Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| import requests | |
| import json | |
| import os | |
| from datetime import datetime, timedelta | |
| from concurrent.futures import ThreadPoolExecutor, as_completed | |
| from functools import lru_cache | |
| from requests.adapters import HTTPAdapter | |
| from requests.packages.urllib3.util.retry import Retry | |
| from openai import OpenAI | |
| from bs4 import BeautifulSoup | |
| import re | |
| import pathlib | |
| import sqlite3 | |
| import pytz | |
| # List of target companies/keywords (์๋ฌธ์ผ๋ก ๊ฒ์์ด๋ ๊ทธ๋๋ก ์ ์ง) | |
| KOREAN_COMPANIES = [ | |
| "NVIDIA", | |
| "ALPHABET", | |
| "APPLE", | |
| "TESLA", | |
| "AMAZON", | |
| "MICROSOFT", | |
| "META", | |
| "INTEL", | |
| "SAMSUNG", | |
| "HYNIX", | |
| "BITCOIN", | |
| "crypto", | |
| "stock", | |
| "Economics", | |
| "Finance", | |
| "investing" | |
| ] | |
| def convert_to_seoul_time(timestamp_str): | |
| """ | |
| ์ฃผ์ด์ง UTC ํ์์คํฌํ ๋ฌธ์์ด์ ์์ธ ์๊ฐ(KST)์ผ๋ก ๋ณํ. | |
| """ | |
| try: | |
| dt = datetime.strptime(timestamp_str, '%Y-%m-%d %H:%M:%S') | |
| seoul_tz = pytz.timezone('Asia/Seoul') | |
| seoul_time = seoul_tz.localize(dt) | |
| return seoul_time.strftime('%Y-%m-%d %H:%M:%S KST') | |
| except Exception as e: | |
| print(f"์๊ฐ ๋ณํ ์ค๋ฅ: {str(e)}") | |
| return timestamp_str | |
| def analyze_sentiment_batch(articles, client): | |
| """ | |
| OpenAI API๋ฅผ ์ฌ์ฉํ์ฌ ๋ด์ค ๊ธฐ์ฌ ๋ชจ์์ ๋ํ ์ ๋ฐ์ ์ธ ๊ฐ์ฑ ๋ถ์์ ์ํํ๋ค. | |
| ๋ถ์ ๊ฒฐ๊ณผ๋ ํ๊ธ๋ก ๋ฐํ๋๋ค. | |
| """ | |
| try: | |
| # ๋ชจ๋ ๊ธฐ์ฌ๋ฅผ ํ๋์ ํ ์คํธ๋ก ๊ฒฐํฉ | |
| combined_text = "\n\n".join([ | |
| f"์ ๋ชฉ: {article.get('title', '')}\n๋ด์ฉ: {article.get('snippet', '')}" | |
| for article in articles | |
| ]) | |
| prompt = f"""์๋ ๋ด์ค ๊ธฐ์ฌ ๋ชจ์์ ๋ํ ์ ๋ฐ์ ์ธ ๊ฐ์ฑ ๋ถ์์ ์ํํ์ธ์. | |
| ๋ด์ค ๋ด์ฉ: | |
| {combined_text} | |
| ๋ค์ ํ์์ ๋ฐ๋ผ ์์ฑํด ์ฃผ์ธ์: | |
| 1. ์ ์ฒด ๊ฐ์ฑ: [๊ธ์ /๋ถ์ /์ค๋ฆฝ] | |
| 2. ์ฃผ์ ๊ธ์ ์์ธ: | |
| - [ํญ๋ชฉ1] | |
| - [ํญ๋ชฉ2] | |
| 3. ์ฃผ์ ๋ถ์ ์์ธ: | |
| - [ํญ๋ชฉ1] | |
| - [ํญ๋ชฉ2] | |
| 4. ์์ฝ: [์์ธํ ์ค๋ช ] | |
| """ | |
| response = client.chat.completions.create( | |
| model="CohereForAI/c4ai-command-r-plus-08-2024", | |
| messages=[{"role": "user", "content": prompt}], | |
| temperature=0.3, | |
| max_tokens=1000 | |
| ) | |
| return response.choices[0].message.content | |
| except Exception as e: | |
| return f"๊ฐ์ฑ ๋ถ์ ์คํจ: {str(e)}" | |
| # ๋ฐ์ดํฐ๋ฒ ์ด์ค ์ด๊ธฐํ | |
| def init_db(): | |
| """ | |
| SQLite ๋ฐ์ดํฐ๋ฒ ์ด์ค(search_results.db)๋ฅผ ์ด๊ธฐํ (์์ผ๋ฉด ์์ฑ). | |
| """ | |
| db_path = pathlib.Path("search_results.db") | |
| conn = sqlite3.connect(db_path) | |
| c = conn.cursor() | |
| c.execute('''CREATE TABLE IF NOT EXISTS searches | |
| (id INTEGER PRIMARY KEY AUTOINCREMENT, | |
| keyword TEXT, | |
