(data);
const contents = $('script:contains("window.__PRELOADED_STATE__")').text();
const regex = /{.*}/;
const regex = /\{.*\}/;
let items = JSON.parse(contents.match(regex)[0]).shop.items;
items = items.filter((item) => item.availableSizes.length !== 0);

View File

@ -355,7 +355,7 @@ export const extractInitialData = ($: CheerioAPI): any => {
const initialDataText = JSON.parse(
$('script:contains("window.__INITIAL_DATA__")')
.text()
.match(/window\.__INITIAL_DATA__\s*=\s*(.*);/)?.[1] ?? '"{}"'
.match(/window\.__INITIAL_DATA__\s*=\s*(\S.*)?;/)?.[1] ?? '"{}"'
);
return JSON.parse(initialDataText);

View File

@ -117,7 +117,7 @@ const getWbiVerifyString = () => {
// 46, 47, 18, 2, 53, 8, 23, 32, 15, 50, 10, 31, 58, 3, 45, 35, 27, 43, 5, 49, 33, 9, 42, 19, 29, 28, 14, 39, 12, 38, 41, 13, 37, 48, 7, 16, 24, 55, 40, 61, 26, 17, 0, 1, 60, 51, 30, 4, 22, 25, 54, 21, 56, 59, 6, 63, 57,
// 62, 11, 36, 20, 34, 44, 52,
// ];
const array = JSON.parse(jsResponse.match(/\[(?:\d+,){63}\d+]/));
const array = JSON.parse(jsResponse.match(/\[(?:\d+,){63}\d+\]/));
const o = [];
for (const t of array) {
r.charAt(t) && o.push(r.charAt(t));
@ -350,7 +350,7 @@ const getArticleDataFromCvid = async (cvid, uid) => {
const newFormatData = JSON.parse(
$('script:contains("window.__INITIAL_STATE__")')
.text()
.match(/window\.__INITIAL_STATE__\s*=\s*(.*?);\(/)[1]
.match(/window\.__INITIAL_STATE__\s*=\s*(\S.*?)?;\(/)[1]
);
if (newFormatData?.readInfo?.opus?.content?.paragraphs) {

View File

@ -55,7 +55,8 @@ async function handler(ctx) {
item.description = $('.article-main').html();
item.author = $('.info')
.text()
.match(/作者:(.*)\s+来源/)[1];
.match(/作者:(.*?)来源/)[1]
.trim();
return item;
})
)

View File

@ -130,7 +130,7 @@ const getItem = (item, selector) => {
const newsDate = item
.find('span')
.text()
.match(/\d{4}(-|\/|.)\d{1,2}\1\d{1,2}/)[0];
.match(/\d{4}(.)\d{1,2}\1\d{1,2}/)[0];
const infoTitle = newsInfo.text();
const link = rootURL + newsInfo.attr('href');

View File

@ -59,7 +59,7 @@ async function handler(ctx) {
const content = load(response.data);
const info = content('div.info')
.text()
.match(/作者:(.*?)\s+发布于:(.*?\s+.*?)\s/);
.match(/作者:(\S*)\s+发布于:(\S*\s+.*?)\s/);
item.author = info[1];
item.pubDate = timezone(parseDate(info[2], 'YYYY-MM-DD HH:mm:ss'), +8);
item.description = content('div#con').html().trim().replaceAll('\n', '');

View File

@ -55,7 +55,7 @@ const apiEndpoints = {
},
};
const pageTypeRegex1 = /\/(?<page>[\w-]*?)\/(?<link>\d{4}-\d{2}-\d{2}\/.*)/;
const pageTypeRegex1 = /\/(?<page>[\w-]*)\/(?<link>\d{4}-\d{2}-\d{2}\/.*)/;
const pageTypeRegex2 = /(?<!news|politics)\/(?<page>features\/|graphics\/)(?<link>.*)/;
const regex = [pageTypeRegex1, pageTypeRegex2];

View File

@ -95,7 +95,7 @@ async function handler(ctx) {
statisticsTages.find('li, br, strong').remove();
const statisticsStr = statisticsTages.text();
const regex = /(?<key>[^\s:]+)\s*:\s*(?<value>.+)/gm;
const regex = /(?<key>[^\s:]+)\s*:\s*(?<value>.+)/g;
const result = {};
for (const match of statisticsStr.matchAll(regex)) {
const { key, value } = match.groups ?? ({} as { key: string; value: string });

View File

@ -183,7 +183,7 @@ async function handler(ctx) {
},
});
const data = JSON.parse(response.data.match(/null\(\[({.*})]\)/)[1]);
const data = JSON.parse(response.data.match(/null\(\[(\{.*\})\]\)/)[1]);
let items: DataItem[];

View File

@ -60,7 +60,7 @@ async function handler(ctx) {
const entity = JSON.parse(
$('script')
.text()
.match(/var entity = ({.*?})/)[1]
.match(/var entity = (\{.*?\})/)[1]
);
const {

View File

@ -14,7 +14,7 @@ export async function getFulltext(url: string) {
if (!config.caixin.cookie) {
return;
}
if (!/(\d+)\.html/.test(url)) {
if (!/\d+\.html/.test(url)) {
return;
}
const articleID = url.match(/(\d+)\.html/)[1];

View File

@ -55,7 +55,7 @@ async function handler() {
const $ = load(response.data);
const author = $('.qtinfo.hidden-lg.hidden-md.hidden-sm').text();
const reg = /文章来源:(.*?)\|/g;
const reg = /文章来源:(.*?)\|/;
item.title = $('p.wztitle').text().trim();
item.author = reg.exec(author)[1].toString().trim();

