ChatGPT/FastGPT
1
0
Fork 0
mirror of https://github.com/labring/FastGPT.git synced 2025-07-23 13:03:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: add order:true to all create transactions (#3948)

Browse Source
This commit is contained in:
Finley Ge
2025-03-03 11:37:51 +08:00
committed by GitHub
parent 113e8f711f
commit 4bc7f21182
30 changed files with 425 additions and 352 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
packages/service/core/dataset/collection/controller.ts
View File

@@ -216,7 +216,7 @@ export async function createOneCollection({
nextSyncTime
}
],
{ session }
{ session, ordered: true }
);
return collection;

2
packages/service/core/dataset/collection/utils.ts
View File

@@ -97,7 +97,7 @@ export const createOrGetCollectionTags = async ({
datasetId,
tag: tagContent
})),
{ session }
{ session, ordered: true }
);
return [...existingTags.map((tag) => tag._id), ...newTags.map((tag) => tag._id)];

3
packages/service/support/permission/inheritPermission.ts
View File

@@ -196,7 +196,8 @@ export async function syncCollaborators({
permission: item.permission
})),
{
session
session,
ordered: true
}
);
}

2
packages/service/support/wallet/sub/utils.ts
View File

@@ -100,7 +100,7 @@ export const initTeamFreePlan = async ({
surplusPoints: freePoints
}
],
{ session }
{ session, ordered: true }
);
};

2
packages/service/support/wallet/usage/controller.ts
View File

@@ -160,7 +160,7 @@ export const createTrainingUsage = async ({
]
}
],
{ session }
{ session, ordered: true }
);
return { billId: String(_id) };

88
plugins/webcrawler/SPIDER/src/controllers/quickfetchController.ts
View File

@@ -5,56 +5,56 @@ import dotenv from 'dotenv';
dotenv.config();
const userAgents = [
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0.3 Safari/605.1.15',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0'
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0.3 Safari/605.1.15',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0'
];
export const quickFetch = async (req: Request, res: Response): Promise<void> => {
const { url } = req.query;
const { url } = req.query;
if (!url) {
res.status(400).json({
status: 400,
error: {
code: "MISSING_PARAM",
message: "缺少必要参数: url"
}
});
return;
}
if (!url) {
res.status(400).json({
status: 400,
error: {
code: 'MISSING_PARAM',
message: '缺少必要参数: url'
}
});
return;
}
try {
const response = await fetch(url as string, {
headers: {
'User-Agent': userAgents[Math.floor(Math.random() * userAgents.length)],
'Referer': 'https://www.google.com/',
'Accept-Language': 'en-US,en;q=0.9',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Connection': 'keep-alive',
'Cache-Control': 'no-cache'
}
});
if (!response.ok) {
throw new Error(`HTTP error! status: ${response.status}`);
}
const data = await response.text();
res.status(200).json({
status: 200,
data: {
content: data
}
});
} catch (error) {
console.error('Error fetching the page:', error);
res.status(500).json({
status: 500,
error: {
code: "INTERNAL_SERVER_ERROR",
message: "发生错误"
}
});
try {
const response = await fetch(url as string, {
headers: {
'User-Agent': userAgents[Math.floor(Math.random() * userAgents.length)],
Referer: 'https://www.google.com/',
'Accept-Language': 'en-US,en;q=0.9',
Accept: 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
Connection: 'keep-alive',
'Cache-Control': 'no-cache'
}
});
if (!response.ok) {
throw new Error(`HTTP error! status: ${response.status}`);
}
const data = await response.text();
res.status(200).json({
status: 200,
data: {
content: data
}
});
} catch (error) {
console.error('Error fetching the page:', error);
res.status(500).json({
status: 500,
error: {
code: 'INTERNAL_SERVER_ERROR',
message: '发生错误'
}
});
}
};
export default { quickFetch };

