paper-search-cli 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.env.example +165 -0
- package/LICENSE +21 -0
- package/README-sc.md +642 -0
- package/README.md +642 -0
- package/dist/cli.d.ts +3 -0
- package/dist/cli.d.ts.map +1 -0
- package/dist/cli.js +637 -0
- package/dist/cli.js.map +1 -0
- package/dist/config/ConfigService.d.ts +26 -0
- package/dist/config/ConfigService.d.ts.map +1 -0
- package/dist/config/ConfigService.js +145 -0
- package/dist/config/ConfigService.js.map +1 -0
- package/dist/config/constants.d.ts +140 -0
- package/dist/config/constants.d.ts.map +1 -0
- package/dist/config/constants.js +93 -0
- package/dist/config/constants.js.map +1 -0
- package/dist/core/diagnostics.d.ts +43 -0
- package/dist/core/diagnostics.d.ts.map +1 -0
- package/dist/core/diagnostics.js +544 -0
- package/dist/core/diagnostics.js.map +1 -0
- package/dist/core/handleToolCall.d.ts +8 -0
- package/dist/core/handleToolCall.d.ts.map +1 -0
- package/dist/core/handleToolCall.js +440 -0
- package/dist/core/handleToolCall.js.map +1 -0
- package/dist/core/schemas.d.ts +454 -0
- package/dist/core/schemas.d.ts.map +1 -0
- package/dist/core/schemas.js +322 -0
- package/dist/core/schemas.js.map +1 -0
- package/dist/core/searchers.d.ts +45 -0
- package/dist/core/searchers.d.ts.map +1 -0
- package/dist/core/searchers.js +73 -0
- package/dist/core/searchers.js.map +1 -0
- package/dist/core/tools.d.ts +7 -0
- package/dist/core/tools.d.ts.map +1 -0
- package/dist/core/tools.js +640 -0
- package/dist/core/tools.js.map +1 -0
- package/dist/models/Paper.d.ts +64 -0
- package/dist/models/Paper.d.ts.map +1 -0
- package/dist/models/Paper.js +70 -0
- package/dist/models/Paper.js.map +1 -0
- package/dist/platforms/ArxivSearcher.d.ts +64 -0
- package/dist/platforms/ArxivSearcher.d.ts.map +1 -0
- package/dist/platforms/ArxivSearcher.js +531 -0
- package/dist/platforms/ArxivSearcher.js.map +1 -0
- package/dist/platforms/BioRxivSearcher.d.ts +47 -0
- package/dist/platforms/BioRxivSearcher.d.ts.map +1 -0
- package/dist/platforms/BioRxivSearcher.js +196 -0
- package/dist/platforms/BioRxivSearcher.js.map +1 -0
- package/dist/platforms/CORESearcher.d.ts +16 -0
- package/dist/platforms/CORESearcher.d.ts.map +1 -0
- package/dist/platforms/CORESearcher.js +148 -0
- package/dist/platforms/CORESearcher.js.map +1 -0
- package/dist/platforms/CrossrefSearcher.d.ts +34 -0
- package/dist/platforms/CrossrefSearcher.d.ts.map +1 -0
- package/dist/platforms/CrossrefSearcher.js +339 -0
- package/dist/platforms/CrossrefSearcher.js.map +1 -0
- package/dist/platforms/EuropePMCSearcher.d.ts +20 -0
- package/dist/platforms/EuropePMCSearcher.d.ts.map +1 -0
- package/dist/platforms/EuropePMCSearcher.js +173 -0
- package/dist/platforms/EuropePMCSearcher.js.map +1 -0
- package/dist/platforms/GoogleScholarSearcher.d.ts +77 -0
- package/dist/platforms/GoogleScholarSearcher.d.ts.map +1 -0
- package/dist/platforms/GoogleScholarSearcher.js +262 -0
- package/dist/platforms/GoogleScholarSearcher.js.map +1 -0
- package/dist/platforms/IACRSearcher.d.ts +51 -0
- package/dist/platforms/IACRSearcher.d.ts.map +1 -0
- package/dist/platforms/IACRSearcher.js +339 -0
- package/dist/platforms/IACRSearcher.js.map +1 -0
- package/dist/platforms/OpenAIRESearcher.d.ts +22 -0
- package/dist/platforms/OpenAIRESearcher.d.ts.map +1 -0
- package/dist/platforms/OpenAIRESearcher.js +223 -0
- package/dist/platforms/OpenAIRESearcher.js.map +1 -0
- package/dist/platforms/OpenAlexSearcher.d.ts +14 -0
- package/dist/platforms/OpenAlexSearcher.d.ts.map +1 -0
- package/dist/platforms/OpenAlexSearcher.js +114 -0
- package/dist/platforms/OpenAlexSearcher.js.map +1 -0
- package/dist/platforms/PMCSearcher.d.ts +20 -0
- package/dist/platforms/PMCSearcher.d.ts.map +1 -0
- package/dist/platforms/PMCSearcher.js +177 -0
- package/dist/platforms/PMCSearcher.js.map +1 -0
- package/dist/platforms/PaperSource.d.ts +143 -0
- package/dist/platforms/PaperSource.d.ts.map +1 -0
- package/dist/platforms/PaperSource.js +125 -0
- package/dist/platforms/PaperSource.js.map +1 -0
- package/dist/platforms/PubMedSearcher.d.ts +104 -0
- package/dist/platforms/PubMedSearcher.d.ts.map +1 -0
- package/dist/platforms/PubMedSearcher.js +422 -0
- package/dist/platforms/PubMedSearcher.js.map +1 -0
- package/dist/platforms/SciHubSearcher.d.ts +66 -0
- package/dist/platforms/SciHubSearcher.d.ts.map +1 -0
- package/dist/platforms/SciHubSearcher.js +398 -0
- package/dist/platforms/SciHubSearcher.js.map +1 -0
- package/dist/platforms/ScienceDirectSearcher.d.ts +42 -0
- package/dist/platforms/ScienceDirectSearcher.d.ts.map +1 -0
- package/dist/platforms/ScienceDirectSearcher.js +326 -0
- package/dist/platforms/ScienceDirectSearcher.js.map +1 -0
- package/dist/platforms/ScopusSearcher.d.ts +43 -0
- package/dist/platforms/ScopusSearcher.d.ts.map +1 -0
- package/dist/platforms/ScopusSearcher.js +364 -0
- package/dist/platforms/ScopusSearcher.js.map +1 -0
- package/dist/platforms/SemanticScholarSearcher.d.ts +96 -0
