归档 artalk-cf 评论后端 + rss-robot 到 blog-admin（含技术选型/模块分布 README）
This commit is contained in:
zqlit committed
1 parent
e1323bd260
commit
299ab57e4d
98 files changed
+15657
No files matched your search
@@ -0,0 +1,208 @@
|
||||
// RSS / Atom / JSON Feed / 自定义 JSON 解析
|
||||
// 迁自 check-feeds.js 的 parseFeedXml / parseJsonFeed / parseCustomJson 等。
|
||||
|
||||
export interface Article {
|
||||
title: string;
|
||||
link: string;
|
||||
pubDate: string;
|
||||
author: string;
|
||||
feedTitle: string;
|
||||
}
|
||||
|
||||
export interface FeedConfig {
|
||||
url: string;
|
||||
feedTitle?: string;
|
||||
format?: string;
|
||||
path?: string;
|
||||
proxy?: boolean;
|
||||
mapping?: Record<string, string>;
|
||||
}
|
||||
|
||||
export interface ParsedFeed {
|
||||
feedTitle: string;
|
||||
articles: Article[];
|
||||
}
|
||||
|
||||
function extractTag(xml: string, tag: string): string {
|
||||
const regex = new RegExp(`<${tag}[^>]*>([\\s\\S]*?)<\\/${tag}>`, 'i');
|
||||
const match = xml.match(regex);
|
||||
return match ? match[1] : '';
|
||||
}
|
||||
|
||||
function decodeXml(str: string): string {
|
||||
return str
|
||||
.replace(/<!\[CDATA\[([\s\S]*?)\]\]>/g, '$1')
|
||||
.replace(/&/g, '&')
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/"/g, '"')
|
||||
.replace(/'/g, "'");
|
||||
}
|
||||
|
||||
export function parseDate(val: unknown): string | null {
|
||||
if (!val) return null;
|
||||
if (typeof val === 'number') {
|
||||
const d = new Date(val > 9999999999 ? val : val * 1000);
|
||||
return isNaN(d.getTime()) ? null : d.toISOString();
|
||||
}
|
||||
const str = String(val).trim();
|
||||
if (!str) return null;
|
||||
const d = new Date(str);
|
||||
if (isNaN(d.getTime())) return null;
|
||||
try {
|
||||
return d.toISOString();
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
export function parseFeedXml(xml: string, feedUrl: string): ParsedFeed {
|
||||
const articles: Article[] = [];
|
||||
let feedTitle = '';
|
||||
|
||||
const titleMatch = xml.match(/<title[^>]*>([\s\S]*?)<\/title>/);
|
||||
if (titleMatch) feedTitle = decodeXml(titleMatch[1]).trim();
|
||||
|
||||
const itemRegex = /<item[\s>]?>([\s\S]*?)<\/item>/gi;
|
||||
const entryRegex = /<entry[\s>]?>([\s\S]*?)<\/entry>/gi;
|
||||
|
||||
const parseItem = (itemXml: string) => {
|
||||
const title = extractTag(itemXml, 'title');
|
||||
let link = '';
|
||||
|
||||
const rssLink = extractTag(itemXml, 'link');
|
||||
if (rssLink) link = rssLink;
|
||||
|
||||
const atomLinkMatch = itemXml.match(/<link[^>]+href=["']([^"']+)["'][^>]*>/i);
|
||||
if (atomLinkMatch && atomLinkMatch[1]) link = atomLinkMatch[1];
|
||||
|
||||
const altLinkMatch = itemXml.match(
|
||||
/<link[^>]+rel=["']alternate["'][^>]+href=["']([^"']+)["']/i,
|
||||
);
|
||||
if (altLinkMatch) link = altLinkMatch[1];
|
||||
|
||||
const pubDate =
|
||||
extractTag(itemXml, 'pubDate') ||
|
||||
extractTag(itemXml, 'published') ||
|
||||
extractTag(itemXml, 'updated') ||
|
||||
extractTag(itemXml, 'dc:date') ||
|
||||
extractTag(itemXml, 'lastBuildDate') ||
|
||||
extractTag(itemXml, 'date') ||
|
||||
extractTag(itemXml, 'modified') ||
|
||||
extractTag(itemXml, 'created');
|
||||
|
||||
const author = extractTag(itemXml, 'dc:creator') || extractTag(itemXml, 'author') || '';
|
||||
const authorName = author.replace(/<name>([\s\S]*?)<\/name>/gi, '$1').trim();
|
||||
|
||||
if (title && link) {
|
||||
articles.push({
|
||||
title: decodeXml(title).trim(),
|
||||
link: link.trim(),
|
||||
pubDate: parseDate(pubDate) || new Date().toISOString(),
|
||||
author: decodeXml(authorName).trim(),
|
||||
feedTitle: feedTitle || feedUrl,
|
||||
});
|
||||
}
|
||||
};
|
||||
|
||||
let match: RegExpExecArray | null;
|
||||
