paper-search-cli 0.1.2 → 0.2.0

package/dist/utils/HttpClient.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"HttpClient.d.ts","sourceRoot":"","sources":["../../src/utils/HttpClient.ts"],"names":[],"mappings":"AAKA;;;GAGG;AACH,wBAAgB,gBAAgB,IAAI,IAAI,CAuBvC"}

package/dist/utils/HttpClient.js

@@ -0,0 +1,30 @@
+import axios from 'axios';
+import { HttpsProxyAgent } from 'https-proxy-agent';
+import { SocksProxyAgent } from 'socks-proxy-agent';
+import { logDebug } from './Logger.js';
+/**
+ * Initializes global HTTP/HTTPS and SOCKS proxy agents for Axios
+ * based on standard proxy environment variables.
+ */
+export function setupGlobalProxy() {
+    const proxy = process.env.HTTPS_PROXY ||
+        process.env.HTTP_PROXY ||
+        process.env.https_proxy ||
+        process.env.http_proxy;
+    if (!proxy) {
+        return;
+    }
+    try {
+        logDebug(`Configuring global HTTP/HTTPS proxy: ${proxy}`);
+        const agent = proxy.startsWith('socks')
+            ? new SocksProxyAgent(proxy)
+            : new HttpsProxyAgent(proxy);
+        // Inject agent as default for both http and https protocols
+        axios.defaults.httpAgent = agent;
+        axios.defaults.httpsAgent = agent;
+    }
+    catch (error) {
+        logDebug(`Failed to initialize global proxy agent: ${error.message}`);
+    }
+}
+//# sourceMappingURL=HttpClient.js.map

package/dist/utils/HttpClient.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"HttpClient.js","sourceRoot":"","sources":["../../src/utils/HttpClient.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,MAAM,OAAO,CAAC;AAC1B,OAAO,EAAE,eAAe,EAAE,MAAM,mBAAmB,CAAC;AACpD,OAAO,EAAE,eAAe,EAAE,MAAM,mBAAmB,CAAC;AACpD,OAAO,EAAE,QAAQ,EAAE,MAAM,aAAa,CAAC;AAEvC;;;GAGG;AACH,MAAM,UAAU,gBAAgB;IAC9B,MAAM,KAAK,GACT,OAAO,CAAC,GAAG,CAAC,WAAW;QACvB,OAAO,CAAC,GAAG,CAAC,UAAU;QACtB,OAAO,CAAC,GAAG,CAAC,WAAW;QACvB,OAAO,CAAC,GAAG,CAAC,UAAU,CAAC;IAEzB,IAAI,CAAC,KAAK,EAAE,CAAC;QACX,OAAO;IACT,CAAC;IAED,IAAI,CAAC;QACH,QAAQ,CAAC,wCAAwC,KAAK,EAAE,CAAC,CAAC;QAC1D,MAAM,KAAK,GAAG,KAAK,CAAC,UAAU,CAAC,OAAO,CAAC;YACrC,CAAC,CAAC,IAAI,eAAe,CAAC,KAAK,CAAC;YAC5B,CAAC,CAAC,IAAI,eAAe,CAAC,KAAK,CAAC,CAAC;QAE/B,4DAA4D;QAC5D,KAAK,CAAC,QAAQ,CAAC,SAAS,GAAG,KAAK,CAAC;QACjC,KAAK,CAAC,QAAQ,CAAC,UAAU,GAAG,KAAK,CAAC;IACpC,CAAC;IAAC,OAAO,KAAU,EAAE,CAAC;QACpB,QAAQ,CAAC,4CAA4C,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC;IACxE,CAAC;AACH,CAAC"}

package/dist/utils/PdfDownload.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"PdfDownload.d.ts","sourceRoot":"","sources":["../../src/utils/PdfDownload.ts"],"names":[],"mappings":"AAKA,MAAM,WAAW,kBAAkB;IACjC,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;CAClC;AAED,wBAAgB,YAAY,CAAC,KAAK,EAAE,MAAM,EAAE,QAAQ,SAAU,GAAG,MAAM,CAGtE;AAED,wBAAgB,WAAW,CAAC,MAAM,EAAE,MAAM,EAAE,WAAW,SAAK,GAAG,OAAO,CAErE;AAED,wBAAsB,kBAAkB,CACtC,MAAM,EAAE,MAAM,EACd,QAAQ,EAAE,MAAM,EAChB,YAAY,EAAE,MAAM,EACpB,OAAO,GAAE,kBAAuB,GAC/B,OAAO,CAAC,MAAM,CAAC,CA4CjB"}
+{"version":3,"file":"PdfDownload.d.ts","sourceRoot":"","sources":["../../src/utils/PdfDownload.ts"],"names":[],"mappings":"AAMA,MAAM,WAAW,kBAAkB;IACjC,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;CAClC;AAED,wBAAgB,YAAY,CAAC,KAAK,EAAE,MAAM,EAAE,QAAQ,SAAU,GAAG,MAAM,CAGtE;AAED,wBAAgB,WAAW,CAAC,MAAM,EAAE,MAAM,EAAE,WAAW,SAAK,GAAG,OAAO,CAErE;AAiCD,wBAAsB,kBAAkB,CACtC,MAAM,EAAE,MAAM,EACd,QAAQ,EAAE,MAAM,EAChB,YAAY,EAAE,MAAM,EACpB,OAAO,GAAE,kBAAuB,GAC/B,OAAO,CAAC,MAAM,CAAC,CA4GjB"}