View File

@ -59,7 +59,7 @@ export const handler = async (ctx: Context): Promise<Data> => {
const metaStr: string = $$('div.newshead p span, div.title p span').text();
const pubDateStr: string | undefined = metaStr?.match(/(\d{4}-\d{2}-\d{2})/)?.[1];
const authors: DataItem['author'] = metaStr?.match(/来源:(.*?)/)?.[1];
const authors: DataItem['author'] = metaStr?.match(/来源:(.*)/)?.[1];
const upDatedStr: string | undefined = pubDateStr;
let processedItem: DataItem = {

View File

@ -17,7 +17,7 @@ const extractDates = (durationStr: string) => {
return { startDate, endDate };
}
const parts = durationStr.split(/——|-||~/).map((p) => p.trim()); // currently ——and- is used, add — or ~ for redundency
const parts = durationStr.split(/——|[-—~]/).map((p) => p.trim()); // currently ——and- is used, add — or ~ for redundency
const startStr = parts[0];
const endStr = parts[1];

View File

@ -40,7 +40,7 @@ async function handler(ctx) {
const initialState = JSON.parse(
$('script:contains("window.__INITIAL_STATE__")')
.text()
.match(/window\.__INITIAL_STATE__\s*=\s*({.*?});/)?.[1] || '{}'
.match(/window\.__INITIAL_STATE__\s*=\s*(\{.*?\});/)?.[1] || '{}'
);
const { dataResult, indNavLists, secondNameFilter, tagList, param } = initialState.data;

View File

@ -35,7 +35,7 @@ export const handler = async (ctx) => {
items = await Promise.all(
items.map((item) =>
cache.tryGet(item.link, async () => {
if (!/^https?:\/\/www\.cisia\.org(\/[^\s]*)?$/.test(item.link)) {
if (!/^https?:\/\/www\.cisia\.org(?:\/\S*)?$/.test(item.link)) {
return item;
}

View File

@ -21,7 +21,7 @@ function extractArticlesFromDOM($: CheerioAPI): DataItem[] {
// Extract date and author with single regex
const metaText = element.find('.text-sm.text-slate-500').text().trim();
const metaMatch = metaText.match(/^([^•]+)\s*•\s*([A-Za-z]+\s+\d{1,2},?\s+\d{4})/);
const metaMatch = metaText.match(/^([^•]+)•\s*([A-Z]+\s+\d{1,2},?\s+\d{4})/i);
const author = metaMatch ? metaMatch[1].trim() : 'Cline Team';
const pubDate = metaMatch ? parseDate(metaMatch[2]) : undefined;

View File

@ -65,7 +65,7 @@ function buildUrl(rootUrl: string, type: PostType, keyword: string | undefined,
function extractHomeList($: CheerioAPI, rootUrl: string, limit: number): DataItem[] {
try {
const scriptText = $('script:contains("_PageData")').text();
const match = scriptText.match(/const\s+_PageData\s*=\s*(\[[\s\S]*?]);/);
const match = scriptText.match(/const\s+_PageData\s*=\s*(\[[\s\S]*?\]);/);
if (!match?.[1]) {
return [];

View File

@ -88,7 +88,7 @@ async function handler(ctx) {
const $ = load(response);
if (item.link?.includes('/videos/')) {
const ldJson = JSON.parse($('script[type="application/ld+json"]:contains("VideoObject")').text());
const videoId = ldJson.embedUrl.match(/embed\/([a-zA-Z0-9_-]+)/)?.[1];
const videoId = ldJson.embedUrl.match(/embed\/([\w-]+)/)?.[1];
item.description =
`<iframe id="ytplayer" type="text/html" width="640" height="360" src="https://www.youtube-nocookie.com/embed/${videoId}" frameborder="0" allowfullscreen referrerpolicy="strict-origin-when-cross-origin"></iframe><br>` +

View File

@ -143,7 +143,7 @@ function extractCategories(article: ReturnType<CheerioAPI>, $: CheerioAPI): stri
const tagText = tagElement.text().trim();
// Skip summary/stats links and navigation
if (tagHref && tagText && !tagHref.includes('article/') && !tagHref.includes('Summary') && tagText.length < 50 && !/^(Summary|stats|About|Tags|Toggle|Trending|Latest|Previous|Next)$/i.test(tagText)) {
if (tagHref && tagText && !tagHref.includes('article/') && !tagHref.includes('Summary') && tagText.length < 50 && !/^(?:Summary|stats|About|Tags|Toggle|Trending|Latest|Previous|Next)$/i.test(tagText)) {
return tagText;
}
return null;

View File

@ -20,14 +20,14 @@ export const handler = async (ctx: Context): Promise<Data> => {
// Group 3: Trailing hyphens (unused, but for context)
// Group 4: Update content
// Uses global and multiline flags for all matches and line start/end anchors
const updateRegex = /^(-+)\s*\n(.*?)\s*\n(-+)\s*\n([\s\S]*?)(?=\n-{2,}|<\/p>)/gm;
const updateRegex = /^-+[^\S\n]*\n(.*)\r?\n-+[^\S\n]*\n([\s\S]*?)(?=\n-{2}|<\/p>)/gm;
const items: DataItem[] = [];
let match: RegExpExecArray | null;
while ((match = updateRegex.exec(response)) !== null && items.length < limit) {
const headerLine: string | undefined = match[2].trim();
const description: string | undefined = match[4].trim()?.replaceAll(/(\s[+-])/g, '<br>$1');
const headerLine: string | undefined = match[1].trim();
const description: string | undefined = match[2].trim()?.replaceAll(/(\s[+-])/g, '<br>$1');
let version = 'N/A';
let pubDateStr: string | undefined = undefined;