while ((match = itemRegex.exec(xml)) !== null) parseItem(match[1]);
|
||||
while ((match = entryRegex.exec(xml)) !== null) parseItem(match[1]);
|
||||
|
||||
return { feedTitle, articles };
|
||||
}
|
||||
|
||||
export function parseJsonFeed(json: any, feedUrl: string): ParsedFeed {
|
||||
const articles: Article[] = [];
|
||||
const feedTitle = json.title || feedUrl;
|
||||
const items = json.items || [];
|
||||
|
||||
for (const item of items) {
|
||||
const title = item.title || '';
|
||||
const link = item.url || item.id || '';
|
||||
const pubDate =
|
||||
item.date_published || item.date_modified || item.date || item.published || item.modified || item.created_at || item.createdAt || item.pubDate || item.timestamp || null;
|
||||
const author = Array.isArray(item.authors)
|
||||
? item.authors.map((a: any) => a.name).join(', ')
|
||||
: item.author?.name || item.author || '';
|
||||
|
||||
if (title && link) {
|
||||
articles.push({
|
||||
title: title.trim(),
|
||||
link: link.trim(),
|
||||
pubDate: parseDate(pubDate) || new Date().toISOString(),
|
||||
author: typeof author === 'string' ? author.trim() : '',
|
||||
feedTitle,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
return { feedTitle, articles };
|
||||
}
|
||||
|
||||
function getNestedValue(obj: any, path?: string): unknown {
|
||||
if (!obj || !path) return undefined;
|
||||
return path.split('.').reduce((o: any, key) => o?.[key], obj);
|
||||
}
|
||||
|
||||
export function parseCustomJson(json: any, config: FeedConfig): ParsedFeed {
|
||||
const articles: Article[] = [];
|
||||
const mapping = config.mapping || {};
|
||||
const path = config.path || '';
|
||||
|
||||
let data: any = json;
|
||||
if (path) {
|
||||
for (const key of path.split('.')) {
|
||||
if (data && typeof data === 'object') data = data[key];
|
||||
}
|
||||
}
|
||||
|
||||
const items = Array.isArray(data) ? data : [];
|
||||
|
||||
const titleKey = mapping.title || 'title';
|
||||
const linkKey = mapping.link || 'link';
|
||||
const pubDateKey = mapping.pubDate || 'pubDate';
|
||||
const authorKey = mapping.author || 'author';
|
||||
const feedTitleKey = mapping.feedTitle || 'feedTitle';
|
||||
|
||||
for (const item of items) {
|
||||
const title = getNestedValue(item, titleKey) || '';
|
||||
const link = getNestedValue(item, linkKey) || getNestedValue(item, 'url') || '';
|
||||
const pubDate =
|
||||
getNestedValue(item, pubDateKey) ||
|
||||
getNestedValue(item, 'publishedAt') ||
|
||||
getNestedValue(item, 'createdAt') ||
|
||||
getNestedValue(item, 'created_at') ||
|
||||
getNestedValue(item, 'date') ||
|
||||
getNestedValue(item, 'published') ||
|
||||
getNestedValue(item, 'updatedAt') ||
|
||||
getNestedValue(item, 'timestamp') ||
|
||||
getNestedValue(item, 'datePublished') ||
|
||||
getNestedValue(item, 'dateModified') ||
|
||||
null;
|
||||
const author = getNestedValue(item, authorKey) || '';
|
||||
const feedTitle = getNestedValue(item, feedTitleKey) || config.feedTitle || config.url || '';
|
||||
|
||||
if (title && link) {
|
||||
articles.push({
|
||||
title: String(title).trim(),
|
||||
link: String(link).trim(),
|
||||
pubDate: parseDate(pubDate) || new Date().toISOString(),
|
||||
author: String(typeof author === 'object' ? '' : author).trim(),
|
||||
feedTitle: String(feedTitle),
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
return { feedTitle: config.feedTitle || config.url || '', articles };
|
||||
}
|
||||
|
||||
export function isJsonResponse(text: string, contentType: string): boolean {
|
||||
if (contentType?.includes('json')) return true;
|
||||
try {
|
||||
const parsed = JSON.parse(text);
|
||||
return typeof parsed === 'object' && parsed !== null;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user