- package/dist/platforms/SemanticScholarSearcher.d.ts.map +1 -0
- package/dist/platforms/SemanticScholarSearcher.js +419 -0
- package/dist/platforms/SemanticScholarSearcher.js.map +1 -0
- package/dist/platforms/SpringerSearcher.d.ts +54 -0
- package/dist/platforms/SpringerSearcher.d.ts.map +1 -0
- package/dist/platforms/SpringerSearcher.js +407 -0
- package/dist/platforms/SpringerSearcher.js.map +1 -0
- package/dist/platforms/UnpaywallSearcher.d.ts +18 -0
- package/dist/platforms/UnpaywallSearcher.d.ts.map +1 -0
- package/dist/platforms/UnpaywallSearcher.js +115 -0
- package/dist/platforms/UnpaywallSearcher.js.map +1 -0
- package/dist/platforms/WebOfScienceSearcher.d.ts +111 -0
- package/dist/platforms/WebOfScienceSearcher.d.ts.map +1 -0
- package/dist/platforms/WebOfScienceSearcher.js +500 -0
- package/dist/platforms/WebOfScienceSearcher.js.map +1 -0
- package/dist/platforms/WileySearcher.d.ts +44 -0
- package/dist/platforms/WileySearcher.d.ts.map +1 -0
- package/dist/platforms/WileySearcher.js +148 -0
- package/dist/platforms/WileySearcher.js.map +1 -0
- package/dist/services/CitationService.d.ts +66 -0
- package/dist/services/CitationService.d.ts.map +1 -0
- package/dist/services/CitationService.js +237 -0
- package/dist/services/CitationService.js.map +1 -0
- package/dist/services/MultiSourceSearchService.d.ts +19 -0
- package/dist/services/MultiSourceSearchService.d.ts.map +1 -0
- package/dist/services/MultiSourceSearchService.js +96 -0
- package/dist/services/MultiSourceSearchService.js.map +1 -0
- package/dist/services/OpenAccessFallbackService.d.ts +20 -0
- package/dist/services/OpenAccessFallbackService.d.ts.map +1 -0
- package/dist/services/OpenAccessFallbackService.js +124 -0
- package/dist/services/OpenAccessFallbackService.js.map +1 -0
- package/dist/utils/ErrorHandler.d.ts +99 -0
- package/dist/utils/ErrorHandler.d.ts.map +1 -0
- package/dist/utils/ErrorHandler.js +266 -0
- package/dist/utils/ErrorHandler.js.map +1 -0
- package/dist/utils/Logger.d.ts +6 -0
- package/dist/utils/Logger.d.ts.map +1 -0
- package/dist/utils/Logger.js +26 -0
- package/dist/utils/Logger.js.map +1 -0
- package/dist/utils/PDFExtractor.d.ts +34 -0
- package/dist/utils/PDFExtractor.d.ts.map +1 -0
- package/dist/utils/PDFExtractor.js +130 -0
- package/dist/utils/PDFExtractor.js.map +1 -0
- package/dist/utils/PdfDownload.d.ts +7 -0
- package/dist/utils/PdfDownload.d.ts.map +1 -0
- package/dist/utils/PdfDownload.js +52 -0
- package/dist/utils/PdfDownload.js.map +1 -0
- package/dist/utils/QuotaManager.d.ts +32 -0
- package/dist/utils/QuotaManager.d.ts.map +1 -0
- package/dist/utils/QuotaManager.js +95 -0
- package/dist/utils/QuotaManager.js.map +1 -0
- package/dist/utils/RateLimiter.d.ts +50 -0
- package/dist/utils/RateLimiter.d.ts.map +1 -0
- package/dist/utils/RateLimiter.js +121 -0
- package/dist/utils/RateLimiter.js.map +1 -0
- package/dist/utils/RequestCache.d.ts +26 -0
- package/dist/utils/RequestCache.d.ts.map +1 -0
- package/dist/utils/RequestCache.js +66 -0
- package/dist/utils/RequestCache.js.map +1 -0
- package/dist/utils/SecurityUtils.d.ts +80 -0
- package/dist/utils/SecurityUtils.d.ts.map +1 -0
- package/dist/utils/SecurityUtils.js +357 -0
- package/dist/utils/SecurityUtils.js.map +1 -0
- package/package.json +111 -0
- package/skills/paper-search/SKILL.md +192 -0
|
@@ -0,0 +1,398 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Sci-Hub 论文搜索和下载器
|
|
3
|
+
* 支持多镜像站点轮询、自动健康检测和故障转移
|
|
4
|
+
*/
|
|
5
|
+
import axios from 'axios';
|
|
6
|
+
import * as cheerio from 'cheerio';
|
|
7
|
+
import * as fs from 'fs';
|
|
8
|
+
import * as path from 'path';
|
|
9
|
+
import { PaperSource } from './PaperSource.js';
|
|
10
|
+
import { PaperFactory } from '../models/Paper.js';
|
|
11
|
+
import { logDebug, logWarn } from '../utils/Logger.js';
|
|
12
|
+
import { TIMEOUTS } from '../config/constants.js';
|
|
13
|
+
export class SciHubSearcher extends PaperSource {
|
|
14
|
+
mirrorSites;
|
|
15
|
+
currentMirrorIndex = 0;
|
|
16
|
+
axiosInstance;
|
|
17
|
+
maxRetries = 3;
|
|
18
|
+
mirrorTestTimeout = TIMEOUTS.HEALTH_CHECK;
|
|
19
|
+
lastHealthCheck = null;
|
|
20
|
+
healthCheckInterval = 300000; // 5 minutes
|
|
21
|
+
constructor() {
|
|
22
|
+
super('Sci-Hub', 'https://sci-hub.se');
|
|
23
|
+
// 初始化镜像站点列表
|
|
24
|
+
this.mirrorSites = [
|
|
25
|
+
{ url: 'https://sci-hub.se', isWorking: true, failureCount: 0 },
|
|
26
|
+
{ url: 'https://sci-hub.st', isWorking: true, failureCount: 0 },
|
|
27
|
+
{ url: 'https://sci-hub.ru', isWorking: true, failureCount: 0 },
|
|
28
|
+
{ url: 'https://sci-hub.ren', isWorking: true, failureCount: 0 },
|
|
29
|
+
{ url: 'https://sci-hub.mksa.top', isWorking: true, failureCount: 0 },
|
|
30
|
+
{ url: 'https://sci-hub.ee', isWorking: true, failureCount: 0 },
|
|
31
|
+
{ url: 'https://sci-hub.wf', isWorking: true, failureCount: 0 },
|
|
32
|
+
{ url: 'https://sci-hub.yt', isWorking: true, failureCount: 0 },
|
|
33
|
+