| country TEXT, | |
| results TEXT, | |
| timestamp DATETIME DEFAULT CURRENT_TIMESTAMP)''') | |
| conn.commit() | |
| conn.close() | |
| def save_to_db(keyword, country, results): | |
| """ | |
| ํน์ (ํค์๋, ๊ตญ๊ฐ) ์กฐํฉ์ ๋ํ ๊ฒ์ ๊ฒฐ๊ณผ๋ฅผ ๋ฐ์ดํฐ๋ฒ ์ด์ค์ ์ ์ฅ. | |
| """ | |
| conn = sqlite3.connect("search_results.db") | |
| c = conn.cursor() | |
| seoul_tz = pytz.timezone('Asia/Seoul') | |
| now = datetime.now(seoul_tz) | |
| timestamp = now.strftime('%Y-%m-%d %H:%M:%S') | |
| c.execute("""INSERT INTO searches | |
| (keyword, country, results, timestamp) | |
| VALUES (?, ?, ?, ?)""", | |
| (keyword, country, json.dumps(results), timestamp)) | |
| conn.commit() | |
| conn.close() | |
| def load_from_db(keyword, country): | |
| """ | |
| ํน์ (ํค์๋, ๊ตญ๊ฐ) ์กฐํฉ์ ๋ํ ๊ฐ์ฅ ์ต๊ทผ ๊ฒ์ ๊ฒฐ๊ณผ๋ฅผ ๋ฐ์ดํฐ๋ฒ ์ด์ค์์ ๋ถ๋ฌ์ด. | |
| ๋ฐ์ดํฐ๋ฅผ ๋ถ๋ฌ์ค๊ณ ํ์์คํฌํ๋ฅผ ๋ณํํ์ฌ ๋ฐํ. | |
| """ | |
| conn = sqlite3.connect("search_results.db") | |
| c = conn.cursor() | |
| c.execute( | |
| "SELECT results, timestamp FROM searches WHERE keyword=? AND country=? ORDER BY timestamp DESC LIMIT 1", | |
| (keyword, country) | |
| ) | |
| result = c.fetchone() | |
| conn.close() | |
| if result: | |
| return json.loads(result[0]), convert_to_seoul_time(result[1]) | |
| return None, None | |
| def display_results(articles): | |
| """ | |
| ๋ด์ค ๊ธฐ์ฌ ๋ชฉ๋ก์ ๋งํฌ๋ค์ด ๋ฌธ์์ด๋ก ๋ณํํ์ฌ ๋ฐํ. | |
| """ | |
| output = "" | |
| for idx, article in enumerate(articles, 1): | |
| output += f"### {idx}. {article['title']}\n" | |
| output += f"์ถ์ฒ: {article['channel']}\n" | |
| output += f"์๊ฐ: {article['time']}\n" | |
| output += f"๋งํฌ: {article['link']}\n" | |
| output += f"์์ฝ: {article['snippet']}\n\n" | |
| return output | |
| ######################################## | |
| # 1) ๊ฒ์ => ๊ธฐ์ฌ + ๊ฐ์ฑ ๋ถ์, DB ์ ์ฅ | |
| ######################################## | |
| def search_company(company): | |
| """ | |
| ๋จ์ผ ํ์ฌ(๋๋ ํค์๋)์ ๋ํด ๋ฏธ๊ตญ ๋ด์ค ๊ฒ์์ ์งํ: | |
| 1) ๊ธฐ์ฌ ๋ชฉ๋ก์ ๊ฒ์ | |
| 2) ๊ฐ์ฑ ๋ถ์ ์ํ | |
| 3) ๊ฒฐ๊ณผ๋ฅผ DB์ ์ ์ฅ | |
| 4) ๊ธฐ์ฌ์ ๋ถ์ ๊ฒฐ๊ณผ๋ฅผ ํ๋์ ์ถ๋ ฅ์ผ๋ก ๋ฐํ | |
| """ | |
| error_message, articles = serphouse_search(company, "United States") | |
| if not error_message and articles: | |
| # ๊ฐ์ฑ ๋ถ์ ์ํ (ํ๊ธ ๊ฒฐ๊ณผ ๋ฐํ) | |
| analysis = analyze_sentiment_batch(articles, client) | |
| # DB์ ์ ์ฅํ ๋ฐ์ดํฐ ์ค๋น | |
| store_dict = { | |
| "articles": articles, | |
| "analysis": analysis | |
| } | |
| save_to_db(company, "United States", store_dict) | |
| # ์ถ๋ ฅ์ฉ ๋ฐ์ดํฐ ์ค๋น | |
| output = display_results(articles) | |
| output += f"\n\n### ๊ฐ์ฑ ๋ถ์ ๋ณด๊ณ ์\n{analysis}\n" | |
| return output | |
| return f"{company}์ ๋ํ ๊ฒ์ ๊ฒฐ๊ณผ๊ฐ ์์ต๋๋ค." | |
| ######################################## | |
| # 2) ๋ถ๋ฌ์ค๊ธฐ => DB์์ ๊ธฐ์ฌ + ๋ถ์ ๊ฒฐ๊ณผ ๋ฐํ | |