44
plugins/webcrawler/SPIDER/src/controllers/readController.ts
View File

@@ -16,16 +16,16 @@ const blacklistDomains = process.env.BLACKLIST ? JSON.parse(process.env.BLACKLIS
export const readPage = async (req: Request, res: Response): Promise<void> => {
const { queryUrl } = req.query;
console.log("-------");
console.log('-------');
console.log(queryUrl);
console.log("-------");
console.log('-------');
if (!queryUrl) {
res.status(400).json({
status: 400,
error: {
code: "MISSING_PARAM",
message: "缺少必要参数: queryUrl"
code: 'MISSING_PARAM',
message: '缺少必要参数: queryUrl'
}
});
return;
@@ -36,8 +36,8 @@ export const readPage = async (req: Request, res: Response): Promise<void> => {
res.status(403).json({
status: 403,
error: {
code: "BLACKLISTED_DOMAIN",
message: "该域名受到保护中"
code: 'BLACKLISTED_DOMAIN',
message: '该域名受到保护中'
}
});
return;
@@ -46,11 +46,14 @@ export const readPage = async (req: Request, res: Response): Promise<void> => {
try {
const response = await fetch(queryUrl as string, {
headers: {
'User-Agent': new UserAgent({ deviceCategory: 'desktop', platform: 'Linux x86_64' }).toString(),
'Referer': 'https://www.google.com/',
'User-Agent': new UserAgent({
deviceCategory: 'desktop',
platform: 'Linux x86_64'
}).toString(),
Referer: 'https://www.google.com/',
'Accept-Language': 'en-US,en;q=0.9',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Connection': 'keep-alive',
Accept: 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
Connection: 'keep-alive',
'Cache-Control': 'no-cache'
}
});
@@ -69,7 +72,7 @@ export const readPage = async (req: Request, res: Response): Promise<void> => {
});
await updateCacheAsync(queryUrl as string, cleanedContent || '');
console.log("Page read successfully");
console.log('Page read successfully');
return;
} else {
throw new Error(`HTTP error! status: ${response.status}`);
@@ -80,22 +83,25 @@ export const readPage = async (req: Request, res: Response): Promise<void> => {
try {
const browser = await puppeteer.launch({
ignoreDefaultArgs: ["--enable-automation"],
ignoreDefaultArgs: ['--enable-automation'],
headless: true,
executablePath: "/usr/bin/chromium", // 明确指定 Chromium 路径
executablePath: '/usr/bin/chromium', // 明确指定 Chromium 路径
pipe: true,
args: [
'--no-sandbox',
'--disable-setuid-sandbox',
'--disable-dev-shm-usage',
'--disable-gpu',
// '--single-process'
'--disable-gpu'
// '--single-process'
]
});
const page = await browser.newPage();
// 检测是否需要特殊处理
if (typeof queryUrl === 'string' && detectWebsites.some(website => queryUrl.includes(website))) {
if (
typeof queryUrl === 'string' &&
detectWebsites.some((website) => queryUrl.includes(website))
) {
await setupPage(page);
} else {
const userAgent = new UserAgent({ deviceCategory: 'desktop', platform: 'Linux x86_64' });
@@ -128,14 +134,14 @@ export const readPage = async (req: Request, res: Response): Promise<void> => {
});
await updateCacheAsync(queryUrl as string, cleanedContent || '');
console.log("Page read successfully");
console.log('Page read successfully');
} catch (error) {
console.error(error);
res.status(500).json({
status: 500,
error: {
code: "INTERNAL_SERVER_ERROR",
message: "读取页面时发生内部服务器错误"
code: 'INTERNAL_SERVER_ERROR',
message: '读取页面时发生内部服务器错误'
}
});
}

74
plugins/webcrawler/SPIDER/src/controllers/searchController.ts
View File

@@ -12,15 +12,21 @@ const detectWebsites = process.env.DETECT_WEBSITES?.split(',') || [];
const maxConcurrency = parseInt(process.env.MAX_CONCURRENCY || '10', 10);
export const search = async (req: Request, res: Response): Promise<void> => {
const { query, pageCount = 10, needDetails = 'false', engine = 'baidu', categories = 'general' } = req.query;
const needDetailsBool = (needDetails === 'true');
const {
query,
pageCount = 10,
needDetails = 'false',
engine = 'baidu',
categories = 'general'
} = req.query;
const needDetailsBool = needDetails === 'true';
if (!query) {
res.status(400).json({
status: 400,
error: {
code: "MISSING_PARAM",
message: "缺少必要参数: query"
code: 'MISSING_PARAM',
message: '缺少必要参数: query'
}
});
return;
@@ -28,24 +34,29 @@ export const search = async (req: Request, res: Response): Promise<void> => {
let fetchSearchResults;
let searchUrlBase;
try {
if (engine === 'baidu') {
fetchSearchResults = fetchBaiduResults;
searchUrlBase = process.env.ENGINE_BAIDUURL;
} else if (engine === 'searchxng') {
fetchSearchResults = fetchSearchxngResults;
searchUrlBase = process.env.ENGINE_SEARCHXNGURL;
} else {
res.status(400).json({
status: 400,
error: {
code: "INVALID_ENGINE",
message: "无效的搜索引擎"
}
});
return;
}
if (engine === 'baidu') {
fetchSearchResults = fetchBaiduResults;
searchUrlBase = process.env.ENGINE_BAIDUURL;
} else if (engine === 'searchxng') {
fetchSearchResults = fetchSearchxngResults;
searchUrlBase = process.env.ENGINE_SEARCHXNGURL;
} else {
res.status(400).json({
status: 400,
error: {
code: 'INVALID_ENGINE',
message: '无效的搜索引擎'
}
});
return;
}
const { resultUrls, results } = await fetchSearchResults(query as string, Number(pageCount), searchUrlBase || '', categories as string);
const { resultUrls, results } = await fetchSearchResults(
query as string,
Number(pageCount),
searchUrlBase || '',
categories as string
);
//如果返回值为空，返回空数组
if (results.size === 0) {
@@ -79,20 +90,27 @@ export const search = async (req: Request, res: Response): Promise<void> => {
concurrency: Cluster.CONCURRENCY_CONTEXT,
maxConcurrency: maxConcurrency,
puppeteerOptions: {
ignoreDefaultArgs: ["--enable-automation"],
headless: "true",
executablePath: "/usr/bin/chromium", // 明确指定 Chromium 路径
ignoreDefaultArgs: ['--enable-automation'],
headless: 'true',
executablePath: '/usr/bin/chromium', // 明确指定 Chromium 路径
pipe: true,
args: [
'--no-sandbox',
'--disable-setuid-sandbox',
'--disable-dev-shm-usage',
'--disable-gpu',
'--disable-gpu'
]
}
});
const sortedResults = await performDeepSearch(clusterInstance, resultUrls, results, strategies, detectWebsites, Number(pageCount));
const sortedResults = await performDeepSearch(
clusterInstance,
resultUrls,
results,
strategies,
detectWebsites,
Number(pageCount)
);
res.status(200).json({
status: 200,
data: {
@@ -104,8 +122,8 @@ export const search = async (req: Request, res: Response): Promise<void> => {
res.status(500).json({
status: 500,
error: {
code: "INTERNAL_SERVER_ERROR",
message: "发生错误"
code: 'INTERNAL_SERVER_ERROR',
message: '发生错误'
}
});
}

