mtg-decks-downloader

commit 12f8aebc3dea18a2d197e08d17ece47a32fa4f46
parent fdd854ef17258ed854c06a26def887224d14a8f0
Author: Kevin Corvisier <git@kevincorvisier.fr>
Date:   Thu, 16 Jan 2025 18:15:02 +0900

Catch page/decklist parsing exceptions
Diffstat:
M
src/main/java/fr/kevincorvisier/mtg/dd/consumers/DecklistConsumersService.java
 | 
3
+--
M
src/main/java/fr/kevincorvisier/mtg/dd/downloaders/TcdecksDecklistDownloader.java
 | 
49
++++++++++++++++++++++++++++---------------------

2 files changed, 29 insertions(+), 23 deletions(-)
diff --git a/src/main/java/fr/kevincorvisier/mtg/dd/consumers/DecklistConsumersService.java b/src/main/java/fr/kevincorvisier/mtg/dd/consumers/DecklistConsumersService.java
@@ -3,7 +3,6 @@ package fr.kevincorvisier.mtg.dd.consumers;
 import java.io.BufferedReader;
 import java.io.IOException;
 import java.io.InputStreamReader;
-import java.sql.SQLException;
 import java.util.Collection;
 
 import org.springframework.stereotype.Service;
@@ -42,7 +41,7 @@ public class DecklistConsumersService
 				content = new DeckContent(MagicOnlineFileReader.read(reader));
 				cache.save(metadata.getUrl(), content);
 			}
-			catch (SQLException | IOException e)
+			catch (final Exception e)
 			{
 				log.error("Error while downloading deck, skipping {}", metadata, e);
 				return;
diff --git a/src/main/java/fr/kevincorvisier/mtg/dd/downloaders/TcdecksDecklistDownloader.java b/src/main/java/fr/kevincorvisier/mtg/dd/downloaders/TcdecksDecklistDownloader.java
@@ -166,34 +166,41 @@ public class TcdecksDecklistDownloader implements DecklistDownloader
 
 	private void downloadTournament(final URL url) throws MalformedURLException
 	{
-		crawler.navigateTo(url);
+		try
+		{
+			crawler.navigateTo(url);
 
-		final String description = crawler.findElement(By.xpath("//article[@class='span8']/fieldset/legend/h5")).getText();
+			final String description = crawler.findElement(By.xpath("//article[@class='span8']/fieldset/legend/h5")).getText();
 
-		log.info("download tournament: {}", description);
+			log.info("download tournament: {}", description);
 
-		final Matcher matcher = pattern.matcher(description);
-		if (!matcher.find())
-		{
-			log.error("Cannot parse tournament description: {}", description);
-			return;
-		}
+			final Matcher matcher = pattern.matcher(description);
+			if (!matcher.find())
+			{
+				log.error("Cannot parse tournament description: {}", description);
+				return;
+			}
 
-		final LocalDate date = LocalDate.of( //
-				Integer.parseInt(matcher.group("year")), //
-				Integer.parseInt(matcher.group("month")), //
-				Integer.parseInt(matcher.group("dayOfMonth")));
+			final LocalDate date = LocalDate.of( //
+					Integer.parseInt(matcher.group("year")), //
+					Integer.parseInt(matcher.group("month")), //
+					Integer.parseInt(matcher.group("dayOfMonth")));
 
-		for (final WebElement tr : crawler.findElements(By.xpath("//table[@class='tourney_list']/tbody/tr")))
-		{
-			if (hasElement(tr, By.xpath("th")))
-				continue; // Header row
+			for (final WebElement tr : crawler.findElements(By.xpath("//table[@class='tourney_list']/tbody/tr")))
+			{
+				if (hasElement(tr, By.xpath("th")))
+					continue; // Header row
 
-			final WebElement archetype = tr.findElement(By.xpath("td[@data-th='Archetype']/a"));
-			final WebElement player = tr.findElement(By.xpath("td[@data-th='Player']/a"));
-			final URL downloadUrl = toDownloadUrl(archetype.getAttribute("href"));
+				final WebElement archetype = tr.findElement(By.xpath("td[@data-th='Archetype']/a"));
+				final WebElement player = tr.findElement(By.xpath("td[@data-th='Player']/a"));
+				final URL downloadUrl = toDownloadUrl(archetype.getAttribute("href"));
 
-			consumers.process(metadataFactory.create(downloadUrl, player.getText(), archetype.getText(), date));
+				consumers.process(metadataFactory.create(downloadUrl, player.getText(), archetype.getText(), date));
+			}
+		}
+		catch (final Exception e)
+		{
+			log.error("downloadTournament: url={}", url, e);
 		}
 	}