package/dist/utils/PdfDownload.js

@@ -1,6 +1,7 @@
 import axios from 'axios';
 import * as fs from 'fs';
 import * as path from 'path';
+import { Readable } from 'stream';
 import { TIMEOUTS, USER_AGENT } from '../config/constants.js';
 export function safeFilename(value, fallback = 'paper') {
     const safe = value.replace(/[^a-zA-Z0-9._-]+/g, '_').replace(/^[_\-.]+|[_\-.]+$/g, '');
@@ -9,6 +10,36 @@ export function safeFilename(value, fallback = 'paper') {
 export function isPdfBuffer(buffer, contentType = '') {
     return contentType.toLowerCase().includes('pdf') || buffer.subarray(0, 4).toString() === '%PDF';
 }
+async function getStreamSnippet(stream, maxBytes = 240) {
+    return new Promise((resolve) => {
+        let buffer = Buffer.alloc(0);
+        const onData = (chunk) => {
+            buffer = Buffer.concat([buffer, chunk]);
+            if (buffer.length >= maxBytes) {
+                cleanup();
+                stream.destroy?.();
+            }
+        };
+        const cleanup = () => {
+            if (typeof stream.off === 'function') {
+                stream.off('data', onData);
+            }
+        };
+        stream.on('data', onData);
+        stream.on('end', () => {
+            cleanup();
+            resolve(buffer.subarray(0, maxBytes).toString('utf8').replace(/\s+/g, ' ').trim());
+        });
+        stream.on('close', () => {
+            cleanup();
+            resolve(buffer.subarray(0, maxBytes).toString('utf8').replace(/\s+/g, ' ').trim());
+        });
+        stream.on('error', () => {
+            cleanup();
+            resolve(buffer.subarray(0, maxBytes).toString('utf8').replace(/\s+/g, ' ').trim());
+        });
+    });
+}
 export async function downloadPdfFromUrl(pdfUrl, savePath, filenameHint, options = {}) {
     if (!pdfUrl) {
         throw new Error('Missing PDF URL');
@@ -19,7 +50,7 @@ export async function downloadPdfFromUrl(pdfUrl, savePath, filenameHint, options
     fs.mkdirSync(savePath, { recursive: true });
     const outputPath = path.join(savePath, `${safeFilename(filenameHint)}.pdf`);
     const response = await axios.get(pdfUrl, {
-        responseType: 'arraybuffer',
+        responseType: 'stream',
         timeout: TIMEOUTS.DOWNLOAD,
         maxRedirects: 5,
         headers: {
@@ -30,23 +61,82 @@ export async function downloadPdfFromUrl(pdfUrl, savePath, filenameHint, options
         validateStatus: status => status < 500
     });
     if (response.status >= 400) {
-        const errorBuffer = Buffer.from(response.data || []);
-        const snippet = errorBuffer.subarray(0, 240).toString('utf8').replace(/\s+/g, ' ').trim();
-        const challenge = response.headers['cf-mitigated'] || /cloudflare|challenge|just a moment/i.test(snippet);
+        let errStream = response.data;
+        if (!(errStream instanceof Readable) && !(errStream && typeof errStream.on === 'function')) {
+            errStream = Readable.from(Buffer.isBuffer(errStream) ? errStream : Buffer.from(errStream || ''));
+        }
+        const errorSnippet = await getStreamSnippet(errStream);
+        const cfHeader = response.headers['cf-mitigated'];
+        const challenge = !!cfHeader || /cloudflare|challenge|just a moment/i.test(errorSnippet);
         const reason = challenge ? 'provider returned an HTML anti-bot challenge instead of a PDF' : 'provider refused the request';
         throw new Error(`PDF download failed with HTTP ${response.status}: ${reason}`);
     }
-    const buffer = Buffer.from(response.data);
-    const contentType = String(response.headers['content-type'] || '').toLowerCase();
-    if (!isPdfBuffer(buffer, contentType)) {
-        const snippet = buffer.subarray(0, 240).toString('utf8').replace(/\s+/g, ' ').trim();
-        const challenge = response.headers['cf-mitigated'] || /cloudflare|challenge|preparing to download|proof-of-work/i.test(snippet);
-        const reason = challenge
-            ? 'the provider returned an HTML challenge page instead of a PDF'
-            : `content-type was ${contentType || 'unknown'}`;
-        throw new Error(`Resolved URL did not return a PDF (${reason}): ${pdfUrl}`);
-    }
-    fs.writeFileSync(outputPath, buffer);
-    return outputPath;
+    return new Promise((resolve, reject) => {
+        const writer = fs.createWriteStream(outputPath);
+        let reader = response.data;
+        if (!(reader instanceof Readable) && !(reader && typeof reader.on === 'function')) {
+            reader = Readable.from(Buffer.isBuffer(reader) ? reader : Buffer.from(reader || ''));
+        }
+        let checked = false;
+        let totalBytes = 0;
+        const contentLengthHeader = response.headers['content-length'];
+        const expectedLength = contentLengthHeader ? parseInt(String(contentLengthHeader), 10) : 0;
+        writer.on('error', (err) => {
+            if (typeof reader.destroy === 'function')
+                reader.destroy();
+            fs.unlink(outputPath, () => { });
+            reject(err);
+        });
+        reader.on('data', (chunk) => {
+            totalBytes += chunk.length;
+            if (!checked) {
+                checked = true;
+                const contentType = String(response.headers['content-type'] || '').toLowerCase();
+                const isPdf = contentType.includes('pdf') || chunk.subarray(0, 4).toString() === '%PDF';
+                if (!isPdf) {
+                    const snippet = chunk.subarray(0, 240).toString('utf8').replace(/\s+/g, ' ').trim();
+                    const cfHeader = response.headers['cf-mitigated'];
+                    const challenge = !!cfHeader || /cloudflare|challenge|preparing to download|proof-of-work|<!doctype html/i.test(snippet);
+                    const reason = challenge
+                        ? 'the provider returned an HTML challenge page instead of a PDF'
+                        : `content-type was ${contentType || 'unknown'}`;
+                    if (typeof reader.destroy === 'function')
+                        reader.destroy();
+                    writer.destroy();
+                    fs.unlink(outputPath, () => { });
+                    reject(new Error(`Resolved URL did not return a PDF (${reason}): ${pdfUrl}`));
+                    return;
+                }
+            }
+            if (!writer.write(chunk)) {
+                if (typeof reader.pause === 'function')
+                    reader.pause();
+            }
+        });
+        writer.on('drain', () => {
+            if (typeof reader.resume === 'function')
+                reader.resume();
+        });
+        reader.on('end', () => {
+            writer.end();
+        });
+        reader.on('close', () => {
+            if (typeof reader.destroy === 'function')
+                reader.destroy();
+        });
+        writer.on('finish', () => {
+            if (expectedLength && totalBytes !== expectedLength) {
+                fs.unlink(outputPath, () => { });
+                reject(new Error(`PDF download incomplete: received ${totalBytes} bytes, expected ${expectedLength} bytes`));
+                return;
+            }
+            resolve(outputPath);
+        });
+        reader.on('error', (err) => {
+            writer.destroy();
+            fs.unlink(outputPath, () => { });
+            reject(err);
+        });
+    });
 }
 //# sourceMappingURL=PdfDownload.js.map

