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 +1,422 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* PubMed E-utilities API集成模块
|
|
3
|
+
* 支持无API密钥的免费使用(3 req/s)和有API密钥的增强使用(10 req/s)
|
|
4
|
+
*/
|
|
5
|
+
import axios from 'axios';
|
|
6
|
+
import * as xml2js from 'xml2js';
|
|
7
|
+
import { PaperFactory } from '../models/Paper.js';
|
|
8
|
+
import { PaperSource } from './PaperSource.js';
|
|
9
|
+
import { RateLimiter } from '../utils/RateLimiter.js';
|
|
10
|
+
import { ErrorHandler } from '../utils/ErrorHandler.js';
|
|
11
|
+
import { TIMEOUTS, USER_AGENT } from '../config/constants.js';
|
|
12
|
+
import { logDebug } from '../utils/Logger.js';
|
|
13
|
+
export class PubMedSearcher extends PaperSource {
|
|
14
|
+
baseApiUrl;
|
|
15
|
+
rateLimiter;
|
|
16
|
+
retMax = 20; // 每次批量获取的最大数量
|
|
17
|
+
constructor(apiKey) {
|
|
18
|
+
super('pubmed', 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils', apiKey);
|
|
19
|
+
this.baseApiUrl = this.baseUrl;
|
|
20
|
+
// 根据是否有API密钥设置不同的速率限制
|
|
21
|
+
const requestsPerSecond = apiKey ? 10 : 3;
|
|
22
|
+
this.rateLimiter = new RateLimiter({
|
|
23
|
+
requestsPerSecond,
|
|
24
|
+
burstCapacity: requestsPerSecond,
|
|
25
|
+
debug: process.env.NODE_ENV === 'development'
|
|
26
|
+
});
|
|
27
|
+
}
|
|
28
|
+
getCapabilities() {
|
|
29
|
+
return {
|
|
30
|
+
search: true,
|
|
31
|
+
download: false, // PubMed不提供直接PDF下载
|
|
32
|
+
fullText: false, // 只有摘要,不是全文
|
|
33
|
+
citations: false, // 基础版本不提供被引统计
|
|
34
|
+
requiresApiKey: false, // 无API密钥也可以使用,但有限制
|
|
35
|
+
supportedOptions: ['maxResults', 'year', 'author', 'journal', 'sortBy']
|
|
36
|
+
};
|
|
37
|
+
}
|
|
38
|
+
/**
|
|
39
|
+
* 搜索PubMed文献
|
|
40
|
+
*/
|
|
41
|
+
async search(query, options = {}) {
|
|
42
|
+
try {
|
|
43
|
+
logDebug(`PubMed Search Starting: query="${query}"`, options);
|
|
44
|
+
// 第一步:使用ESearch获取PMID列表
|
|
45
|
+
const pmids = await this.searchPMIDs(query, options);
|
|
46
|
+
if (pmids.length === 0) {
|
|
47
|
+
return [];
|
|
48
|
+
}
|
|
49
|
+
// 第二步:批量获取详细信息
|
|
50
|
+
const papers = [];
|
|
51
|
+
for (let i = 0; i < pmids.length; i += this.retMax) {
|
|
52
|
+
const batch = pmids.slice(i, i + this.retMax);
|
|
53
|
+
const batchPapers = await this.fetchPaperDetails(batch);
|
|
54
|
+
papers.push(...batchPapers);
|
|
55
|
+
}
|
|
56
|
+
return papers;
|
|
57
|
+
}
|
|
58
|
+
catch (error) {
|
|
59
|
+
logDebug('PubMed Search Error:', error.message);
|
|
60
|
+
this.handleHttpError(error, 'search');
|
|
61
|
+
}
|
|
62
|
+
}
|
|
63
|
+
/**
|
|
64
|
+
* 搜索获取PMID列表
|
|
65
|
+
*/
|
|
66
|
+
async searchPMIDs(query, options) {
|
|
67
|
+
await this.rateLimiter.waitForPermission();
|
|
68
|
+
const searchQuery = this.buildSearchQuery(query, options);
|
|
69
|
+
const params = {
|
|
70
|
+
db: 'pubmed',
|
|
71
|
+
term: searchQuery,
|
|
72
|
+
retmax: (options.maxResults || 10).toString(),
|
|
73
|
+
retmode: 'xml',
|
|
74
|
+
sort: this.mapSortField(options.sortBy || 'relevance')
|
|
75
|
+
};
|
|
76
|
+
// 添加API密钥(如果有)
|
|
77
|
+
if (this.apiKey) {
|
|
78
|
+
params.api_key = this.apiKey;
|
|
79
|
+
}
|
|
80
|
+
const url = `${this.baseApiUrl}/esearch.fcgi`;
|
|
81
|
+
logDebug(`PubMed ESearch Request: GET ${url}`);
|
|
82
|
+
logDebug('PubMed ESearch params:', params);
|
|
83
|
+
const response = await ErrorHandler.retryWithBackoff(() => axios.get(url, {
|
|
84
|
+
params,
|
|
85
|
+
timeout: TIMEOUTS.DEFAULT,
|
|
86
|
+
headers: { 'User-Agent': USER_AGENT }
|
|
87
|
+
}), { context: 'PubMed ESearch' });
|
|
88
|
+
logDebug(`PubMed ESearch Response: ${response.status} ${response.statusText}`);
|
|
89
|
+
logDebug('PubMed ESearch Response data:', response.data.substring(0, 500));
|
|
90
|
+
const result = await this.parseXmlResponse(response.data);
|
|
91
|
+
let pmids = result.eSearchResult.IdList?.Id || [];
|
|
92
|
+
// 处理单个ID vs ID数组
|
|
93
|
+
if (typeof pmids === 'string') {
|
|
94
|
+
pmids = [pmids];
|
|
95
|
+
}
|
|
96
|
+
logDebug(`PubMed Found ${pmids.length} PMIDs:`, pmids.slice(0, 5));
|
|
97
|
+