View File

@ -41,7 +41,7 @@ async function handler(ctx) {
const response = await got.get(currentUrl);
const $ = load(response.data);
const lists = $('div.c-box > div > div.c-zx-list > ul > li');
const reg = /日期:(.*?(\s\(.*?\))?)\s/;
const reg = /日期:(.*?(?:\s\(.*?\))?)\s/;
const list = lists.toArray().map((item) => {
item = $(item).find('div');
let date = reg.exec(item.find('div.r > p.other').text())[1];

View File

@ -28,7 +28,7 @@ const ProcessFeed = async (items, cookies, browser, limit, cache) => {
const data = JSON.parse(response);
let body = data.content;
body = body.replaceAll(/(?=https?:\/\/).*?(?<=\.(jpe?g|gif|png))/gi, (m) => `<img src="${m}">`);
body = body.replaceAll(/(?=https?:\/\/).*(?<!jpe?g"?>?)$/gim, (m) => `<a href="${m}">${m}</a>`);
body = body.replaceAll(/(?=https?:\/\/).+(?<!jpe?g"?>?)$/gim, (m) => `<a href="${m}">${m}</a>`);
body = body.replaceAll('\n', '<br>');
return body;

View File

@ -60,7 +60,7 @@ async function fetchPage() {
link: item.post_url || item.link || '',
description: item.post_excerpt || item.excerpt || '',
pubDate: item.post_date ? new Date(item.post_date).toUTCString() : item.date ? new Date(item.date).toUTCString() : '',
category: item.category_link ? item.category_link.replaceAll(/(<([^>]+)>)/gi, '') : '', // Clean HTML if category_link exists
category: item.category_link ? item.category_link.replaceAll(/(<([^>]+)>)/g, '') : '', // Clean HTML if category_link exists
image: item.image_url ? item.image_url.replace(/\?.*$/, '') : '', // Remove query parameters if image_url exists
}));

View File

@ -5,7 +5,7 @@ import type { Route } from '@/types';
import got from '@/utils/got';
import { parseDate } from '@/utils/parse-date';
const mentionPattern = /<\u2267\u2746>{"name":"(.*?)","uid":"\d+","at":"1"}<\/\u2266\u2746>/g;
const mentionPattern = /<\u2267\u2746>\{"name":"(.*?)","uid":"\d+","at":"1"\}<\/\u2266\u2746>/g;
const formatNoteText = (text = '') => text.replaceAll('\n\n', '</p><p>').replaceAll(mentionPattern, ' @$1');

View File

@ -11,7 +11,7 @@ const types = {
12: '视频',
};
const mentionPattern = /<\u2267\u2746>{"name":"(.*?)","uid":"\d+","at":"1"}<\/\u2266\u2746>/g;
const mentionPattern = /<\u2267\u2746>\{"name":"(.*?)","uid":"\d+","at":"1"\}<\/\u2266\u2746>/g;
const formatNoteText = (text = '') => text.replaceAll('\n\n', '</p><p>').replaceAll(mentionPattern, ' @$1');

View File

@ -70,7 +70,7 @@ export const handler = async (ctx) => {
return {
title: $('title')
.text()
.replace(/\|.*?$/, `| ${$('li.onthis').text()}`),
.replace(/\|.*$/, `| ${$('li.onthis').text()}`),
description: $('meta[name="Description"]').prop('content'),
link: currentUrl,
item: items,

View File

@ -75,7 +75,7 @@ async function handler(ctx) {
headerGeneratorOptions: PRESETS.MODERN_IOS,
});
const nickNameReg = /window\.nickName = "(.*?)"/g;
const nickNameReg = /window\.nickName = "(.*?)"/;
const nickName = nickNameReg.exec(pageResponse as string)?.[1];
const response = await ofetch(`https://m.dianping.com/member/ajax/NobleUserFeeds?userId=${id}`, {

View File

@ -69,7 +69,7 @@ const extractArticle = (item) =>
const { data: response } = await got(item.link);
const $ = load(response);
const scriptTagContent = $('script#fusion-metadata').text();
const jsonData = JSON.parse(scriptTagContent.match(/Fusion\.globalContent=({.*?});Fusion\.globalContentConfig/)[1]).content_elements;
const jsonData = JSON.parse(scriptTagContent.match(/Fusion\.globalContent=(\{.*?\});Fusion\.globalContentConfig/)[1]).content_elements;
const filteredData = [];
for (const v of jsonData) {
if (v.type === 'header' && v.content.includes('What were reading')) {

View File

@ -44,7 +44,7 @@ export async function handler(ctx) {
.map((item) => $(item).find('a').text());
// Process date
const timeText = $('p.dna-update').text();
const dateMatch = timeText.match(/Updated\s*:\s*([\w\s,:\d]+?)(?:\s*\||$)/);
const dateMatch = timeText.match(/Updated\s*:([\w\s,:]+)/);
let time = dateMatch ? dateMatch[1].trim() : '';
time = time.replace(/\s+IST$/, '');
const pubDate = timezone(parseDate(time), +5.5);