353
plugins/webcrawler/SPIDER/src/engines/baiduEngine.ts
View File

@@ -5,200 +5,203 @@ import { setupPage } from '../utils/setupPage';
import { Cluster } from 'puppeteer-cluster';
async function randomWait(min: number, max: number) {
// 随机等待时间
const delay = Math.floor(Math.random() * (max - min + 1)) + min;
return new Promise(resolve => setTimeout(resolve, delay));
// 随机等待时间
const delay = Math.floor(Math.random() * (max - min + 1)) + min;
return new Promise((resolve) => setTimeout(resolve, delay));
}
export const fetchSearchResults = async (query: string, pageCount: number, searchUrlBase: string, categories: string) => {
console.log(`Fetching Baidu search results for query: ${query}`);
// 如果 searchUrlBase 为空，返回空数组
if (!searchUrlBase) {
return { resultUrls: [], results: new Map() };
export const fetchSearchResults = async (
query: string,
pageCount: number,
searchUrlBase: string,
categories: string
) => {
console.log(`Fetching Baidu search results for query: ${query}`);
// 如果 searchUrlBase 为空，返回空数组
if (!searchUrlBase) {
return { resultUrls: [], results: new Map() };
}
const resultUrls: string[] = [];
const results = new Map<string, any>();
const pagesToFetch = Math.ceil(pageCount / 10);
const browser = await puppeteer.launch({
ignoreDefaultArgs: ['--enable-automation'],
headless: true,
executablePath: '/usr/bin/chromium', // 明确指定 Chromium 路径
pipe: true,
args: [
'--no-sandbox',
'--disable-setuid-sandbox',
'--disable-dev-shm-usage',
'--disable-gpu'
// '--single-process'
]
});
const page = await browser.newPage();
await setupPage(page);
for (let i = 0; i < pagesToFetch; i++) {
const searchUrl = new URL(`${searchUrlBase}?wd=${encodeURIComponent(query)}&pn=${i * 10}`);
console.log(`Fetching page ${i + 1} from Baidu: ${searchUrl.toString()}`);
let retryCount = 0;
let success = false;
while (retryCount < 5 && !success) {
try {
console.time(`Page Load Time for page ${i + 1}`);
await page.goto(searchUrl.toString(), { waitUntil: 'load' });
console.timeEnd(`Page Load Time for page ${i + 1}`);
let content = await page.content();
let dom = new JSDOM(content);
let document = dom.window.document;
console.log(document.title);
// 如果是百度安全验证页面，重新设置页面并重新访问
if (document.title.includes('百度安全验证')) {
console.log('Detected Baidu security verification, retrying...');
await setupPage(page);
retryCount++;
//随机等待时间
await randomWait(1000, 3000);
continue;
}
// 解析搜索结果
console.time(`Link Retrieval Time for page ${i + 1}`);
const resultContainers = document.querySelectorAll('.result.c-container');
for (const result of resultContainers) {
if (resultUrls.length > pageCount + 5) {
break;
}
const titleElement = result.querySelector('h3 a');
const title = titleElement ? titleElement.textContent : '';
const url = titleElement ? titleElement.getAttribute('href') : '';
const contentElement = result.querySelector('[class^="content"]');
const content = contentElement ? contentElement.textContent : '';
if (url) {
resultUrls.push(url);
results.set(url, {
title,
url,
snippet: content,
source: 'baidu',
crawlStatus: 'Pending',
score: 0
});
}
}
console.timeEnd(`Link Retrieval Time for page ${i + 1}`);
success = true;
} catch (error) {
console.error(`Error fetching page ${i + 1}:`, error);
retryCount++;
}
}
const resultUrls: string[] = [];
const results = new Map<string, any>();
}
const pagesToFetch = Math.ceil(pageCount / 10);
await browser.close();
const browser = await puppeteer.launch({
ignoreDefaultArgs: ["--enable-automation"],
headless: true,
executablePath: "/usr/bin/chromium", // 明确指定 Chromium 路径
pipe: true,
args: [
'--no-sandbox',
'--disable-setuid-sandbox',
'--disable-dev-shm-usage',
'--disable-gpu',
// '--single-process'
]
console.log('fetch all fake urls');
// 快速检索真实 URL
const urlsToProcessWithPuppeteer = [];
for (const url of resultUrls) {
try {
const response = await fetch(url, {
headers: {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
Referer: 'https://www.google.com/',
'Accept-Language': 'en-US,en;q=0.9',
Accept: 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
Connection: 'keep-alive',
'Cache-Control': 'no-cache'
}
});
const page = await browser.newPage();
await setupPage(page);
for (let i = 0; i < pagesToFetch; i++) {
const searchUrl = new URL(`${searchUrlBase}?wd=${encodeURIComponent(query)}&pn=${i * 10}`);
console.log(`Fetching page ${i + 1} from Baidu: ${searchUrl.toString()}`);
let retryCount = 0;
let success = false;
while (retryCount < 5 && !success) {
try {
console.time(`Page Load Time for page ${i + 1}`);
await page.goto(searchUrl.toString(), { waitUntil: 'load' });
console.timeEnd(`Page Load Time for page ${i + 1}`);
let content = await page.content();
let dom = new JSDOM(content);
let document = dom.window.document;
console.log(document.title);
// 如果是百度安全验证页面，重新设置页面并重新访问
if (document.title.includes('百度安全验证')) {
console.log('Detected Baidu security verification, retrying...');
await setupPage(page);
retryCount++;
//随机等待时间
await randomWait(1000, 3000);
continue;
}
// 解析搜索结果
console.time(`Link Retrieval Time for page ${i + 1}`);
