Compare commits

..

10 Commits

Author SHA1 Message Date
dcea9e83b5 tokens 2025-05-22 16:58:05 +02:00
316beb2054 de 0 2025-05-22 16:43:20 +02:00
8265b76acf analisis trends 2025-05-22 16:36:59 +02:00
cc43fc0fcc noticias con menos de 8 meses 2025-04-07 19:23:04 +02:00
eea2d8ae2f enlaces 2025-04-01 16:28:10 +02:00
2e78736b63 Busqueda sin enlaces 2025-03-28 19:28:59 +01:00
deaee1656b imprimir mensaje 2025-03-28 16:53:17 +01:00
0dce6d7606 cambio a html 2025-03-28 16:41:01 +01:00
d310fea974 más errores 2025-03-28 16:25:37 +01:00
936217f526 tracing error 2025-03-28 16:15:32 +01:00
6 changed files with 273 additions and 54 deletions

View File

@ -1,5 +1,8 @@
package es.imunnic.inversionitasBot;
import es.imunnic.inversionitasBot.services.GoogleNewsScraperService;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import org.springframework.context.ApplicationContext;
@ -8,9 +11,12 @@ import org.telegram.telegrambots.meta.TelegramBotsApi;
import org.telegram.telegrambots.meta.exceptions.TelegramApiException;
import org.telegram.telegrambots.updatesreceivers.DefaultBotSession;
import java.util.List;
@SpringBootApplication
@EnableScheduling
public class InversionitasBotApplication {
private static final Logger logger = LoggerFactory.getLogger(GoogleNewsScraperService.class);
public static void main(String[] args) {
ApplicationContext context = SpringApplication.run(InversionitasBotApplication.class, args);
@ -28,4 +34,5 @@ public class InversionitasBotApplication {
}
}
}

View File

@ -6,6 +6,10 @@ public class NewsArticle {
private String url;
private String content;
public NewsArticle(String title, String description, String url) {
this(title,description,url,null);
}
public NewsArticle(String title, String description, String url, String content) {
this.title = title;
this.description = description;