View File

@ -30,7 +30,7 @@ function getDomList($, detailUrl) {
export function getItemList($, detailUrl, second) {
const encoded = $('.article script[type]')
.text()
.match(/return p}\('(.*)',(\d+),(\d+),'(.*)'.split\(/);
.match(/return p\}\('(.*)',(\d+),(\d+),'(.*)'.split\(/);
// 若 script 标签没有内容,直接解析 dom
if (!encoded) {
return getDomList($, detailUrl);

View File

@ -145,7 +145,7 @@ const ProcessFeedType3 = (item, response) => {
const initialState = JSON.parse(
$('script:contains("window.__INITIAL_STATE__")')
.text()
.match(/window\.__INITIAL_STATE__\s*=\s*(.*?);\(/)[1]
.match(/window\.__INITIAL_STATE__\s*=\s*((?:\S.*?)??);\(/)[1]
);
// filter out undefined item

View File

@ -85,6 +85,6 @@ async function getContent(nextBuildId: string, contentId: string) {
content
.html()
?.replaceAll(rubyRegex, '$1$2')
?.replaceAll(/[^\u0009\u000A\u000D\u0020-\uD7FF\uE000-\uFDCF\uFDE0-\uFFFD]/gm, '') ?? '';
?.replaceAll(/[^\t\n\r\u0020-\uD7FF\uE000-\uFDCF\uFDE0-\uFFFD]/g, '') ?? '';
return description;
}

View File

@ -56,7 +56,7 @@ async function handler(ctx) {
method: 'get',
url: item.link,
});
const match = detailResponse.data.match(/'comments':(.*)}],/);
const match = detailResponse.data.match(/'comments':(.*)\}\],/);
if (match.length > 1) {
const content = load(detailResponse.data);

View File

@ -55,7 +55,7 @@ async function handler(ctx) {
url: item.link,
});
const comments = JSON.parse(detailResponse.data.match(/'comments':(.*)}],/)[1] + '}]');
const comments = JSON.parse(detailResponse.data.match(/'comments':(.*)\}\],/)[1] + '}]');
for (const c of comments) {
if (c.id === item.link.split('#')[1]) {

View File

@ -17,7 +17,7 @@ async function loadContent(link) {
const shotData = JSON.parse(
$('script')
.text()
.match(/shotData:\s({.+?}),\n/)?.[1] ?? '{}'
.match(/shotData:\s(\{.+?\}),\n/)?.[1] ?? '{}'
);
// Join multiple shots together by selecting elements with class 'media-shot' or 'main-shot' or 'block-media-wrapper'

View File

@ -161,7 +161,7 @@ function getBittorrent(cache, bittorrent_page_url) {
const match = onclick.match(/'(.*?)'/);
if (match) {
bittorrent_url = match[1];
const match_p = bittorrent_url.match(/torrent\?p=(.*?)$/);
const match_p = bittorrent_url.match(/torrent\?p=(.*)$/);
if (match_p) {
p = match_p[1];
}

View File

@ -76,7 +76,7 @@ async function handler(ctx: Context): Promise<Data> {
const initialState = JSON.parse(
$('script:contains("window.__INITIAL_STATE__")')
.text()
.match(/window\.__INITIAL_STATE__\s*=\s*(.*);/)?.[1] ?? '{}'
.match(/window\.__INITIAL_STATE__\s*=\s*(\S.*);/)?.[1] ?? '{}'
);
const page = initialState.page as Page;

View File

@ -29,34 +29,32 @@ export const route: Route = {
};
async function handlerRoute(): Promise<Data> {
const response = await ofetch('https://flashcat.cloud/blog/');
const baseUrl = 'https://flashcat.cloud';
const link = `${baseUrl}/blog/`;
const response = await ofetch(link);
const $ = load(response);
const items = $('.post-preview')
const items = $('.fc-content-card')
.toArray()
.map((elem) => {
const $elem = $(elem);
const $item = $(elem);
const [author, date] = $item
.find('.fc-content-card-meta')
.text()
.split('·')
.map((s) => s.trim());
return {
title: $elem.find('.post-title').text(),
description: $elem.find('.post-content-preview').text(),
link: $elem.find('a').attr('href'),
pubDate: parseDate(
$elem
.find('.post-meta')
.text()
.match(/on\s+(\w+,\s+\w+\s+\d{1,2},\s+\d{4})/)?.[1] || ''
),
author:
$elem
.find('.post-meta')
.text()
.match(/by\s+(.+?)\s+on/)?.[1] || '',
title: $item.find('.fc-content-card-title').text(),
description: $item.find('.fc-content-card-summary').text().trim(),
link: new URL($item.find('.fc-content-card-link').attr('href')!, baseUrl).href,
pubDate: date ? parseDate(date, 'YYYY-MM-DD') : undefined,
author,
};
});
return {
title: 'Flashcat 快猫星云博客',
link: 'https://flashcat.cloud/blog/',
link,
item: items,
};
}

View File

@ -41,7 +41,7 @@ async function handler(ctx) {
}
const anime = response.data.anime;
const title = anime.title.replaceAll(/\[\d+?]$/g, '').trim();
const title = anime.title.replaceAll(/\[\d+\]$/g, '').trim();
const items = anime.volumes[0]
.map((item) => ({

