NatureSearchPageProcessor.java
11.1 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
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
package com.canrd.webmagic.processor;
import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import com.baomidou.mybatisplus.core.toolkit.CollectionUtils;
import com.canrd.webmagic.common.utils.DateUtil;
import com.canrd.webmagic.common.utils.KeywordUtil;
import com.canrd.webmagic.common.utils.StringUtils;
import com.canrd.webmagic.domain.ArticleTypeEnum;
import com.canrd.webmagic.domain.dto.ArticleDO;
import com.canrd.webmagic.processor.config.Agent;
import com.canrd.webmagic.processor.pipeline.ArticlePipeline;
import lombok.extern.slf4j.Slf4j;
import org.springframework.stereotype.Component;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.processor.PageProcessor;
import us.codecraft.webmagic.selector.Html;
import us.codecraft.webmagic.selector.Selectable;
import us.codecraft.webmagic.selector.XpathSelector;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.*;
import java.util.stream.Collectors;
/**
* @author: xms
* @description: TODO
* @date: 2024/4/1 14:19
* @version: 1.0
*/
@Slf4j
@Component
public class NatureSearchPageProcessor implements PageProcessor {
private String agent = Agent.getRandom();
// 抓取网站的相关配置，包括编码、抓取间隔、重试次数等
private Site site = Site.me().setRetryTimes(3).setSleepTime(100);
/**
* 定制爬虫逻辑的核心接口，在这里编写抽取逻辑
*
* @param page
*/
@Override
public void process(Page page) {
if (page.getUrl().get().contains("search")) {
doArticleList(page);
} else if (page.getUrl().get().contains("research-articles")) {
doArticleList4ReSearch(page);
} else if (page.getUrl().get().contains("/articles?searchType=journalSearch")) {
doArticleList4ReSearch(page);
}else {
doArticleContent(page);
}
}
/**
* @param page
*/
private void doArticleList4ReSearch(Page page) {
String url = page.getUrl().get();
/**
* 通过page.getHtml()可以获取到main函数中Spider.create(new BaiduHotSearchPageProcessor()).addUrl中的地址的网页内容
* 1、通过$或css()方法获取到该page html下某元素dom
*/
Selectable selectable = page.getHtml().$(".app-article-list-row").select(
new XpathSelector("li[@class='app-article-list-row__item']")
);
List<Selectable> nodes = selectable.nodes();
/**
* 获取到指定的dom后，从这些dom中提取元素内容。
*/
for (int i = 1; i <= nodes.size() - 1; i++) {
Selectable node = nodes.get(i).$(".u-full-height").nodes().get(2).nodes().get(0).$(".u-full-height").select(new XpathSelector("a[@class='c-card__link u-link-inherit']")).nodes().get(0);
String link = node.$("a", "href").get();
String title = node.$("a", "text").get();
if (KeywordUtil.containKeywordsInTitle(title)) {
page.addTargetRequest(link);
log.info("research文章列表链接：{},标题:{},文章链接：{}", url, title, link);
}
}
}
/**
* @param page
*/
private void doArticleContent(Page page) {
if (page.getUrl().get().contains("redirect") || !page.getUrl().get().contains("nature")) {
return;
}
//解析页面
Html html = page.getHtml();
String articleCode = page.getUrl().get();
Selectable headSelectable = html.xpath("//div[@class='c-article-header']/header");
List<Selectable> authorEmailSelectables = html.xpath("//p[@id='corresponding-author-list']/a").nodes();
Selectable referencesSelectable = html.xpath("//ol[@class='c-article-references']").select(new XpathSelector("li[@class='c-article-references__item js-c-reading-companion-references-item']"));
Selectable authorAddressSelectable = html.xpath("//ol[@class='c-article-author-affiliation__list']").select(new XpathSelector("li"));
String title = headSelectable.xpath("//div/h1/text()").get();
if (StringUtils.isBlank(title)) {
title = headSelectable.xpath("//h1/text()").get();
}
String articleDesc = html.xpath("//div[@class='c-article-section__content']/p/text()").get();
String publishTime;
Date publishTimeDateTime = null;
try {
publishTime = headSelectable.xpath("//ul").nodes().get(0).xpath("//li").nodes().get(2).xpath("//li/time/text()").get();
} catch (Exception e) {
try {
publishTime = headSelectable.xpath("//ul").nodes().get(0).xpath("//li").nodes().get(1).xpath("//li/time/text()").get();
} catch (Exception e1) {
publishTime = headSelectable.xpath("//ul").nodes().get(0).xpath("//li").nodes().get(0).xpath("//li/time/text()").get();
}
}
SimpleDateFormat formatter = new SimpleDateFormat("dd MMMM yyyy", Locale.ENGLISH);
try {
publishTimeDateTime = formatter.parse(publishTime);
} catch (ParseException e) {
e.printStackTrace();
}
Selectable authorSelectable = headSelectable.xpath("//ul").nodes().get(1).select(new XpathSelector("li[@class='c-article-author-list__item']"));