| ######################################## | |
| def load_company(company): | |
| """ | |
| ์ฃผ์ด์ง ํ์ฌ(๋๋ ํค์๋)์ ๋ํด ๋ฐ์ดํฐ๋ฒ ์ด์ค์์ ๊ฐ์ฅ ์ต๊ทผ ๋ฏธ๊ตญ ๋ด์ค ๊ฒ์ ๊ฒฐ๊ณผ(๊ธฐ์ฌ + ๊ฐ์ฑ ๋ถ์)๋ฅผ ๋ถ๋ฌ์ด. | |
| """ | |
| data, timestamp = load_from_db(company, "United States") | |
| if data: | |
| articles = data.get("articles", []) | |
| analysis = data.get("analysis", "") | |
| output = f"### {company} ๊ฒ์ ๊ฒฐ๊ณผ\n๋ง์ง๋ง ์ ๋ฐ์ดํธ: {timestamp}\n\n" | |
| output += display_results(articles) | |
| output += f"\n\n### ๊ฐ์ฑ ๋ถ์ ๋ณด๊ณ ์\n{analysis}\n" | |
| return output | |
| return f"{company}์ ๋ํ ์ ์ฅ๋ ๊ฒฐ๊ณผ๊ฐ ์์ต๋๋ค." | |
| ######################################## | |
| # 3) show_stats() โ ๋ณด๊ณ ์ ์ ๋ชฉ ๋ณ๊ฒฝ | |
| ######################################## | |
| def show_stats(): | |
| """ | |
| ๊ฐ ํ์ฌ(KOREAN_COMPANIES)์ ๋ํด: | |
| - DB์ ์ ์ฅ๋ ์ต์ ํ์์คํฌํ | |
| - ์ ์ฅ๋ ๊ธฐ์ฌ ๊ฐ์ | |
| - ๊ฐ์ฑ ๋ถ์ ๊ฒฐ๊ณผ | |
| ์ ๋ณด๊ณ ์ ํ์์ผ๋ก ๋ฐํ. | |
| ์ ๋ชฉ: "EarnBOT ๋ถ์ ๋ณด๊ณ ์" | |
| """ | |
| conn = sqlite3.connect("search_results.db") | |
| c = conn.cursor() | |
| output = "## EarnBOT ๋ถ์ ๋ณด๊ณ ์\n\n" | |
| data_list = [] | |
| for company in KOREAN_COMPANIES: | |
| c.execute(""" | |
| SELECT results, timestamp | |
| FROM searches | |
| WHERE keyword = ? | |
| ORDER BY timestamp DESC | |
| LIMIT 1 | |
| """, (company,)) | |
| row = c.fetchone() | |
| if row: | |
| results_json, timestamp = row | |
| data_list.append((company, timestamp, results_json)) | |
| conn.close() | |
| def analyze_data(item): | |
| comp, tstamp, results_json = item | |
| data = json.loads(results_json) | |
| articles = data.get("articles", []) | |
| analysis = data.get("analysis", "") | |
| count_articles = len(articles) | |
| return (comp, tstamp, count_articles, analysis) | |
| results_list = [] | |
| with ThreadPoolExecutor(max_workers=5) as executor: | |
| futures = [executor.submit(analyze_data, dl) for dl in data_list] | |
| for future in as_completed(futures): | |
| results_list.append(future.result()) | |
| for comp, tstamp, count, analysis in results_list: | |
| seoul_time = convert_to_seoul_time(tstamp) | |
| output += f"### {comp}\n" | |
| output += f"- ๋ง์ง๋ง ์ ๋ฐ์ดํธ: {seoul_time}\n" | |
| output += f"- ์ ์ฅ๋ ๊ธฐ์ฌ ์: {count}\n\n" | |
| if analysis: | |
| output += "#### ๋ด์ค ๊ฐ์ฑ ๋ถ์\n" | |
| output += f"{analysis}\n\n" | |
| output += "---\n\n" | |
| return output | |
| def search_all_companies(): | |
| """ | |
| KOREAN_COMPANIES์ ๋ชจ๋ ํญ๋ชฉ์ ๋ํด(๋ณ๋ ฌ ์ฒ๋ฆฌ) ๊ฒ์ ํ, | |
| ๊ฐ์ฑ ๋ถ์ ์ํ ๋ฐ DB ์ ์ฅ => ๋ชจ๋ ๊ฒฐ๊ณผ๋ฅผ ๋งํฌ๋ค์ด ๋ฌธ์์ด๋ก ๋ฐํ. | |
| """ | |
| overall_result = "# [์ ์ฒด ํ์ฌ ๊ฒ์ ๊ฒฐ๊ณผ]\n\n" | |
| def do_search(comp): | |
| return comp, search_company(comp) | |
| with ThreadPoolExecutor(max_workers=5) as executor: | |