View File

@ -31,7 +31,7 @@ async function handler(ctx) {
const { data: response } = await got(apiUrl);
const items = (Array.isArray(response) ? response : JSON.parse(response.match(/(\[.*])$/)[1])).slice(0, limit).map((item) => {
const items = (Array.isArray(response) ? response : JSON.parse(response.match(/(\[.*\])$/)[1])).slice(0, limit).map((item) => {
const terminologies = item._embedded['wp:term'];
const content = load(item.content?.rendered ?? item.content);

View File

@ -22,7 +22,7 @@ const getAbsoluteUrl = (path: string | undefined) => (path ? new URL(path, ROOT_
const getArticleAuthor = ($: ReturnType<typeof load>) =>
$('#article .items p')
.text()
.match(/Posted by\s+(.+)$/)?.[1]
.match(/Posted by\s+(\S.*)$/)?.[1]
?.trim();
const getArticleCategories = ($: ReturnType<typeof load>) => [
...new Set(

View File

@ -50,7 +50,7 @@ async function handler(ctx) {
item
.find('p.p4')
.text()
.match(/] (\d+\.\d+);/)[1],
.match(/\] (\d+\.\d+);/)[1],
],
enclosure_url: link,
enclosure_length:

View File

@ -28,7 +28,7 @@ async function handler(ctx) {
const real_url = response.request.options.url.href;
const info = JSON.parse(response.data.match(/AF_initDataCallback.*?data:(\[[\S\s]*])\s/m)[1]) || [];
const info = JSON.parse(response.data.match(/AF_initDataCallback.*?data:(\[[\s\S]*\])\s/)[1]) || [];
const album_name = info[3][1];
const owner_name = info[3][5][2];

View File

@ -34,7 +34,7 @@ async function handler(ctx) {
let description = `Google Scholar Monitor Query: ${query}`;
if (params.includes('as_q=')) {
const reg = /as_q=(.*?)&/g;
const reg = /as_q=(.*?)&/;
query = reg.exec(params)[1];
description = `Google Scholar Monitor Advanced Query: ${query}`;
} else {

View File

@ -23,10 +23,10 @@ async function handler(ctx) {
const title = $('a.bt_link').last().text().replace('>', '');
const dataJs = $('div.left.zhengce_right > script[language="javascript"]').html() || $('div.centent_width > script[language="javascript"]').html();
let items = dataJs
.match(/urls\[i]='(.*?)';headers\[i]="(.*?)";year\[i]='(\d+)';month\[i]='(\d+)';day\[i]='(\d+)';/g)
.match(/urls\[i\]='(.*?)';headers\[i\]="(.*?)";year\[i\]='(\d+)';month\[i\]='(\d+)';day\[i\]='(\d+)';/g)
.slice(0, ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit')) : 25)
.map((item) => {
const result = item.match(/urls\[i]='(.*?)';headers\[i]="(.*?)";year\[i]='(\d+)';month\[i]='(\d+)';day\[i]='(\d+)';/);
const result = item.match(/urls\[i\]='(.*?)';headers\[i\]="(.*?)";year\[i\]='(\d+)';month\[i\]='(\d+)';day\[i\]='(\d+)';/);
return {
title: load(result[2])('a').attr('title') || result[2],
link: new URL(result[1], rootUrl).href,

View File

@ -29,7 +29,7 @@ async function handler(ctx) {
.toArray()
.map((item) => {
const href = $(item).attr('href');
if (href && /(?:http:)?\/\/www\.cac\.gov\.cn(.*?)\/(A.*?\.htm)/.test(href)) {
if (href && /(?:http:)?\/\/www\.cac\.gov\.cn.*?\/A.*?\.htm/.test(href)) {
const matchArray = href.match(/(?:http:)?\/\/www\.cac\.gov\.cn(.*?)\/(A.*?\.htm)/);
if (matchArray && matchArray.length > 2) {
const path = matchArray[1];

View File

@ -10,7 +10,7 @@ const cookieJar = new CookieJar();
const owner = '中央纪委国家监委网站';
const rootUrl = 'https://www.ccdi.gov.cn';
const regex = /(?<key>[A-Z_]+)=(?<value>(?:.*?(?=; max-age)|[\dA-Fa-f]+))/gm;
const regex = /(?<key>[A-Z_]+)=(?<value>.*?(?=; max-age)|[\dA-Fa-f]+)/g;
const parseCookie = async (body) => {
let m;

View File

@ -88,13 +88,13 @@ async function handler(ctx) {
let pubDate;
let author;
let category;
if (/dysMiddleResultConItemTitle/g.test(item.html())) {
if (/dysMiddleResultConItemTitle/.test(item.html())) {
if (contentUrl.includes('content')) {
fullTextGet = await got.get(contentUrl);
fullTextData = load(fullTextGet.data);
fullTextData('.shuzi').remove(); // 移除videobg的图片
fullTextData('#myFlash').remove(); // 移除flash
description = /pages_content/g.test(fullTextData.html()) ? fullTextData('.pages_content').html() : fullTextData('#UCAP-CONTENT').html();
description = /pages_content/.test(fullTextData.html()) ? fullTextData('.pages_content').html() : fullTextData('#UCAP-CONTENT').html();
} else {
description = item.find('a').text(); // 忽略获取吹风会的全文
}
@ -105,13 +105,13 @@ async function handler(ctx) {
pubDate = timezone(parseDate(fullTextData('meta[name="firstpublishedtime"]').attr('content'), 'YYYY-MM-DD HH:mm:ss'), 8);
author = fullTextData('meta[name="author"]').attr('content');
category = fullTextData('meta[name="keywords"]').attr('content').split(/[,;]/);
if (/zhengceku/g.test(contentUrl)) {
if (/zhengceku/.test(contentUrl)) {
// 政策文件库
description = fullTextData('.pages_content').html();
} else {
fullTextData('.shuzi').remove(); // 移除videobg的图片
fullTextData('#myFlash').remove(); // 移除flash
description = /UCAP-CONTENT/g.test($1) ? fullTextData('#UCAP-CONTENT').html() : fullTextData('body').html();
description = /UCAP-CONTENT/.test($1) ? fullTextData('#UCAP-CONTENT').html() : fullTextData('body').html();
}
} else {
description = item.find('a').text(); // 忽略获取吹风会的全文

