java编写的一段简单的网络爬虫demo代码

功能：

从网站上下载附件，并从页面中提取页面文章内容

关于NIO

在大多数情况下，Java 应用程序并非真的受着 I/O 的束缚。操作系统并非不能快速传送
数据，让 Java 有事可做；相反，是 JVM 自身在 I/O 方面效率欠佳。操作系统与 Java 基于流的 I/O
模型有些不匹配。操作系统要移动的是大块数据（缓冲区），这往往是在硬件直接存储器存取
（DMA）的协助下完成的。而 JVM 的 I/O 类喜欢操作小块数据——单个字节、几行文本。结果，
操作系统送来整缓冲区的数据，java.io 的流数据类再花大量时间把它们拆成小块，往往拷贝一
个小块就要往返于几层对象。操作系统喜欢整卡车地运来数据，java.io 类则喜欢一铲子一铲子
地加工数据。有了 NIO，就可以轻松地把一卡车数据备份到您能直接使用的地方（ByteBuffer 对
象）。

以下代码使用了Java NIO以便提高文件读写效率。java NIO与原始IO差别，可以阅读《Java NIO》中文版了解。

使用Xpath抓取文章中特定dom节点的内容。

代码如下（已测试，可用，注意修改具体被爬行网站的接口）：

import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.common.collect.ImmutableMap;
import com.google.common.io.ByteStreams;
import lombok.extern.slf4j.Slf4j;
import org.apache.commons.collections4.MapUtils;
import org.apache.commons.lang3.RegExUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.NameValuePair;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.conn.ssl.SSLConnectionSocketFactory;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClientBuilder;
import org.apache.http.message.BasicNameValuePair;
import org.apache.http.ssl.SSLContextBuilder;
import org.apache.http.util.EntityUtils;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.InputSource;

import javax.net.ssl.SSLContext;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathExpressionException;
import javax.xml.xpath.XPathFactory;
import java.io.BufferedWriter;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.StringReader;
import java.nio.ByteBuffer;
import java.nio.channels.FileChannel;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.nio.file.StandardOpenOption;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.LinkedHashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.StringJoiner;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

@Slf4j
public class Main {
    private static Pattern pattern = Pattern.compile("<div class=\"frame_subhead\">[\\s\\S]*?</div>");
    private static Pattern pattern2 = Pattern.compile("<table class=\"form_table\">[\\s\\S]*?</table>");

    String base = "http://172.16.3.122:9000";

    Set<String> attachments = new LinkedHashSet<>();

    public static void main(String[] args) throws IOException {

        Main bootstrap = new Main();

        String jsonArray = bootstrap.getResponseBody("http://172.16.3.122:9000/pdfs");

        log.info("爬虫程序已启动...");

        bootstrap.attachments.addAll(
                bootstrap.getAttachments(jsonArray)
        );

        boolean succeed = bootstrap.login("admin", "123456");

        log.info("正在登陆网站获取cookie...");

        if (succeed) {
            List<String> sites = bootstrap.list();
            sites.forEach(site -> {
                try {
                    bootstrap.crawl(site);
                } catch (IOException | XPathExpressionException e) {
                    log.error("出错网站:{},{}",site,e);
                    System.err.println("出错网站:"+site);
                    e.printStackTrace();
                }
            });

        }
    }

    List<String> getAttachments(String rawArray) throws IOException {
        ObjectMapper objectMapper = new ObjectMapper();
        String[] attachments = objectMapper.readValue(rawArray, String[].class);
        return Arrays.asList(attachments);
    }

    void crawl(String site) throws IOException, XPathExpressionException {

        Path path = Paths.get(String.format("d:/download/%s", site));
        char[] chars = path.getFileName().toFile().getName().toCharArray();

        if ((int) chars[0] != 8195) {

            if (!Files.exists(path)) {
                Files.createDirectories(path);
            }

            downloadAttachment(site);

            List<Integer> array = Arrays.asList(3, 5, 6,7, 8);
            for (int i = 1; i <= 11; i++) {
                ///昆山吉山会津塑料工业股份有限公司/html/1.html
                String url = String.format("%s/%s/html/%d.html", base, site, i);
                String html = getResponseBody(url);
                if (StringUtils.isNotBlank(html)) {
                    String pattern = "tabContent_" + i;
                    int start = html.indexOf(pattern);
                    String title = extractSubTitle(start, html);
                    Path file = Paths.get(String.format("d:/download/%s/%s.txt", site, title));
                    if (array.contains(i)) {
                        saveFile(start, file, html);
                    }
                }
            }
        }
    }

    void xQuery(String text,Path path) throws IOException, XPathExpressionException {
        String xml = text.substring(text.indexOf("<tbody>"));