package/dist/utils/PdfDownload.js.map

@@ -1 +1 @@
-{"version":3,"file":"PdfDownload.js","sourceRoot":"","sources":["../../src/utils/PdfDownload.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,MAAM,OAAO,CAAC;AAC1B,OAAO,KAAK,EAAE,MAAM,IAAI,CAAC;AACzB,OAAO,KAAK,IAAI,MAAM,MAAM,CAAC;AAC7B,OAAO,EAAE,QAAQ,EAAE,UAAU,EAAE,MAAM,wBAAwB,CAAC;AAM9D,MAAM,UAAU,YAAY,CAAC,KAAa,EAAE,QAAQ,GAAG,OAAO;IAC5D,MAAM,IAAI,GAAG,KAAK,CAAC,OAAO,CAAC,mBAAmB,EAAE,GAAG,CAAC,CAAC,OAAO,CAAC,oBAAoB,EAAE,EAAE,CAAC,CAAC;IACvF,OAAO,CAAC,IAAI,IAAI,QAAQ,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;AAC1C,CAAC;AAED,MAAM,UAAU,WAAW,CAAC,MAAc,EAAE,WAAW,GAAG,EAAE;IAC1D,OAAO,WAAW,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,MAAM,CAAC,QAAQ,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,QAAQ,EAAE,KAAK,MAAM,CAAC;AAClG,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,kBAAkB,CACtC,MAAc,EACd,QAAgB,EAChB,YAAoB,EACpB,UAA8B,EAAE;IAEhC,IAAI,CAAC,MAAM,EAAE,CAAC;QACZ,MAAM,IAAI,KAAK,CAAC,iBAAiB,CAAC,CAAC;IACrC,CAAC;IACD,IAAI,MAAM,CAAC,UAAU,CAAC,QAAQ,CAAC,EAAE,CAAC;QAChC,MAAM,IAAI,KAAK,CAAC,2DAA2D,MAAM,EAAE,CAAC,CAAC;IACvF,CAAC;IAED,EAAE,CAAC,SAAS,CAAC,QAAQ,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IAC5C,MAAM,UAAU,GAAG,IAAI,CAAC,IAAI,CAAC,QAAQ,EAAE,GAAG,YAAY,CAAC,YAAY,CAAC,MAAM,CAAC,CAAC;IAE5E,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,CAAc,MAAM,EAAE;QACpD,YAAY,EAAE,aAAa;QAC3B,OAAO,EAAE,QAAQ,CAAC,QAAQ;QAC1B,YAAY,EAAE,CAAC;QACf,OAAO,EAAE;YACP,YAAY,EAAE,UAAU;YACxB,MAAM,EAAE,qBAAqB;YAC7B,GAAG,CAAC,OAAO,CAAC,OAAO,IAAI,EAAE,CAAC;SAC3B;QACD,cAAc,EAAE,MAAM,CAAC,EAAE,CAAC,MAAM,GAAG,GAAG;KACvC,CAAC,CAAC;IAEH,IAAI,QAAQ,CAAC,MAAM,IAAI,GAAG,EAAE,CAAC;QAC3B,MAAM,WAAW,GAAG,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC;QACrD,MAAM,OAAO,GAAG,WAAW,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;QAC1F,MAAM,SAAS,GAAG,QAAQ,CAAC,OAAO,CAAC,cAAc,CAAC,IAAI,qCAAqC,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;QAC1G,MAAM,MAAM,GAAG,SAAS,CAAC,CAAC,CAAC,+DAA+D,CAAC,CAAC,CAAC,8BAA8B,CAAC;QAC5H,MAAM,IAAI,KAAK,CAAC,iCAAiC,QAAQ,CAAC,MAAM,KAAK,MAAM,EAAE,CAAC,CAAC;IACjF,CAAC;IAED,MAAM,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IAC1C,MAAM,WAAW,GAAG,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC,cAAc,CAAC,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC;IACjF,IAAI,CAAC,WAAW,CAAC,MAAM,EAAE,WAAW,CAAC,EAAE,CAAC;QACtC,MAAM,OAAO,GAAG,MAAM,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;QACrF,MAAM,SAAS,GAAG,QAAQ,CAAC,OAAO,CAAC,cAAc,CAAC,IAAI,2DAA2D,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;QAChI,MAAM,MAAM,GAAG,SAAS;YACtB,CAAC,CAAC,+DAA+D;YACjE,CAAC,CAAC,oBAAoB,WAAW,IAAI,SAAS,EAAE,CAAC;QACnD,MAAM,IAAI,KAAK,CAAC,sCAAsC,MAAM,MAAM,MAAM,EAAE,CAAC,CAAC;IAC9E,CAAC;IAED,EAAE,CAAC,aAAa,CAAC,UAAU,EAAE,MAAM,CAAC,CAAC;IACrC,OAAO,UAAU,CAAC;AACpB,CAAC"}
