javier/Stirling-PDF
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

html to pdf

Browse Source
This commit is contained in:
Anthony Stirling
2023-07-23 00:03:25 +01:00
parent 2fd8c643af
commit 116d103119
9 changed files with 129 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/main/java/stirling/software/SPDF/config/EndpointConfiguration.java
View File

@@ -83,7 +83,9 @@ public class EndpointConfiguration {
addEndpointToGroup("Convert", "pdf-to-text");
addEndpointToGroup("Convert", "pdf-to-html");
addEndpointToGroup("Convert", "pdf-to-xml");
addEndpointToGroup("Convert", "html-to-pdf");
addEndpointToGroup("Convert", "url-to-pdf");
// Adding endpoints to "Security" group
addEndpointToGroup("Security", "add-password");
addEndpointToGroup("Security", "remove-password");
@@ -125,12 +127,15 @@ public class EndpointConfiguration {
addEndpointToGroup("CLI", "pdf-to-html");
addEndpointToGroup("CLI", "pdf-to-xml");
addEndpointToGroup("CLI", "ocr-pdf");
addEndpointToGroup("CLI", "html-to-pdf");
addEndpointToGroup("CLI", "url-to-pdf");
//python
addEndpointToGroup("Python", "extract-image-scans");
addEndpointToGroup("Python", "remove-blanks");
addEndpointToGroup("Python", "html-to-pdf");
addEndpointToGroup("Python", "url-to-pdf");
//openCV
addEndpointToGroup("OpenCV", "extract-image-scans");

122
src/main/java/stirling/software/SPDF/controller/api/converters/ConvertHtmlToPDF.java
View File

@@ -4,9 +4,13 @@ import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.List;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;
import java.util.*;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestPart;
@@ -40,61 +44,83 @@ public class ConvertHtmlToPDF {
if (originalFilename == null || (!originalFilename.endsWith(".html") && !originalFilename.endsWith(".zip"))) {
throw new IllegalArgumentException("File must be either .html or .zip format.");
}
Path tempOutputFile = Files.createTempFile("output_", ".pdf");
Path tempInputFile;
if (originalFilename.endsWith(".html")) {
tempInputFile = Files.createTempFile("input_", ".html");
Files.write(tempInputFile, fileInput.getBytes());
} else {
tempInputFile = unzipAndGetMainHtml(fileInput);
Path tempInputFile = null;
byte[] pdfBytes;
try {
if (originalFilename.endsWith(".html")) {
tempInputFile = Files.createTempFile("input_", ".html");
Files.write(tempInputFile, fileInput.getBytes());
} else {
tempInputFile = unzipAndGetMainHtml(fileInput);
}
List<String> command = new ArrayList<>();
command.add("weasyprint");
command.add(tempInputFile.toString());
command.add(tempOutputFile.toString());
int returnCode = 0;
if (originalFilename.endsWith(".zip")) {
returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT)
.runCommandWithOutputHandling(command, tempInputFile.getParent().toFile());
} else {
returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT)
.runCommandWithOutputHandling(command);
}
pdfBytes = Files.readAllBytes(tempOutputFile);
} finally {
// Clean up temporary files
Files.delete(tempOutputFile);
Files.delete(tempInputFile);
if (originalFilename.endsWith(".zip")) {
GeneralUtils.deleteDirectory(tempInputFile.getParent());
}
}
List<String> command = new ArrayList<>();
command.add("weasyprint");
command.add(tempInputFile.toString());
command.add(tempOutputFile.toString());
int returnCode = 0;
if (originalFilename.endsWith(".zip")) {
returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT)
.runCommandWithOutputHandling(command, tempInputFile.getParent().toFile());
} else {
returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT)
.runCommandWithOutputHandling(command);
}
byte[] pdfBytes = Files.readAllBytes(tempOutputFile);
// Clean up temporary files
Files.delete(tempOutputFile);
Files.delete(tempInputFile);
if (originalFilename.endsWith(".zip")) {
GeneralUtils.deleteDirectory(tempInputFile.getParent());
}
String outputFilename = originalFilename.replaceFirst("[.][^.]+$", "") + ".pdf"; // Remove file extension and append .pdf
return WebResponseUtils.bytesToWebResponse(pdfBytes, outputFilename);
}
private Path unzipAndGetMainHtml(MultipartFile zipFile) throws IOException {
Path tempDirectory = Files.createTempDirectory("unzipped_");
try (ZipInputStream zipIn = new ZipInputStream(new ByteArrayInputStream(zipFile.getBytes()))) {
ZipEntry entry = zipIn.getNextEntry();
while (entry != null) {
Path filePath = tempDirectory.resolve(entry.getName());
if (!entry.isDirectory()) {
Files.copy(zipIn, filePath);
}
zipIn.closeEntry();
entry = zipIn.getNextEntry();
}
}
return tempDirectory.resolve("index.html");
}
private Path unzipAndGetMainHtml(MultipartFile zipFile) throws IOException {
Path tempDirectory = Files.createTempDirectory("unzipped_");
try (ZipInputStream zipIn = new ZipInputStream(new ByteArrayInputStream(zipFile.getBytes()))) {
ZipEntry entry = zipIn.getNextEntry();
while (entry != null) {
Path filePath = tempDirectory.resolve(entry.getName());
if (entry.isDirectory()) {
Files.createDirectories(filePath); // Explicitly create the directory structure
} else {
Files.createDirectories(filePath.getParent()); // Create parent directories if they don't exist
Files.copy(zipIn, filePath);
}
zipIn.closeEntry();
entry = zipIn.getNextEntry();
}
}
//search for the main HTML file.
try (Stream<Path> walk = Files.walk(tempDirectory)) {
List<Path> htmlFiles = walk.filter(file -> file.toString().endsWith(".html"))
.collect(Collectors.toList());
if (htmlFiles.isEmpty()) {
throw new IOException("No HTML files found in the unzipped directory.");
}
// Prioritize 'index.html' if it exists, otherwise use the first .html file
for (Path htmlFile : htmlFiles) {
if (htmlFile.getFileName().toString().equals("index.html")) {
return htmlFile;
}
}
return htmlFiles.get(0);
}
}