{ url: 'https://sci-hub.sci-hub.se', isWorking: true, failureCount: 0 },
|
|
34
|
+
{ url: 'https://sci-hub.sci-hub.st', isWorking: true, failureCount: 0 },
|
|
35
|
+
{ url: 'https://sci-hub.sci-hub.ru', isWorking: true, failureCount: 0 },
|
|
36
|
+
];
|
|
37
|
+
this.axiosInstance = axios.create({
|
|
38
|
+
timeout: TIMEOUTS.DEFAULT,
|
|
39
|
+
headers: {
|
|
40
|
+
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
|
41
|
+
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
|
|
42
|
+
'Accept-Language': 'en-US,en;q=0.5',
|
|
43
|
+
'Accept-Encoding': 'gzip, deflate, br',
|
|
44
|
+
'DNT': '1',
|
|
45
|
+
'Connection': 'keep-alive',
|
|
46
|
+
'Upgrade-Insecure-Requests': '1'
|
|
47
|
+
},
|
|
48
|
+
maxRedirects: 5,
|
|
49
|
+
validateStatus: (status) => status < 500
|
|
50
|
+
});
|
|
51
|
+
}
|
|
52
|
+
getCapabilities() {
|
|
53
|
+
return {
|
|
54
|
+
search: true,
|
|
55
|
+
download: true,
|
|
56
|
+
fullText: false,
|
|
57
|
+
citations: false,
|
|
58
|
+
requiresApiKey: false,
|
|
59
|
+
supportedOptions: ['maxResults']
|
|
60
|
+
};
|
|
61
|
+
}
|
|
62
|
+
/**
|
|
63
|
+
* 检测所有镜像站点的健康状态
|
|
64
|
+
*/
|
|
65
|
+
async checkMirrorHealth() {
|
|
66
|
+
logDebug('Checking Sci-Hub mirror sites health...');
|
|
67
|
+
const healthPromises = this.mirrorSites.map(async (mirror, index) => {
|
|
68
|
+
try {
|
|
69
|
+
const startTime = Date.now();
|
|
70
|
+
const response = await axios.get(mirror.url, {
|
|
71
|
+
timeout: this.mirrorTestTimeout,
|
|
72
|
+
headers: this.axiosInstance.defaults.headers,
|
|
73
|
+
maxRedirects: 2
|
|
74
|
+
});
|
|
75
|
+
const responseTime = Date.now() - startTime;
|
|
76
|
+
// 检查响应是否包含 Sci-Hub 特征
|
|
77
|
+
const html = response.data;
|
|
78
|
+
const isValidSciHub = html.includes('sci-hub') ||
|
|
79
|
+
html.includes('Sci-Hub') ||
|
|
80
|
+
html.includes('alexandra elbakyan');
|
|
81
|
+
this.mirrorSites[index] = {
|
|
82
|
+
...mirror,
|
|
83
|
+
lastChecked: new Date(),
|
|
84
|
+
responseTime,
|
|
85
|
+
isWorking: response.status === 200 && isValidSciHub,
|
|
86
|
+
failureCount: 0
|
|
87
|
+
};
|
|
88
|
+
if (this.mirrorSites[index].isWorking) {
|
|
89
|
+
logDebug(`${mirror.url} - OK (${responseTime}ms)`);
|
|
90
|
+
}
|
|
91
|
+
else {
|
|
92
|
+
logDebug(`${mirror.url} - Invalid response`);
|
|
93
|
+
}
|
|
94
|
+
}
|
|
95
|
+
catch (error) {
|
|
96
|
+
this.mirrorSites[index] = {
|
|
97
|
+
...mirror,
|
|
98
|
+
lastChecked: new Date(),
|
|
99
|
+
isWorking: false,
|
|
100
|
+
failureCount: mirror.failureCount + 1
|
|
101
|
+
};
|
|
102
|
+
logDebug(`${mirror.url} - Failed`);
|
|
103
|
+
}
|
|
104
|
+
});
|
|
105
|
+
await Promise.allSettled(healthPromises);
|
|
106
|
+
// 按响应时间排序可用的镜像
|
|
107
|
+
this.mirrorSites.sort((a, b) => {
|
|
108
|
+
if (a.isWorking && !b.isWorking)
|
|
109
|
+
return -1;
|
|
110
|
+
if (!a.isWorking && b.isWorking)
|
|
111
|
+
return 1;
|
|
112
|
+
if (a.isWorking && b.isWorking) {
|
|
113
|
+
return (a.responseTime || Infinity) - (b.responseTime || Infinity);
|
|
114
|
+
}
|
|
115
|
+
return 0;
|
|
116
|
+
});
|
|
117
|
+
this.lastHealthCheck = new Date();
|
|
118
|
+
const workingCount = this.mirrorSites.filter(m => m.isWorking).length;
|
|
119
|
+
logDebug(`Health check complete: ${workingCount}/${this.mirrorSites.length} mirrors working`);
|
|
120
|
+
if (workingCount === 0) {
|
|
121
|
+
logWarn('Warning: No Sci-Hub mirrors are currently accessible!');
|
|
122
|
+
}
|
|
123
|
+
}
|
|
124
|
+
/**
|
|
125
|
+
* 获取当前可用的镜像站点
|
|
126
|
+
*/
|
|
127
|
+
async getCurrentMirror() {
|
|
128
|
+
// 定期进行健康检查
|
|
129
|
+
if (!this.lastHealthCheck ||
|
|
130
|
+
Date.now() - this.lastHealthCheck.getTime() > this.healthCheckInterval) {
|
|
131
|
+
await this.checkMirrorHealth();
|
|
132
|
+
}
|
|
133
|
+
// 找到第一个可用的镜像
|
|
134
|
+
const workingMirror = this.mirrorSites.find(m => m.isWorking);
|
|
135
|
+
if (!workingMirror) {
|
|
136
|
+
// 如果没有可用镜像,重新检测
|
|
137
|
+
await this.checkMirrorHealth();
|
|
138
|
+
const retryMirror = this.mirrorSites.find(m => m.isWorking);
|
|
139
|
+
if (!retryMirror) {
|
|
140
|
+
throw new Error('No working Sci-Hub mirrors available');
|
|
141
|
+
}
|
|
142
|
+
return retryMirror.url;
|
|
143
|
+
}
|
|
144
|
+
return workingMirror.url;
|
|
145
|
+
}
|
|
146
|
+
/**
|
|
147
|
+
* 标记镜像站点失败并切换到下一个
|
|
148
|
+
*/
|
|
149
|
+
async markMirrorFailed(mirrorUrl) {
|
|
150
|
+
const mirrorIndex = this.mirrorSites.findIndex(m => m.url === mirrorUrl);
|
|
151
|
+
if (mirrorIndex !== -1) {
|
|
152
|
+
this.mirrorSites[mirrorIndex].failureCount++;
|
|
153
|
+
if (this.mirrorSites[mirrorIndex].failureCount >= 3) {
|
|
154
|
+
this.mirrorSites[mirrorIndex].isWorking = false;
|
|
155
|
+
logDebug(`Mirror ${mirrorUrl} marked as failed after multiple attempts`);
|
|
156
|
+
}
|
|
157
|
+
}
|
|
158
|
+
// 尝试下一个镜像
|
|
159
|
+
const nextWorkingMirror = this.mirrorSites.find((m, idx) => idx > mirrorIndex && m.isWorking);
|
|
160
|
+
if (nextWorkingMirror) {
|
|
161
|
+
return nextWorkingMirror.url;
