pdf 转html(不需本地生成html上传oss,直接传递输出流给OSS)
e-iceblue
spire.pdf.free
4.3.0
import com.spire.pdf.FileFormat;
import com.spire.pdf.PdfDocument;
@Override
public void synchJuchaoOssPdfToHtml() {
// 记录起始时间
long start = System.currentTimeMillis();
//2查询出MySQL 需要同步的公告数据 | status=0 初始 | status=1已上传pdf | status=2已解析html | status=3已上传html
OssMetaGq ossMetaGq = new OssMetaGq();
ossMetaGq.setStatus(1);
ossMetaGq.setPublishdate(DateUtils.parseDate("2019-12-30"));//最近三年;
List searchList = ossMetaGqMapper.selectOssMetaGqList(ossMetaGq);
try {
if (searchList != null && searchList.size() > 0) {
// 1 文件处理pdf/txt 上传阿里云,并更新数据库pdf路径地址
searchList.forEach(ossMetaGqDto -> {
try {
//加载pdf文档
PdfDocument pdf = new PdfDocument();
pdf.loadFromStream(HttpUtils.byteByUrl(ossMetaGqDto.getUrl()));
//设置useembeddedsvg和 useembeddedimg布尔值为true
pdf.getConvertOptions().setPdfToHtmlOptions(true, true);
//保存到流
ByteArrayOutputStream outputstream = new ByteArrayOutputStream();
pdf.saveToStream(outputstream, FileFormat.HTML);
pdf.close();
2上传阿里云html文件
String announcementTxtUrl = aliyunOSSService.fileUploadOssByte(Constants.ANNOUNCEMENT_TXT, ossMetaGqDto.getStockcode(), outputstream.toByteArray(), ".html");
ossMetaGqDto.setParsepath(announcementTxtUrl);
} catch (IOException e) {
e.printStackTrace();
ossMetaGqDto.setStatus(1);
log.error("读取pdf格式转换异常:{}", e);
}
ossMetaGqDto.setStatus(3);
});
//获取阿里云OSS文件
//log.info("getUrl " + aliyunOSSService.getFileUrl("announcement/pdf/000502/2022/04/08/38EFE9B5521B471A93AB0D2CEC79B43D.PDF"));
//log.info("getUrl " + aliyunOSSService.getFileUrl("announcement/txt/000502/2022/04/08/71A93AB0D2CEC79B43D.txt"));
//3 批处理更新处理状态;
SqlSession sqlSession = null;
try {
sqlSession = sqlSessionFactory.openSession(ExecutorType.BATCH, false);
OssMetaGqMapper metaGqMapperNew = sqlSession.getMapper(OssMetaGqMapper.class);
searchList.stream().forEach(student -> metaGqMapperNew.updateOssMetaGq(student));
sqlSession.commit();
} catch (Exception e) {
sqlSession.rollback();
log.error("批量处理异常:{}", e);
} finally {
if (sqlSession != null) {
sqlSession.close();
}
}
log.info("批量处理结果:{}", (System.currentTimeMillis() - start));
}
} catch (Exception e) {
e.printStackTrace();
}
}
public String fileUploadOssByte(String fileDir, String stockCode, byte[] content, String fileSuffix) {
//在文件名称里面添加随机唯一值,使用UUID生成
String newFileName = Long.toString(snowflakeIdWorker.nextId());
//获取当前日期,转换/2019/11/17
String generateDayDir = format.format(new Date());
// 填写Object完整路径,完整路径中不能包含Bucket名称,例如exampledir/exampleobject.txt。
String fullFileName = fileDir + stockCode + generateDayDir + "/" + newFileName + fileSuffix;
// 创建OSSClient实例
OSS ossClient = new OSSClientBuilder().build(AliyunOSSConfig.OSS_ENDPOINT_URL, AliyunOSSConfig.ACCESS_KEY_ID,
AliyunOSSConfig.ACCESS_KEY_SECRET);
try {
// 创建PutObject请求。
ossClient.putObject(AliyunOSSConfig.OSS_BUCKET_NAME, fullFileName, new ByteArrayInputStream(content));
} catch (Exception ce) {
log.error("Caught an ClientException, which means the client encountered "
+ "a serious internal problem while trying to communicate with OSS, "
+ "such as not being able to access the network.");
log.error("Error Message:" + ce.getMessage());
} finally {
if (ossClient != null) {
ossClient.shutdown();
}
}
return fullFileName;
}
package com.realize.framework.util;
import org.apache.commons.lang3.StringUtils;
import org.apache.http.HttpResponse;
import org.apache.http.NameValuePair;
import org.apache.http.client.HttpClient;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.HttpDelete;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.client.methods.HttpPut;
import org.apache.http.conn.ClientConnectionManager;
import org.apache.http.conn.scheme.Scheme;
import org.apache.http.conn.scheme.SchemeRegistry;
import org.apache.http.conn.ssl.SSLSocketFactory;
import org.apache.http.entity.ByteArrayEntity;
import org.apache.http.entity.StringEntity;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.message.BasicNameValuePair;
import javax.net.ssl.SSLContext;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;
import java.io.*;
import java.net.URL;
import java.net.URLEncoder;
import java.security.KeyManagementException;
import java.security.NoSuchAlgorithmException;
import java.security.cert.X509Certificate;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
public class HttpUtils {
public static HttpResponse doGet(String host, String path, String method,
Map headers,
Map querys)
throws Exception {
HttpClient httpClient = wrapClient(host);
HttpGet request = new HttpGet(buildUrl(host, path, querys));
for (Map.Entry e : headers.entrySet()) {
request.addHeader(e.getKey(), e.getValue());
}
return httpClient.execute(request);
}
public static HttpResponse doPost(String host, String path, String method,
Map headers,
Map querys,
Map bodys)
throws Exception {
HttpClient httpClient = wrapClient(host);