View File

@ -2,8 +2,10 @@ package es.imunnic.inversionitasBot;
import es.imunnic.inversionitasBot.services.ApiService;
import es.imunnic.inversionitasBot.services.GoogleNewsScraperService;
import org.json.JSONObject;
import org.springframework.beans.factory.annotation.Value;
import es.imunnic.inversionitasBot.services.ResultadosService;
import es.imunnic.inversionitasBot.services.Trends24Scrapper;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.scheduling.annotation.Scheduled;
import org.springframework.stereotype.Component;
import org.telegram.telegrambots.bots.TelegramLongPollingBot;
@ -11,6 +13,7 @@ import org.telegram.telegrambots.meta.api.objects.Update;
import org.telegram.telegrambots.meta.api.methods.send.SendMessage;
import org.telegram.telegrambots.meta.exceptions.TelegramApiException;
import java.io.IOException;
import java.time.LocalDate;
import java.time.format.DateTimeFormatter;
import java.util.ArrayList;
@ -21,12 +24,15 @@ import java.util.Map;
@Component
public class TelegramBot extends TelegramLongPollingBot {
private static final Logger logger = LoggerFactory.getLogger(GoogleNewsScraperService.class);
private GoogleNewsScraperService scrapper = new GoogleNewsScraperService();
private Trends24Scrapper trendScrapper = new Trends24Scrapper();
private ResultadosService resultadosService = new ResultadosService();
//@Value("${telegram.bot.username}")
private String BOT_USERNAME = "Inversionitas_Bot";
//@Value("${telegram.bot.token}")
private String BOT_TOKEN = "7626026035:AAHEMp_iIN3y8AwywL0R6OTQvNi7EcJZ0iY";
//private String BOT_TOKEN = "8017576757:AAHNGvY8RK_PbnlV1frM8KZMQ45tdMSvO3c";
protected String CHAT_ID = "-1002289752202";
protected Integer THREAD_INDICES = 138;
protected Integer THREAD_NOTICIAS = 137;
@ -53,6 +59,12 @@ public class TelegramBot extends TelegramLongPollingBot {
} else if (messageText.toLowerCase().startsWith("/busca ")) {
String query = messageText.substring(7).trim();
buscarNoticiasYEnviar(chatId, query);
} else if (messageText.toLowerCase().startsWith("/resultados ")) {
String query = messageText.substring(12).trim();
buscarResultadosYEnviar(chatId, query);
} else if (messageText.toLowerCase().startsWith("/trends ")) {
String country = messageText.substring(8).trim().toLowerCase().replace(" ", "-");
enviarTrends(chatId, country); // NUEVO
} else {
sendMessage(chatId, "Comando no reconocido. Usa /resumen para obtener el resumen diario.");
}
@ -85,6 +97,30 @@ public class TelegramBot extends TelegramLongPollingBot {
}
}
protected void sendMessageHtml(String chatId, String text){
this.sendMessageHtml(chatId, text, null);
}
protected void sendMessageHtml(String chatId, String text, Integer threadId) {
String parte = this.escapeHtml(text);
SendMessage sendMessage = new SendMessage();
sendMessage.setChatId(chatId);
sendMessage.setText(parte);
sendMessage.setParseMode("HTML"); // Se debe usar HTML si el contenido es HTML
if (threadId != null) {
sendMessage.setMessageThreadId(threadId);
}
try {
execute(sendMessage);
} catch (TelegramApiException e) {
e.printStackTrace();
}
}
@Scheduled(cron = "0 0 13,20 * * ?", zone = "Europe/Paris")
private void mensajeProgramado(){
this.construirResumenNoticias(this.CHAT_ID);
@ -154,24 +190,50 @@ public class TelegramBot extends TelegramLongPollingBot {
}
private void buscarNoticiasYEnviar(String chatId, String query) {
List<NewsArticle> noticias = scrapper.searchNews(query);
String mensajeInicio = "Analizando noticias... esto puede tardar un poco, ten paciencia...";
String mensajeError = "Lo siento... se me ha licuado el cerebro... Mira los logs para saber más.";
sendMessageHtml(chatId, mensajeInicio); // Enviar mensaje inicial
if (noticias.isEmpty()) {
sendMessage(chatId, "No encontré noticias sobre: *" + escapeMarkdown(query) + "*");
try {
List<NewsArticle> noticias = scrapper.searchNews(query);
if (noticias.isEmpty()) {
sendMessageHtml(chatId, "No encontré noticias sobre: " + query);
return;
}
StringBuilder mensaje = new StringBuilder("<b>📰 Noticias sobre " + query + ":</b>\n\n");
for (NewsArticle noticia : noticias) {
mensaje.append("🔹 <a href=\"")
.append(noticia.getUrl()) // URL de la noticia
.append("\">")
.append(escapeHtml(noticia.getTitle())) // Título de la noticia
.append("</a>\n");
}
sendMessageHtml(chatId, mensaje.toString());
} catch (Exception e) {
sendMessageHtml(chatId, mensajeError);
}
}
private void buscarResultadosYEnviar(String chatId, String query){
Map<String, String> resultados = resultadosService.getBeneficioNetoAnual(query);
if (resultados.isEmpty()) {
sendMessageHtml(chatId, "<b>No se encontraron resultados financieros para:</b> " + query);
return;
}
sendMessage(chatId, "Analizando noticias...esto puede tardar un poco, ten paciencia...");
StringBuilder mensaje = new StringBuilder("📰 *Noticias sobre " + escapeMarkdown(query) + "*:\n\n");
for (NewsArticle noticia : noticias) {
mensaje.append("🔹 [")
.append(escapeMarkdown(noticia.getTitle()))
.append("](")
.append(noticia.getUrl())
.append(")\n");
}
sendMessage(chatId, mensaje.toString());
StringBuilder resultMessage = new StringBuilder();
resultMessage.append("<b>Beneficio neto anual para: ").append(query).append("</b>\n\n");
resultados.forEach((año, beneficio) -> {
resultMessage.append("📅 <b>").append(año).append(":</b> ").append(beneficio).append("\n");
});
sendMessageHtml(chatId, resultMessage.toString());
}
// Método para escapar caracteres especiales en Markdown
@ -179,23 +241,35 @@ public class TelegramBot extends TelegramLongPollingBot {
if (text == null) {
return "";
}
return text.replace("_", "\\_")
.replace("*", "\\*")
.replace("[", "\\[")
.replace("]", "\\]")
.replace("(", "\\(")
.replace(")", "\\)")
.replace("~", "\\~")
.replace("`", "\\`")
.replace(">", "\\>")
.replace("#", "\\#")
.replace("+", "\\+")
.replace("-", "\\-")
.replace("=", "\\=")
.replace("|", "\\|")
.replace("{", "\\{")
.replace("}", "\\}")
.replace(".", "\\.")
.replace("!", "\\!");
return text.replaceAll("([_*\\[\\]()~`>#+\\-=|{}.!])", "\\\\$1");
}
private String escapeHtml(String text) {
return text.replace("&", "&amp;");
}
private void enviarTrends(String chatId, String country) {
try {
List<String> trends = trendScrapper.getTopTrends(country);
if (trends.isEmpty()) {
sendMessage(chatId, "No se encontraron tendencias para: " + country);
return;
}
StringBuilder mensaje = new StringBuilder();
mensaje.append("📈 <b>Top 20 tendencias en ").append(country.replace("-", " ")).append(":</b>\n\n");
int index = 1;
for (String trend : trends) {
mensaje.append(index++).append(". ").append(escapeHtml(trend)).append("\n");
}
sendMessageHtml(chatId, mensaje.toString());
} catch (IOException e) {
sendMessage(chatId, "❌ Error al obtener las tendencias de Trends24, compruebe el nombre del pais");
e.printStackTrace();
}
}
}