+{"version":3,"file":"PdfDownload.js","sourceRoot":"","sources":["../../src/utils/PdfDownload.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,MAAM,OAAO,CAAC;AAC1B,OAAO,KAAK,EAAE,MAAM,IAAI,CAAC;AACzB,OAAO,KAAK,IAAI,MAAM,MAAM,CAAC;AAC7B,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAC;AAClC,OAAO,EAAE,QAAQ,EAAE,UAAU,EAAE,MAAM,wBAAwB,CAAC;AAM9D,MAAM,UAAU,YAAY,CAAC,KAAa,EAAE,QAAQ,GAAG,OAAO;IAC5D,MAAM,IAAI,GAAG,KAAK,CAAC,OAAO,CAAC,mBAAmB,EAAE,GAAG,CAAC,CAAC,OAAO,CAAC,oBAAoB,EAAE,EAAE,CAAC,CAAC;IACvF,OAAO,CAAC,IAAI,IAAI,QAAQ,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;AAC1C,CAAC;AAED,MAAM,UAAU,WAAW,CAAC,MAAc,EAAE,WAAW,GAAG,EAAE;IAC1D,OAAO,WAAW,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,MAAM,CAAC,QAAQ,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,QAAQ,EAAE,KAAK,MAAM,CAAC;AAClG,CAAC;AAED,KAAK,UAAU,gBAAgB,CAAC,MAAW,EAAE,QAAQ,GAAG,GAAG;IACzD,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE;QAC7B,IAAI,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;QAC7B,MAAM,MAAM,GAAG,CAAC,KAAa,EAAE,EAAE;YAC/B,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC,CAAC;YACxC,IAAI,MAAM,CAAC,MAAM,IAAI,QAAQ,EAAE,CAAC;gBAC9B,OAAO,EAAE,CAAC;gBACV,MAAM,CAAC,OAAO,EAAE,EAAE,CAAC;YACrB,CAAC;QACH,CAAC,CAAC;QACF,MAAM,OAAO,GAAG,GAAG,EAAE;YACnB,IAAI,OAAO,MAAM,CAAC,GAAG,KAAK,UAAU,EAAE,CAAC;gBACrC,MAAM,CAAC,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;YAC7B,CAAC;QACH,CAAC,CAAC;QACF,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;QAC1B,MAAM,CAAC,EAAE,CAAC,KAAK,EAAE,GAAG,EAAE;YACpB,OAAO,EAAE,CAAC;YACV,OAAO,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC,EAAE,QAAQ,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QACrF,CAAC,CAAC,CAAC;QACH,MAAM,CAAC,EAAE,CAAC,OAAO,EAAE,GAAG,EAAE;YACtB,OAAO,EAAE,CAAC;YACV,OAAO,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC,EAAE,QAAQ,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QACrF,CAAC,CAAC,CAAC;QACH,MAAM,CAAC,EAAE,CAAC,OAAO,EAAE,GAAG,EAAE;YACtB,OAAO,EAAE,CAAC;YACV,OAAO,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC,EAAE,QAAQ,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QACrF,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;AACL,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,kBAAkB,CACtC,MAAc,EACd,QAAgB,EAChB,YAAoB,EACpB,UAA8B,EAAE;IAEhC,IAAI,CAAC,MAAM,EAAE,CAAC;QACZ,MAAM,IAAI,KAAK,CAAC,iBAAiB,CAAC,CAAC;IACrC,CAAC;IACD,IAAI,MAAM,CAAC,UAAU,CAAC,QAAQ,CAAC,EAAE,CAAC;QAChC,MAAM,IAAI,KAAK,CAAC,2DAA2D,MAAM,EAAE,CAAC,CAAC;IACvF,CAAC;IAED,EAAE,CAAC,SAAS,CAAC,QAAQ,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IAC5C,MAAM,UAAU,GAAG,IAAI,CAAC,IAAI,CAAC,QAAQ,EAAE,GAAG,YAAY,CAAC,YAAY,CAAC,MAAM,CAAC,CAAC;IAE5E,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,CAAC,MAAM,EAAE;QACvC,YAAY,EAAE,QAAQ;QACtB,OAAO,EAAE,QAAQ,CAAC,QAAQ;QAC1B,YAAY,EAAE,CAAC;QACf,OAAO,EAAE;YACP,YAAY,EAAE,UAAU;YACxB,MAAM,EAAE,qBAAqB;YAC7B,GAAG,CAAC,OAAO,CAAC,OAAO,IAAI,EAAE,CAAC;SAC3B;QACD,cAAc,EAAE,MAAM,CAAC,EAAE,CAAC,MAAM,GAAG,GAAG;KACvC,CAAC,CAAC;IAEH,IAAI,QAAQ,CAAC,MAAM,IAAI,GAAG,EAAE,CAAC;QAC3B,IAAI,SAAS,GAAG,QAAQ,CAAC,IAAI,CAAC;QAC9B,IAAI,CAAC,CAAC,SAAS,YAAY,QAAQ,CAAC,IAAI,CAAC,CAAC,SAAS,IAAI,OAAO,SAAS,CAAC,EAAE,KAAK,UAAU,CAAC,EAAE,CAAC;YAC3F,SAAS,GAAG,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,SAAS,IAAI,EAAE,CAAC,CAAC,CAAC;QACnG,CAAC;QACD,MAAM,YAAY,GAAG,MAAM,gBAAgB,CAAC,SAAS,CAAC,CAAC;QACvD,MAAM,QAAQ,GAAG,QAAQ,CAAC,OAAO,CAAC,cAAc,CAAC,CAAC;QAClD,MAAM,SAAS,GAAG,CAAC,CAAC,QAAQ,IAAI,qCAAqC,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC;QACzF,MAAM,MAAM,GAAG,SAAS,CAAC,CAAC,CAAC,+DAA+D,CAAC,CAAC,CAAC,8BAA8B,CAAC;QAC5H,MAAM,IAAI,KAAK,CAAC,iCAAiC,QAAQ,CAAC,MAAM,KAAK,MAAM,EAAE,CAAC,CAAC;IACjF,CAAC;IAED,OAAO,IAAI,OAAO,CAAS,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QAC7C,MAAM,MAAM,GAAG,EAAE,CAAC,iBAAiB,CAAC,UAAU,CAAC,CAAC;QAChD,IAAI,MAAM,GAAG,QAAQ,CAAC,IAAI,CAAC;QAC3B,IAAI,CAAC,CAAC,MAAM,YAAY,QAAQ,CAAC,IAAI,CAAC,CAAC,MAAM,IAAI,OAAO,MAAM,CAAC,EAAE,KAAK,UAAU,CAAC,EAAE,CAAC;YAClF,MAAM,GAAG,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,CAAC;QACvF,CAAC;QACD,IAAI,OAAO,GAAG,KAAK,CAAC;QACpB,IAAI,UAAU,GAAG,CAAC,CAAC;QACnB,MAAM,mBAAmB,GAAG,QAAQ,CAAC,OAAO,CAAC,gBAAgB,CAAC,CAAC;QAC/D,MAAM,cAAc,GAAG,mBAAmB,CAAC,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,mBAAmB,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;QAE3F,MAAM,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,GAAG,EAAE,EAAE;YACzB,IAAI,OAAO,MAAM,CAAC,OAAO,KAAK,UAAU;gBAAE,MAAM,CAAC,OAAO,EAAE,CAAC;YAC3D,EAAE,CAAC,MAAM,CAAC,UAAU,EAAE,GAAG,EAAE,GAAE,CAAC,CAAC,CAAC;YAChC,MAAM,CAAC,GAAG,CAAC,CAAC;QACd,CAAC,CAAC,CAAC;QAEH,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,CAAC,KAAa,EAAE,EAAE;YAClC,UAAU,IAAI,KAAK,CAAC,MAAM,CAAC;YAE3B,IAAI,CAAC,OAAO,EAAE,CAAC;gBACb,OAAO,GAAG,IAAI,CAAC;gBACf,MAAM,WAAW,GAAG,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC,cAAc,CAAC,