|
|
162
|
+
}
|
|
163
|
+
// 如果没有更多镜像,重新检测健康状态
|
|
164
|
+
await this.checkMirrorHealth();
|
|
165
|
+
return this.getCurrentMirror();
|
|
166
|
+
}
|
|
167
|
+
/**
|
|
168
|
+
* 通过 DOI 或 URL 搜索论文
|
|
169
|
+
*/
|
|
170
|
+
async search(query, options) {
|
|
171
|
+
// Sci-Hub 主要通过 DOI 或直接 URL 工作
|
|
172
|
+
// 如果输入不是 DOI 或 URL,返回空结果
|
|
173
|
+
if (!this.isValidDOIOrURL(query)) {
|
|
174
|
+
return [];
|
|
175
|
+
}
|
|
176
|
+
try {
|
|
177
|
+
const paperInfo = await this.fetchPaperInfo(query);
|
|
178
|
+
if (paperInfo) {
|
|
179
|
+
return [paperInfo];
|
|
180
|
+
}
|
|
181
|
+
}
|
|
182
|
+
catch (error) {
|
|
183
|
+
logDebug('Sci-Hub search error:', error);
|
|
184
|
+
}
|
|
185
|
+
return [];
|
|
186
|
+
}
|
|
187
|
+
/**
|
|
188
|
+
* 验证输入是否为有效的 DOI 或 URL
|
|
189
|
+
*/
|
|
190
|
+
isValidDOIOrURL(input) {
|
|
191
|
+
// DOI 模式:10.xxxx/xxxxx
|
|
192
|
+
const doiPattern = /^10\.\d{4,}\/[-._;()\/:a-zA-Z0-9]+$/;
|
|
193
|
+
// URL 模式
|
|
194
|
+
const urlPattern = /^https?:\/\/.+/;
|
|
195
|
+
// 也接受带有 doi: 前缀的格式
|
|
196
|
+
const doiPrefixPattern = /^doi:\s*10\.\d{4,}\/[-._;()\/:a-zA-Z0-9]+$/i;
|
|
197
|
+
return doiPattern.test(input) ||
|
|
198
|
+
urlPattern.test(input) ||
|
|
199
|
+
doiPrefixPattern.test(input);
|
|
200
|
+
}
|
|
201
|
+
/**
|
|
202
|
+
* 从 Sci-Hub 获取论文信息
|
|
203
|
+
*/
|
|
204
|
+
async fetchPaperInfo(doiOrUrl) {
|
|
205
|
+
let currentMirror = await this.getCurrentMirror();
|
|
206
|
+
let retries = 0;
|
|
207
|
+
// 清理 DOI 格式
|
|
208
|
+
const cleanedQuery = doiOrUrl.replace(/^doi:\s*/i, '');
|
|
209
|
+
while (retries < this.maxRetries) {
|
|
210
|
+
try {
|
|
211
|
+
const searchUrl = `${currentMirror}/${cleanedQuery}`;
|
|
212
|
+
logDebug(`Searching on ${currentMirror} for: ${cleanedQuery}`);
|
|
213
|
+
const response = await this.axiosInstance.get(searchUrl);
|
|
214
|
+
if (response.status === 200) {
|
|
215
|
+
const $ = cheerio.load(response.data);
|
|
216
|
+
// 检查是否找到论文
|
|
217
|
+
const pdfFrame = $('#pdf');
|
|
218
|
+
const pdfEmbed = $('embed[type="application/pdf"]');
|
|
219
|
+
const pdfIframe = $('iframe[src*=".pdf"]');
|
|
220
|
+
let pdfUrl = '';
|
|
221
|
+
// 尝试多种方式获取 PDF URL
|
|
222
|
+
if (pdfFrame.length > 0) {
|
|
223
|
+
pdfUrl = pdfFrame.attr('src') || '';
|
|
224
|
+
}
|
|
225
|
+
else if (pdfEmbed.length > 0) {
|
|
226
|
+
pdfUrl = pdfEmbed.attr('src') || '';
|
|
227
|
+
}
|
|
228
|
+
else if (pdfIframe.length > 0) {
|
|
229
|
+
pdfUrl = pdfIframe.attr('src') || '';
|
|
230
|
+
}
|
|
231
|
+
else {
|
|
232
|
+
// 查找下载按钮
|
|
233
|
+
const downloadButton = $('button[onclick*="download"]');
|
|
234
|
+
if (downloadButton.length > 0) {
|
|
235
|
+
const onclickAttr = downloadButton.attr('onclick') || '';
|
|
236
|
+
const match = onclickAttr.match(/location\.href='([^']+)'/);
|
|
237
|
+
if (match) {
|
|
238
|
+
pdfUrl = match[1];
|
|
239
|
+
}
|
|
240
|
+
}
|
|
241
|
+
}
|
|
242
|
+
// 处理相对 URL
|
|
243
|
+
if (pdfUrl && !pdfUrl.startsWith('http')) {
|
|
244
|
+
if (pdfUrl.startsWith('//')) {
|
|
245
|
+
pdfUrl = 'https:' + pdfUrl;
|
|
246
|
+
}
|
|
247
|
+
else if (pdfUrl.startsWith('/')) {
|
|
248
|
+
pdfUrl = currentMirror + pdfUrl;
|
|
249
|
+
}
|
|
250
|
+
}
|
|
251
|
+
if (pdfUrl) {
|
|
252
|
+
// 提取标题(尝试从页面标题或 citation 信息获取)
|
|
253
|
+
let title = $('title').text();
|
|
254
|
+
const citation = $('#citation').text();
|
|
255
|
+
if (citation) {
|
|
256
|
+
// 从引用信息中提取标题
|
|
257
|
+
const titleMatch = citation.match(/([^.]+)\./);
|
|
258
|
+
if (titleMatch) {
|
|
259
|
+
title = titleMatch[1].trim();
|
|
260
|
+
}
|
|
261
|
+
}
|
|
262
|
+
// 清理标题
|
|
263
|
+
title = title.replace(/\s*\|\s*Sci-Hub.*$/, '')
|
|
264
|
+
.replace(/Sci-Hub\s*:\s*/, '')
|
|
265
|
+
.trim();
|
|
266
|
+
return PaperFactory.create({
|
|
267
|
+
paperId: cleanedQuery,
|
|
268
|
+
title: title || `Paper: ${cleanedQuery}`,
|
|
269
|
+
source: 'scihub',
|
|
270
|
+
authors: [],
|
|
271
|
+
abstract: '',
|
|
272
|
+
doi: this.isValidDOIOrURL(cleanedQuery) && cleanedQuery.includes('10.')
|
|
273
|
+
? cleanedQuery
|
|
274
|
+
: '',
|
|
275
|
+
publishedDate: null,
|
|
276
|
+
pdfUrl: pdfUrl,
|
|
277
|
+
url: searchUrl,
|
|
278
|
+
extra: {
|
|
279
|
+
mirror: currentMirror,
|
|
280
|
+
fetchedAt: new Date().toISOString()
|
|
281
|
+
}
|
|
282
|
+
});
|
|
283
|
+
}
|
|
284
|
+
else {
|
|
285
|
+
logDebug(`Paper not found on ${currentMirror}`);
|
|
286
|
+
currentMirror = await this.markMirrorFailed(currentMirror);
|
|
287
|
+
retries++;
|
|
288
|
+
}
|
|
289
|
+
}
|
|
290
|
+
else {
|
|
291
|
+
logDebug(`Unexpected status ${response.status} from ${currentMirror}`);
|
|
292
|
+
currentMirror = await this.markMirrorFailed(currentMirror);
|
|
293
|
+
retries++;
|
|
294
|
+
}
|
|
295
|
+
}
|
|
296
|
+
catch (error) {
|
|
297
|
+
logDebug(`Error fetching from ${currentMirror}:`, error.message);
|
|
298
|
+
currentMirror = await this.markMirrorFailed(currentMirror);
|
|
299
|
+
retries++;
|
|
300
|
+
}
|
|
301
|
+
}
|
|
302
|
+