return pmids;
|
|
98
|
+
}
|
|
99
|
+
/**
|
|
100
|
+
* 获取论文详细信息
|
|
101
|
+
*/
|
|
102
|
+
async fetchPaperDetails(pmids) {
|
|
103
|
+
await this.rateLimiter.waitForPermission();
|
|
104
|
+
const params = {
|
|
105
|
+
db: 'pubmed',
|
|
106
|
+
id: pmids.join(','),
|
|
107
|
+
retmode: 'xml'
|
|
108
|
+
};
|
|
109
|
+
// 添加API密钥(如果有)
|
|
110
|
+
if (this.apiKey) {
|
|
111
|
+
params.api_key = this.apiKey;
|
|
112
|
+
}
|
|
113
|
+
const url = `${this.baseApiUrl}/efetch.fcgi`;
|
|
114
|
+
const response = await ErrorHandler.retryWithBackoff(() => axios.get(url, {
|
|
115
|
+
params,
|
|
116
|
+
timeout: TIMEOUTS.DEFAULT,
|
|
117
|
+
headers: { 'User-Agent': USER_AGENT }
|
|
118
|
+
}), { context: 'PubMed EFetch' });
|
|
119
|
+
const result = await this.parseXmlResponse(response.data);
|
|
120
|
+
// 处理xml2js的单个元素vs数组问题
|
|
121
|
+
let articles = result.PubmedArticleSet?.PubmedArticle || [];
|
|
122
|
+
if (!Array.isArray(articles)) {
|
|
123
|
+
articles = [articles]; // 将单个对象转换为数组
|
|
124
|
+
}
|
|
125
|
+
return this.parsePubMedArticles(articles);
|
|
126
|
+
}
|
|
127
|
+
/**
|
|
128
|
+
* 构建搜索查询
|
|
129
|
+
*/
|
|
130
|
+
buildSearchQuery(query, options) {
|
|
131
|
+
let searchQuery = query;
|
|
132
|
+
// 添加作者过滤
|
|
133
|
+
if (options.author) {
|
|
134
|
+
searchQuery += ` AND ${options.author}[Author]`;
|
|
135
|
+
}
|
|
136
|
+
// 添加期刊过滤
|
|
137
|
+
if (options.journal) {
|
|
138
|
+
searchQuery += ` AND "${options.journal}"[Journal]`;
|
|
139
|
+
}
|
|
140
|
+
// 添加年份过滤
|
|
141
|
+
if (options.year) {
|
|
142
|
+
if (options.year.includes('-')) {
|
|
143
|
+
const [startYear, endYear] = options.year.split('-');
|
|
144
|
+
if (startYear && endYear) {
|
|
145
|
+
searchQuery += ` AND ${startYear}:${endYear}[Publication Date]`;
|
|
146
|
+
}
|
|
147
|
+
else if (startYear) {
|
|
148
|
+
searchQuery += ` AND ${startYear}:3000[Publication Date]`;
|
|
149
|
+
}
|
|
150
|
+
else if (endYear) {
|
|
151
|
+
searchQuery += ` AND 1900:${endYear}[Publication Date]`;
|
|
152
|
+
}
|
|
153
|
+
}
|
|
154
|
+
else {
|
|
155
|
+
searchQuery += ` AND ${options.year}[Publication Date]`;
|
|
156
|
+
}
|
|
157
|
+
}
|
|
158
|
+
// 添加文献类型过滤
|
|
159
|
+
if (options.publicationType && options.publicationType.length > 0) {
|
|
160
|
+
const typeQuery = options.publicationType
|
|
161
|
+
.map(type => `"${type}"[Publication Type]`)
|
|
162
|
+
.join(' OR ');
|
|
163
|
+
searchQuery += ` AND (${typeQuery})`;
|
|
164
|
+
}
|
|
165
|
+
return searchQuery;
|
|
166
|
+
}
|
|
167
|
+
/**
|
|
168
|
+
* 映射排序字段
|
|
169
|
+
*/
|
|
170
|
+
mapSortField(sortBy) {
|
|
171
|
+
const fieldMap = {
|
|
172
|
+
'relevance': 'relevance',
|
|
173
|
+
'date': 'pub+date',
|
|
174
|
+
'citations': 'relevance' // PubMed不直接支持按被引排序
|
|
175
|
+
};
|
|
176
|
+
return fieldMap[sortBy] || 'relevance';
|
|
177
|
+
}
|
|
178
|
+
/**
|
|
179
|
+
* 解析XML响应
|
|
180
|
+
*/
|
|
181
|
+
async parseXmlResponse(xmlData) {
|
|
182
|
+
const parser = new xml2js.Parser({
|
|
183
|
+
explicitArray: false, // 简化数组处理
|
|
184
|
+
mergeAttrs: false,
|
|
185
|
+
normalize: true,
|
|
186
|
+
normalizeTags: false,
|
|
187
|
+
trim: true
|
|
188
|
+
});
|
|
189
|
+
logDebug('PubMed XML Parsing - Data preview:', xmlData.substring(0, 200));
|
|
190
|
+
const result = await parser.parseStringPromise(xmlData);
|
|
191
|
+
logDebug('PubMed XML Parsed result structure:', JSON.stringify(result, null, 2).substring(0, 1000));
|
|
192
|
+
return result;
|
|
193
|
+
}
|
|
194
|
+
/**
|
|
195
|
+
* 解析PubMed文章列表
|
|
196
|
+
*/
|
|
197
|
+
parsePubMedArticles(articles) {
|
|
198
|
+
return articles.map(article => this.parsePubMedArticle(article))
|
|
199
|
+
.filter(paper => paper !== null);
|
|
200
|
+
}
|
|
201
|
+
/**
|
|
202
|
+
* 解析单个PubMed文章
|
|
203
|
+
*/
|
|
204
|
+
parsePubMedArticle(article) {
|
|
205
|
+
try {
|
|
206
|
+
const medlineCitation = article.MedlineCitation;
|
|
207
|
+
const articleData = medlineCitation.Article;
|
|
208
|
+
const pubmedData = article.PubmedData;
|
|
209
|
+
// 提取PMID
|
|
210
|
+
const pmid = medlineCitation.PMID._;
