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

eol

Browse Source
This commit is contained in:
Anthony Stirling
2024-01-03 17:59:04 +00:00
parent 0c2b05eabf
commit 6fe268adcb
28 changed files with 3006 additions and 3007 deletions
Download Patch File Download Diff File Expand all files Collapse all files

154
src/main/java/stirling/software/SPDF/controller/api/converters/ConvertWebsiteToPDF.java
View File

@@ -1,77 +1,77 @@
package stirling.software.SPDF.controller.api.converters;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.List;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.ModelAttribute;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;
import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.model.api.converters.UrlToPdfRequest;
import stirling.software.SPDF.utils.GeneralUtils;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@Tag(name = "Convert", description = "Convert APIs")
@RequestMapping("/api/v1/convert")
public class ConvertWebsiteToPDF {
@PostMapping(consumes = "multipart/form-data", value = "/url/pdf")
@Operation(
summary = "Convert a URL to a PDF",
description =
"This endpoint fetches content from a URL and converts it to a PDF format. Input:N/A Output:PDF Type:SISO")
public ResponseEntity<byte[]> urlToPdf(@ModelAttribute UrlToPdfRequest request)
throws IOException, InterruptedException {
String URL = request.getUrlInput();
// Validate the URL format
if (!URL.matches("^https?://.*") || !GeneralUtils.isValidURL(URL)) {
throw new IllegalArgumentException("Invalid URL format provided.");
}
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());
ProcessExecutorResult 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);
return WebResponseUtils.bytesToWebResponse(pdfBytes, outputFilename);
}
private String convertURLToFileName(String url) {
String safeName = url.replaceAll("[^a-zA-Z0-9]", "_");
if (safeName.length() > 50) {
safeName = safeName.substring(0, 50); // restrict to 50 characters
}
return safeName + ".pdf";
}
}
package stirling.software.SPDF.controller.api.converters;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.List;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.ModelAttribute;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;
import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.model.api.converters.UrlToPdfRequest;
import stirling.software.SPDF.utils.GeneralUtils;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@Tag(name = "Convert", description = "Convert APIs")
@RequestMapping("/api/v1/convert")
public class ConvertWebsiteToPDF {
@PostMapping(consumes = "multipart/form-data", value = "/url/pdf")
@Operation(
summary = "Convert a URL to a PDF",
description =
"This endpoint fetches content from a URL and converts it to a PDF format. Input:N/A Output:PDF Type:SISO")
public ResponseEntity<byte[]> urlToPdf(@ModelAttribute UrlToPdfRequest request)
throws IOException, InterruptedException {
String URL = request.getUrlInput();
// Validate the URL format
if (!URL.matches("^https?://.*") || !GeneralUtils.isValidURL(URL)) {
throw new IllegalArgumentException("Invalid URL format provided.");
}
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());
ProcessExecutorResult 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);
return WebResponseUtils.bytesToWebResponse(pdfBytes, outputFilename);
}
private String convertURLToFileName(String url) {
String safeName = url.replaceAll("[^a-zA-Z0-9]", "_");
if (safeName.length() > 50) {
safeName = safeName.substring(0, 50); // restrict to 50 characters
}
return safeName + ".pdf";
}
}