return null;
|
|
303
|
+
}
|
|
304
|
+
/**
|
|
305
|
+
* 下载 PDF 文件
|
|
306
|
+
*/
|
|
307
|
+
async downloadPdf(paperId, options) {
|
|
308
|
+
const savePath = options?.savePath || './downloads';
|
|
309
|
+
// 确保下载目录存在
|
|
310
|
+
if (!fs.existsSync(savePath)) {
|
|
311
|
+
fs.mkdirSync(savePath, { recursive: true });
|
|
312
|
+
}
|
|
313
|
+
// 首先获取论文信息
|
|
314
|
+
const paperInfo = await this.fetchPaperInfo(paperId);
|
|
315
|
+
if (!paperInfo || !paperInfo.pdfUrl) {
|
|
316
|
+
throw new Error(`Cannot find PDF for: ${paperId}`);
|
|
317
|
+
}
|
|
318
|
+
const fileName = `${paperId.replace(/[^a-zA-Z0-9]/g, '_')}.pdf`;
|
|
319
|
+
const filePath = path.join(savePath, fileName);
|
|
320
|
+
// 检查文件是否已存在
|
|
321
|
+
if (fs.existsSync(filePath) && !options?.overwrite) {
|
|
322
|
+
return filePath;
|
|
323
|
+
}
|
|
324
|
+
// 下载 PDF
|
|
325
|
+
let retries = 0;
|
|
326
|
+
let currentPdfUrl = paperInfo.pdfUrl;
|
|
327
|
+
while (retries < this.maxRetries) {
|
|
328
|
+
try {
|
|
329
|
+
logDebug(`Downloading PDF from: ${currentPdfUrl}`);
|
|
330
|
+
const response = await this.axiosInstance.get(currentPdfUrl, {
|
|
331
|
+
responseType: 'stream',
|
|
332
|
+
timeout: TIMEOUTS.DOWNLOAD
|
|
333
|
+
});
|
|
334
|
+
if (response.status === 200) {
|
|
335
|
+
const writer = fs.createWriteStream(filePath);
|
|
336
|
+
response.data.pipe(writer);
|
|
337
|
+
return new Promise((resolve, reject) => {
|
|
338
|
+
writer.on('finish', () => {
|
|
339
|
+
resolve(filePath);
|
|
340
|
+
});
|
|
341
|
+
writer.on('error', reject);
|
|
342
|
+
});
|
|
343
|
+
}
|
|
344
|
+
else {
|
|
345
|
+
throw new Error(`Failed to download PDF: status ${response.status}`);
|
|
346
|
+
}
|
|
347
|
+
}
|
|
348
|
+
catch (error) {
|
|
349
|
+
logDebug(`Download attempt ${retries + 1} failed:`, error.message);
|
|
350
|
+
retries++;
|
|
351
|
+
if (retries < this.maxRetries) {
|
|
352
|
+
// 尝试重新获取论文信息(可能 PDF URL 已更改)
|
|
353
|
+
const updatedInfo = await this.fetchPaperInfo(paperId);
|
|
354
|
+
if (updatedInfo?.pdfUrl && updatedInfo.pdfUrl !== currentPdfUrl) {
|
|
355
|
+
currentPdfUrl = updatedInfo.pdfUrl;
|
|
356
|
+
logDebug('Trying updated PDF URL...');
|
|
357
|
+
}
|
|
358
|
+
else {
|
|
359
|
+
// 等待后重试
|
|
360
|
+
await new Promise(resolve => setTimeout(resolve, 2000 * retries));
|
|
361
|
+
}
|
|
362
|
+
}
|
|
363
|
+
}
|
|
364
|
+
}
|
|
365
|
+
throw new Error(`Failed to download PDF after ${this.maxRetries} attempts`);
|
|
366
|
+
}
|
|
367
|
+
/**
|
|
368
|
+
* 读取论文内容(Sci-Hub 不提供文本提取)
|
|
369
|
+
*/
|
|
370
|
+
async readPaper(paperId, options) {
|
|
371
|
+
// Sci-Hub 只提供 PDF 下载,不提供文本提取
|
|
372
|
+
const filePath = await this.downloadPdf(paperId, options);
|
|
373
|
+
return `PDF downloaded to: ${filePath}. Please use a PDF reader to view the content.`;
|
|
374
|
+
}
|
|
375
|
+
/**
|
|
376
|
+
* 根据 DOI 获取论文
|
|
377
|
+
*/
|
|
378
|
+
async getPaperByDoi(doi) {
|
|
379
|
+
return this.fetchPaperInfo(doi);
|
|
380
|
+
}
|
|
381
|
+
/**
|
|
382
|
+
* 获取镜像站点状态
|
|
383
|
+
*/
|
|
384
|
+
getMirrorStatus() {
|
|
385
|
+
return this.mirrorSites.map(mirror => ({
|
|
386
|
+
url: mirror.url,
|
|
387
|
+
status: mirror.isWorking ? 'Working' : 'Failed',
|
|
388
|
+
responseTime: mirror.responseTime
|
|
389
|
+
}));
|
|
390
|
+
}
|
|
391
|
+
/**
|
|
392
|
+
* 手动触发健康检查
|
|
393
|
+
*/
|
|
394
|
+
async forceHealthCheck() {
|
|
395
|
+
await this.checkMirrorHealth();
|
|
396
|
+
}
|
|
397
|
+
}
|
|
398
|
+
//# sourceMappingURL=SciHubSearcher.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"SciHubSearcher.js","sourceRoot":"","sources":["../../src/platforms/SciHubSearcher.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,KAAwB,MAAM,OAAO,CAAC;AAC7C,OAAO,KAAK,OAAO,MAAM,SAAS,CAAC;AACnC,OAAO,KAAK,EAAE,MAAM,IAAI,CAAC;AACzB,OAAO,KAAK,IAAI,MAAM,MAAM,CAAC;AAC7B,OAAO,EAAE,WAAW,EAAwD,MAAM,kBAAkB,CAAC;AACrG,OAAO,EAAS,YAAY,EAAE,MAAM,oBAAoB,CAAC;AACzD,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,MAAM,oBAAoB,CAAC;AACvD,OAAO,EAAE,QAAQ,EAAE,MAAM,wBAAwB,CAAC;AAUlD,MAAM,OAAO,cAAe,SAAQ,WAAW;IACrC,WAAW,CAAe;IAC1B,kBAAkB,GAAW,CAAC,CAAC;IAC/B,aAAa,CAAgB;IACpB,UAAU,GAAW,CAAC,CAAC;IACvB,iBAAiB,GAAW,QAAQ,CAAC,YAAY,CAAC;IAC3D,eAAe,GAAgB,IAAI,CAAC;IAC3B,mBAAmB,GAAW,MAAM,CAAC,CAAC,YAAY;IAEnE;QACE,KAAK,CAAC,SAAS,EAAE,oBAAoB,CAAC,CAAC;QAEvC,YAAY;QACZ,IAAI,CAAC,WAAW,GAAG;YACjB,EAAE,GAAG,EAAE,oBAAoB,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;YAC/D,EAAE,GAAG,EAAE,oBAAoB,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;YAC/D,EAAE,GAAG,EAAE,oBAAoB,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;YAC/D,EAAE,GAAG,EAAE,qBAAqB,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;YAChE,EAAE,GAAG,EAAE,0BAA0B,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;YACrE,EAAE,GAAG,EAAE,oBAAoB,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;YAC/D,EAAE,GAAG,EAAE,oBAAoB,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;YAC/D,EAAE,GAAG,EAAE,oBAAoB,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;YAC