const resultContainers = document.querySelectorAll('.result.c-container');
for (const result of resultContainers) {
if (resultUrls.length > pageCount + 5) {
break;
}
const titleElement = result.querySelector('h3 a');
const title = titleElement ? titleElement.textContent : '';
const url = titleElement ? titleElement.getAttribute('href') : '';
const contentElement = result.querySelector('[class^="content"]');
const content = contentElement ? contentElement.textContent : '';
if (url) {
resultUrls.push(url);
results.set(url, {
title,
url,
snippet: content,
source: 'baidu',
crawlStatus: 'Pending',
score: 0
});
}
}
console.timeEnd(`Link Retrieval Time for page ${i + 1}`);
success = true;
} catch (error) {
console.error(`Error fetching page ${i + 1}:`, error);
retryCount++;
}
if (response.ok) {
const realUrl = response.url;
console.log('realurl:', realUrl);
const result = results.get(url);
if (result) {
result.url = realUrl;
result.crawlStatus = 'Success';
}
} else {
throw new Error(`HTTP error! status: ${response.status}`);
}
} catch (error) {
console.error(`Error fetching original URL for ${url}:`, error);
urlsToProcessWithPuppeteer.push(url);
}
}
await browser.close();
console.log('pass quickfetch');
console.log('fetch all fake urls');
// 快速检索真实 URL
const urlsToProcessWithPuppeteer = [];
for (const url of resultUrls) {
try {
const response = await fetch(url, {
headers: {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
'Referer': 'https://www.google.com/',
'Accept-Language': 'en-US,en;q=0.9',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Connection': 'keep-alive',
'Cache-Control': 'no-cache'
}
});
if (response.ok) {
const realUrl = response.url;
console.log('realurl:', realUrl);
const result = results.get(url);
if (result) {
result.url = realUrl;
result.crawlStatus = 'Success';
}
} else {
throw new Error(`HTTP error! status: ${response.status}`);
}
} catch (error) {
console.error(`Error fetching original URL for ${url}:`, error);
urlsToProcessWithPuppeteer.push(url);
}
// 并发处理真实 URL
const cluster = await Cluster.launch({
concurrency: Cluster.CONCURRENCY_CONTEXT,
maxConcurrency: 10,
puppeteerOptions: {
ignoreDefaultArgs: ['--enable-automation'],
headless: 'true',
executablePath: '/usr/bin/chromium', // 明确指定 Chromium 路径
pipe: true,
args: ['--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage', '--disable-gpu']
}
});
console.log('pass quickfetch');
let failedUrlCount = 0;
// 并发处理真实 URL
const cluster = await Cluster.launch({
concurrency: Cluster.CONCURRENCY_CONTEXT,
maxConcurrency: 10,
puppeteerOptions: {
ignoreDefaultArgs: ["--enable-automation"],
headless: "true",
executablePath: "/usr/bin/chromium", // 明确指定 Chromium 路径
pipe: true,
args: [
'--no-sandbox',
'--disable-setuid-sandbox',
'--disable-dev-shm-usage',
'--disable-gpu',
]
await cluster.task(async ({ page, data: url }) => {
let retryUrlCount = 0;
let urlSuccess = false;
while (retryUrlCount < 3 && !urlSuccess) {
console.log(`Fetching original URL for ${url}, attempt ${retryUrlCount + 1}`);
try {
await page.goto(url, { waitUntil: 'load' });
// 检查页面是否被分离
if (page.isClosed()) {
throw new Error('Page has been closed');
}
});
let failedUrlCount = 0;
await cluster.task(async ({ page, data: url }) => {
let retryUrlCount = 0;
let urlSuccess = false;
while (retryUrlCount < 3 && !urlSuccess) {
console.log(`Fetching original URL for ${url}, attempt ${retryUrlCount + 1}`);
try {
await page.goto(url, { waitUntil: 'load' });
// 检查页面是否被分离
if (page.isClosed()) {
throw new Error('Page has been closed');
}
const realUrl = page.url(); // 获取真实 URL
const result = results.get(url);
if (result) {
result.url = realUrl;
result.crawlStatus = 'Success';
}
urlSuccess = true;
} catch (error) {
console.error(`Error fetching original URL, retrying...`, error);
retryUrlCount++;
await randomWait(1000, 3000);
}
const realUrl = page.url(); // 获取真实 URL
const result = results.get(url);
if (result) {
result.url = realUrl;
result.crawlStatus = 'Success';
}
if (!urlSuccess) {
failedUrlCount++;
}
});
for (const url of urlsToProcessWithPuppeteer) {
cluster.queue(url);
urlSuccess = true;
} catch (error) {
console.error(`Error fetching original URL, retrying...`, error);
retryUrlCount++;
await randomWait(1000, 3000);
}
}
if (!urlSuccess) {
failedUrlCount++;
}
});
await cluster.idle();
await cluster.close();
for (const url of urlsToProcessWithPuppeteer) {
cluster.queue(url);
}
console.log(`Number of URLs that failed to return a real URL: ${failedUrlCount}`);
await cluster.idle();
await cluster.close();
// 过滤并返回前 pageCount 个结果
const filteredResults = Array.from(results.values()).slice(0, pageCount);
console.log(`Number of URLs that failed to return a real URL: ${failedUrlCount}`);
return { resultUrls: filteredResults.map(result => result.url), results: new Map(filteredResults.map(result => [result.url, result])) };
// 过滤并返回前 pageCount 个结果
const filteredResults = Array.from(results.values()).slice(0, pageCount);
return {
resultUrls: filteredResults.map((result) => result.url),
results: new Map(filteredResults.map((result) => [result.url, result]))
};
};