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC;gBACjF,MAAM,KAAK,GAAG,WAAW,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,KAAK,CAAC,QAAQ,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,QAAQ,EAAE,KAAK,MAAM,CAAC;gBAExF,IAAI,CAAC,KAAK,EAAE,CAAC;oBACX,MAAM,OAAO,GAAG,KAAK,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;oBACpF,MAAM,QAAQ,GAAG,QAAQ,CAAC,OAAO,CAAC,cAAc,CAAC,CAAC;oBAClD,MAAM,SAAS,GAAG,CAAC,CAAC,QAAQ,IAAI,0EAA0E,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;oBACzH,MAAM,MAAM,GAAG,SAAS;wBACtB,CAAC,CAAC,+DAA+D;wBACjE,CAAC,CAAC,oBAAoB,WAAW,IAAI,SAAS,EAAE,CAAC;oBAEnD,IAAI,OAAO,MAAM,CAAC,OAAO,KAAK,UAAU;wBAAE,MAAM,CAAC,OAAO,EAAE,CAAC;oBAC3D,MAAM,CAAC,OAAO,EAAE,CAAC;oBACjB,EAAE,CAAC,MAAM,CAAC,UAAU,EAAE,GAAG,EAAE,GAAE,CAAC,CAAC,CAAC;oBAChC,MAAM,CAAC,IAAI,KAAK,CAAC,sCAAsC,MAAM,MAAM,MAAM,EAAE,CAAC,CAAC,CAAC;oBAC9E,OAAO;gBACT,CAAC;YACH,CAAC;YAED,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC;gBACzB,IAAI,OAAO,MAAM,CAAC,KAAK,KAAK,UAAU;oBAAE,MAAM,CAAC,KAAK,EAAE,CAAC;YACzD,CAAC;QACH,CAAC,CAAC,CAAC;QAEH,MAAM,CAAC,EAAE,CAAC,OAAO,EAAE,GAAG,EAAE;YACtB,IAAI,OAAO,MAAM,CAAC,MAAM,KAAK,UAAU;gBAAE,MAAM,CAAC,MAAM,EAAE,CAAC;QAC3D,CAAC,CAAC,CAAC;QAEH,MAAM,CAAC,EAAE,CAAC,KAAK,EAAE,GAAG,EAAE;YACpB,MAAM,CAAC,GAAG,EAAE,CAAC;QACf,CAAC,CAAC,CAAC;QAEH,MAAM,CAAC,EAAE,CAAC,OAAO,EAAE,GAAG,EAAE;YACtB,IAAI,OAAO,MAAM,CAAC,OAAO,KAAK,UAAU;gBAAE,MAAM,CAAC,OAAO,EAAE,CAAC;QAC7D,CAAC,CAAC,CAAC;QAEH,MAAM,CAAC,EAAE,CAAC,QAAQ,EAAE,GAAG,EAAE;YACvB,IAAI,cAAc,IAAI,UAAU,KAAK,cAAc,EAAE,CAAC;gBACpD,EAAE,CAAC,MAAM,CAAC,UAAU,EAAE,GAAG,EAAE,GAAE,CAAC,CAAC,CAAC;gBAChC,MAAM,CAAC,IAAI,KAAK,CAAC,qCAAqC,UAAU,oBAAoB,cAAc,QAAQ,CAAC,CAAC,CAAC;gBAC7G,OAAO;YACT,CAAC;YACD,OAAO,CAAC,UAAU,CAAC,CAAC;QACtB,CAAC,CAAC,CAAC;QAEH,MAAM,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,GAAQ,EAAE,EAAE;YAC9B,MAAM,CAAC,OAAO,EAAE,CAAC;YACjB,EAAE,CAAC,MAAM,CAAC,UAAU,EAAE,GAAG,EAAE,GAAE,CAAC,CAAC,CAAC;YAChC,MAAM,CAAC,GAAG,CAAC,CAAC;QACd,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;AACL,CAAC"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "paper-search-cli",
-  "version": "0.1.2",
+  "version": "0.2.0",
   "description": "Agent-friendly CLI for searching and downloading academic papers from multiple sources.",
   "main": "dist/cli.js",
   "type": "module",
@@ -43,8 +43,10 @@
     "axios": "^1.7.2",
     "cheerio": "^1.1.2",
     "dotenv": "^16.4.5",
+    "https-proxy-agent": "^7.0.0",
     "lru-cache": "^11.2.5",
     "pdf-parse": "^1.1.4",
+    "socks-proxy-agent": "^8.0.0",
     "xml2js": "^0.6.2",
     "zod": "^3.23.8"
   },