HttpPost request = new HttpPost(buildUrl(host, path, querys));
for (Map.Entry e : headers.entrySet()) {
request.addHeader(e.getKey(), e.getValue());
}
if (bodys != null) {
List nameValuePairList = new ArrayList();
for (String key : bodys.keySet()) {
nameValuePairList.add(new BasicNameValuePair(key, bodys.get(key)));
}
UrlEncodedFormEntity formEntity = new UrlEncodedFormEntity(nameValuePairList, "utf-8");
formEntity.setContentType("application/x-www-form-urlencoded; charset=UTF-8");
request.setEntity(formEntity);
}
return httpClient.execute(request);
}
public static HttpResponse doPost(String host, String path, String method,
Map headers,
Map querys,
String body)
throws Exception {
HttpClient httpClient = wrapClient(host);
HttpPost request = new HttpPost(buildUrl(host, path, querys));
for (Map.Entry e : headers.entrySet()) {
request.addHeader(e.getKey(), e.getValue());
}
if (StringUtils.isNotBlank(body)) {
request.setEntity(new StringEntity(body, "utf-8"));
}
return httpClient.execute(request);
}
public static HttpResponse doPost(String host, String path, String method,
Map headers,
Map querys,
byte[] body)
throws Exception {
HttpClient httpClient = wrapClient(host);
HttpPost request = new HttpPost(buildUrl(host, path, querys));
for (Map.Entry e : headers.entrySet()) {
request.addHeader(e.getKey(), e.getValue());
}
if (body != null) {
request.setEntity(new ByteArrayEntity(body));
}
return httpClient.execute(request);
}
public static HttpResponse doPut(String host, String path, String method,
Map headers,
Map querys,
String body)
throws Exception {
HttpClient httpClient = wrapClient(host);
HttpPut request = new HttpPut(buildUrl(host, path, querys));
for (Map.Entry e : headers.entrySet()) {
request.addHeader(e.getKey(), e.getValue());
}
if (StringUtils.isNotBlank(body)) {
request.setEntity(new StringEntity(body, "utf-8"));
}
return httpClient.execute(request);
}
public static HttpResponse doPut(String host, String path, String method,
Map headers,
Map querys,
byte[] body)
throws Exception {
HttpClient httpClient = wrapClient(host);
HttpPut request = new HttpPut(buildUrl(host, path, querys));
for (Map.Entry e : headers.entrySet()) {
request.addHeader(e.getKey(), e.getValue());
}
if (body != null) {
request.setEntity(new ByteArrayEntity(body));
}
return httpClient.execute(request);
}
public static HttpResponse doDelete(String host, String path, String method,
Map headers,
Map querys)
throws Exception {
HttpClient httpClient = wrapClient(host);
HttpDelete request = new HttpDelete(buildUrl(host, path, querys));
for (Map.Entry e : headers.entrySet()) {
request.addHeader(e.getKey(), e.getValue());
}
return httpClient.execute(request);
}
private static String buildUrl(String host, String path, Map querys) throws UnsupportedEncodingException {
StringBuilder sbUrl = new StringBuilder();
sbUrl.append(host);
if (!StringUtils.isBlank(path)) {
sbUrl.append(path);
}
if (null != querys) {
StringBuilder sbQuery = new StringBuilder();
for (Map.Entry query : querys.entrySet()) {
if (0 < sbQuery.length()) {
sbQuery.append("&");
}
if (StringUtils.isBlank(query.getKey()) && !StringUtils.isBlank(query.getValue())) {
sbQuery.append(query.getValue());
}
if (!StringUtils.isBlank(query.getKey())) {
sbQuery.append(query.getKey());
if (!StringUtils.isBlank(query.getValue())) {
sbQuery.append("=");
sbQuery.append(URLEncoder.encode(query.getValue(), "utf-8"));
}
}
}
if (0 < sbQuery.length()) {
sbUrl.append("?").append(sbQuery);
}
}
return sbUrl.toString();
}
private static HttpClient wrapClient(String host) {
HttpClient httpClient = new DefaultHttpClient();
if (host.startsWith("https://")) {
sslClient(httpClient);
}
return httpClient;
}
private static void sslClient(HttpClient httpClient) {
try {
SSLContext ctx = SSLContext.getInstance("TLS");
X509TrustManager tm = new X509TrustManager() {
public X509Certificate[] getAcceptedIssuers() {
return null;
}
public void checkClientTrusted(X509Certificate[] xcs, String str) {
}
public void checkServerTrusted(X509Certificate[] xcs, String str) {
}
};
ctx.init(null, new TrustManager[] { tm }, null);
SSLSocketFactory ssf = new SSLSocketFactory(ctx);
ssf.setHostnameVerifier(SSLSocketFactory.ALLOW_ALL_HOSTNAME_VERIFIER);
ClientConnectionManager ccm = httpClient.getConnectionManager();
SchemeRegistry registry = ccm.getSchemeRegistry();
registry.register(new Scheme("https", 443, ssf));
} catch (KeyManagementException ex) {
throw new RuntimeException(ex);
} catch (NoSuchAlgorithmException ex) {
throw new RuntimeException(ex);
}
}
public static InputStream byteByUrl(String urlOrPath) throws IOException {
InputStream in = null;
byte[] bytes;
if (urlOrPath.toLowerCase().startsWith("http")) {
URL url = new URL(urlOrPath);
return url.openStream();
} else {
File file = new File(urlOrPath);
if (!file.isFile() || !file.exists() || !file.canRead()) {
return null;
}
return new FileInputStream(file);
}
}
}