        StringJoiner joiner = new StringJoiner("","<root>","</root>");
        InputSource inputXML = new InputSource( new StringReader( joiner.add(xml).toString() ) );

        XPath xPath = XPathFactory.newInstance().newXPath();

        NodeList tBodyNodes = (NodeList) xPath.evaluate("/root/tbody", inputXML, XPathConstants.NODESET);

        try (BufferedWriter writer = Files.newBufferedWriter(path, Charset.defaultCharset(), StandardOpenOption.CREATE)) {
            for (int i = 0; i < tBodyNodes.getLength(); i++) {
                Node node = tBodyNodes.item(i);

                NodeList trNodes = (NodeList) xPath.evaluate("tr", node, XPathConstants.NODESET);
                for (int k = 0; k < trNodes.getLength(); k++) {

                    NodeList childList = (NodeList) xPath.evaluate("td", trNodes.item(k), XPathConstants.NODESET);
                    for (int j = 0; j < childList.getLength(); j++) {
                        Node child = childList.item(j);
                        String content = child.getTextContent();

                        writer.write(content);
                        if (j <childList.getLength() - 1) {
                            writer.write("\t");
                        }
                    }
                    writer.write("\r\n");
                }

                writer.write("\r\n");
            }
        }
    }

    void saveFile(int start,Path path, String html) throws XPathExpressionException, IOException {
        Matcher matcher = pattern2.matcher(html);
        int step = 0;
        String tableText = "";
        while (step++ < 1 && matcher.find(start)) {
            tableText = RegExUtils.replacePattern(matcher.group(), "<table class=\"form_table\">|</table>", "").trim();
        }
        xQuery(tableText,path);
    }

    void downloadAttachment(String site) {
        List<String> list = attachments.stream().filter(name -> name.startsWith(site)).collect(Collectors.toList());

        list.forEach(name -> {

            String filename = name.substring(name.lastIndexOf("/") + 1);
            log.info("正在下载 --{} -附件:{}", site, filename);

            String url = base + "/" + name;
            String dest = "d:/download/" + site + "/" + filename;

            Path file = Paths.get(dest).toAbsolutePath().normalize();

            if (!Files.exists(file)) {

                Path path = file.getParent();

                if (!Files.exists(path)) {
                    log.info("首次下载,正在创建目录:{}",path);
                    try {
                        Files.createDirectories(path);
                    } catch (IOException e) {
                        log.error("目录创建失败:{}",e);
                    }
                }

                log.info("正在保存采集来的附件,保存到:{}",file);
                try (FileChannel fc = new FileOutputStream(dest).getChannel()) {
                    ByteBuffer buffer = getResponseAttachment(url);
                    fc.write(buffer);
                    log.info("文件{}已经成功保存",file);
                } catch (IOException e) {
                    log.error("文件{}保存出错:{}",file,e);
                }
            }
        });

    }

    List<String> list() throws IOException {
        String url = base + "/%E5%88%97%E8%A1%A8%E9%A1%B5%E9%9D%A2/%E6%B1%9F%E8%8B%8F%E7%9C%81%E9%AB%98%E6%96%B0%E6%8A%80%E6%9C%AF%E4%BC%81%E4%B8%9A%E8%BE%85%E5%8A%A9%E6%9D%90%E6%96%99%E6%8F%90%E4%BA%A4%E7%B3%BB%E7%BB%9F_files/Dir_Main.html";
        return Files.list(Paths.get("E:\\pdf"))
                .map(path -> path.getFileName().toFile().getName())
                .filter(path -> (!path.startsWith(" ")) && !path.startsWith("　"))
                .filter(dirName -> {
                    return !Arrays.asList("登录网页", "列表页面").contains(dirName);
                }).collect(Collectors.toList());
    }

    boolean login(String username, String password) {
        String url = base + "/index.html";
        ImmutableMap<String, String> map = ImmutableMap.<String, String>builder()
                .put("username", "admin")
                .put("password", "123456")
                .build();
        try {
            HttpResponse response = doPost(url, null, map);
            return true;
        } catch (IOException e) {
            log.error("登录出错:{}", e);
            ;
            return false;
        }
    }

    /**
     * 信任SSL证书
     *
     * @return
     */
    public CloseableHttpClient buildDefaultHttpClientTrustSSL() {
        SSLContext sslContext = null;
        try {
            sslContext = SSLContextBuilder.create().useProtocol(SSLConnectionSocketFactory.SSL).loadTrustMaterial((x, y) -> true).build();
        } catch (Exception e) {
            e.printStackTrace();
        }
        RequestConfig config = RequestConfig.custom()
                .setSocketTimeout(30000)
                .setConnectTimeout(30000)
                .setConnectionRequestTimeout(30000)
                .setContentCompressionEnabled(true)
                .build();
        return HttpClientBuilder.create().setDefaultRequestConfig(config).setSSLContext(sslContext).setSSLHostnameVerifier((x, y) -> true).build();
    }