package/skills/paper-search/SKILL.md

@@ -3,12 +3,14 @@ name: paper-search
 description: |
   学术文献检索与论文获取调度器，基于 paper-search CLI，而不是 MCP server。
   用于：搜索论文、查找相似研究、做文献综述初筛、验证 PMID/DOI、下载论文 PDF、
-  调用 Crossref/OpenAlex/PubMed/PMC/Europe PMC/arXiv/bioRxiv/medRxiv/Semantic Scholar/CORE/OpenAIRE/IACR 等来源，
-  以及使用 Semantic Scholar Open Access snippet 索引检索论文正文片段中的方法学细节。
+  调用 Crossref/OpenAlex/PubMed/PMC/Europe PMC/arXiv/bioRxiv/medRxiv/Semantic Scholar/CORE/OpenAIRE/DBLP/ACM/USENIX/OpenReview/IACR 等来源，
+  使用 Semantic Scholar Open Access snippet 索引检索论文正文片段中的方法学细节，
+  以及通过 EasyScholar 查询期刊影响因子、JCR/SSCI 分区、中科院分区、JCI、ESI、预警和等级指标。
   当用户提到“搜文献”“找论文”“文献检索”“search papers”“find papers”“literature search”
   “查一下有没有相关研究”“帮我找几篇参考文献”“看看别人怎么做的”“下载论文 PDF”
   “验证 PMID”“验证 DOI”“正文片段检索”“snippet search”“Methods 里怎么做的”
-  “方法学细节检索”等任务时使用。
+  “方法学细节检索”“影响因子”“IF”“JCR 分区”“中科院分区”“期刊分区”
+  “期刊等级”“目标期刊指标”“journal metrics”等任务时使用。
   此 skill 只负责指导 agent 调用 paper-search CLI；API key 必须通过 paper-search setup、
   paper-search config、.env 或环境变量配置，绝不要写入 Skill 文件。
 ---
@@ -26,7 +28,7 @@ command -v paper-search
 paper-search status --pretty
 ```
 
-如果涉及 Semantic Scholar 正文片段、CORE、Unpaywall、Web of Science、Scopus、ScienceDirect、Springer 或 Wiley 等需要 key/邮箱的能力，再运行：
+如果涉及 Semantic Scholar 正文片段、EasyScholar 期刊指标、CORE、Unpaywall、Web of Science、IEEE Xplore、Scopus、ScienceDirect、Springer/SpringerLink 或 Wiley 等需要 key/邮箱的能力，再运行：
 
 ```bash
 paper-search config doctor --pretty
@@ -37,6 +39,7 @@ paper-search config doctor --pretty
 ```bash
 paper-search setup
 paper-search config set SEMANTIC_SCHOLAR_API_KEY your_key
+paper-search setup EASYSCHOLAR_KEY
 paper-search config doctor --pretty
 ```
 
@@ -65,6 +68,8 @@ paper-search status --pretty
 paper-search search "machine learning" --platform crossref --max-results 5 --pretty
 paper-search search "osteoarthritis occupational exposure" --platform pubmed --max-results 10 --pretty
 paper-search search "transformer attention mechanism" --sources arxiv,semantic,crossref --max-results 5 --pretty
+paper-search search "graph neural networks" --platform dblp --max-results 5 --pretty
+paper-search search "large language models" --platform openreview --max-results 5 --pretty
 ```
 
 `--platform all` 或 `--sources all` 只用于需要广覆盖召回时。精确任务优先指定平台或 `--sources`。
@@ -74,6 +79,8 @@ paper-search search "transformer attention mechanism" --sources arxiv,semantic,c
 ```bash
 paper-search run search_pubmed --arg query="osteoarthritis occupational exposure" --arg maxResults=10 --pretty
 paper-search run search_openalex --arg query="causal inference target trial emulation" --arg maxResults=5 --pretty
+paper-search run search_acm --arg query="software testing" --arg maxResults=5 --pretty
+paper-search run search_usenix --arg query="file systems" --arg maxResults=5 --pretty
 paper-search run get_paper_by_doi --arg doi="10.xxxx/xxxxx" --pretty
 ```
 
@@ -83,15 +90,29 @@ paper-search run get_paper_by_doi --arg doi="10.xxxx/xxxxx" --pretty
 paper-search run search_semantic_scholar --json-args '{"query":"graph neural network medicine","maxResults":5,"year":"2020-2025"}' --pretty
 ```
 