| futures = [executor.submit(do_search, c) for c in KOREAN_COMPANIES] | |
| for future in as_completed(futures): | |
| comp, res_text = future.result() | |
| overall_result += f"## {comp}\n" | |
| overall_result += res_text + "\n\n" | |
| return overall_result | |
| def load_all_companies(): | |
| """ | |
| DB์ ์ ์ฅ๋ ๋ชจ๋ ํ์ฌ(KOREAN_COMPANIES)์ ๊ธฐ์ฌ์ ๋ถ์ ๊ฒฐ๊ณผ๋ฅผ ๋ถ๋ฌ์ ๋งํฌ๋ค์ด์ผ๋ก ๋ฐํ. | |
| """ | |
| overall_result = "# [์ ์ฒด ํ์ฌ ๋ฐ์ดํฐ ์ถ๋ ฅ]\n\n" | |
| for comp in KOREAN_COMPANIES: | |
| overall_result += f"## {comp}\n" | |
| overall_result += load_company(comp) | |
| overall_result += "\n" | |
| return overall_result | |
| def full_summary_report(): | |
| """ | |
| 1) ๋ชจ๋ ํ์ฌ๋ฅผ ๊ฒ์(๋ณ๋ ฌ ์ฒ๋ฆฌ) -> 2) DB์์ ๊ฒฐ๊ณผ ๋ถ๋ฌ์ค๊ธฐ -> 3) ๊ฐ์ฑ ๋ถ์ ํต๊ณ ํ์ | |
| ์ธ ๋จ๊ณ์ ๊ฒฐ๊ณผ๋ฅผ ํ๋์ ์ข ํฉ ๋ณด๊ณ ์๋ก ๋ฐํ. | |
| """ | |
| # 1) ๋ชจ๋ ํ์ฌ ๊ฒ์ ๋ฐ DB ์ ์ฅ | |
| search_result_text = search_all_companies() | |
| # 2) DB์์ ๊ฒฐ๊ณผ ๋ถ๋ฌ์ค๊ธฐ | |
| load_result_text = load_all_companies() | |
| # 3) ํต๊ณ ํ์ โ EarnBOT ๋ถ์ ๋ณด๊ณ ์ | |
| stats_text = show_stats() | |
| combined_report = ( | |
| "# ์ ์ฒด ๋ถ์ ์ข ํฉ ๋ณด๊ณ ์\n\n" | |
| "์คํ ์์:\n" | |
| "1. ๋ชจ๋ ํ์ฌ ๊ฒ์(๋ณ๋ ฌ ์ฒ๋ฆฌ) ๋ฐ ๊ฐ์ฑ ๋ถ์ โ 2. DB์์ ๊ฒฐ๊ณผ ๋ถ๋ฌ์ค๊ธฐ โ 3. ์ ์ฒด ๊ฐ์ฑ ๋ถ์ ํต๊ณ ํ์\n\n" | |
| f"{search_result_text}\n\n" | |
| f"{load_result_text}\n\n" | |
| "## [์ ์ฒด ๊ฐ์ฑ ๋ถ์ ํต๊ณ]\n\n" | |
| f"{stats_text}" | |
| ) | |
| return combined_report | |
| ######################################## | |
| # ์ถ๊ฐ ๊ธฐ๋ฅ: ์ฌ์ฉ์ ์ ์ ๊ฒ์ | |
| ######################################## | |
| def search_custom(query, country): | |
| """ | |
| ์ฌ์ฉ์๊ฐ ์ ๋ ฅํ (ํค์๋, ๊ตญ๊ฐ)์ ๋ํด: | |
| 1) ๊ฒ์ ๋ฐ ๊ฐ์ฑ ๋ถ์ ์ํ ํ DB ์ ์ฅ | |
| 2) DB์์ ๋ถ๋ฌ์ ๊ธฐ์ฌ์ ๋ถ์ ๊ฒฐ๊ณผ ํ์ | |
| """ | |
| error_message, articles = serphouse_search(query, country) | |
| if error_message: | |
| return f"์ค๋ฅ ๋ฐ์: {error_message}" | |
| if not articles: | |
| return "์ ๋ ฅํ์ ๊ฒ์์ด์ ๋ํ ๊ฒฐ๊ณผ๊ฐ ์์ต๋๋ค." | |
| # 1) ๊ฐ์ฑ ๋ถ์ ์ํ (ํ๊ธ) | |
| analysis = analyze_sentiment_batch(articles, client) | |
| # 2) DB์ ์ ์ฅ | |
| save_data = { | |
| "articles": articles, | |
| "analysis": analysis | |
| } | |
| save_to_db(query, country, save_data) | |
| # 3) DB์์ ๋ถ๋ฌ์ค๊ธฐ | |
| loaded_data, timestamp = load_from_db(query, country) | |
| if not loaded_data: | |
| return "DB์์ ๋ฐ์ดํฐ๋ฅผ ๋ถ๋ฌ์ค์ง ๋ชปํ์ต๋๋ค." | |
| # 4) ์ต์ข ์ถ๋ ฅ ์ค๋น | |
| out = f"## [์ฌ์ฉ์ ์ ์ ๊ฒ์ ๊ฒฐ๊ณผ]\n\n" | |
| out += f"**๊ฒ์์ด**: {query}\n\n" | |
| out += f"**๊ตญ๊ฐ**: {country}\n\n" | |
| out += f"**ํ์์คํฌํ**: {timestamp}\n\n" | |
| arts = loaded_data.get("articles", []) | |
| analy = loaded_data.get("analysis", "") | |
| out += display_results(arts) | |
| out += f"### ๋ด์ค ๊ฐ์ฑ ๋ถ์\n{analy}\n" | |
| return out | |