/D,EAAE,GAAG,EAAE,4BAA4B,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;YACvE,EAAE,GAAG,EAAE,4BAA4B,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;YACvE,EAAE,GAAG,EAAE,4BAA4B,EAAE,SAAS,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,EAAE;SACxE,CAAC;QAEF,IAAI,CAAC,aAAa,GAAG,KAAK,CAAC,MAAM,CAAC;YAChC,OAAO,EAAE,QAAQ,CAAC,OAAO;YACzB,OAAO,EAAE;gBACP,YAAY,EAAE,iHAAiH;gBAC/H,QAAQ,EAAE,4EAA4E;gBACtF,iBAAiB,EAAE,gBAAgB;gBACnC,iBAAiB,EAAE,mBAAmB;gBACtC,KAAK,EAAE,GAAG;gBACV,YAAY,EAAE,YAAY;gBAC1B,2BAA2B,EAAE,GAAG;aACjC;YACD,YAAY,EAAE,CAAC;YACf,cAAc,EAAE,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,GAAG,GAAG;SACzC,CAAC,CAAC;IACL,CAAC;IAED,eAAe;QACb,OAAO;YACL,MAAM,EAAE,IAAI;YACZ,QAAQ,EAAE,IAAI;YACd,QAAQ,EAAE,KAAK;YACf,SAAS,EAAE,KAAK;YAChB,cAAc,EAAE,KAAK;YACrB,gBAAgB,EAAE,CAAC,YAAY,CAAC;SACjC,CAAC;IACJ,CAAC;IAED;;OAEG;IACK,KAAK,CAAC,iBAAiB;QAC7B,QAAQ,CAAC,yCAAyC,CAAC,CAAC;QAEpD,MAAM,cAAc,GAAG,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,EAAE;YAClE,IAAI,CAAC;gBACH,MAAM,SAAS,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;gBAC7B,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG,EAAE;oBAC3C,OAAO,EAAE,IAAI,CAAC,iBAAiB;oBAC/B,OAAO,EAAE,IAAI,CAAC,aAAa,CAAC,QAAQ,CAAC,OAAc;oBACnD,YAAY,EAAE,CAAC;iBAChB,CAAC,CAAC;gBAEH,MAAM,YAAY,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,SAAS,CAAC;gBAE5C,sBAAsB;gBACtB,MAAM,IAAI,GAAG,QAAQ,CAAC,IAAI,CAAC;gBAC3B,MAAM,aAAa,GAAG,IAAI,CAAC,QAAQ,CAAC,SAAS,CAAC;oBACzB,IAAI,CAAC,QAAQ,CAAC,SAAS,CAAC;oBACxB,IAAI,CAAC,QAAQ,CAAC,oBAAoB,CAAC,CAAC;gBAEzD,IAAI,CAAC,WAAW,CAAC,KAAK,CAAC,GAAG;oBACxB,GAAG,MAAM;oBACT,WAAW,EAAE,IAAI,IAAI,EAAE;oBACvB,YAAY;oBACZ,SAAS,EAAE,QAAQ,CAAC,MAAM,KAAK,GAAG,IAAI,aAAa;oBACnD,YAAY,EAAE,CAAC;iBAChB,CAAC;gBAEF,IAAI,IAAI,CAAC,WAAW,CAAC,KAAK,CAAC,CAAC,SAAS,EAAE,CAAC;oBACtC,QAAQ,CAAC,GAAG,MAAM,CAAC,GAAG,UAAU,YAAY,KAAK,CAAC,CAAC;gBACrD,CAAC;qBAAM,CAAC;oBACN,QAAQ,CAAC,GAAG,MAAM,CAAC,GAAG,qBAAqB,CAAC,CAAC;gBAC/C,CAAC;YACH,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBACf,IAAI,CAAC,WAAW,CAAC,KAAK,CAAC,GAAG;oBACxB,GAAG,MAAM;oBACT,WAAW,EAAE,IAAI,IAAI,EAAE;oBACvB,SAAS,EAAE,KAAK;oBAChB,YAAY,EAAE,MAAM,CAAC,YAAY,GAAG,CAAC;iBACtC,CAAC;gBACF,QAAQ,CAAC,GAAG,MAAM,CAAC,GAAG,WAAW,CAAC,CAAC;YACrC,CAAC;QACH,CAAC,CAAC,CAAC;QAEH,MAAM,OAAO,CAAC,UAAU,CAAC,cAAc,CAAC,CAAC;QAEzC,eAAe;QACf,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE;YAC7B,IAAI,CAAC,CAAC,SAAS,IAAI,CAAC,CAAC,CAAC,SAAS;gBAAE,OAAO,CAAC,CAAC,CAAC;YAC3C,IAAI,CAAC,CAAC,CAAC,SAAS,IAAI,CAAC,CAAC,SAAS;gBAAE,OAAO,CAAC,CAAC;YAC1C,IAAI,CAAC,CAAC,SAAS,IAAI,CAAC,CAAC,SAAS,EAAE,CAAC;gBAC/B,OAAO,CAAC,CAAC,CAAC,YAAY,IAAI,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,YAAY,IAAI,QAAQ,CAAC,CAAC;YACrE,CAAC;YACD,OAAO,CAAC,CAAC;QACX,CAAC,CAAC,CAAC;QAEH,IAAI,CAAC,eAAe,GAAG,IAAI,IAAI,EAAE,CAAC;QAElC,MAAM,YAAY,GAAG,IAAI,CAAC,WAAW,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,MAAM,CAAC;QACtE,QAAQ,CAAC,0BAA0B,YAAY,IAAI,IAAI,CAAC,WAAW,CAAC,MAAM,kBAAkB,CAAC,CAAC;QAE9F,IAAI,YAAY,KAAK,CAAC,EAAE,CAAC;YACvB,OAAO,CAAC,uDAAuD,CAAC,CAAC;QACnE,CAAC;IACH,CAAC;IAED;;OAEG;IACK,KAAK,CAAC,gBAAgB;QAC5B,WAAW;QACX,IAAI,CAAC,IAAI,CAAC,eAAe;YACrB,IAAI,CAAC,GAAG,EAAE,GAAG,IAAI,CAAC,eAAe,CAAC,OAAO,EAAE,GAAG,IAAI,CAAC,mBAAmB,EAAE,CAAC;YAC3E,MAAM,IAAI,CAAC,iBAAiB,EAAE,CAAC;QACjC,CAAC;QAED,aAAa;QACb,MAAM,aAAa,GAAG,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC;QAC9D,IAAI,CAAC,aAAa,EAAE,CAAC;YACnB,gBAAgB;YAChB,MAAM,IAAI,CAAC,iBAAiB,EAAE,CAAC;YAC/B,MAAM,WAAW,GAAG,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC;YAC5D,IAAI,CAAC,WAAW,EAAE,CAAC;gBACjB,MAAM,IAAI,KAAK,CAAC,sCAAsC,CAAC,CAAC;YAC1D,CAAC;YACD,OAAO,WAAW,CAAC,GAAG,CAAC;QACzB,CAAC;QAED,OAAO,aAAa,CAAC,GAAG,CAAC;IAC3B,CAAC;IAED;;OAEG;IACK,KAAK,CAAC,gBAAgB,CAAC,SAAiB;QAC9C,MAAM,WAAW,GAAG,IAAI,CAAC,WAAW,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,KAAK,SAAS,CAAC,CAAC;QACzE,IAAI,WAAW,KAAK,CAAC,CAAC,EAAE,CAAC;YACvB,IAAI,CAAC,WAAW,CAAC,WAAW,CAAC,CAAC,YAAY,EAAE,CAAC;YAC7C,IAAI,IAAI,CAAC,WAAW,CAAC,WAAW,CAAC,CAAC,YAAY,IAAI,CAAC,EAAE,CAAC;gBACpD,IAAI,CAAC,WAAW,CAAC,WAAW,CAAC,CAAC,SAAS,GAAG,KAAK,CAAC;gBAChD,QAAQ,CAAC,UAAU,SAAS,2CAA2C,CAAC,CAAC;YAC3E,CAAC;QACH,CAAC;QAED,UAAU;QACV,MAAM,iBAAiB,GAAG,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,EAAE,CACzD,GAAG,GAAG,WAAW,IAAI,CAAC,CAAC,SAAS,CACjC,CAAC;QAEF,IAAI,iBAAiB,EAAE,CAAC;YACtB,OAAO,iBAAiB,CAAC,GAAG,CAAC;QAC/B,CAAC;QAED,oBAAoB;QACpB,MAAM,IAAI,CAAC,iBAAiB,EAAE,CAAC;QAC/B,OAAO,IAAI,CAAC,gBAAgB,EAAE,CAAC;IACjC,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,MAAM,CAAC,KAAa,EAAE,OAAuB;QACjD,8BAA8B;QAC9B,yBAAyB;QACzB,IAAI,CAAC,IAAI,CAAC,eAAe,CAAC,KAAK,CAAC,EAAE,CAAC;YACjC,OAAO,EAAE,CAAC;QACZ,CAAC;QAED,IAAI,CAAC;YACH,MAAM,SAAS,GAAG,MAAM,IAAI,CAAC,cAAc,CAAC,KAAK,CAAC,CAAC;YACnD,IAAI,SAAS,EAAE,CAAC;gBACd,OAAO,CAAC,SAAS,CAAC,CAAC;YACrB,CAAC;QACH,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,QAAQ,CAAC,uBAAuB,EAAE,KAAK,CAAC,CAAC;QAC3C,CAAC;QAED,OAAO,EAAE,CAAC;IACZ,CAAC;IAED;;OAEG;IACK,eAAe,CAAC,KAAa;QACnC,uBAAuB;QACvB,MAAM,UAAU,GAAG,qCAAqC,CAAC;QAEzD,SAAS;QACT,MAAM,UAAU,GAAG,gBAAgB,CAAC;QAEpC,mBAAmB;QACnB,MAAM,gBAAgB,GAAG,6CAA6C,CAAC;QAEvE,OAAO,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC;YACtB,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC;YACtB,gBAAgB,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IACtC,CAAC;IAED;;OAEG;IACK,KAAK,CAAC,cAAc,CAAC,QAAgB;QAC3C,IAAI,aAAa,GAAG,MAAM,IAAI,CAAC,gBAAgB,EAAE,CAAC;QAClD,IAAI,OAAO,GAAG,CAAC,CAAC;QAEhB,YAAY;QACZ,MAAM,YAAY,GAAG,QAAQ,CAAC,OAAO,CAAC,WAAW,EAAE,EAAE,CAAC,CAAC;QAEvD,OAAO,OAAO,GAAG,IAAI,CAAC,UAAU,EAAE,CAAC;YACjC,IAAI,CAAC;gBACH,MAAM,SAAS,GAAG,GAAG,aAAa,IAAI,YAAY,EAAE,CAAC;gBACrD,QAAQ,CAAC,gBAAgB,aAAa,SAAS,YAAY,EAAE,CAAC,CAAC;gBAE/D,MAAM,QAAQ,GAAG,MAAM,IAAI,CAAC,aAAa,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;gBAEzD,IAAI,QAAQ,CAAC,MAAM,KAAK,GAAG,EAAE,CAAC;oBAC5B,MAAM,CAAC,GAAG,OAAO,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;oBAEtC,WAAW;oBACX,MAAM,QAAQ,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC;oBAC3B,MAAM,QAAQ,GAAG,CAAC,CAAC,+BAA+B,CAAC,CAAC;oBACpD,MAAM,SAAS,GAAG,CAAC,CAAC,qBAAqB,CAAC,CAAC;oBAE3C,IAAI,MAAM,GAAG,EAAE,CAAC;oBAEhB,mBAAmB;oBACnB,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;wBACxB,MAAM,GAAG,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC;oBACtC,CAAC;yBAAM,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;wBAC/B,MAAM,GAAG,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC;oBACtC,CAAC;yBAAM,IAAI,SAAS,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;wBAChC,MAAM,GAAG,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC;oBACvC,CAAC;yBAAM,CAAC;wBACN,SAAS;wBACT,MAAM,cAAc,GAAG,CAAC,CAAC,6BAA6B,CAAC,CAAC;wBACxD,IAAI,cAAc,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;4BAC9B,MAAM,WAAW,GAAG,cAAc,CAAC,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,CAAC;4BACzD,MAAM,KAAK,GAAG,WAAW,CAAC,KAAK,CAAC,0BAA0B,CAAC,CAAC;4BAC5D,IAAI,KAAK,EAAE,CAAC;gCACV,MAAM,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;4BACpB,CAAC;wBACH,CAAC;oBACH,CAAC;oBAED,WAAW;oBACX,IAAI,MAAM,IAAI,CAAC,MAAM,CAAC,UAAU,CAAC,MAAM,CAAC,EAAE,CAAC;wBACzC,IAAI,MAAM,CAAC,UAAU,CAAC,IAAI,CAAC,EAAE,CAAC;4BAC5B,MAAM,GAAG,QAAQ,GAAG,MAAM,CAAC;wBAC7B,CAAC;6BAAM,IAAI,MAAM,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;4BAClC,MAAM,GAAG,aAAa,GAAG,MAAM,CAAC;wBAClC,CAAC;oBACH,CAAC;oBAED,IAAI,MAAM,EAAE,CAAC;wBACX,+BAA+B;wBAC/B,IAAI,KAAK,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,CAAC;wBAC9B,MAAM,QAAQ,GAAG,CAAC,CAAC,WAAW,CAAC,CAAC,IAAI,EAAE,CAAC;wBACvC,IAAI,QAAQ,EAAE,CAAC;4BACb,aAAa;4BACb,MAAM,UAAU,GAAG,QAAQ,CAAC,KAAK,CAAC,WAAW,CAAC,CAAC;4BAC/C,IAAI,UAAU,EAAE,CAAC;gCACf,KAAK,GAAG,UAAU,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;4BAC/B,CAAC;wBACH,CAAC;wBAED,OAAO;wBACP,KAAK,GAAG,KAAK,CAAC,OAAO,CAAC,oBAAoB,EAAE,EAAE,CAAC;6BAClC,OAAO,CAAC,gBAAgB,EAAE,EAAE,CAAC;6BAC7B,IAAI,EAAE,CAAC;wBAEpB,OAAO,YAAY,CAAC,MAAM,CAAC;4BACzB,OAAO,EAAE,YAAY;4BACrB,KAAK,EAAE,KAAK,IAAI,UAAU,YAAY,EAAE;4BACxC,MAAM,EAAE,QAAQ;4BAChB,OAAO,EAAE,EAAE;4BACX,QAAQ,EAAE,EAAE;4BACZ,GAAG,EAAE,IAAI,CAAC,eAAe,CAAC,YAAY,CAAC,IAAI,YAAY,CAAC,QAAQ,CAAC,KAAK,CAAC;gCAClE,CAAC,CAAC,YAAY;gCACd,CAAC,CAAC,EAAE;4BACT,aAAa,EAAE,IAAI;4BACnB,MAAM,EAAE,MAAM;4BACd,GAAG,EAAE,SAAS;4BACd,KAAK,EAAE;gCACL,MAAM,EAAE,aAAa;gCACrB,SAAS,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;6BACpC;yBACF,CAAC,CAAC;oBACL,CAAC;yBAAM,CAAC;wBACN,QAAQ,CAAC,sBAAsB,aAAa,EAAE,CAAC,CAAC;wBAChD,aAAa,GAAG,MAAM,IAAI,CAAC,gBAAgB,CAAC,aAAa,CAAC,CAAC;wBAC3D,OAAO,EAAE,CAAC;oBACZ,CAAC;gBACH,CAAC;qBAAM,CAAC;oBACN,QAAQ,CAAC,qBAAqB,QAAQ,CAAC,MAAM,SAAS,aAAa,EAAE,CAAC,CAAC;oBACvE,aAAa,GAAG,MAAM,IAAI,CAAC,gBAAgB,CAAC,aAAa,CAAC,CAAC;oBAC3D,OAAO,EAAE,CAAC;gBACZ,CAAC;YACH,CAAC;YAAC,OAAO,KAAU,EAAE,CAAC;gBACpB,QAAQ,CAAC,uBAAuB,aAAa,GAAG,EAAE,KAAK,CAAC,OAAO,CAAC,CAAC;gBACjE,aAAa,GAAG,MAAM,IAAI,CAAC,gBAAgB,CAAC,aAAa,CAAC,CAAC;gBAC3D,OAAO,EAAE,CAAC;YACZ,CAAC;QACH,CAAC;QAED,OAAO,IAAI,CAAC;IACd,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,WAAW,CAAC,OAAe,EAAE,OAAyB;QAC1D,MAAM,QAAQ,GAAG,OAAO,EAAE,QAAQ,IAAI,aAAa,CAAC;QAEpD,WAAW;QACX,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,QAAQ,CAAC,EAAE,CAAC;YAC7B,EAAE,CAAC,SAAS,CAAC,QAAQ,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;QAC9C,CAAC;QAED,WAAW;QACX,MAAM,SAAS,GAAG,MAAM,IAAI,CAAC,cAAc,CAAC,OAAO,CAAC,CAAC;QACrD,IAAI,CAAC,SAAS,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,CAAC;YACpC,MAAM,IAAI,KAAK,CAAC,wBAAwB,OAAO,EAAE,CAAC,CAAC;QACrD,CAAC;QAED,MAAM,QAAQ,GAAG,GAAG,OAAO,CAAC,OAAO,CAAC,eAAe,EAAE,GAAG,CAAC,MAAM,CAAC;QAChE,MAAM,QAAQ,GAAG,IAAI,CAAC,IAAI,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAC;QAE/C,YAAY;QACZ,IAAI,EAAE,CAAC,UAAU,CAAC,QAAQ,CAAC,IAAI,CAAC,OAAO,EAAE,SAAS,EAAE,CAAC;YACnD,OAAO,QAAQ,CAAC;QAClB,CAAC;QAED,SAAS;QACT,IAAI,OAAO,GAAG,CAAC,CAAC;QAChB,IAAI,aAAa,GAAG,SAAS,CAAC,MAAM,CAAC;QAErC,OAAO,OAAO,GAAG,IAAI,CAAC,UAAU,EAAE,CAAC;YACjC,IAAI,CAAC;gBACH,QAAQ,CAAC,yBAAyB,aAAa,EAAE,CAAC,CAAC;gBAEnD,MAAM,QAAQ,GAAG,MAAM,IAAI,CAAC,aAAa,CAAC,GAAG,CAAC,aAAa,EAAE;oBAC3D,YAAY,EAAE,QAAQ;oBACtB,OAAO,EAAE,QAAQ,CAAC,QAAQ;iBAC3B,CAAC,CAAC;gBAEH,IAAI,QAAQ,CAAC,MAAM,KAAK,GAAG,EAAE,CAAC;oBAC5B,MAAM,MAAM,GAAG,EAAE,CAAC,iBAAiB,CAAC,QAAQ,CAAC,CAAC;oBAC9C,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;oBAE3B,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;wBACrC,MAAM,CAAC,EAAE,CAAC,QAAQ,EAAE,GAAG,EAAE;4BACvB,OAAO,CAAC,QAAQ,CAAC,CAAC;wBACpB,CAAC,CAAC,CAAC;wBACH,MAAM,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC;oBAC7B,CAAC,CAAC,CAAC;gBACL,CAAC;qBAAM,CAAC;oBACN,MAAM,IAAI,KAAK,CAAC,kCAAkC,QAAQ,CAAC,MAAM,EAAE,CAAC,CAAC;gBACvE,CAAC;YACH,CAAC;YAAC,OAAO,KAAU,EAAE,CAAC;gBACpB,QAAQ,CAAC,oBAAoB,OAAO,GAAG,CAAC,UAAU,EAAE,KAAK,CAAC,OAAO,CAAC,CAAC;gBACnE,OAAO,EAAE,CAAC;gBAEV,IAAI,OAAO,GAAG,IAAI,CAAC,UAAU,EAAE,CAAC;oBAC9B,6BAA6B;oBAC7B,MAAM,WAAW,GAAG,MAAM,IAAI,CAAC,cAAc,CAAC,OAAO,CAAC,CAAC;oBACvD,IAAI,WAAW,EAAE,MAAM,IAAI,WAAW,CAAC,MAAM,KAAK,aAAa,EAAE,CAAC;wBAChE,aAAa,GAAG,WAAW,CAAC,MAAM,CAAC;wBACnC,QAAQ,CAAC,2BAA2B,CAAC,CAAC;oBACxC,CAAC;yBAAM,CAAC;wBACN,QAAQ;wBACR,MAAM,IAAI,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC,UAAU,CAAC,OAAO,EAAE,IAAI,GAAG,OAAO,CAAC,CAAC,CAAC;oBACpE,CAAC;gBACH,CAAC;YACH,CAAC;QACH,CAAC;QAED,MAAM,IAAI,KAAK,CAAC,gCAAgC,IAAI,CAAC,UAAU,WAAW,CAAC,CAAC;IAC9E,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,SAAS,CAAC,OAAe,EAAE,OAAyB;QACxD,6BAA6B;QAC7B,MAAM,QAAQ,GAAG,MAAM,IAAI,CAAC,WAAW,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC;QAC1D,OAAO,sBAAsB,QAAQ,gDAAgD,CAAC;IACxF,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,aAAa,CAAC,GAAW;QAC7B,OAAO,IAAI,CAAC,cAAc,CAAC,GAAG,CAAC,CAAC;IAClC,CAAC;IAED;;OAEG;IACH,eAAe;QACb,OAAO,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;YACrC,GAAG,EAAE,MAAM,CAAC,GAAG;YACf,MAAM,EAAE,MAAM,CAAC,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,QAAQ;YAC/C,YAAY,EAAE,MAAM,CAAC,YAAY;SAClC,CAAC,CAAC,CAAC;IACN,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,gBAAgB;QACpB,MAAM,IAAI,CAAC,iBAAiB,EAAE,CAAC;IACjC,CAAC;CACF"}
|
|
@@ -0,0 +1,42 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* ScienceDirect (Elsevier) Searcher
|
|
3
|
+
*
|
|
4
|
+
* Documentation: https://dev.elsevier.com/
|
|
5
|
+
* API Endpoints:
|
|
6
|
+
* - Search API: https://api.elsevier.com/content/search/sciencedirect
|
|
7
|
+
* - Article API: https://api.elsevier.com/content/article/doi/
|
|
8
|
+
*
|
|
9
|
+
* Required API Key: Yes (X-ELS-APIKey header)
|
|
10
|
+
* Get API key from: https://dev.elsevier.com/apikey/manage
|
|
11
|
+
*/
|
|
12
|
+
import { PaperSource, SearchOptions, DownloadOptions, PlatformCapabilities } from './PaperSource.js';
|
|
13
|
+
import { Paper } from '../models/Paper.js';
|
|
14
|
+
export declare class ScienceDirectSearcher extends PaperSource {
|
|
15
|
+
private client;
|
|
16
|
+
private rateLimiter;
|
|
17
|
+
private quotaManager;
|
|
18
|
+
constructor(apiKey?: string);
|
|
19
|
+
search(query: string, options?: SearchOptions): Promise<Paper[]>;
|
|
20
|
+
/**
|
|
21
|
+
* Parse result from new PUT API format
|
|
22
|
+
*/
|
|
23
|
+
private parseNewApiResult;
|
|
24
|
+
/**
|
|
25
|
+
* Enrich papers with abstracts using Article Retrieval API
|
|
26
|
+
*/
|
|
27
|
+
private enrichPapersWithAbstracts;
|
|
28
|
+
private parseEntry;
|
|
29
|
+
getArticleDetails(doi: string): Promise<Paper | null>;
|
|
30
|
+
getCapabilities(): PlatformCapabilities;
|
|
31
|
+
downloadPdf(paperId: string, options?: DownloadOptions): Promise<string>;
|
|
32
|
+
readPaper(paperId: string, options?: DownloadOptions): Promise<string>;
|
|
33
|
+
/**
|
|
34
|
+
* 获取引用此论文的文献列表(通过Crossref/OpenCitations)
|
|
35
|
+
*/
|
|
36
|
+
getCitations(paperId: string): Promise<Paper[]>;
|
|
37
|
+
/**
|
|
38
|
+
* 获取论文的参考文献列表(通过Crossref)
|
|
39
|
+
*/
|
|
40
|
+
getReferences(paperId: string): Promise<Paper[]>;
|
|
41
|
+
}
|
|
42
|
+
//# sourceMappingURL=ScienceDirectSearcher.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"ScienceDirectSearcher.d.ts","sourceRoot":"","sources":["../../src/platforms/ScienceDirectSearcher.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAGH,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE,eAAe,EAAE,oBAAoB,EAAE,MAAM,kBAAkB,CAAC;AACrG,OAAO,EAAE,KAAK,EAAgB,MAAM,oBAAoB,CAAC;AA+DzD,qBAAa,qBAAsB,SAAQ,WAAW;IACpD,OAAO,CAAC,MAAM,CAAgB;IAC9B,OAAO,CAAC,WAAW,CAAc;IACjC,OAAO,CAAC,YAAY,CAAe;gBAEvB,MAAM,CAAC,EAAE,MAAM;IA8BrB,MAAM,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,GAAE,aAAkB,GAAG,OAAO,CAAC,KAAK,EAAE,CAAC;IAsE1E;;OAEG;IACH,OAAO,CAAC,iBAAiB;IAqDzB;;OAEG;YACW,yBAAyB;YA6BzB,UAAU;IAwClB,iBAAiB,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,KAAK,GAAG,IAAI,CAAC;IAiD3D,eAAe,IAAI,oBAAoB;IAWjC,WAAW,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,GAAE,eAAoB,GAAG,OAAO,CAAC,MAAM,CAAC;IAI5E,SAAS,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,GAAE,eAAoB,GAAG,OAAO,CAAC,MAAM,CAAC;IAQhF;;OAEG;IACG,YAAY,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,KAAK,EAAE,CAAC;IAkBrD;;OAEG;IACG,aAAa,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,KAAK,EAAE,CAAC;CAiBvD"}
|