View File

@ -9,39 +9,72 @@ import com.rometools.rome.feed.synd.SyndEntry;
import com.rometools.rome.feed.synd.SyndFeed;
import com.rometools.rome.io.SyndFeedInput;
import com.rometools.rome.io.XmlReader;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.stereotype.Service;
import java.net.HttpURLConnection;
import java.net.URL;
import java.time.LocalDate;
import java.time.ZoneId;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
@Service
public class GoogleNewsScraperService {
private static final Logger logger = LoggerFactory.getLogger(GoogleNewsScraperService.class);
private static final String USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36";
public List<NewsArticle> searchNews(String query) {
List<NewsArticle> newsList = new ArrayList<>();
String rssUrl = "https://news.google.com/rss/search?q=" + query.replace(" ", "+") + "&hl=es&gl=ES&ceid=ES%3Aes";
logger.info("Buscando noticias para: {}", query);
logger.info("URL del RSS: {}", rssUrl);
try {
URL url = new URL(rssUrl);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty("User-Agent", USER_AGENT);
SyndFeedInput input = new SyndFeedInput();
SyndFeed feed = input.build(new XmlReader(conn.getInputStream()));
for (SyndEntry entry : feed.getEntries()) {
List<SyndEntry> entries = feed.getEntries();
// Calcular la fecha límite (hace 8 meses)
LocalDate currentDate = LocalDate.now();
LocalDate thresholdDate = currentDate.minusMonths(8);
int count = 0;
for (SyndEntry entry : entries) {
if (count >= 10) break;
Date pubDate = entry.getPublishedDate();
if (pubDate == null) continue;
LocalDate entryDate = pubDate.toInstant().atZone(ZoneId.systemDefault()).toLocalDate();
if (entryDate.isBefore(thresholdDate)) {
logger.info("Noticia descartada por antigüedad: {}", entry.getTitle());
continue;
}
String title = entry.getTitle();
String link = entry.getLink();
String description = (entry.getDescription() != null) ? entry.getDescription().getValue() : "Sin descripción";
String finalUrl = resolveFinalUrl(link);
String content = extractArticleContent(finalUrl);
newsList.add(new NewsArticle(title, description, finalUrl, content));
logger.info("Noticia {}: {}", (count + 1), title);
logger.info("Enlace: {}", finalUrl);
newsList.add(new NewsArticle(title, description, finalUrl));
count++;
}
logger.info("Total de noticias procesadas: {}", newsList.size());
} catch (Exception e) {
e.printStackTrace();
logger.error("Error al obtener las noticias", e);
}
return newsList;
}
@ -52,23 +85,13 @@ public class GoogleNewsScraperService {
conn.setInstanceFollowRedirects(true);
conn.setRequestProperty("User-Agent", USER_AGENT);
conn.connect();
return (conn.getHeaderField("Location") != null) ? conn.getHeaderField("Location") : url;
} catch (Exception e) {
return url;
}
}
String resolvedUrl = (conn.getHeaderField("Location") != null) ? conn.getHeaderField("Location") : url;
private String extractArticleContent(String url) {
try {
Document doc = Jsoup.connect(url).userAgent(USER_AGENT).get();
Elements paragraphs = doc.select("article p, .post-content p, .entry-content p, .content p, #article-body p");
StringBuilder content = new StringBuilder();
for (Element p : paragraphs) {
content.append(p.text()).append("\n");
}
return content.length() > 0 ? content.toString() : "No se encontró contenido relevante";
logger.debug("Redirección resuelta: {} → {}", url, resolvedUrl);
return resolvedUrl;
} catch (Exception e) {
return "Error al extraer contenido";
logger.warn("No se pudo resolver la URL: {}", url, e);
return url;
}
}
}

