Наметки сбора информации о видео

http://animevost.org/

ks.server/pom.xml

@@ -76,6 +76,23 @@
             <version>${jetty.version}</version>
         </dependency>
 
+        <!-- BROWSER -->
+        <dependency>
+            <groupId>commons-io</groupId>
+            <artifactId>commons-io</artifactId>
+            <version>2.5</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.httpcomponents</groupId>
+            <artifactId>httpclient</artifactId>
+            <version>4.5.2</version>
+        </dependency>
+        <dependency>
+            <groupId>org.jsoup</groupId>
+            <artifactId>jsoup</artifactId>
+            <version>1.8.3</version>
+        </dependency>
+
         <!-- COMPONENTS -->
         <dependency>
             <groupId>org.projectlombok</groupId>

ks.server/src/main/java/ks/server/SpringConfigMVC.java

@@ -4,17 +4,23 @@ import org.springframework.context.annotation.ComponentScan;
 import org.springframework.context.annotation.Configuration;
 import org.springframework.http.converter.HttpMessageConverter;
 import org.springframework.http.converter.json.GsonHttpMessageConverter;
+import org.springframework.web.servlet.config.annotation.ContentNegotiationConfigurer;
 import org.springframework.web.servlet.config.annotation.EnableWebMvc;
 import org.springframework.web.servlet.config.annotation.WebMvcConfigurer;
 
 import java.util.List;
 
 @Configuration
-@ComponentScan({ "ks.server.controllers" })
+@ComponentScan({ "ks.server.controllers", "ks.server.browser" })
 @EnableWebMvc
 public class SpringConfigMVC implements WebMvcConfigurer {
     @Override
     public void configureMessageConverters(List<HttpMessageConverter<?>> converters) {
         converters.add(new GsonHttpMessageConverter());
     }
+
+    @Override
+    public void configureContentNegotiation(ContentNegotiationConfigurer configurer) {
+        configurer.favorPathExtension(false);
+    }
 }

ks.server/src/main/java/ks/server/WebApplication.java

@@ -1,7 +1,5 @@
 package ks.server;
 
-import ks.server.controllers.ErrorPageController;
-import ks.server.controllers.WebController;
 import lombok.RequiredArgsConstructor;
 import lombok.extern.slf4j.Slf4j;
 import org.eclipse.jetty.server.ConnectionFactory;

ks.server/src/main/java/ks/server/browser/ApacheBrowser.java

@@ -0,0 +1,47 @@
+package ks.server.browser;
+
+import lombok.Setter;
+import lombok.extern.slf4j.Slf4j;
+import org.apache.commons.io.IOUtils;
+import org.apache.http.HttpResponse;
+import org.apache.http.client.HttpClient;
+import org.apache.http.client.methods.HttpGet;
+import org.apache.http.impl.client.HttpClients;
+import org.springframework.context.annotation.Scope;
+import org.springframework.context.annotation.ScopedProxyMode;
+import org.springframework.stereotype.Component;
+import org.springframework.web.context.WebApplicationContext;
+
+import java.io.IOException;
+
+@Slf4j
+@Component
+@Scope(scopeName = WebApplicationContext.SCOPE_REQUEST, proxyMode = ScopedProxyMode.TARGET_CLASS)
+public class ApacheBrowser implements Browser {
+    @Setter
+    private String encoding = "UTF-8";
+
+    private void setupHeaders(HttpGet request) {
+        request.addHeader("Connection", "close");
+        request.addHeader("Accept-Encoding", "deflate");
+        request.addHeader("User-Agent", "Mozilla/5.0 (Linux; Android 7.0; SM-G892A Build/NRD90M; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/67.0.3396.87 Mobile Safari/537.36");
+    }
+
+    @Override
+    public String get(String url) {
+        HttpClient client = HttpClients.createDefault();
+        HttpGet request = new HttpGet(url);
+        setupHeaders(request);
+
+        String result = "";
+        try {
+            HttpResponse response = client.execute(request);
+            result = IOUtils.toString(response.getEntity().getContent(), encoding);
+        } catch (IOException e) {
+            log.warn("Error i/o from GET url \"{}\": {}", url, e.getMessage());
+            log.debug("", e);
+        }
+
+        return result;
+    }
+}

ks.server/src/main/java/ks/server/browser/Browser.java

@@ -0,0 +1,6 @@
+package ks.server.browser;
+
+public interface Browser {
+    void setEncoding(String encoding);
+    String get(String url);
+}

ks.server/src/main/java/ks/server/controllers/WebController.java

@@ -1,21 +1,101 @@
 package ks.server.controllers;
 