|
|
211
|
+
// 提取标题
|
|
212
|
+
const title = articleData.ArticleTitle || 'No title available';
|
|
213
|
+
// 提取作者
|
|
214
|
+
const authors = this.extractAuthors(articleData.AuthorList?.Author || []);
|
|
215
|
+
// 提取摘要
|
|
216
|
+
const abstract = this.extractAbstract(articleData.Abstract);
|
|
217
|
+
// 提取期刊信息
|
|
218
|
+
const journal = articleData.Journal.Title || articleData.Journal.ISOAbbreviation || '';
|
|
219
|
+
// 提取发布日期
|
|
220
|
+
const publishedDate = this.extractPublishedDate(articleData.Journal.JournalIssue.PubDate);
|
|
221
|
+
// 提取DOI和其他ID
|
|
222
|
+
const { doi, pmc } = this.extractArticleIds([
|
|
223
|
+
...(articleData.ArticleIdList?.ArticleId || []),
|
|
224
|
+
...(pubmedData.ArticleIdList?.ArticleId || [])
|
|
225
|
+
]);
|
|
226
|
+
// 提取页码
|
|
227
|
+
const pages = articleData.Pagination?.MedlinePgn || '';
|
|
228
|
+
// 构建URL
|
|
229
|
+
const url = `https://pubmed.ncbi.nlm.nih.gov/${pmid}/`;
|
|
230
|
+
const pdfUrl = pmc ? `https://www.ncbi.nlm.nih.gov/pmc/articles/${pmc}/pdf/` : '';
|
|
231
|
+
return PaperFactory.create({
|
|
232
|
+
paperId: pmid,
|
|
233
|
+
title: this.cleanText(title),
|
|
234
|
+
authors: authors,
|
|
235
|
+
abstract: this.cleanText(abstract),
|
|
236
|
+
doi: doi,
|
|
237
|
+
publishedDate: publishedDate,
|
|
238
|
+
pdfUrl: pdfUrl,
|
|
239
|
+
url: url,
|
|
240
|
+
source: 'pubmed',
|
|
241
|
+
journal: journal,
|
|
242
|
+
volume: articleData.Journal.JournalIssue.Volume || undefined,
|
|
243
|
+
issue: articleData.Journal.JournalIssue.Issue || undefined,
|
|
244
|
+
pages: pages || undefined,
|
|
245
|
+
year: publishedDate?.getFullYear(),
|
|
246
|
+
extra: {
|
|
247
|
+
pmid: pmid,
|
|
248
|
+
pmc: pmc || undefined
|
|
249
|
+
}
|
|
250
|
+
});
|
|
251
|
+
}
|
|
252
|
+
catch (error) {
|
|
253
|
+
logDebug('Error parsing PubMed article:', error);
|
|
254
|
+
return null;
|
|
255
|
+
}
|
|
256
|
+
}
|
|
257
|
+
/**
|
|
258
|
+
* 提取作者信息
|
|
259
|
+
*/
|
|
260
|
+
extractAuthors(authorList) {
|
|
261
|
+
if (!Array.isArray(authorList)) {
|
|
262
|
+
return [];
|
|
263
|
+
}
|
|
264
|
+
return authorList.map(author => {
|
|
265
|
+
if (author.CollectiveName) {
|
|
266
|
+
return author.CollectiveName;
|
|
267
|
+
}
|
|
268
|
+
const lastName = author.LastName || '';
|
|
269
|
+
const foreName = author.ForeName || author.Initials || '';
|
|
270
|
+
if (lastName && foreName) {
|
|
271
|
+
return `${lastName}, ${foreName}`;
|
|
272
|
+
}
|
|
273
|
+
else if (lastName) {
|
|
274
|
+
return lastName;
|
|
275
|
+
}
|
|
276
|
+
else if (foreName) {
|
|
277
|
+
return foreName;
|
|
278
|
+
}
|
|
279
|
+
return 'Unknown Author';
|
|
280
|
+
}).filter(name => name && name !== 'Unknown Author');
|
|
281
|
+
}
|
|
282
|
+
/**
|
|
283
|
+
* 提取摘要
|
|
284
|
+
*/
|
|
285
|
+
extractAbstract(abstractData) {
|
|
286
|
+
if (!abstractData) {
|
|
287
|
+
return '';
|
|
288
|
+
}
|
|
289
|
+
if (typeof abstractData.AbstractText === 'string') {
|
|
290
|
+
return abstractData.AbstractText;
|
|
291
|
+
}
|
|
292
|
+
if (Array.isArray(abstractData.AbstractText)) {
|
|
293
|
+
return abstractData.AbstractText.join(' ');
|
|
294
|
+
}
|
|
295
|
+
return '';
|
|
296
|
+
}
|
|
297
|
+
/**
|
|
298
|
+
* 提取发布日期
|
|
299
|
+
*/
|
|
300
|
+
extractPublishedDate(pubDate) {
|
|
301
|
+
if (!pubDate) {
|
|
302
|
+
return null;
|
|
303
|
+
}
|
|
304
|
+
const year = pubDate.Year;
|
|
305
|
+
const month = pubDate.Month;
|
|
306
|
+
const day = pubDate.Day;
|
|
307
|
+
if (year) {
|
|
308
|
+
const monthNum = month ? this.parseMonth(month) : 1;
|
|
309
|
+
const dayNum = day ? parseInt(day, 10) : 1;
|
|
310
|
+
return new Date(parseInt(year, 10), monthNum - 1, dayNum);
|
|
311
|
+
}
|
|
312
|
+
return null;
|
|
313
|
+
}
|
|
314
|
+
/**
|
|
315
|
+
* 解析月份(支持英文和数字)
|
|
316
|
+
*/
|
|
317
|
+
parseMonth(month) {
|
|
318
|
+
const monthMap = {
|
|
319
|
+
'Jan': 1, 'Feb': 2, 'Mar': 3, 'Apr': 4, 'May': 5, 'Jun': 6,
|
|
320
|
+
'Jul': 7, 'Aug': 8, 'Sep': 9, 'Oct': 10, 'Nov': 11, 'Dec': 12,
|
|
321
|
+
'January': 1, 'February': 2, 'March': 3, 'April': 4, 'June': 6,