19
plugins/webcrawler/SPIDER/src/engines/searchxngEngine.ts
View File

@@ -6,9 +6,13 @@ dotenv.config();
const blacklistDomains = process.env.BLACKLIST ? JSON.parse(process.env.BLACKLIST) : [];
export const fetchSearchResults = async (query: string, pageCount: number, searchUrlBase: string, categories: string) => {
const MAX_PAGES = (pageCount / 10 +1) * 2+1; // 最多搜索的页面数
export const fetchSearchResults = async (
query: string,
pageCount: number,
searchUrlBase: string,
categories: string
) => {
const MAX_PAGES = (pageCount / 10 + 1) * 2 + 1; // 最多搜索的页面数
//如果searchUrlBase为空，返回空数组，pagecount是需要搜索结果的数量
if (!searchUrlBase) {
return { resultUrls: [], results: new Map() };
@@ -20,7 +24,9 @@ export const fetchSearchResults = async (query: string, pageCount: number, searc
let pageIndex = 0;
while (fetchedResultsCount < pageCount && pageIndex < MAX_PAGES) {
const searchUrl = new URL(`${searchUrlBase}?q=${encodeURIComponent(query)}&pageno=${pageIndex + 1}&format=json&categories=${categories}`);
const searchUrl = new URL(
`${searchUrlBase}?q=${encodeURIComponent(query)}&pageno=${pageIndex + 1}&format=json&categories=${categories}`
);
console.log(`Fetching page ${pageIndex + 1} from SearchXNG: ${searchUrl.toString()}`);
const response = await axios.get(searchUrl.toString());
const jsonResults = response.data.results;
@@ -28,7 +34,10 @@ export const fetchSearchResults = async (query: string, pageCount: number, searc
for (let index = 0; index < jsonResults.length; index++) {
const result = jsonResults[index];
const resultDomain = new URL(result.url).hostname;
if (blacklistDomains.some((domain: string) => resultDomain.endsWith(domain)) || resultDomain.includes('zhihu')) {
if (
blacklistDomains.some((domain: string) => resultDomain.endsWith(domain)) ||
resultDomain.includes('zhihu')
) {
continue;
}
resultUrls.push(result.url);