| ######################################## | |
| # API ์ธ์ฆ ์ค์ | |
| ######################################## | |
| ACCESS_TOKEN = os.getenv("HF_TOKEN") | |
| if not ACCESS_TOKEN: | |
| raise ValueError("HF_TOKEN ํ๊ฒฝ๋ณ์๊ฐ ์ค์ ๋์ด ์์ง ์์ต๋๋ค.") | |
| client = OpenAI( | |
| base_url="https://api-inference.huggingface.co/v1/", | |
| api_key=ACCESS_TOKEN, | |
| ) | |
| API_KEY = os.getenv("SERPHOUSE_API_KEY") | |
| ######################################## | |
| # ๊ตญ๊ฐ๋ณ ์ค์ | |
| ######################################## | |
| COUNTRY_LANGUAGES = { | |
| "United States": "en", | |
| "KOREA": "ko", | |
| "United Kingdom": "en", | |
| "Taiwan": "zh-TW", | |
| "Canada": "en", | |
| "Australia": "en", | |
| "Germany": "de", | |
| "France": "fr", | |
| "Japan": "ja", | |
| "India": "hi", | |
| "Brazil": "pt", | |
| "Mexico": "es", | |
| "Russia": "ru", | |
| "Italy": "it", | |
| "Spain": "es", | |
| "Netherlands": "nl", | |
| "Singapore": "en", | |
| "Hong Kong": "zh-HK", | |
| "Indonesia": "id", | |
| "Malaysia": "ms", | |
| "Philippines": "tl", | |
| "Thailand": "th", | |
| "Vietnam": "vi", | |
| "Belgium": "nl", | |
| "Denmark": "da", | |
| "Finland": "fi", | |
| "Ireland": "en", | |
| "Norway": "no", | |
| "Poland": "pl", | |
| "Sweden": "sv", | |
| "Switzerland": "de", | |
| "Austria": "de", | |
| "Czech Republic": "cs", | |
| "Greece": "el", | |
| "Hungary": "hu", | |
| "Portugal": "pt", | |
| "Romania": "ro", | |
| "Turkey": "tr", | |
| "Israel": "he", | |
| "Saudi Arabia": "ar", | |
| "United Arab Emirates": "ar", | |
| "South Africa": "en", | |
| "Argentina": "es", | |
| "Chile": "es", | |
| "Colombia": "es", | |
| "Peru": "es", | |
| "Venezuela": "es", | |
| "New Zealand": "en", | |
| "Bangladesh": "bn", | |
| "Pakistan": "ur", | |
| "Egypt": "ar", | |
| "Morocco": "ar", | |
| "Nigeria": "en", | |
| "Kenya": "sw", | |
| "Ukraine": "uk", | |
| "Croatia": "Croatia", | |
| "Slovakia": "Slovakia", | |
| "Bulgaria": "bg", | |
| "Serbia": "sr", | |
| "Estonia": "et", | |
| "Latvia": "lv", | |
| "Lithuania": "lt", | |
| "Slovenia": "sl", | |
| "Luxembourg": "Luxembourg", | |
| "Malta": "Malta", | |
| "Cyprus": "Cyprus", | |
| "Iceland": "Iceland" | |
| } | |
| COUNTRY_LOCATIONS = { | |
| "United States": "United States", | |
| "KOREA": "kr", | |
| "United Kingdom": "United Kingdom", | |
| "Taiwan": "Taiwan", | |
| "Canada": "Canada", | |
| "Australia": "Australia", | |
| "Germany": "Germany", | |
| "France": "France", | |
| "Japan": "Japan", | |
| "India": "India", | |
| "Brazil": "Brazil", | |
| "Mexico": "Mexico", | |
| "Russia": "Russia", | |
| "Italy": "Italy", | |
| "Spain": "Spain", | |
| "Netherlands": "Netherlands", | |
| "Singapore": "Singapore", | |
| "Hong Kong": "Hong Kong", | |
| "Indonesia": "Indonesia", | |