|
|
322
|
+
'July': 7, 'August': 8, 'September': 9, 'October': 10, 'November': 11, 'December': 12
|
|
323
|
+
};
|
|
324
|
+
const mapped = monthMap[month];
|
|
325
|
+
if (mapped) {
|
|
326
|
+
return mapped;
|
|
327
|
+
}
|
|
328
|
+
const num = parseInt(month, 10);
|
|
329
|
+
return (num >= 1 && num <= 12) ? num : 1;
|
|
330
|
+
}
|
|
331
|
+
/**
|
|
332
|
+
* 提取文章ID(DOI、PMC等)
|
|
333
|
+
*/
|
|
334
|
+
extractArticleIds(articleIds) {
|
|
335
|
+
let doi = '';
|
|
336
|
+
let pmc = '';
|
|
337
|
+
if (Array.isArray(articleIds)) {
|
|
338
|
+
for (const id of articleIds) {
|
|
339
|
+
const idType = id.$?.IdType?.toLowerCase();
|
|
340
|
+
const value = id._;
|
|
341
|
+
if (idType === 'doi' && !doi) {
|
|
342
|
+
doi = value;
|
|
343
|
+
}
|
|
344
|
+
else if (idType === 'pmc' && !pmc) {
|
|
345
|
+
pmc = value;
|
|
346
|
+
}
|
|
347
|
+
}
|
|
348
|
+
}
|
|
349
|
+
return { doi, pmc };
|
|
350
|
+
}
|
|
351
|
+
/**
|
|
352
|
+
* PubMed通常不支持直接PDF下载
|
|
353
|
+
*/
|
|
354
|
+
async downloadPdf(paperId, options) {
|
|
355
|
+
// 尝试获取PMC链接
|
|
356
|
+
const paper = await this.getPaperByPmid(paperId);
|
|
357
|
+
if (paper?.extra?.pmc) {
|
|
358
|
+
const pmcUrl = `https://www.ncbi.nlm.nih.gov/pmc/articles/${paper.extra.pmc}/pdf/`;
|
|
359
|
+
throw new Error(`PubMed paper may be available as PDF at PMC: ${pmcUrl}. Direct download not supported through this API.`);
|
|
360
|
+
}
|
|
361
|
+
throw new Error('PubMed does not support direct PDF download. Please access the paper through the publisher or PMC.');
|
|
362
|
+
}
|
|
363
|
+
/**
|
|
364
|
+
* PubMed不提供全文内容
|
|
365
|
+
*/
|
|
366
|
+
async readPaper(paperId, options) {
|
|
367
|
+
throw new Error('PubMed does not provide full-text content. Only abstracts and metadata are available.');
|
|
368
|
+
}
|
|
369
|
+
/**
|
|
370
|
+
* 根据PMID获取论文信息
|
|
371
|
+
*/
|
|
372
|
+
async getPaperByPmid(pmid) {
|
|
373
|
+
try {
|
|
374
|
+
const papers = await this.fetchPaperDetails([pmid]);
|
|
375
|
+
return papers.length > 0 ? papers[0] : null;
|
|
376
|
+
}
|
|
377
|
+
catch (error) {
|
|
378
|
+
logDebug('Error getting paper by PMID:', error);
|
|
379
|
+
return null;
|
|
380
|
+
}
|
|
381
|
+
}
|
|
382
|
+
/**
|
|
383
|
+
* 根据DOI获取论文信息
|
|
384
|
+
*/
|
|
385
|
+
async getPaperByDoi(doi) {
|
|
386
|
+
try {
|
|
387
|
+
const results = await this.search(`"${doi}"[DOI]`, { maxResults: 1 });
|
|
388
|
+
return results.length > 0 ? results[0] : null;
|
|
389
|
+
}
|
|
390
|
+
catch (error) {
|
|
391
|
+
logDebug('Error getting paper by DOI from PubMed:', error);
|
|
392
|
+
return null;
|
|
393
|
+
}
|
|
394
|
+
}
|
|
395
|
+
/**
|
|
396
|
+
* 获取速率限制器状态
|
|
397
|
+
*/
|
|
398
|
+
getRateLimiterStatus() {
|
|
399
|
+
return this.rateLimiter.getStatus();
|
|
400
|
+
}
|
|
401
|
+
/**
|
|
402
|
+
* 验证API密钥(如果提供)
|
|
403
|
+
*/
|
|
404
|
+
async validateApiKey() {
|
|
405
|
+
if (!this.apiKey) {
|
|
406
|
+
return true; // 无API密钥时总是有效(使用免费限制)
|
|
407
|
+
}
|
|
408
|
+
try {
|
|
409
|
+
await this.search('test', { maxResults: 1 });
|
|
410
|
+
return true;
|
|
411
|
+
}
|
|
412
|
+
catch (error) {
|
|
413
|
+
// API密钥无效通常返回400或403错误
|
|
414
|
+
if (error.response?.status === 400 || error.response?.status === 403) {
|
|
415
|
+
return false;
|
|
416
|
+
}
|
|
417
|
+
// 其他错误可能是网络问题,认为密钥可能有效
|
|
418
|
+
return true;
|
|
419
|
+
}
|
|
420
|
+
}
|
|
421
|
+
}
|
|
422
|
+
//# sourceMappingURL=PubMedSearcher.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"PubMedSearcher.js","sourceRoot":"","sources":["../../src/platforms/PubMedSearcher.