+### 期刊指标查询
+
+当用户询问影响因子、JCR/SSCI 分区、中科院分区、JCI、ESI、预警、北大核心、南大核心、CSCD、A&HCI、CCF、EI 或目标期刊等级时，使用 EasyScholar 原生 CLI 工具，而不是通用论文检索。
+
+```bash
+paper-search journal-metrics "Nature" "BMJ" --pretty
+paper-search journal-metrics --file journals.txt --include-raw --pretty
+paper-search run query_journal_metrics --json-args '{"journals":["Nature"],"includeRaw":true}' --pretty
+```
+
+返回时优先解释标准化的 `core` 字段：`impact_factor`、`impact_factor_5y`、`jcr_quartile`、`ssci_quartile`、`jci`、`cas_base`、`cas_upgraded`、`cas_small`、`cas_top`、`cas_zone`、`esi`、`warning`、`pku`、`cssci`、`cscd`、`ahci`、`ccf`、`ei`、`china_st_core`。如果需要完整字段，使用 `--include-raw` 并检查 `official_all`、`official_select`、`custom_rank`。
+
+EasyScholar 文档要求每秒最多 2 次请求；批量查询时不要并发调用。
+
 ### 下载 PDF
 
 ```bash
 paper-search download 2301.12345 --platform arxiv --save-path ./downloads --pretty
 paper-search run download_paper --arg paperId="10.xxxx/xxxxx" --arg platform=springer --arg savePath="./downloads" --pretty
-paper-search run download_with_fallback --json-args '{"doi":"10.xxxx/xxxxx","title":"Paper title","savePath":"./downloads","useSciHub":false}' --pretty
+paper-search run download_with_fallback --json-args '{"source":"crossref","paperId":"10.xxxx/xxxxx","doi":"10.xxxx/xxxxx","title":"Paper title","savePath":"./downloads"}' --pretty
 ```
 
-默认不要启用 Sci-Hub；只有用户明确要求并承担相应访问边界时，才把 `useSciHub` 设为 `true`。
+下载漏斗默认包含 Sci-Hub 作为最后兜底；只有用户明确要求关闭该阶段时，才把 `useSciHub` 设为 `false`。
 
 ## 平台选择
 
@@ -100,11 +121,19 @@ paper-search run download_with_fallback --json-args '{"doi":"10.xxxx/xxxxx","tit
 | 生物医学、临床、药学、公卫 | `pubmed` | `pmc`, `europepmc`, `semantic`, `crossref` |
 | 正文方法学片段 | `search_semantic_snippets` | 先用 `pubmed`/`semantic` 找题名和同义词 |
 | 计算机、AI、数学、物理 | `arxiv` | `semantic`, `crossref`, `openalex` |
+| 计算机文献目录/会议元数据 | `dblp` | `acm`, `usenix`, `openreview`, `ieee` 需要 key |
 | 跨学科广覆盖 | `crossref` | `openalex`, `semantic` |
 | 开放获取全文发现 | `pmc`, `europepmc`, `core`, `openaire`, `unpaywall` | `download_with_fallback` |
+| 期刊影响因子/分区/等级 | `journal-metrics` | `query_journal_metrics` |
 | 密码学 | `iacr` | `arxiv` |
 | 引用统计排序 | `semantic`, `crossref`, `openalex` | `webofscience`, `scopus` 需要 key |
-| 出版商/付费数据库 | `webofscience`, `scopus`, `sciencedirect`, `springer`, `wiley` | 仅在 key 已配置时使用 |
+| 出版商/付费数据库 | `webofscience`, `ieee`, `scopus`, `sciencedirect`, `springer`/`springerlink`, `wiley` | 仅在 key 已配置时使用 |
+
+平台边界：
+
+- `acm` 通过 Crossref 的 ACM DOI 前缀检索元数据，不抓取 ACM Digital Library 页面。
+- `usenix` 通过 DBLP 返回 USENIX 相关会议/期刊元数据，不抓取 USENIX 搜索页。
+- `springerlink` 是 `springer` 的别名，仍需要 Springer API key。
 
 查询构建规则：
 
@@ -179,7 +208,9 @@ paper-search run search_crossref --arg query="full paper title" --arg maxResults
 |---|---|
 | CLI 不存在 | 提示安装 `npm install -g paper-search-cli` |
 | API key 缺失 | 提示运行 `paper-search setup`；不要索要或保存 key |
+| EasyScholar key 缺失 | 提示运行 `paper-search setup EASYSCHOLAR_KEY`；不要让用户在聊天中发送 SecretKey |
 | 429 限流 | 降低 `--max-results`，换平台，或提示配置可选 key |
+| EasyScholar 批量查询 | 控制在每秒最多 2 次请求；优先使用单次 `journal-metrics` 多期刊输入，不要并发 |
 | 0 结果 | 放宽关键词，换英文同义词，换平台，或用 `--sources` 扩展 |
 | 下载失败 | 优先开放获取来源和 `download_with_fallback`，报告失败原因 |
 | 用户要求完整正文 | 先下载 PDF；再交给当前环境可用的 PDF/MinerU 解析流程 |
@@ -189,4 +220,3 @@ paper-search run search_crossref --arg query="full paper title" --arg maxResults
 - 不管理 Zotero、Obsidian 或其他文献库。
 - 不写论文正文，不做语言润色。
 - 不把 API key、token、cookie 写入 Skill、README 或回复。
-- 当前公开 CLI 不提供期刊 IF、JCR 分区或中科院分区查询；遇到这类请求时说明能力边界，除非用户另行指定本地私有工具。