Blame view

src/main/java/com/canrd/webmagic/processor/NatureSearchPageProcessor.java 10.9 KB
谢茂盛 authored
1
2
package com.canrd.webmagic.processor;
谢茂盛 authored
3
4
import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
谢茂盛 authored
5
import com.baomidou.mybatisplus.core.toolkit.CollectionUtils;
谢茂盛 authored
6
import com.canrd.webmagic.common.utils.DateUtil;
谢茂盛 authored
7
import com.canrd.webmagic.common.utils.KeywordUtil;
谢茂盛 authored
8
import com.canrd.webmagic.common.utils.StringUtils;
谢茂盛 authored
9
10
import com.canrd.webmagic.domain.ArticleTypeEnum;
import com.canrd.webmagic.domain.dto.ArticleDO;
11
import com.canrd.webmagic.processor.config.Agent;
谢茂盛 authored
12
import com.canrd.webmagic.processor.pipeline.ArticlePipeline;
谢茂盛 authored
13
import lombok.extern.slf4j.Slf4j;
14
import org.springframework.stereotype.Component;
谢茂盛 authored
15
16
17
18
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.processor.PageProcessor;
谢茂盛 authored
19
import us.codecraft.webmagic.selector.Html;
谢茂盛 authored
20
21
22
import us.codecraft.webmagic.selector.Selectable;
import us.codecraft.webmagic.selector.XpathSelector;
谢茂盛 authored
23
24
25
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.*;
谢茂盛 authored
26
import java.util.stream.Collectors;
谢茂盛 authored
27
28
29
30
31
32
33

/**
 * @author: xms
 * @description: TODO
 * @date: 2024/4/1 14:19
 * @version: 1.0
 */
谢茂盛 authored
34
@Slf4j
35
@Component
谢茂盛 authored
36
public class NatureSearchPageProcessor implements PageProcessor {
37
    private String agent = Agent.getRandom();
谢茂盛 authored
38
39

    // 抓取网站的相关配置,包括编码、抓取间隔、重试次数等
谢茂盛 authored
40
    private Site site = Site.me().setRetryTimes(3).setSleepTime(100);
谢茂盛 authored
41
42
43
44
45
46
47
48

    /**
     * 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) {
49
        if (page.getUrl().get().contains("search")) {
谢茂盛 authored
50
            doArticleList(page);
谢茂盛 authored
51
52
        } else if (page.getUrl().get().contains("research-articles")) {
            doArticleList4ReSearch(page);
谢茂盛 authored
53
        } else {
谢茂盛 authored
54
55
56
57
58
            doArticleContent(page);
        }

    }
谢茂盛 authored
59
60
61
    /**
     * @param page
     */
谢茂盛 authored
62
    private void doArticleList4ReSearch(Page page) {
谢茂盛 authored
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
        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();
谢茂盛 authored
80
81
82
83
            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);
            }
谢茂盛 authored
84
85
86
        }
    }
谢茂盛 authored
87
88
89
    /**
     * @param page
     */
谢茂盛 authored
90
    private void doArticleContent(Page page) {
谢茂盛 authored
91
92
93
        if (page.getUrl().get().contains("redirect") || !page.getUrl().get().contains("nature")) {
            return;
        }
谢茂盛 authored
94
95
        //解析页面
        Html html = page.getHtml();
谢茂盛 authored
96
        String articleCode = page.getUrl().get();
谢茂盛 authored
97
98
        Selectable headSelectable = html.xpath("//div[@class='c-article-header']/header");
        List<Selectable> authorEmailSelectables = html.xpath("//p[@id='corresponding-author-list']/a").nodes();
谢茂盛 authored
99
100
        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"));
谢茂盛 authored
101
102
103
104
105