+import ks.server.browser.Browser;
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.http.MediaType;
-import org.springframework.stereotype.Controller;
 import org.springframework.web.bind.annotation.RequestMapping;
 import org.springframework.web.bind.annotation.RequestMethod;
-import org.springframework.web.bind.annotation.ResponseBody;
+import org.springframework.web.bind.annotation.RestController;
 
+import javax.servlet.http.HttpServletRequest;
 import java.util.Collections;
+import java.util.HashMap;
 import java.util.Map;
+import java.util.stream.Collectors;
+import java.util.stream.Stream;
 
-@Controller
+@RestController
-@RequestMapping(path = "/", produces = MediaType.APPLICATION_JSON_UTF8_VALUE)
+@RequestMapping(
-@ResponseBody
+        path = "/",
+        method = RequestMethod.GET,
+        produces = MediaType.APPLICATION_JSON_UTF8_VALUE)
 public class WebController {
+    @Autowired
+    private Browser browser;
 
-    @RequestMapping(method = RequestMethod.GET)
+    private String subpath(String requestUri, String marker) {
+        return requestUri.substring(requestUri.indexOf(marker) + marker.length());
+    }
+
+    @RequestMapping
     public Map<String, String> index() {
         return Collections.singletonMap("message", "hello?");
     }
+
+    @RequestMapping(path = "/c/animevost/info/**")
+    public Map<String, Object> animevostInfo(HttpServletRequest request) {
+        final String domainUri = "http://animevost.org/";
+        final String path = subpath(request.getRequestURI(), "/info/");
+        final String cinemaRequestUri = domainUri + path;
+
+        final Map<String, Object> resultMap = new HashMap<>();
+        resultMap.put("_uri", cinemaRequestUri);
+
+        Document htmlDocument = Jsoup.parse(browser.get(cinemaRequestUri));
+
+        // /html/body/section/div/div[1]/div[2]/div[2]
+        // .infoContent
+        Element infoContent = htmlDocument.select(".infoContent").first();
+
+        // /html/body/section/div/div[1]/div[2]/div[2]/div[1]/h3
+        // .infoContent > h3:nth-child(1)
+        resultMap.put("title",
+                infoContent.select("h3:nth-child(1)").first().text());
+
+        // /html/body/section/div/div[1]/div[2]/div[2]/div[1]/div[1]/img
+        // .infoContent > div:nth-child(2) > img:nth-child(1)
+        resultMap.put("poster", domainUri +
+                infoContent.select("div:nth-child(2) > img:nth-child(1)").first().attr("src"));
+
+        // /html/body/section/div/div[1]/div[2]/div[2]/div[1]/p[1]
+        // .infoContent > p:nth-child(3)
+        resultMap.put("year",
+            Integer.parseInt(infoContent.select("p:nth-child(3)").first().childNode(1).toString().trim()));
+
+        // /html/body/section/div/div[1]/div[2]/div[2]/div[1]/p[2]
+        // .infoContent > p:nth-child(4)
+        resultMap.put("genre", Stream.of(
+                infoContent.select("p:nth-child(4)").first().childNode(1).toString().trim()
+                        .split(","))
+                .map(String::trim).collect(Collectors.toList()));
+
+        // /html/body/section/div/div[1]/div[2]/div[2]/div[1]/p[3]
+        // .infoContent > p:nth-child(5)
+        resultMap.put("type",
+                infoContent.select("p:nth-child(5)").first().childNode(1).toString().trim());
+
+        // /html/body/section/div/div[1]/div[2]/div[2]/div[1]/p[4]
+        // .infoContent > p:nth-child(6)
+        resultMap.put("countSeries",
+                infoContent.select("p:nth-child(6)").first().childNode(1).toString().trim());
+
+        // /html/body/section/div/div[1]/div[2]/div[2]/div[1]/p[5]/a
+        // .infoContent > p:nth-child(7) > a:nth-child(2)
+        resultMap.put("director",
+                infoContent.select("p:nth-child(7) > a:nth-child(2)").first().text());
+
+        // /html/body/section/div/div[1]/div[2]/div[2]/div[1]/p[6]
+        // .infoContent > p:nth-child(8)
+        resultMap.put("description",
+                infoContent.select("p:nth-child(8)").first().childNodes().stream()
+                        .skip(1)
+                        .map(node -> node.toString().trim())
+                        .filter(text -> !text.isEmpty() && !text.equalsIgnoreCase("<br>"))
+                        .collect(Collectors.joining(" ")));
+
+        return resultMap;
+    }
 }