List<Selectable> authorNodes = authorSelectable.nodes();
StringBuffer authorName = new StringBuffer();
for (Selectable node : authorNodes) {
authorName.append(node.xpath("//a/text()"));
}
JSONArray authorAddress = new JSONArray();
List<Selectable> authorAddressList = authorAddressSelectable.nodes();
if (CollectionUtils.isNotEmpty(authorAddressList)) {
for (Selectable selectable : authorAddressList) {
String address = selectable.xpath("//p").xpath("//p[@class='c-article-author-affiliation__address']/text()").get();
String authorNames = selectable.xpath("//p").xpath("//p[@class='c-article-author-affiliation__authors-list']/text()").get();
JSONObject object = new JSONObject();
object.put("address", address);
object.put("authorNames", authorNames);
authorAddress.add(object);
}
}
JSONArray references = new JSONArray();
List<Selectable> referenceList = referencesSelectable.nodes();
if (CollectionUtils.isNotEmpty(referenceList)) {
for (Selectable reference : referenceList) {
String referenceTitle = reference.xpath("//p").xpath("//p[@class='c-article-references__text']/text()").get();
List<Selectable> referenceLinks = reference.xpath("//p").xpath("//p[@class='c-article-references__links u-hide-print']").links().nodes();
List<String> links = new ArrayList<>();
if (CollectionUtils.isNotEmpty(referenceLinks)) {
links = referenceLinks.stream().map(x -> x.get()).collect(Collectors.toList());
}
JSONObject object = new JSONObject();
object.put("referenceTitle", referenceTitle);
object.put("links", links);
// if (CollectionUtils.isNotEmpty(links)) {
// page.addTargetRequests(links.stream().filter(x -> x.contains("nature")).collect(Collectors.toList()));
// }
references.add(object);
}
}
JSONArray authorEmail = new JSONArray();
for (Selectable authorEmailSelectable : authorEmailSelectables) {
String[] split = authorEmailSelectable.xpath("//a").links().get().split(":");
String email = Objects.isNull(split) ? "" : split[split.length - 1];
String authorEmailName = authorEmailSelectable.xpath("//a/text()").get();
JSONObject jsonObject = new JSONObject();
jsonObject.put("authorEmailName", authorEmailName);
jsonObject.put("email", email);
authorEmail.add(jsonObject);
}
log.info("文章链接：{},发布时间:{},标题:{},作者:{},邮箱信息:{}", articleCode, publishTime, title, authorEmail.toJSONString());
page.putField("article", ArticleDO.builder()
.articleType(ArticleTypeEnum.NATURE.getType())
.articleCode(articleCode)
.authorName(authorName.toString())
.title(title)
.publishTime(Objects.isNull(publishTimeDateTime) ? publishTime : DateUtil.format(publishTimeDateTime, DateUtil.DATE))
.emailInfo(authorEmail.toJSONString())
.articleDesc(articleDesc)
.authorAddress(authorAddress.toJSONString())
.referenceInfo(references.toJSONString()).build());
}
private void doArticleList(Page page) {
String url = page.getUrl().get();
/**
* 通过page.getHtml()可以获取到main函数中Spider.create(new BaiduHotSearchPageProcessor()).addUrl中的地址的网页内容
* 1、通过$或css()方法获取到该page html下某元素dom
*/
Selectable selectable = page.getHtml().$(".app-article-list-row").select(
new XpathSelector("li[@class='app-article-list-row__item']")
);
List<Selectable> nodes = selectable.nodes();
/**
* 获取到指定的dom后，从这些dom中提取元素内容。
*/
for (int i = 0; i <= nodes.size() - 1; i++) {
Selectable node = nodes.get(i).$(".u-full-height").nodes().get(2).nodes().get(0).$(".u-full-height").select(new XpathSelector("a[@class='c-card__link u-link-inherit']")).nodes().get(0);
String link = node.links().get();
String title = node.$("a", "text").get();
if (KeywordUtil.containKeywordsInTitle(title)) {
String publishTime = nodes.get(i).xpath("//div[@class='c-card__section c-meta']/time/text()").get();
SimpleDateFormat formatter = new SimpleDateFormat("dd MMMM yyyy", Locale.ENGLISH);
try {
Date publishTimeDateTime = formatter.parse(publishTime);
if (!publishTimeDateTime.before(DateUtil.localDate2Date(DateUtil.parseDate("2000-01-01", DateUtil.DATE)))) {
page.addTargetRequest(link);
log.info("关键字文章列表链接：{},标题:{},文章链接：{}", url, title, link);
}
} catch (ParseException e) {
e.printStackTrace();
}
}
}
}
@Override
public Site getSite() {
return site;
}
public static void main(String[] args) {
// 创建一个Spider，并把我们的处理器放进去
Spider.create(new NatureSearchPageProcessor())
// 添加这个Spider要爬取的网页地址
.addUrl("https://www.nature.com/nature/research-articles?sort=PubDate&page=1")
.addPipeline(new ArticlePipeline())
// 开启5个线程执行，并开始爬取
.thread(5).run();
}
}