2
plugins/webcrawler/SPIDER/src/middleware/authMiddleware.ts
View File

@@ -4,7 +4,7 @@ const authMiddleware = (req: Request, res: Response, next: NextFunction) => {
const bearerHeader = req.headers['authorization'];
if (bearerHeader) {
console.log("bearerHeader:" + bearerHeader);
console.log('bearerHeader:' + bearerHeader);
const bearer = bearerHeader.split(' ');
const bearerToken = bearer[1];

11
plugins/webcrawler/SPIDER/src/specialHandlers/index.ts
View File

@@ -3,17 +3,22 @@ import { Page } from 'puppeteer';
export const handleSpecialWebsite = async (page: Page, url: string): Promise<string | null> => {
if (url.includes('blog.csdn.net')) {
await page.waitForSelector('article');
const content = await page.$eval('article', el => el.innerHTML);
const content = await page.$eval('article', (el) => el.innerHTML);
return content;
}
if (url.includes('zhuanlan.zhihu.com')) {
console.log('是知乎，需要点击按掉！');
console.log(await page.content());
if((await page.content()).includes('{"error":{"message":"您当前请求存在异常，暂时限制本次访问。如有疑问，您可以通过手机摇一摇或登录后私信知乎小管家反馈。","code":40362}}')) return null;
if (
(await page.content()).includes(
'{"error":{"message":"您当前请求存在异常，暂时限制本次访问。如有疑问，您可以通过手机摇一摇或登录后私信知乎小管家反馈。","code":40362}}'
)
)
return null;
await page.waitForSelector('button[aria-label="关闭"]');
await page.click('button[aria-label="关闭"]'); // 使用 aria-label 选择按钮
await page.waitForSelector('article');
const content = await page.$eval('article', el => el.innerHTML);
const content = await page.$eval('article', (el) => el.innerHTML);
return content;
}
// 可以添加更多特殊网站的处理逻辑

18
plugins/webcrawler/SPIDER/src/utils/cacheUpdater.ts
View File

@@ -1,4 +1,3 @@
import NodeCache from 'node-cache';
import { MongoClient } from 'mongodb';
import crypto from 'crypto';
@@ -19,10 +18,15 @@ const connectToMongo = async () => {
const createTTLIndex = async () => {
try {
const db = await connectToMongo();
await db.collection(collectionName).createIndex({ "updatedAt": 1 }, { expireAfterSeconds: parseInt(process.env.EXPIRE_AFTER_SECONDS || '9000') });
console.log("TTL index created successfully");
await db
.collection(collectionName)
.createIndex(
{ updatedAt: 1 },
{ expireAfterSeconds: parseInt(process.env.EXPIRE_AFTER_SECONDS || '9000') }
);
console.log('TTL index created successfully');
} catch (error) {
console.error("Error creating TTL index:", error);
console.error('Error creating TTL index:', error);
}
};
@@ -53,11 +57,7 @@ const savePageToCache = async (url: string, content: string) => {
try {
const db = await connectToMongo();
await db.collection(collectionName).updateOne(
{ url },
{ $set: page },
{ upsert: true }
); // 更新持久化缓存
await db.collection(collectionName).updateOne({ url }, { $set: page }, { upsert: true }); // 更新持久化缓存
} catch (error) {
console.error('Error saving page to cache:', error);
throw error;