        String title = headSelectable.xpath("//div/h1/text()").get();
        if (StringUtils.isBlank(title)) {
            title = headSelectable.xpath("//h1/text()").get();
        }
谢茂盛 authored
106
        String articleDesc = html.xpath("//div[@class='c-article-section__content']/p/text()").get();
107
        String publishTime;
谢茂盛 authored
108
        Date publishTimeDateTime = null;
109
110
        try {
            publishTime = headSelectable.xpath("//ul").nodes().get(0).xpath("//li").nodes().get(2).xpath("//li/time/text()").get();
谢茂盛 authored
111
        } catch (Exception e) {
112
113
            try {
                publishTime = headSelectable.xpath("//ul").nodes().get(0).xpath("//li").nodes().get(1).xpath("//li/time/text()").get();
谢茂盛 authored
114
            } catch (Exception e1) {
115
116
117
                publishTime = headSelectable.xpath("//ul").nodes().get(0).xpath("//li").nodes().get(0).xpath("//li/time/text()").get();
            }
        }
谢茂盛 authored
118
119
120
121
122
123
124
        SimpleDateFormat formatter = new SimpleDateFormat("dd MMMM yyyy", Locale.ENGLISH);

        try {
            publishTimeDateTime = formatter.parse(publishTime);
        } catch (ParseException e) {
            e.printStackTrace();
        }
谢茂盛 authored
125
126
        Selectable authorSelectable = headSelectable.xpath("//ul").nodes().get(1).select(new XpathSelector("li[@class='c-article-author-list__item']"));
        List<Selectable> authorNodes = authorSelectable.nodes();
谢茂盛 authored
127
        StringBuffer authorName = new StringBuffer();
谢茂盛 authored
128
        for (Selectable node : authorNodes) {
谢茂盛 authored
129
130
            authorName.append(node.xpath("//a/text()"));
        }
谢茂盛 authored
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

        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();
谢茂盛 authored
166
167
168
169
170
171
172
        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);
谢茂盛 authored
173
            authorEmail.add(jsonObject);
谢茂盛 authored
174
        }
谢茂盛 authored
175
        log.info("文章链接:{},发布时间:{},标题:{},作者:{},邮箱信息:{}", articleCode, publishTime, title, authorEmail.toJSONString());
176
谢茂盛 authored
177
178
        page.putField("article", ArticleDO.builder()
                .articleType(ArticleTypeEnum.NATURE.getType())
179
180
181
                .articleCode(articleCode)
                .authorName(authorName.toString())
                .title(title)
谢茂盛 authored
182
                .publishTime(Objects.isNull(publishTimeDateTime) ? publishTime : DateUtil.format(publishTimeDateTime, DateUtil.DATE))
谢茂盛 authored
183
184
185
186
                .emailInfo(authorEmail.toJSONString())
                .articleDesc(articleDesc)
                .authorAddress(authorAddress.toJSONString())
                .referenceInfo(references.toJSONString()).build());
谢茂盛 authored
187
    }
谢茂盛 authored
188
谢茂盛 authored
189
190
    private void doArticleList(Page page) {
        String url = page.getUrl().get();
谢茂盛 authored
191
192
193
194
195
196
197
198
199
200
201
202
        /**
         * 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。
         */
谢茂盛 authored
203
        for (int i = 0; i <= nodes.size() - 1; i++) {
谢茂盛 authored
204
            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);
谢茂盛 authored
205
            String link = node.links().get();
谢茂盛 authored
206
            String title = node.$("a", "text").get();
谢茂盛 authored
207
            if (KeywordUtil.containKeywordsInTitle(title)) {
谢茂盛 authored
208
209
210
211
212
213
214
215
216
217
218
219
                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();
                }
谢茂盛 authored
220
            }
谢茂盛 authored
221
谢茂盛 authored
222
223
224
225
226
227
228
229
230
231
232
233
        }
    }

    @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
谢茂盛 authored
234
                .addUrl("https://www.nature.com/nature/research-articles?sort=PubDate&page=1")
谢茂盛 authored
235
                .addPipeline(new ArticlePipeline())
谢茂盛 authored
236
237
238
239
                // 开启5个线程执行,并开始爬取
                .thread(5).run();
    }
}