| "Malaysia": "Malaysia", | |
| "Philippines": "Philippines", | |
| "Thailand": "Thailand", | |
| "Vietnam": "Vietnam", | |
| "Belgium": "Belgium", | |
| "Denmark": "Denmark", | |
| "Finland": "Finland", | |
| "Ireland": "Ireland", | |
| "Norway": "Norway", | |
| "Poland": "Poland", | |
| "Sweden": "Sweden", | |
| "Switzerland": "Switzerland", | |
| "Austria": "Austria", | |
| "Czech Republic": "Czech Republic", | |
| "Greece": "Greece", | |
| "Hungary": "Hungary", | |
| "Portugal": "Portugal", | |
| "Romania": "Romania", | |
| "Turkey": "Turkey", | |
| "Israel": "Israel", | |
| "Saudi Arabia": "Saudi Arabia", | |
| "United Arab Emirates": "United Arab Emirates", | |
| "South Africa": "South Africa", | |
| "Argentina": "Argentina", | |
| "Chile": "Chile", | |
| "Colombia": "Colombia", | |
| "Peru": "Peru", | |
| "Venezuela": "Venezuela", | |
| "New Zealand": "New Zealand", | |
| "Bangladesh": "Bangladesh", | |
| "Pakistan": "Pakistan", | |
| "Egypt": "Egypt", | |
| "Morocco": "Morocco", | |
| "Nigeria": "Nigeria", | |
| "Kenya": "Kenya", | |
| "Ukraine": "Ukraine", | |
| "Croatia": "Croatia", | |
| "Slovakia": "Slovakia", | |
| "Bulgaria": "Bulgaria", | |
| "Serbia": "Serbia", | |
| "Estonia": "et", | |
| "Latvia": "lv", | |
| "Lithuania": "lt", | |
| "Slovenia": "sl", | |
| "Luxembourg": "Luxembourg", | |
| "Malta": "Malta", | |
| "Cyprus": "Cyprus", | |
| "Iceland": "Iceland" | |
| } | |
| def translate_query(query, country): | |
| """ | |
| ๋น๊ณต์ Google Translation API๋ฅผ ์ฌ์ฉํด ๋์ ๊ตญ๊ฐ์ ์ธ์ด๋ก ๊ฒ์์ด ๋ฒ์ญ. | |
| ๋ฒ์ญ์ ์คํจํ๊ฑฐ๋ ์์ด์ผ ๊ฒฝ์ฐ ์๋ณธ ๊ฒ์์ด ๋ฐํ. | |
| """ | |
| try: | |
| if is_english(query): | |
| return query | |
| if country in COUNTRY_LANGUAGES: | |
| if country == "South Korea": | |
| return query | |
| target_lang = COUNTRY_LANGUAGES[country] | |
| url = "https://translate.googleapis.com/translate_a/single" | |
| params = { | |
| "client": "gtx", | |
| "sl": "auto", | |
| "tl": target_lang, | |
| "dt": "t", | |
| "q": query | |
| } | |
| session = requests.Session() | |
| retries = Retry(total=3, backoff_factor=0.5) | |
| session.mount('https://', HTTPAdapter(max_retries=retries)) | |
| response = session.get(url, params=params, timeout=(5, 10)) | |
| translated_text = response.json()[0][0][0] | |
| return translated_text | |
| return query | |
| except Exception as e: | |
| print(f"๋ฒ์ญ ์ค๋ฅ: {str(e)}") | |
| return query | |
| def is_english(text): | |
| """ | |
| ๋ฌธ์์ด์ด ์ฃผ๋ก ์์ด์ธ์ง ํ์ธ (๋ฌธ์ ์ฝ๋ ๋ฒ์ ํ์ธ). | |
| """ | |
| return all(ord(char) < 128 for char in text.replace(' ', '').replace('-', '').replace('_', '')) | |
| def search_serphouse(query, country, page=1, num_result=10): | |
| """ | |
| SerpHouse API์ ์ค์๊ฐ ๊ฒ์ ์์ฒญ์ ๋ณด๋ด๋ฉฐ, | |