View File

@ -186,7 +186,7 @@ const gdgov = async (info, ctx) => {
title: data.art_title,
description: renderZcjdpt(data),
pubDate: timezone(parseDate(data.pub_time), +8),
author: /(|本网|本站)/.test(data.pub_unite) ? authorisme : data.pub_unite,
author: /本/.test(data.pub_unite) ? authorisme : data.pub_unite,
};
});
} else if (idlink.host === 'mp.weixin.qq.com') {
@ -217,7 +217,7 @@ const gdgov = async (info, ctx) => {
title,
description,
pubDate: timezone(parseDate(pubDate, pubDate_format), +8),
author: /本|本网|本站/.test(author) ? authorisme : author,
author: /本/.test(author) ? authorisme : author,
};
});
}

View File

@ -34,7 +34,7 @@ async function handler() {
const tfxtqJsUrl = `${rootUrl}/data/gzWeather/weatherTips.js`;
const response = await got.get(tfxtqJsUrl);
const data = JSON.parse(`[{${response.data.match(/Tips = {(.*?)}/)[1]}}]`);
const data = JSON.parse(`[{${response.data.match(/Tips = \{(.*?)\}/)[1]}}]`);
const items = data.map((item) => ({
title: item.title,

View File

@ -72,7 +72,7 @@ async function handler(ctx) {
item.description = content('#con_con')
.html()
?.replaceAll(/(<iframe.*?src=")(.*?)(".*?>)/g, '$1' + rootUrl + '$2$3');
?.replaceAll(/(<iframe.*?src=")([^"]*)(".*?>)/g, '$1' + rootUrl + '$2$3');
return item;
})

View File

@ -71,7 +71,7 @@ async function handler() {
item.description = content('#con_con')
.html()
?.replaceAll(/(<iframe.*?src=")(.*?)(".*?>)/g, '$1' + rootUrl + '$2$3');
?.replaceAll(/(<iframe.*?src=")([^"]*)(".*?>)/g, '$1' + rootUrl + '$2$3');
return item;
})

View File

@ -47,7 +47,7 @@ async function handler(ctx) {
cache.tryGet(item.link, async () => {
let responses = await got(item.link);
// xwfb/xwlxfbh || xwfb/xwztfbh
const redirect = responses.data.match(/_cofing1={href:"(.*)",type/) || responses.data.match(/window\.location\.href='(.*)'/);
const redirect = responses.data.match(/_cofing1=\{href:"(.*)",type/) || responses.data.match(/window\.location\.href='(.*)'/);
if (redirect) {
responses = await got(redirect[1], {
headers: {

View File

@ -45,7 +45,7 @@ async function handler(ctx) {
url: currentUrl,
});
const regex = /<!\[cdata\[([\S\s]*?)]]>(?=\s*<)/gi;
const regex = /<!\[cdata\[([\s\S]*?)\]\]>(?=\s*<)/gi;
const data = response.data.replaceAll(regex, '$1');
const $ = load(data, {

View File

@ -46,7 +46,7 @@ async function handler(ctx) {
title: item.prop('title') ?? item.text(),
link: new URL(item.prop('href'), rootUrl).href,
guid: `nsfc-${item.prop('id')}`,
pubDate: parseDate(item.next().text().replace(/\[]/g, '', ['YYYY-MM-DD', 'YY-MM-DD'])),
pubDate: parseDate(item.next().text().replace(/\[\]/g, '', ['YYYY-MM-DD', 'YY-MM-DD'])),
};
});

View File

@ -115,7 +115,7 @@ async function handler(ctx) {
// articles from www.news.cn or www.gov.cn
if (/(news\.cn|www\.gov\.cn)/.test(item.link)) {
if (/news\.cn|www\.gov\.cn/.test(item.link)) {
if (content('.year').text()) {
item.pubDate = timezone(parseDate(`${content('.year').text()}/${content('.day').text()} ${content('.time').text()}`, 'YYYY/MM/DD HH:mm:ss'), +8);
item.author = content('.source')

View File

@ -52,7 +52,7 @@ async function handler(ctx) {
});
const query = `${params.toString()}&${advance}`;
const res = await got.get(link, {
searchParams: query.replaceAll(/([\u4E00-\u9FA5])/g, (str) => encodeURIComponent(str)),
searchParams: query.replaceAll(/[\u4E00-\u9FA5]/g, (str) => encodeURIComponent(str)),
});
const $ = load(res.data);

View File

@ -35,7 +35,7 @@ export const route: Route = {
return {
title: `宁波市国资委-${noticeCate}:${title.text()}`,
link: `http://gzw.ningbo.gov.cn${title.attr('href')}`,
pubDate: parseDate($('p').text().replaceAll(/\[|]/g, '')),
pubDate: parseDate($('p').text().replaceAll(/\[|\]/g, '')),
author: '宁波市国资委',
description: title.text(),
};