36
plugins/webcrawler/SPIDER/src/utils/deepSearch.ts
View File

@@ -13,12 +13,19 @@ interface CachedPage {
updatedAt: Date;
}
export const performDeepSearch = async (clusterInstance: Cluster, resultUrls: string[], results: Map<string, any>, strategies: any[], detectWebsites: string[], pageCount: number) => {
export const performDeepSearch = async (
clusterInstance: Cluster,
resultUrls: string[],
results: Map<string, any>,
strategies: any[],
detectWebsites: string[],
pageCount: number
) => {
const tasks = [];
await clusterInstance.task(async ({ page, data: { searchUrl } }) => {
try {
const cachedPage = await getCachedPage(searchUrl) as CachedPage | null;
const cachedPage = (await getCachedPage(searchUrl)) as CachedPage | null;
if (cachedPage) {
const result = results.get(searchUrl);
if (result) {
@@ -29,18 +36,25 @@ export const performDeepSearch = async (clusterInstance: Cluster, resultUrls: st
}
} catch (error) {
console.error(`从缓存获取页面 ${searchUrl} 时发生错误:`, error);
results.set(searchUrl, { url: searchUrl, error: (error as Error).message, crawlStatus: 'Failed' });
results.set(searchUrl, {
url: searchUrl,
error: (error as Error).message,
crawlStatus: 'Failed'
});
return;
}
try {
const response = await fetch(searchUrl, {
headers: {
'User-Agent': new UserAgent({ deviceCategory: 'desktop', platform: 'Linux x86_64' }).toString(),
'Referer': 'https://www.google.com/',
'User-Agent': new UserAgent({
deviceCategory: 'desktop',
platform: 'Linux x86_64'
}).toString(),
Referer: 'https://www.google.com/',
'Accept-Language': 'en-US,en;q=0.9',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Connection': 'keep-alive',
Accept: 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
Connection: 'keep-alive',
'Cache-Control': 'no-cache'
}
});
@@ -66,7 +80,7 @@ export const performDeepSearch = async (clusterInstance: Cluster, resultUrls: st
}
try {
if (detectWebsites.some(website => searchUrl.includes(website))) {
if (detectWebsites.some((website) => searchUrl.includes(website))) {
await setupPage(page);
} else {
const userAgent = new UserAgent({ deviceCategory: 'desktop', platform: 'Linux x86_64' });
@@ -118,7 +132,11 @@ export const performDeepSearch = async (clusterInstance: Cluster, resultUrls: st
await updateCacheAsync(searchUrl, cleanedContent || '');
} catch (error) {
results.set(searchUrl, { url: searchUrl, error: (error as Error).message, crawlStatus: 'Failed' });
results.set(searchUrl, {
url: searchUrl,
error: (error as Error).message,
crawlStatus: 'Failed'
});
} finally {
await page.close().catch(() => {});
}

52
plugins/webcrawler/SPIDER/src/utils/setupPage.ts
View File

@@ -8,7 +8,7 @@ const getRandomUserAgent = () => {
};
const getRandomPlatform = () => {
const platforms = ["Win32", "MacIntel", "Linux x86_64"];
const platforms = ['Win32', 'MacIntel', 'Linux x86_64'];
return platforms[Math.floor(Math.random() * platforms.length)];
};
@@ -16,14 +16,16 @@ const getRandomPlatform = () => {
const validateproxy = process.env.VALIDATE_PROXY ? JSON.parse(process.env.VALIDATE_PROXY) : [];
const getRandomProxy = () => {
return validateproxy.length > 0 ? validateproxy[Math.floor(Math.random() * validateproxy.length)] : null;
return validateproxy.length > 0
? validateproxy[Math.floor(Math.random() * validateproxy.length)]
: null;
};
const getRandomLanguages = () => {
const languages = [
["zh-CN", "zh", "en"],
["en-US", "en", "fr"],
["es-ES", "es", "en"]
['zh-CN', 'zh', 'en'],
['en-US', 'en', 'fr'],
['es-ES', 'es', 'en']
];
return languages[Math.floor(Math.random() * languages.length)];
};
@@ -42,30 +44,38 @@ export const setupPage = async (page: Page): Promise<void> => {
delete newProto.webdriver;
(navigator as any).__proto__ = newProto;
(window as any).chrome = {};
(window as any).chrome.app = {"InstallState":"testt", "RunningState":"estt", "getDetails":"stte", "getIsInstalled":"ttes"};
(window as any).chrome.csi = function(){};
(window as any).chrome.loadTimes = function(){};
(window as any).chrome.runtime = function(){};
(window as any).chrome.app = {
InstallState: 'testt',
RunningState: 'estt',
getDetails: 'stte',
getIsInstalled: 'ttes'
};
(window as any).chrome.csi = function () {};
(window as any).chrome.loadTimes = function () {};
(window as any).chrome.runtime = function () {};
Object.defineProperty(navigator, 'userAgent', {
get: () => getRandomUserAgent(),
get: () => getRandomUserAgent()
});
Object.defineProperty(navigator, 'platform', {
get: () => getRandomPlatform(),
get: () => getRandomPlatform()
});
Object.defineProperty(navigator, 'plugins', {
get: () => [{"description": "Shockwave Flash",
"filename": "pepflashplayer.dll",
"length": 1,
"name": "Shockwave Flash"}]
get: () => [
{
description: 'Shockwave Flash',
filename: 'pepflashplayer.dll',
length: 1,
name: 'Shockwave Flash'
}
]
});
Object.defineProperty(navigator, 'languages', {
get: () => getRandomLanguages(),
get: () => getRandomLanguages()
});
const originalQuery = (window.navigator.permissions as any).query;
(window.navigator.permissions as any).query = (parameters: any) => (
parameters.name === 'notifications' ?
Promise.resolve({ state: Notification.permission } as PermissionStatus) :
originalQuery(parameters)
);
(window.navigator.permissions as any).query = (parameters: any) =>
parameters.name === 'notifications'
? Promise.resolve({ state: Notification.permission } as PermissionStatus)
: originalQuery(parameters);
});
};