| 'news' ํญ(๋ ์ง์ ์ ๋ ฌ)๋ก ๊ฒ์. | |
| ๋ฐํ๊ฐ์ 'results' ๋๋ 'error'๊ฐ ํฌํจ๋ dict. | |
| """ | |
| url = "https://api.serphouse.com/serp/live" | |
| now = datetime.utcnow() | |
| yesterday = now - timedelta(days=1) | |
| date_range = f"{yesterday.strftime('%Y-%m-%d')},{now.strftime('%Y-%m-%d')}" | |
| translated_query = translate_query(query, country) | |
| payload = { | |
| "data": { | |
| "q": translated_query, | |
| "domain": "google.com", | |
| "loc": COUNTRY_LOCATIONS.get(country, "United States"), | |
| "lang": COUNTRY_LANGUAGES.get(country, "en"), | |
| "device": "desktop", | |
| "serp_type": "news", | |
| "page": str(page), | |
| "num": "100", | |
| "date_range": date_range, | |
| "sort_by": "date" | |
| } | |
| } | |
| headers = { | |
| "accept": "application/json", | |
| "content-type": "application/json", | |
| "authorization": f"Bearer {API_KEY}" | |
| } | |
| try: | |
| session = requests.Session() | |
| retries = Retry( | |
| total=5, | |
| backoff_factor=1, | |
| status_forcelist=[500, 502, 503, 504, 429], | |
| allowed_methods=["POST"] | |
| ) | |
| adapter = HTTPAdapter(max_retries=retries) | |
| session.mount('http://', adapter) | |
| session.mount('https://', adapter) | |
| response = session.post( | |
| url, | |
| json=payload, | |
| headers=headers, | |
| timeout=(30, 30) | |
| ) | |
| response.raise_for_status() | |
| return {"results": response.json(), "translated_query": translated_query} | |
| except requests.exceptions.Timeout: | |
| return { | |
| "error": "๊ฒ์ ์๊ฐ์ด ์ด๊ณผ๋์์ต๋๋ค. ์ ์ ํ ๋ค์ ์๋ํด ์ฃผ์ธ์.", | |
| "translated_query": query | |
| } | |
| except requests.exceptions.RequestException as e: | |
| return { | |
| "error": f"๊ฒ์ ์ค ์ค๋ฅ ๋ฐ์: {str(e)}", | |
| "translated_query": query | |
| } | |
| except Exception as e: | |
| return { | |
| "error": f"์์์น ๋ชปํ ์ค๋ฅ ๋ฐ์: {str(e)}", | |
| "translated_query": query | |
| } | |
| def format_results_from_raw(response_data): | |
| """ | |
| SerpHouse API์ ์๋ต ๋ฐ์ดํฐ๋ฅผ ์ฒ๋ฆฌํ์ฌ (์ค๋ฅ ๋ฉ์์ง, ๊ธฐ์ฌ ๋ชฉ๋ก)์ ๋ฐํ. | |
| """ | |
| if "error" in response_data: | |
| return "์ค๋ฅ: " + response_data["error"], [] | |
| try: | |
| results = response_data["results"] | |
| translated_query = response_data["translated_query"] | |
| news_results = results.get('results', {}).get('results', {}).get('news', []) | |
| if not news_results: | |
| return "๊ฒ์ ๊ฒฐ๊ณผ๊ฐ ์์ต๋๋ค.", [] | |
| # ํ๊ตญ ๋๋ฉ์ธ ๋ฐ ํค์๋ ํํฐ๋ง (์์) | |
| korean_domains = [ | |
| '.kr', 'korea', 'korean', 'yonhap', 'hankyung', 'chosun', | |
| 'donga', 'joins', 'hani', 'koreatimes', 'koreaherald' | |
| ] | |
| korean_keywords = [ | |
| 'korea', 'korean', 'seoul', 'busan', 'incheon', 'daegu', | |
| 'gwangju', 'daejeon', 'ulsan', 'sejong' | |
| ] | |
| filtered_articles = [] | |