View File

@ -35,7 +35,7 @@ export const route: Route = {
return {
title: `宁波人社公告-${noticeCate}:${title.text()}`,
link: `http://rsj.ningbo.gov.cn${title.attr('href')}`,
pubDate: parseDate($('.news_date').text().replaceAll(/\[|]/g, '')),
pubDate: parseDate($('.news_date').text().replaceAll(/\[|\]/g, '')),
author: '宁波市人力资源和社会保障局',
description: title.text(),
};

View File

@ -38,7 +38,7 @@ async function handler(ctx) {
const minuteRelativeTime = /(\d+)\s*分钟前/;
const hourRelativeTime = /(\d+)\s*小时前/;
const yesterdayRelativeTime = /昨天\s*(\d+):(\d+)/;
const shortDate = /(\d+)-(\d+)\s*(\d+):(\d+)/;
const shortDate = /(\d+)-(\d+)\s+(\d+):(\d+)/;
// offset to ADD for transforming China time to UTC
const chinaToUtcOffset = -8 * 3600 * 1000;

View File

@ -110,7 +110,7 @@ const ProcessItems = (items, limit, tryGet) =>
url: item.link,
});
const content = JSON.parse(detailResponse.data.match(/"__NEXT_DATA__" type="application\/json">({"props":.*})<\/script>/)[1]);
const content = JSON.parse(detailResponse.data.match(/"__NEXT_DATA__" type="application\/json">(\{"props":.*\})<\/script>/)[1]);
item.description = renderDescription({
image: content.props.initialProps.pageProps.article.originalImage.cdnUrl,

View File

@ -158,7 +158,7 @@ async function handler(ctx) {
.toArray()
.map((e) => content(e).text().trim());
item.description = renderDesc(articleImg, content('div#article-content').html());
item.pubDate = timezone(/(今|昨)/.test(pubDate) ? parseRelativeDate(pubDate) : parseDate(pubDate, 'YYYY M D'), +8);
item.pubDate = timezone(/今|昨/.test(pubDate) ? parseRelativeDate(pubDate) : parseDate(pubDate, 'YYYY M D'), +8);
return item;
})

View File

@ -70,7 +70,7 @@ async function handler(ctx) {
url: apiUrl,
});
const list = JSON.parse(response.data.match(/"data":(\[{.*}])}/)[1]).map((item) => {
const list = JSON.parse(response.data.match(/"data":(\[\{.*\}\])\}/)[1]).map((item) => {
let link: string;
if (item.UrlPath_en) {

View File

@ -24,7 +24,7 @@ const MAPs = {
};
const ProcessFeed = async (type, id, order) => {
let link = MAPs[type].url.replace(/{id}/, id).replace(/{order}/, order || 'add');
let link = MAPs[type].url.replace(/\{id\}/, id).replace(/\{order\}/, order || 'add');
let response = await got({
method: 'get',
url: link,
@ -35,7 +35,7 @@ const ProcessFeed = async (type, id, order) => {
let $ = load(response.data);
if (type === 'work') {
const overviewLink = MAPs.overview.url.replace(/{id}/, id);
const overviewLink = MAPs.overview.url.replace(/\{id\}/, id);
const overviewResponse = await got({
method: 'get',
url: overviewLink,

View File

@ -238,8 +238,8 @@ export function getEntryDetails(item: DataItem): Promise<DataItem> {
// Possible formats: 10:21, 45分钟前, 09-15 19:57
const currentYear = new Date().getFullYear();
const currentDate = new Date();
const monthDayTimePattern = /^(\d{2})-(\d{2}) (\d{2}):(\d{2})$/;
const timeOnlyPattern = /^(\d{1,2}):(\d{2})$/;
const monthDayTimePattern = /^\d{2}-\d{2} \d{2}:\d{2}$/;
const timeOnlyPattern = /^\d{1,2}:\d{2}$/;
let processedDateString = pubDateString;
if (monthDayTimePattern.test(pubDateString)) {

View File

@ -48,7 +48,7 @@ async function handler() {
allUrlList.map(async (item) => {
const { data: response } = await got(item);
const $$ = load(response);
const regVol = /(?<=Vol. )(\w+)/;
const regVol = /(?<=Vol. )\w+/;
const match = regVol.exec($$('div.vp-page-title').find('h1').text());
const volume = match ? match[0] : '';
const links = $$('div.theme-hope-content > ul a')

View File

@ -67,7 +67,7 @@ async function handler(ctx) {
const _allData = JSON.parse(
$('script')
.text()
.match(/var allData = ({.*?});/)[1]
.match(/var allData = (\{.*?\});/)[1]
);
if (type === 'doc') {
item.description = extractDoc(_allData.docData.contentData.contentList);

View File

@ -29,7 +29,7 @@ async function handler(ctx) {
const $ = load(response.data);
const newsStream = JSON.parse(response.data.match(/"newsstream":(\[.*?]),"cooperation"/)[1]);
const newsStream = JSON.parse(response.data.match(/"newsstream":(\[.*?\]),"cooperation"/)[1]);
let items = newsStream.slice(0, limit).map((item) => ({
title: item.title,
@ -47,9 +47,9 @@ async function handler(ctx) {
});
item.author = detailResponse.data.match(/"editorName":"(.*?)",/)[1];
item.category = detailResponse.data.match(/},"keywords":"(.*?)",/)[1].split(',');
item.category = detailResponse.data.match(/\},"keywords":"(.*?)",/)[1].split(',');
const image = item.description;
const description = JSON.parse(detailResponse.data.match(/"contentList":(\[.*?]),/)[1]).map((content) => content.data);
const description = JSON.parse(detailResponse.data.match(/"contentList":(\[.*?\]),/)[1]).map((content) => content.data);
item.description = renderToString(
<>
{image ? (

