NatureController.java
3.47 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
package com.canrd.webmagic.controller;
import com.canrd.webmagic.common.constant.ServerResult;
import com.canrd.webmagic.common.utils.KeywordUtil;
import com.canrd.webmagic.common.utils.StringUtils;
import com.canrd.webmagic.processor.NatureSearchPageProcessor;
import com.canrd.webmagic.processor.download.Downloader;
import com.canrd.webmagic.processor.pipeline.ArticlePipeline;
import org.apache.logging.log4j.core.util.UuidUtil;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RequestParam;
import org.springframework.web.bind.annotation.RestController;
import us.codecraft.webmagic.Spider;
import javax.annotation.Resource;
/**
* nature-文章信息(NatureArticle)表控制层
*
* @author makejava
* @since 2024-04-07 18:39:41
*/
@RestController
@RequestMapping("/nature/article")
public class NatureController {
@Resource
private NatureSearchPageProcessor natureSearchPageProcessor;
@Resource
private ArticlePipeline articlePipeline;
@Resource
private Downloader downloader;
/**
* @return
*/
@GetMapping("/start")
public ServerResult start(@RequestParam(value = "indexSize") Integer indexSize) {
for (int i = 1; i <= indexSize; i++) {
Spider.create(natureSearchPageProcessor)
.addUrl("https://www.nature.com/nature/research-articles?sort=PubDate&page=" + i)
.addUrl("https://www.nature.com/nature/articles?searchType=journalSearch&sort=PubDate&type=article&page=" + i)
.addUrl("https://www.nature.com/nenergy/research-articles?searchType=journalSearch&sort=PubDate&page=" + i)
.addUrl("https://www.nature.com/nmat/articles?searchType=journalSearch&sort=PubDate&page=" + i)
.addUrl("https://www.nature.com/ncomms/articles?searchType=journalSearch&sort=PubDate&type=editorial&page=" + i)
.addPipeline(articlePipeline)
// .setDownloader(downloader.newIpDownloader())
// 开启5个线程执行，并开始爬取
.thread(20).run();
}
return ServerResult.success();
}
/**
* journal: natcomputsci/nnano/nphys/nmeth
*
* @return
*/
@GetMapping("/search")
public ServerResult search(@RequestParam(value = "indexSize") Integer indexSize,
@RequestParam(value = "orderBy") String orderBy,
@RequestParam(value = "journal") String journal) {
StringBuffer url = new StringBuffer("https://www.nature.com/search?q=");
for (int i = 1; i <= indexSize; i++) {
for (String keyword : KeywordUtil.getKeyWordList()) {
if (StringUtils.isBlank(orderBy)) {
url.append(keyword).append("&page=" + i);
} else {
url.append(keyword).append("&order=" + orderBy).append("&page=" + i);
}
if (StringUtils.isNotBlank(journal)) {
url.append("&journal=" + journal);
}
Spider.create(natureSearchPageProcessor)
.addUrl(url.toString())
// 开启5个线程执行，并开始爬取
.setUUID(UuidUtil.getTimeBasedUuid().toString())
.thread(5).run();
}
}
return ServerResult.success();
}
}