View File

@ -0,0 +1,69 @@
package es.imunnic.inversionitasBot.services;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.stereotype.Service;
import java.io.IOException;
import java.util.LinkedHashMap;
import java.util.Map;
@Service
public class ResultadosService {
private static final Logger logger = LoggerFactory.getLogger(ResultadosService.class);
private static final String USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36";
/**
* Realiza el scrap de los beneficios netos anuales de la empresa dada.
*
* @param companyName nombre de la empresa en la URL
* @return Mapa con años como clave y beneficio neto como valor
*/
public Map<String, String> getBeneficioNetoAnual(String companyName) {
Map<String, String> resultados = new LinkedHashMap<>();
String url = "https://es.investing.com/equities/" + companyName + "-financial-summary"; // Cambia esta URL a la real
logger.info("Scrapeando resultados financieros de: {}", companyName);
logger.info("URL objetivo: {}", url);
try {
Document doc = Jsoup.connect(url)
.userAgent(USER_AGENT)
.header("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
.header("Accept-Language", "es-ES,es;q=0.9")
.header("Referer", "https://www.google.com/")
.proxy("51.44.176.151", 20202)
.timeout(10000)
.get();
// Buscar la fila con el texto "Beneficio neto"
Elements filas = doc.select("tr");
for (Element fila : filas) {
Element primeraColumna = fila.selectFirst("td");
if (primeraColumna != null && primeraColumna.text().equalsIgnoreCase("Beneficio neto")) {
Elements celdas = fila.select("td");
for (int i = 2; i < celdas.size(); i++) { // Saltar los primeros <td> con el título
String texto = celdas.get(i).text().trim();
String año = String.valueOf(2020 + (i - 2)); // Ajusta esto si hay más o menos columnas
if (!texto.equals("-") && !texto.isEmpty()) {
resultados.put(año, texto);
logger.info("Año {} → Beneficio neto: {}", año, texto);
}
}
break;
}
}
} catch (IOException e) {
logger.error("Error durante el scraping de resultados de {}", companyName, e);
}
logger.info("Beneficios netos encontrados: {}", resultados.size());
return resultados;
}
}

View File

@ -0,0 +1,42 @@
package es.imunnic.inversionitasBot.services;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
public class Trends24Scrapper {
private static final String BASE_URL = "https://trends24.in/";
/**
* Obtiene los 20 primeros trending topics de Trends24 para el país especificado.
* @param country El país en inglés, tal como aparece en la URL (ejemplo: "united-states").
* @return Lista de trending topics (Strings).
* @throws IOException Si falla la conexión o parsing.
*/
public List<String> getTopTrends(String country) throws IOException {
String url = BASE_URL + country + "/";
Document doc = Jsoup.connect(url).get();
List<String> trends = new ArrayList<>();
Element trendList = doc.selectFirst("section#timeline ol.trend-card__list");
if (trendList != null) {
Elements trendElements = trendList.select("li .trend-name a");
for (int i = 0; i < Math.min(20, trendElements.size()); i++) {
Element trend = trendElements.get(i);
trends.add(trend.text());
}
} else {
System.out.println("❌ No se encontró la lista de tendencias.");
}
return trends;
}
}