View File

@ -62,7 +62,7 @@ async function handler(ctx) {
parseDate(
$('div.editor')
.html()
.split(/(\s\s+)/)[2]
.split(/(\s{2,})/)[2]
),
+8
);

View File

@ -19,7 +19,7 @@ export const parseThumbnail = (type: 'video' | 'image', item: any) => {
}
// regex borrowed from https://stackoverflow.com/a/3726073
const match = /https?:\/\/(?:www\.)?youtu(?:be\.com\/watch\?v=|\.be\/)([\w-]*)(&(amp;)?[\w=?]*)?/.exec(item.embedUrl);
const match = /https?:\/\/(?:www\.)?youtu(?:be\.com\/watch\?v=|\.be\/)([\w-]*)(?:&(?:amp;)?[\w=?]*)?/.exec(item.embedUrl);
if (match) {
return `<img src="${imageRootUrl}/image/embed/original/youtube/${match[1]}">`;
}

View File

@ -44,7 +44,7 @@ async function handler(ctx) {
throw new Error('Failed to find SSR_HYDRATED_DATA');
}
const jsonData = JSON.parse(jsData.match(/var\s+data\s*=\s*({.*?});/s)?.[1].replaceAll('undefined', 'null') || '{}');
const jsonData = JSON.parse(jsData.match(/var\s+data\s*=\s*(\{.*?\});/s)?.[1].replaceAll('undefined', 'null') || '{}');
const {
AuthorVideoList: { videoList: videoInfos },

View File

@ -20,7 +20,7 @@ export const extractPageId = async (url: string, referer: string): Promise<strin
$('script').each((_, script) => {
const content = $(script).html() || '';
const match = content.match(/PAGE\s*=\s*{\s*id\s*:\s*(\d+)\s*}/);
const match = content.match(/PAGE\s*=\s*\{\s*id\s*:\s*(\d+)\s*\}/);
if (match) {
pageId = match[1];
}

View File

@ -12,7 +12,7 @@ import got from '@/utils/got';
import { parseDate } from '@/utils/parse-date';
const toSize = (raw) => {
const matches = raw.match(/(\d+(\.\d+)?)(\w+)/);
const matches = raw.match(/(\d+(\.\d+)?)(\D\w*)/);
return matches[3] === 'GB' ? matches[1] * 1024 : matches[1];
};
@ -154,7 +154,7 @@ async function handler(ctx) {
// To fetch magnets.
try {
const matches = detailResponse.data.match(/var gid = (\d+);[\S\s]*var uc = (\d+);[\S\s]*var img = '(.*)';/);
const matches = detailResponse.data.match(/var gid = (\d+);[\s\S]*var uc = (\d+);[\s\S]*var img = '(.*)';/);
const magnetResponse = await got({
method: 'get',

View File

@ -34,7 +34,7 @@ export const handler = async (ctx): Promise<Data> => {
const href = item.prop('href');
const link = href ? (href.startsWith('/') ? new URL(href, rootUrl).href : href) : undefined;
if (link && /\/(article|video)\/\w+\.html/.test(link)) {
if (link && /\/(?:article|video)\/\w+\.html/.test(link)) {
items[link] = {
title: item.text(),
link,

View File

@ -139,7 +139,7 @@ async function handler(ctx) {
const single = {
title: `${typeMap[item.type]}了: ${shortenTitle}`,
description: `${content}${linkTemplate}${imgTemplate}`.replace(/(<br>|\s)+$/, ''),
description: `${content}${linkTemplate}${imgTemplate}`.replace(/(?:<br>|\s)+$/, ''),
pubDate: parseDate(item.createdAt),
link: getLink(item.id, item.type),
_extra: repostContent && {

View File

@ -117,7 +117,7 @@ const topicDataHanding = (data, ctx) =>
// default:
// break;
// }
const imgUrl = /\.[\da-z]+?\?imageMogr2/.test(pic.picUrl) ? pic.picUrl.split('?imageMogr2/')[0] : pic.picUrl.replace(/thumbnail\/.+/, '');
const imgUrl = /\.[\da-z]+\?imageMogr2/.test(pic.picUrl) ? pic.picUrl.split('?imageMogr2/')[0] : pic.picUrl.replace(/thumbnail\/.+/, '');
description += `<br><img src="${imgUrl}">`;
// description += `<br><picture><source srcset="${
// pic.picUrl.split('/thumbnail/')[0]

View File

@ -62,7 +62,7 @@ async function handler(ctx) {
const bookInfoWrap = detailPage('div.info_wrap').html() || '';
const processedDescription = bookDescription.replaceAll(/<img\b[^>]*>/g, (imgTag) =>
imgTag.replaceAll(/\b(src|data-src)="(?!http|https|\/\/)([^"]*)"/g, (_, attrName, relativePath) => {
imgTag.replaceAll(/\b(src|data-src)="(?!http|\/\/)([^"]*)"/g, (_, attrName, relativePath) => {
const absoluteImageUrl = new URL(relativePath, baseUrl).href;
return `${attrName}="${absoluteImageUrl}"`;
})

Some files were not shown because too many files have changed in this diff Show More