10
projects/app/src/pages/api/admin/initv485.ts
View File

@@ -63,7 +63,7 @@ async function initHttp(teamId?: string): Promise<any> {
}
}
],
{ session }
{ session, ordered: true }
);
/* 批量创建子插件 */
@@ -88,7 +88,7 @@ async function initHttp(teamId?: string): Promise<any> {
}
}
],
{ session }
{ session, ordered: true }
);
if (item.version === 'v2') {
await MongoAppVersion.create(
@@ -100,7 +100,7 @@ async function initHttp(teamId?: string): Promise<any> {
edges: item.edges
}
],
{ session }
{ session, ordered: true }
);
}
}
@@ -160,7 +160,7 @@ async function initPlugin(teamId?: string): Promise<any> {
}
}
],
{ session }
{ session, ordered: true }
);
if (plugin.version === 'v2') {
@@ -173,7 +173,7 @@ async function initPlugin(teamId?: string): Promise<any> {
edges: plugin.edges
}
],
{ session }
{ session, ordered: true }
);
}

3
projects/app/src/pages/api/admin/resetMilvus.ts
View File

@@ -98,7 +98,8 @@ async function handler(
}
],
{
session
session,
ordered: true
}
);
}

4
projects/app/src/pages/api/core/app/create.ts
View File

@@ -126,7 +126,7 @@ export const onCreateApp = async ({
'pluginData.nodeVersion': defaultNodeVersion
}
],
{ session }
{ session, ordered: true }
);
if (!AppFolderTypeList.includes(type!)) {
@@ -144,7 +144,7 @@ export const onCreateApp = async ({
isPublish: true
}
],
{ session }
{ session, ordered: true }
);
}

3
projects/app/src/pages/api/core/app/folder/create.ts
View File

@@ -89,7 +89,8 @@ async function handler(req: ApiRequestProps<CreateAppFolderBody>) {
}
],
{
session
session,
ordered: true
}
);
}

2
projects/app/src/pages/api/core/app/version/publish.ts
View File

@@ -45,7 +45,7 @@ async function handler(req: ApiRequestProps<PostPublishAppProps>, res: NextApiRe
tmbId
}
],
{ session }
{ session, ordered: true }
);
// update app

2
projects/app/src/pages/api/core/dataset/create.ts
View File

@@ -88,7 +88,7 @@ async function handler(
yuqueServer
}
],
{ session }
{ session, ordered: true }
);
await refreshSourceAvatar(avatar, undefined, session);

2
projects/app/src/pages/api/core/dataset/folder/create.ts
View File

@@ -87,7 +87,7 @@ async function handler(
permission: OwnerPermissionVal
}
],
{ session }
{ session, ordered: true }
);
}
});

3
projects/app/src/pages/api/core/dataset/training/rebuildEmbedding.ts
View File

@@ -122,7 +122,8 @@ async function handler(req: ApiRequestProps<rebuildEmbeddingBody>): Promise<Resp
}
],
{
session
session,
ordered: true
}
);
}

4
projects/app/src/service/core/dataset/data/controller.ts
View File

@@ -98,7 +98,7 @@ export async function insertData2Dataset({
}))
}
],
{ session }
{ session, ordered: true }
);
// 3. Create mongo data text
@@ -112,7 +112,7 @@ export async function insertData2Dataset({
fullTextToken: jiebaSplit({ text: qaStr })
}
],
{ session }
{ session, ordered: true }
);
return {

2
projects/app/src/service/events/generateVector.ts
View File

@@ -192,7 +192,7 @@ const rebuildData = async ({
retryCount: 50
}
],
{ session }
{ session, ordered: true }
);
}
});

2
projects/app/src/service/mongo.ts
View File

@@ -37,7 +37,7 @@ export async function initRootUser(retry = 3): Promise<any> {
password: hashStr(psw)
}
],
{ session }
{ session, ordered: true }
);
rootId = _id;
}