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,KAAK,MAAM,OAAO,CAAC;AAC1B,OAAO,KAAK,MAAM,MAAM,QAAQ,CAAC;AACjC,OAAO,EAAS,YAAY,EAAE,MAAM,oBAAoB,CAAC;AACzD,OAAO,EAAE,WAAW,EAAwD,MAAM,kBAAkB,CAAC;AACrG,OAAO,EAAE,WAAW,EAAE,MAAM,yBAAyB,CAAC;AACtD,OAAO,EAAE,YAAY,EAAE,MAAM,0BAA0B,CAAC;AACxD,OAAO,EAAE,QAAQ,EAAE,UAAU,EAAE,MAAM,wBAAwB,CAAC;AAC9D,OAAO,EAAE,QAAQ,EAAE,MAAM,oBAAoB,CAAC;AAoH9C,MAAM,OAAO,cAAe,SAAQ,WAAW;IAC5B,UAAU,CAAS;IACnB,WAAW,CAAc;IACzB,MAAM,GAAW,EAAE,CAAC,CAAC,cAAc;IAEpD,YAAY,MAAe;QACzB,KAAK,CAAC,QAAQ,EAAE,+CAA+C,EAAE,MAAM,CAAC,CAAC;QACzE,IAAI,CAAC,UAAU,GAAG,IAAI,CAAC,OAAO,CAAC;QAE/B,sBAAsB;QACtB,MAAM,iBAAiB,GAAG,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;QAC1C,IAAI,CAAC,WAAW,GAAG,IAAI,WAAW,CAAC;YACjC,iBAAiB;YACjB,aAAa,EAAE,iBAAiB;YAChC,KAAK,EAAE,OAAO,CAAC,GAAG,CAAC,QAAQ,KAAK,aAAa;SAC9C,CAAC,CAAC;IACL,CAAC;IAED,eAAe;QACb,OAAO;YACL,MAAM,EAAE,IAAI;YACZ,QAAQ,EAAE,KAAK,EAAE,mBAAmB;YACpC,QAAQ,EAAE,KAAK,EAAE,YAAY;YAC7B,SAAS,EAAE,KAAK,EAAE,cAAc;YAChC,cAAc,EAAE,KAAK,EAAE,mBAAmB;YAC1C,gBAAgB,EAAE,CAAC,YAAY,EAAE,MAAM,EAAE,QAAQ,EAAE,SAAS,EAAE,QAAQ,CAAC;SACxE,CAAC;IACJ,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,MAAM,CAAC,KAAa,EAAE,UAA+B,EAAE;QAC3D,IAAI,CAAC;YACH,QAAQ,CAAC,kCAAkC,KAAK,GAAG,EAAE,OAAO,CAAC,CAAC;YAE9D,wBAAwB;YACxB,MAAM,KAAK,GAAG,MAAM,IAAI,CAAC,WAAW,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC;YAErD,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;gBACvB,OAAO,EAAE,CAAC;YACZ,CAAC;YAED,eAAe;YACf,MAAM,MAAM,GAAY,EAAE,CAAC;YAC3B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACnD,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC;gBAC9C,MAAM,WAAW,GAAG,MAAM,IAAI,CAAC,iBAAiB,CAAC,KAAK,CAAC,CAAC;gBACxD,MAAM,CAAC,IAAI,CAAC,GAAG,WAAW,CAAC,CAAC;YAC9B,CAAC;YAED,OAAO,MAAM,CAAC;QAChB,CAAC;QAAC,OAAO,KAAU,EAAE,CAAC;YACpB,QAAQ,CAAC,sBAAsB,EAAE,KAAK,CAAC,OAAO,CAAC,CAAC;YAChD,IAAI,CAAC,eAAe,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAC;QACxC,CAAC;IACH,CAAC;IAED;;OAEG;IACK,KAAK,CAAC,WAAW,CAAC,KAAa,EAAE,OAA4B;QACnE,MAAM,IAAI,CAAC,WAAW,CAAC,iBAAiB,EAAE,CAAC;QAE3C,MAAM,WAAW,GAAG,IAAI,CAAC,gBAAgB,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC;QAC1D,MAAM,MAAM,GAA2B;YACrC,EAAE,EAAE,QAAQ;YACZ,IAAI,EAAE,WAAW;YACjB,MAAM,EAAE,CAAC,OAAO,CAAC,UAAU,IAAI,EAAE,CAAC,CAAC,QAAQ,EAAE;YAC7C,OAAO,EAAE,KAAK;YACd,IAAI,EAAE,IAAI,CAAC,YAAY,CAAC,OAAO,CAAC,MAAM,IAAI,WAAW,CAAC;SACvD,CAAC;QAEF,eAAe;QACf,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;YAChB,MAAM,CAAC,OAAO,GAAG,IAAI,CAAC,MAAM,CAAC;QAC/B,CAAC;QAED,MAAM,GAAG,GAAG,GAAG,IAAI,CAAC,UAAU,eAAe,CAAC;QAE9C,QAAQ,CAAC,+BAA+B,GAAG,EAAE,CAAC,CAAC;QAC/C,QAAQ,CAAC,wBAAwB,EAAE,MAAM,CAAC,CAAC;QAE3C,MAAM,QAAQ,GAAG,MAAM,YAAY,CAAC,gBAAgB,CAClD,GAAG,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,GAAG,EAAE;YACnB,MAAM;YACN,OAAO,EAAE,QAAQ,CAAC,OAAO;YACzB,OAAO,EAAE,EAAE,YAAY,EAAE,UAAU,EAAE;SACtC,CAAC,EACF,EAAE,OAAO,EAAE,gBAAgB,EAAE,CAC9B,CAAC;QAEF,QAAQ,CAAC,4BAA4B,QAAQ,CAAC,MAAM,IAAI,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAC;QAC/E,QAAQ,CAAC,+BAA+B,EAAE,QAAQ,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC;QAE3E,MAAM,MAAM,GAAoB,MAAM,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;QAC3E,IAAI,KAAK,GAAG,MAAM,CAAC,aAAa,CAAC,MAAM,EAAE,EAAE,IAAI,EAAE,CAAC;QAElD,iBAAiB;QACjB,IAAI,OAAO,KAAK,KAAK,QAAQ,EAAE,CAAC;YAC9B,KAAK,GAAG,CAAC,KAAK,CAAC,CAAC;QAClB,CAAC;QAED,QAAQ,CAAC,gBAAgB,KAAK,CAAC,MAAM,SAAS,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;QAEnE,OAAO,KAAK,CAAC;IACf,CAAC;IAED;;OAEG;IACK,KAAK,CAAC,iBAAiB,CAAC,KAAe;QAC7C,MAAM,IAAI,CAAC,WAAW,CAAC,iBAAiB,EAAE,CAAC;QAE3C,MAAM,MAAM,GAA2B;YACrC,EAAE,EAAE,QAAQ;YACZ,EAAE,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC;YACnB,OAAO,EAAE,KAAK;SACf,CAAC;QAEF,eAAe;QACf,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;YAChB,MAAM,CAAC,OAAO,GAAG,IAAI,CAAC,MAAM,CAAC;QAC/B,CAAC;QAED,MAAM,GAAG,GAAG,GAAG,IAAI,CAAC,UAAU,cAAc,CAAC;QAC7C,MAAM,QAAQ,GAAG,MAAM,YAAY,CAAC,gBAAgB,CAClD,GAAG,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,GAAG,EAAE;YACnB,MAAM;YACN,OAAO,EAAE,QAAQ,CAAC,OAAO;YACzB,OAAO,EAAE,EAAE,YAAY,EAAE,UAAU,EAAE;SACtC,CAAC,EACF,EAAE,OAAO,EAAE,eAAe,EAAE,CAC7B,CAAC;QAEF,MAAM,MAAM,GAAmB,MAAM,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;QAE1E,sBAAsB;QACtB,IAAI,QAAQ,GAAG,MAAM,CAAC,gBAAgB,EAAE,aAAa,IAAI,EAAE,CAAC;QAC5D,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,QAAQ,CAAC,EAAE,CAAC;YAC7B,QAAQ,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,aAAa;QACtC,CAAC;QAED,OAAO,IAAI,CAAC,mBAAmB,CAAC,QAAQ,CAAC,CAAC;IAC5C,CAAC;IAED;;OAEG;IACK,gBAAgB,CAAC,KAAa,EAAE,OAA4B;QAClE