Merge pull request 'feat(scrapper): use jsoup directly for the manga livre blog provider' (#22) from feature/flare-solverr into main

Reviewed-on: #22

src/main/java/com/magamochi/mangamochi/client/WebScrapperClient.java

@@ -1,18 +0,0 @@
-package com.magamochi.mangamochi.client;
-
-import org.springframework.cloud.openfeign.FeignClient;
-import org.springframework.http.MediaType;
-import org.springframework.web.bind.annotation.PostMapping;
-import org.springframework.web.bind.annotation.RequestBody;
-
-@FeignClient(name = "web-scrapper", url = "${web-scrapper.endpoint}")
-public interface WebScrapperClient {
-  @PostMapping(
-      consumes = MediaType.APPLICATION_JSON_VALUE,
-      produces = MediaType.APPLICATION_JSON_VALUE)
-  Response scrape(@RequestBody Request dto);
-
-  record Request(String url) {}
-
-  record Response(String page_source) {}
-}

src/main/java/com/magamochi/mangamochi/service/WebScrapperClientProxyService.java

@@ -1,23 +0,0 @@
-package com.magamochi.mangamochi.service;
-
-import com.magamochi.mangamochi.client.WebScrapperClient;
-import java.io.IOException;
-import lombok.RequiredArgsConstructor;
-import org.jsoup.Jsoup;
-import org.jsoup.nodes.Document;
-import org.springframework.stereotype.Service;
-
-@Service
-@RequiredArgsConstructor
-public class WebScrapperClientProxyService {
-  private final WebScrapperClient webScrapperClient;
-
-  public Document scrapeToJsoupDocument(String url) throws IOException {
-    var htmlContent = scrape(url);
-    return Jsoup.parse(htmlContent);
-  }
-
-  private String scrape(String url) {
-    return webScrapperClient.scrape(new WebScrapperClient.Request(url)).page_source();
-  }
-}

src/main/java/com/magamochi/mangamochi/service/providers/impl/MangaLivreBlogProvider.java

@@ -4,7 +4,6 @@ import com.magamochi.mangamochi.model.dto.ContentProviderMangaChapterResponseDTO
 import com.magamochi.mangamochi.model.dto.ContentProviderMangaInfoResponseDTO;
 import com.magamochi.mangamochi.model.entity.MangaProvider;
 import com.magamochi.mangamochi.model.enumeration.MangaStatus;
-import com.magamochi.mangamochi.service.WebScrapperClientProxyService;
 import com.magamochi.mangamochi.service.providers.ContentProvider;
 import com.magamochi.mangamochi.service.providers.ContentProviders;
 import com.magamochi.mangamochi.service.providers.PagedContentProvider;
@@ -16,6 +15,7 @@ import java.util.stream.IntStream;
 import lombok.RequiredArgsConstructor;
 import lombok.extern.log4j.Log4j2;
 import org.apache.commons.lang3.StringUtils;
+import org.jsoup.Jsoup;
 import org.jsoup.nodes.Element;
 import org.springframework.stereotype.Service;
 
@@ -27,8 +27,6 @@ public class MangaLivreBlogProvider implements ContentProvider, PagedContentProv
 
   private final String url = "https://mangalivre.blog/manga/";
 
-  private final WebScrapperClientProxyService webScrapperClientProxyService;
-
   @Override
   public List<ContentProviderMangaChapterResponseDTO> getAvailableChapters(
       MangaProvider mangaProvider) {
@@ -38,7 +36,7 @@ public class MangaLivreBlogProvider implements ContentProvider, PagedContentProv
         mangaProvider.getManga().getTitle());
 
     try {
-      var document = webScrapperClientProxyService.scrapeToJsoupDocument(mangaProvider.getUrl());
+      var document = Jsoup.connect(mangaProvider.getUrl()).get();
 
       var chapterList = document.getElementsByClass("chapters-list").getFirst();
       var chapterItems = chapterList.getElementsByClass("chapter-item");
@@ -67,7 +65,7 @@ public class MangaLivreBlogProvider implements ContentProvider, PagedContentProv
     log.info("Getting images from {}, url {}", ContentProviders.MANGA_LIVRE_BLOG, chapterUrl);
 
     try {
-      var document = webScrapperClientProxyService.scrapeToJsoupDocument(chapterUrl);
+      var document = Jsoup.connect(chapterUrl).get();
 
       var chapterImageContainers = document.getElementsByClass("chapter-image-container");
       var imageUrls =
@@ -107,7 +105,7 @@ public class MangaLivreBlogProvider implements ContentProvider, PagedContentProv
     log.info("Getting mangas from {}, page {}", ContentProviders.MANGA_LIVRE_BLOG, page);
 
     try {
-      var document = webScrapperClientProxyService.scrapeToJsoupDocument(url + "page/" + page);
+      var document = Jsoup.connect(url + "page/" + page).get();
 
       var mangaGrid = document.getElementsByClass("manga-grid").getFirst();
       var mangaElements = mangaGrid.getElementsByTag("article");
@@ -160,7 +158,7 @@ public class MangaLivreBlogProvider implements ContentProvider, PagedContentProv
     log.info("Getting total pages for {}", ContentProviders.MANGA_LIVRE_BLOG);
 
     try {
-      var document = webScrapperClientProxyService.scrapeToJsoupDocument(url);
+      var document = Jsoup.connect(url).get();
 
       var navLinks = document.getElementsByClass("nav-links").getFirst();
       var links = navLinks.getElementsByTag("a");

src/main/resources/application.yml

@@ -35,9 +35,6 @@ springdoc:
   api-docs:
     path: /api-docs
 
-web-scrapper:
-  endpoint: ${WEBSCRAPPER_ENDPOINT}
-
 flare-solverr:
   endpoint: ${FLARESOLVERR_ENDPOINT}