    /***
     * 从响应的报文中提取网站标题
     * @param responseBody
     * @return
     */
    public String extractSubTitle(int start, String responseBody) {
        Matcher matcher = pattern.matcher(responseBody);
        int i = 0;
        String subHead = "";
        while (i++ < 1 && matcher.find(start)) {
            subHead = StringUtils.replacePattern(matcher.group(), "<div class=\"frame_subhead\">|</div>", "").trim();
        }

        int offset1 = subHead.indexOf("、");
        if (offset1 >= 0) {
            subHead = subHead.substring(offset1 + 1);
        }

        return subHead;

    }

    public String extract(String body, String pattern) {
        Pattern regex = Pattern.compile(pattern);
        return "";
    }

    HttpResponse doGet(String url, Map<String, String> headerRefs) throws IOException {
        //巡检时更改为信任证书
        CloseableHttpClient httpClient = buildDefaultHttpClientTrustSSL();

        HttpGet httpGet = new HttpGet(url);
        httpGet.addHeader("User-Agent", "Mozilla/5.0 (Windows NT 6.1; Win64; x64)spider");
        httpGet.addHeader("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8");
        httpGet.addHeader("Accept-Encoding", "gzip, deflate");
        httpGet.addHeader("Accept-Language", "zh-CN,zh;q=0.9");

        if (MapUtils.isNotEmpty(headerRefs)) {
            for (Map.Entry<String, String> entry : headerRefs.entrySet()) {
                String name = entry.getKey();
                String value = entry.getValue();
                httpGet.setHeader(name, value);
            }
        }

        return httpClient.execute(httpGet);
    }

    HttpResponse doPost(String url, Map<String, String> headerRefs, Map<String, String> data) throws IOException {
        //巡检时更改为信任证书
        CloseableHttpClient httpClient = buildDefaultHttpClientTrustSSL();

        HttpPost httpPost = new HttpPost(url);
        httpPost.addHeader("User-Agent", "Mozilla/5.0 (Windows NT 6.1; Win64; x64) spider");
        httpPost.addHeader("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8");
        httpPost.addHeader("Accept-Encoding", "gzip, deflate");
        httpPost.addHeader("Accept-Language", "zh-CN,zh;q=0.9");

        if (MapUtils.isNotEmpty(headerRefs)) {
            for (Map.Entry<String, String> entry : headerRefs.entrySet()) {
                String name = entry.getKey();
                String value = entry.getValue();
                httpPost.setHeader(name, value);
            }
        }

        if (MapUtils.isNotEmpty(data)) {

            List<NameValuePair> nvps = new ArrayList<NameValuePair>();

            for (Map.Entry<String, String> entry : data.entrySet()) {
                String name = entry.getKey();
                String value = entry.getValue();
                nvps.add(new BasicNameValuePair(name, value));
            }
            httpPost.setEntity(new UrlEncodedFormEntity(nvps));
        }
        return httpClient.execute(httpPost);
    }

    /***
     * 下载附件
     * @param url
     * @param headerRefs
     * @return
     * @throws IOException
     */
    ByteBuffer getResponseAttachment(String url, Map<String, String> headerRefs) throws IOException {
        HttpResponse response = doGet(url, headerRefs);
        HttpEntity entity = response.getEntity();
        if (entity != null) {
            try (InputStream responseStream = entity.getContent()) {
                byte[] targetArray = ByteStreams.toByteArray(responseStream);
                ByteBuffer bufferByte = ByteBuffer.wrap(targetArray);
                return bufferByte;
            }
        }
        return ByteBuffer.wrap(new byte[0]);
    }

    ByteBuffer getResponseAttachment(String url) throws IOException {
        return getResponseAttachment(url, null);
    }

    /***
     * 下载html响应报文主题(html代码)
     * @param url
     * @param headerRefs
     * @param charset
     * @return
     * @throws IOException
     */
    String getResponseBody(String url, Map<String, String> headerRefs, Charset charset) throws IOException {
        HttpResponse response = doGet(url, headerRefs);

        int status = response.getStatusLine().getStatusCode();
        if (status != 200) {
            return "";
        }
        HttpEntity entity = response.getEntity();
        if (entity != null) {
            return EntityUtils.toString(entity, charset);
        }
        return "";
    }

    String getResponseBody(String url, Charset charset) throws IOException {
        return getResponseBody(url, null, charset);
    }

    String getResponseBody(String url) throws IOException {
        return getResponseBody(url, null, StandardCharsets.UTF_8);
    }

}