41
src/main/java/stirling/software/SPDF/controller/api/converters/ConvertWebsiteToPDF.java
View File

@@ -34,27 +34,30 @@ public class ConvertWebsiteToPDF {
String URL) throws IOException, InterruptedException {
// Validate the URL format
if(!URL.matches("^https?://.*") && GeneralUtils.isValidURL(URL)) {
if(!URL.matches("^https?://.*") || !GeneralUtils.isValidURL(URL)) {
throw new IllegalArgumentException("Invalid URL format provided.");
}
// Prepare the output file path
Path tempOutputFile = Files.createTempFile("output_", ".pdf");
// Prepare the OCRmyPDF command
List<String> command = new ArrayList<>();
command.add("weasyprint");
command.add(URL);
command.add(tempOutputFile.toString());
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT).runCommandWithOutputHandling(command);
// Read the optimized PDF file
byte[] pdfBytes = Files.readAllBytes(tempOutputFile);
// Clean up the temporary files
Files.delete(tempOutputFile);
Path tempOutputFile = null;
byte[] pdfBytes;
try {
// Prepare the output file path
tempOutputFile = Files.createTempFile("output_", ".pdf");
// Prepare the OCRmyPDF command
List<String> command = new ArrayList<>();
command.add("weasyprint");
command.add(URL);
command.add(tempOutputFile.toString());
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT).runCommandWithOutputHandling(command);
// Read the optimized PDF file
pdfBytes = Files.readAllBytes(tempOutputFile);
}
finally {
// Clean up the temporary files
Files.delete(tempOutputFile);
}
// Convert URL to a safe filename
String outputFilename = convertURLToFileName(URL);