,IAAI,WAAW,GAAG,KAAK,CAAC;QAExB,SAAS;QACT,IAAI,OAAO,CAAC,MAAM,EAAE,CAAC;YACnB,WAAW,IAAI,QAAQ,OAAO,CAAC,MAAM,UAAU,CAAC;QAClD,CAAC;QAED,SAAS;QACT,IAAI,OAAO,CAAC,OAAO,EAAE,CAAC;YACpB,WAAW,IAAI,SAAS,OAAO,CAAC,OAAO,YAAY,CAAC;QACtD,CAAC;QAED,SAAS;QACT,IAAI,OAAO,CAAC,IAAI,EAAE,CAAC;YACjB,IAAI,OAAO,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC;gBAC/B,MAAM,CAAC,SAAS,EAAE,OAAO,CAAC,GAAG,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;gBACrD,IAAI,SAAS,IAAI,OAAO,EAAE,CAAC;oBACzB,WAAW,IAAI,QAAQ,SAAS,IAAI,OAAO,oBAAoB,CAAC;gBAClE,CAAC;qBAAM,IAAI,SAAS,EAAE,CAAC;oBACrB,WAAW,IAAI,QAAQ,SAAS,yBAAyB,CAAC;gBAC5D,CAAC;qBAAM,IAAI,OAAO,EAAE,CAAC;oBACnB,WAAW,IAAI,aAAa,OAAO,oBAAoB,CAAC;gBAC1D,CAAC;YACH,CAAC;iBAAM,CAAC;gBACN,WAAW,IAAI,QAAQ,OAAO,CAAC,IAAI,oBAAoB,CAAC;YAC1D,CAAC;QACH,CAAC;QAED,WAAW;QACX,IAAI,OAAO,CAAC,eAAe,IAAI,OAAO,CAAC,eAAe,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAClE,MAAM,SAAS,GAAG,OAAO,CAAC,eAAe;iBACtC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,IAAI,qBAAqB,CAAC;iBAC1C,IAAI,CAAC,MAAM,CAAC,CAAC;YAChB,WAAW,IAAI,SAAS,SAAS,GAAG,CAAC;QACvC,CAAC;QAED,OAAO,WAAW,CAAC;IACrB,CAAC;IAED;;OAEG;IACK,YAAY,CAAC,MAAc;QACjC,MAAM,QAAQ,GAA2B;YACvC,WAAW,EAAE,WAAW;YACxB,MAAM,EAAE,UAAU;YAClB,WAAW,EAAE,WAAW,CAAC,mBAAmB;SAC7C,CAAC;QACF,OAAO,QAAQ,CAAC,MAAM,CAAC,IAAI,WAAW,CAAC;IACzC,CAAC;IAED;;OAEG;IACK,KAAK,CAAC,gBAAgB,CAAI,OAAe;QAC/C,MAAM,MAAM,GAAG,IAAI,MAAM,CAAC,MAAM,CAAC;YAC/B,aAAa,EAAE,KAAK,EAAG,SAAS;YAChC,UAAU,EAAE,KAAK;YACjB,SAAS,EAAE,IAAI;YACf,aAAa,EAAE,KAAK;YACpB,IAAI,EAAE,IAAI;SACX,CAAC,CAAC;QAEH,QAAQ,CAAC,oCAAoC,EAAE,OAAO,CAAC,SAAS,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC;QAC1E,MAAM,MAAM,GAAG,MAAM,MAAM,CAAC,kBAAkB,CAAC,OAAO,CAAC,CAAC;QACxD,QAAQ,CAAC,qCAAqC,EAAE,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC;QAEpG,OAAO,MAAM,CAAC;IAChB,CAAC;IAED;;OAEG;IACK,mBAAmB,CAAC,QAA+B;QACzD,OAAO,QAAQ,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC,IAAI,CAAC,kBAAkB,CAAC,OAAO,CAAC,CAAC;aAC7D,MAAM,CAAC,KAAK,CAAC,EAAE,CAAC,KAAK,KAAK,IAAI,CAAY,CAAC;IAChD,CAAC;IAED;;OAEG;IACK,kBAAkB,CAAC,OAA4B;QACrD,IAAI,CAAC;YACH,MAAM,eAAe,GAAG,OAAO,CAAC,eAAe,CAAC;YAChD,MAAM,WAAW,GAAG,eAAe,CAAC,OAAO,CAAC;YAC5C,MAAM,UAAU,GAAG,OAAO,CAAC,UAAU,CAAC;YAEtC,SAAS;YACT,MAAM,IAAI,GAAG,eAAe,CAAC,IAAI,CAAC,CAAC,CAAC;YAEpC,OAAO;YACP,MAAM,KAAK,GAAG,WAAW,CAAC,YAAY,IAAI,oBAAoB,CAAC;YAE/D,OAAO;YACP,MAAM,OAAO,GAAG,IAAI,CAAC,cAAc,CAAC,WAAW,CAAC,UAAU,EAAE,MAAM,IAAI,EAAE,CAAC,CAAC;YAE1E,OAAO;YACP,MAAM,QAAQ,GAAG,IAAI,CAAC,eAAe,CAAC,WAAW,CAAC,QAAQ,CAAC,CAAC;YAE5D,SAAS;YACT,MAAM,OAAO,GAAG,WAAW,CAAC,OAAO,CAAC,KAAK,IAAI,WAAW,CAAC,OAAO,CAAC,eAAe,IAAI,EAAE,CAAC;YAEvF,SAAS;YACT,MAAM,aAAa,GAAG,IAAI,CAAC,oBAAoB,CAAC,WAAW,CAAC,OAAO,CAAC,YAAY,CAAC,OAAO,CAAC,CAAC;YAE1F,aAAa;YACb,MAAM,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,IAAI,CAAC,iBAAiB,CAAC;gBAC1C,GAAG,CAAC,WAAW,CAAC,aAAa,EAAE,SAAS,IAAI,EAAE,CAAC;gBAC/C,GAAG,CAAC,UAAU,CAAC,aAAa,EAAE,SAAS,IAAI,EAAE,CAAC;aAC/C,CAAC,CAAC;YAEH,OAAO;YACP,MAAM,KAAK,GAAG,WAAW,CAAC,UAAU,EAAE,UAAU,IAAI,EAAE,CAAC;YAEvD,QAAQ;YACR,MAAM,GAAG,GAAG,mCAAmC,IAAI,GAAG,CAAC;YACvD,MAAM,MAAM,GAAG,GAAG,CAAC,CAAC,CAAC,6CAA6C,GAAG,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC;YAElF,OAAO,YAAY,CAAC,MAAM,CAAC;gBACzB,OAAO,EAAE,IAAI;gBACb,KAAK,EAAE,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC;gBAC5B,OAAO,EAAE,OAAO;gBAChB,QAAQ,EAAE,IAAI,CAAC,SAAS,CAAC,QAAQ,CAAC;gBAClC,GAAG,EAAE,GAAG;gBACR,aAAa,EAAE,aAAa;gBAC5B,MAAM,EAAE,MAAM;gBACd,GAAG,EAAE,GAAG;gBACR,MAAM,EAAE,QAAQ;gBAChB,OAAO,EAAE,OAAO;gBAChB,MAAM,EAAE,WAAW,CAAC,OAAO,CAAC,YAAY,CAAC,MAAM,IAAI,SAAS;gBAC5D,KAAK,EAAE,WAAW,CAAC,OAAO,CAAC,YAAY,CAAC,KAAK,IAAI,SAAS;gBAC1D,KAAK,EAAE,KAAK,IAAI,SAAS;gBACzB,IAAI,EAAE,aAAa,EAAE,WAAW,EAAE;gBAClC,KAAK,EAAE;oBACL,IAAI,EAAE,IAAI;oBACV,GAAG,EAAE,GAAG,IAAI,SAAS;iBACtB;aACF,CAAC,CAAC;QACL,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,QAAQ,CAAC,+BAA+B,EAAE,KAAK,CAAC,CAAC;YACjD,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IAED;;OAEG;IACK,cAAc,CAAC,UAAiB;QACtC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,UAAU,CAAC,EAAE,CAAC;YAC/B,OAAO,EAAE,CAAC;QACZ,CAAC;QAED,OAAO,UAAU,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE;YAC7B,IAAI,MAAM,CAAC,cAAc,EAAE,CAAC;gBAC1B,OAAO,MAAM,CAAC,cAAc,CAAC;YAC/B,CAAC;YAED,MAAM,QAAQ,GAAG,MAAM,CAAC,QAAQ,IAAI,EAAE,CAAC;YACvC,MAAM,QAAQ,GAAG,MAAM,CAAC,QAAQ,IAAI,MAAM,CAAC,QAAQ,IAAI,EAAE,CAAC;YAE1D,IAAI,QAAQ,IAAI,QAAQ,EAAE,CAAC;gBACzB,OAAO,GAAG,QAAQ,KAAK,QAAQ,EAAE,CAAC;YACpC,CAAC;iBAAM,IAAI,QAAQ,EAAE,CAAC;gBACpB,OAAO,QAAQ,CAAC;YAClB,CAAC;iBAAM,IAAI,QAAQ,EAAE,CAAC;gBACpB,OAAO,QAAQ,CAAC;YAClB,CAAC;YAED,OAAO,gBAAgB,CAAC;QAC1B,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,IAAI,IAAI,KAAK,gBAAgB,CAAC,CAAC;IACvD,CAAC;IAED;;OAEG;IACK,eAAe,CAAC,YAAiB;QACvC,IAAI,CAAC,YAAY,EAAE,CAAC;YAClB,OAAO,EAAE,CAAC;QACZ,CAAC;QAED,IAAI,OAAO,YAAY,CAAC,YAAY,KAAK,QAAQ,EAAE,CAAC;YAClD,OAAO,YAAY,CAAC,YAAY,CAAC;QACnC,CAAC;QAED,IAAI,KAAK,CAAC,OAAO,CAAC,YAAY,CAAC,YAAY,CAAC,EAAE,CAAC;YAC7C,OAAO,YAAY,CAAC,YAAY,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;QAC7C,CAAC;QAED,OAAO,EAAE,CAAC;IACZ,CAAC;IAED;;OAEG;IACK,oBAAoB,CAAC,OAAY;QACvC,IAAI,CAAC,OAAO,EAAE,CAAC;YACb,OAAO,IAAI,CAAC;QACd,CAAC;QAED,MAAM,IAAI,GAAG,OAAO,CAAC,IAAI,CAAC;QAC1B,MAAM,KAAK,GAAG,OAAO,CAAC,KAAK,CAAC;QAC5B,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC;QAExB,IAAI,IAAI,EAAE,CAAC;YACT,MAAM,QAAQ,GAAG,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;YACpD,MAAM,MAAM,GAAG,GAAG,CAAC,CAAC,CAAC,QAAQ,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;YAE3C,OAAO,IAAI,IAAI,CAAC,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC,EAAE,QAAQ,GAAG,CAAC,EAAE,MAAM,CAAC,CAAC;QAC5D,CAAC;QAED,OAAO,IAAI,CAAC;IACd,CAAC;IAED;;OAEG;IACK,UAAU,CAAC,KAAa;QAC9B,MAAM,QAAQ,GAA2B;YACvC,KAAK,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC;YAC1D,KAAK,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,KAAK,EAAE,EAAE,EAAE,KAAK,EAAE,EAAE,EAAE,KAAK,EAAE,EAAE;YAC7D,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC;YAC9D,MAAM,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,EAAE,SAAS,EAAE,EAAE,EAAE,UAAU,EAAE,EAAE,EAAE,UAAU,EAAE,EAAE;SACtF,CAAC;QAEF,MAAM,MAAM,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC;QAC/B,IAAI,MAAM,EAAE,CAAC;YACX,OAAO,MAAM,CAAC;QAChB,CAAC;QAED,MAAM,GAAG,GAAG,QAAQ,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;QAChC,OAAO,CAAC,GAAG,IAAI,CAAC,IAAI,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;IAC3C,CAAC;IAED;;OAEG;IACK,iBAAiB,CAAC,UAAiB;QACzC,IAAI,GAAG,GAAG,EAAE,CAAC;QACb,IAAI,GAAG,GAAG,EAAE,CAAC;QAEb,IAAI,KAAK,CAAC,OAAO,CAAC,UAAU,CAAC,EAAE,CAAC;YAC9B,KAAK,MAAM,EAAE,IAAI,UAAU,EAAE,CAAC;gBAC5B,MAAM,MAAM,GAAG,EAAE,CAAC,CAAC,EAAE,MAAM,EAAE,WAAW,EAAE,CAAC;gBAC3C,MAAM,KAAK,GAAG,EAAE,CAAC,CAAC,CAAC;gBAEnB,IAAI,MAAM,KAAK,KAAK,IAAI,CAAC,GAAG,EAAE,CAAC;oBAC7B,GAAG,GAAG,KAAK,CAAC;gBACd,CAAC;qBAAM,IAAI,MAAM,KAAK,KAAK,IAAI,CAAC,GAAG,EAAE,CAAC;oBACpC,GAAG,GAAG,KAAK,CAAC;gBACd,CAAC;YACH,CAAC;QACH,CAAC;QAED,OAAO,EAAE,GAAG,EAAE,GAAG,EAAE,CAAC;IACtB,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,WAAW,CAAC,OAAe,EAAE,OAAyB;QAC1D,YAAY;QACZ,MAAM,KAAK,GAAG,MAAM,IAAI,CAAC,cAAc,CAAC,OAAO,CAAC,CAAC;QACjD,IAAI,KAAK,EAAE,KAAK,EAAE,GAAG,EAAE,CAAC;YACtB,MAAM,MAAM,GAAG,6CAA6C,KAAK,CAAC,KAAK,CAAC,GAAG,OAAO,CAAC;YACnF,MAAM,IAAI,KAAK,CAAC,gDAAgD,MAAM,mDAAmD,CAAC,CAAC;QAC7H,CAAC;QAED,MAAM,IAAI,KAAK,CAAC,oGAAoG,CAAC,CAAC;IACxH,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,SAAS,CAAC,OAAe,EAAE,OAAyB;QACxD,MAAM,IAAI,KAAK,CAAC,uFAAuF,CAAC,CAAC;IAC3G,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,cAAc,CAAC,IAAY;QAC/B,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,iBAAiB,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC;YACpD,OAAO,MAAM,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;QAC9C,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,QAAQ,CAAC,8BAA8B,EAAE,KAAK,CAAC,CAAC;YAChD,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,aAAa,CAAC,GAAW;QAC7B,IAAI,CAAC;YACH,MAAM,OAAO,GAAG,MAAM,IAAI,CAAC,MAAM,CAAC,IAAI,GAAG,QAAQ,EAAE,EAAE,UAAU,EAAE,CAAC,EAAE,CAAC,CAAC;YACtE,OAAO,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;QAChD,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,QAAQ,CAAC,yCAAyC,EAAE,KAAK,CAAC,CAAC;YAC3D,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IAED;;OAEG;IACH,oBAAoB;QAClB,OAAO,IAAI,CAAC,WAAW,CAAC,SAAS,EAAE,CAAC;IACtC,CAAC;IAED;;OAEG;IACH,KAAK,CAAC,cAAc;QAClB,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;YACjB,OAAO,IAAI,CAAC,CAAC,sBAAsB;QACrC,CAAC;QAED,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,MAAM,CAAC,MAAM,EAAE,EAAE,UAAU,EAAE,CAAC,EAAE,CAAC,CAAC;YAC7C,OAAO,IAAI,CAAC;QACd,CAAC;QAAC,OAAO,KAAU,EAAE,CAAC;YACpB,uBAAuB;YACvB,IAAI,KAAK,CAAC,QAAQ,EAAE,MAAM,KAAK,GAAG,IAAI,KAAK,CAAC,QAAQ,EAAE,MAAM,KAAK,GAAG,EAAE,CAAC;gBACrE,OAAO,KAAK,CAAC;YACf,CAAC;YACD,uBAAuB;YACvB,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;CACF"}
|
|
@@ -0,0 +1,66 @@
|
|
|
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 { PaperSource, SearchOptions, DownloadOptions, PlatformCapabilities } from './PaperSource.js';
|
|
6
|
+
import { Paper } from '../models/Paper.js';
|
|
7
|
+
export declare class SciHubSearcher extends PaperSource {
|
|
8
|
+
private mirrorSites;
|
|
9
|
+
private currentMirrorIndex;
|
|
10
|
+
private axiosInstance;
|
|
11
|
+
private readonly maxRetries;
|
|
12
|
+
private readonly mirrorTestTimeout;
|
|
13
|
+
private lastHealthCheck;
|
|
14
|
+
private readonly healthCheckInterval;
|
|
15
|
+
constructor();
|
|
16
|
+
getCapabilities(): PlatformCapabilities;
|
|
17
|
+
/**
|
|
18
|
+
* 检测所有镜像站点的健康状态
|
|
19
|
+
*/
|
|
20
|
+
private checkMirrorHealth;
|
|
21
|
+
/**
|
|
22
|
+
* 获取当前可用的镜像站点
|
|
23
|
+
*/
|
|
24
|
+
private getCurrentMirror;
|
|
25
|
+
/**
|
|
26
|
+
* 标记镜像站点失败并切换到下一个
|
|
27
|
+
*/
|
|
28
|
+
private markMirrorFailed;
|
|
29
|
+
/**
|
|
30
|
+
* 通过 DOI 或 URL 搜索论文
|
|
31
|
+
*/
|
|
32
|
+
search(query: string, options?: SearchOptions): Promise<Paper[]>;
|
|
33
|
+
/**
|
|
34
|
+
* 验证输入是否为有效的 DOI 或 URL
|
|
35
|
+
*/
|
|
36
|
+
private isValidDOIOrURL;
|
|
37
|
+
/**
|
|
38
|
+
* 从 Sci-Hub 获取论文信息
|
|
39
|
+
*/
|
|
40
|
+
private fetchPaperInfo;
|
|
41
|
+
/**
|
|
42
|
+
* 下载 PDF 文件
|
|
43
|
+
*/
|
|
44
|
+
downloadPdf(paperId: string, options?: DownloadOptions): Promise<string>;
|
|
45
|
+
/**
|
|
46
|
+
* 读取论文内容(Sci-Hub 不提供文本提取)
|
|
47
|
+
*/
|
|
48
|
+
readPaper(paperId: string, options?: DownloadOptions): Promise<string>;
|
|
49
|
+
/**
|
|
50
|
+
* 根据 DOI 获取论文
|
|
51
|
+
*/
|
|
52
|
+
getPaperByDoi(doi: string): Promise<Paper | null>;
|
|
53
|
+
/**
|
|
54
|
+
* 获取镜像站点状态
|
|
55
|
+
*/
|
|
56
|
+
getMirrorStatus(): {
|
|
57
|
+
url: string;
|
|
58
|
+
status: string;
|
|
59
|
+
responseTime?: number;
|
|
60
|
+
}[];
|
|
61
|
+
/**
|
|
62
|
+
* 手动触发健康检查
|
|
63
|
+
*/
|
|
64
|
+
forceHealthCheck(): Promise<void>;
|
|
65
|
+
}
|
|
66
|
+
//# sourceMappingURL=SciHubSearcher.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"SciHubSearcher.d.ts","sourceRoot":"","sources":["../../src/platforms/SciHubSearcher.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAMH,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE,eAAe,EAAE,oBAAoB,EAAE,MAAM,kBAAkB,CAAC;AACrG,OAAO,EAAE,KAAK,EAAgB,MAAM,oBAAoB,CAAC;AAYzD,qBAAa,cAAe,SAAQ,WAAW;IAC7C,OAAO,CAAC,WAAW,CAAe;IAClC,OAAO,CAAC,kBAAkB,CAAa;IACvC,OAAO,CAAC,aAAa,CAAgB;IACrC,OAAO,CAAC,QAAQ,CAAC,UAAU,CAAa;IACxC,OAAO,CAAC,QAAQ,CAAC,iBAAiB,CAAiC;IACnE,OAAO,CAAC,eAAe,CAAqB;IAC5C,OAAO,CAAC,QAAQ,CAAC,mBAAmB,CAAkB;;IAoCtD,eAAe,IAAI,oBAAoB;IAWvC;;OAEG;YACW,iBAAiB;IAkE/B;;OAEG;YACW,gBAAgB;IAsB9B;;OAEG;YACW,gBAAgB;IAwB9B;;OAEG;IACG,MAAM,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,aAAa,GAAG,OAAO,CAAC,KAAK,EAAE,CAAC;IAmBtE;;OAEG;IACH,OAAO,CAAC,eAAe;IAevB;;OAEG;YACW,cAAc;IA0G5B;;OAEG;IACG,WAAW,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,eAAe,GAAG,OAAO,CAAC,MAAM,CAAC;IAqE9E;;OAEG;IACG,SAAS,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,eAAe,GAAG,OAAO,CAAC,MAAM,CAAC;IAM5E;;OAEG;IACG,aAAa,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,KAAK,GAAG,IAAI,CAAC;IAIvD;;OAEG;IACH,eAAe,IAAI;QAAE,GAAG,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAC;QAAC,YAAY,CAAC,EAAE,MAAM,CAAA;KAAE,EAAE;IAQ3E;;OAEG;IACG,gBAAgB,IAAI,OAAO,CAAC,IAAI,CAAC;CAGxC"}
|