| for idx, result in enumerate(news_results, 1): | |
| url = result.get("url", result.get("link", "")).lower() | |
| title = result.get("title", "").lower() | |
| channel = result.get("channel", result.get("source", "")).lower() | |
| is_korean_content = ( | |
| any(domain in url or domain in channel for domain in korean_domains) or | |
| any(keyword in title for keyword in korean_keywords) | |
| ) | |
| # ํ๊ตญ ๊ด๋ จ ์ฝํ ์ธ ์ ์ธ | |
| if not is_korean_content: | |
| filtered_articles.append({ | |
| "index": idx, | |
| "title": result.get("title", "์ ๋ชฉ ์์"), | |
| "link": url, | |
| "snippet": result.get("snippet", "๋ด์ฉ ์์"), | |
| "channel": result.get("channel", result.get("source", "์ ์ ์์")), | |
| "time": result.get("time", result.get("date", "์๊ฐ ์ ๋ณด ์์")), | |
| "image_url": result.get("img", result.get("thumbnail", "")), | |
| "translated_query": translated_query | |
| }) | |
| return "", filtered_articles | |
| except Exception as e: | |
| return f"๊ฒฐ๊ณผ ์ฒ๋ฆฌ ์ค ์ค๋ฅ ๋ฐ์: {str(e)}", [] | |
| def serphouse_search(query, country): | |
| """ | |
| ๊ฒ์ ๋ฐ ๊ฒฐ๊ณผ ํฌ๋งทํ ์ ์ํ ํฌํผ ํจ์. | |
| (์ค๋ฅ ๋ฉ์์ง, ๊ธฐ์ฌ ๋ชฉ๋ก)์ ๋ฐํ. | |
| """ | |
| response_data = search_serphouse(query, country) | |
| return format_results_from_raw(response_data) | |
| # Refined, modern, and sleek custom CSS | |
| css = """ | |
| body { | |
| background: linear-gradient(to bottom right, #f9fafb, #ffffff); | |
| font-family: 'Arial', sans-serif; | |
| } | |
| /* Hide default Gradio footer */ | |
| footer { | |
| visibility: hidden; | |
| } | |
| /* Header/Status area */ | |
| #status_area { | |
| background: rgba(255, 255, 255, 0.9); | |
| padding: 15px; | |
| border-bottom: 1px solid #ddd; | |
| margin-bottom: 20px; | |
| box-shadow: 0 2px 5px rgba(0,0,0,0.1); | |
| } | |
| /* Results area */ | |
| #results_area { | |
| padding: 10px; | |
| margin-top: 10px; | |
| } | |
| /* Tabs style */ | |
| .tabs { | |
| border-bottom: 2px solid #ddd !important; | |
| margin-bottom: 20px !important; | |
| } | |
| .tab-nav { | |
| border-bottom: none !important; | |
| margin-bottom: 0 !important; | |
| } | |
| .tab-nav button { | |
| font-weight: bold !important; | |
| padding: 10px 20px !important; | |
| background-color: #f0f0f0 !important; | |
| border: 1px solid #ccc !important; | |
| border-radius: 5px !important; | |
| margin-right: 5px !important; | |
| } | |
| .tab-nav button.selected { | |
| border-bottom: 2px solid #1f77b4 !important; | |
| background-color: #e6f2fa !important; | |
| color: #1f77b4 !important; | |
| } | |
| /* Status message styling */ | |
| #status_area .markdown-text { | |
| font-size: 1.1em; | |
| color: #2c3e50; | |
| padding: 10px 0; | |
| } | |
| /* Main container grouping */ | |
| .group { | |
| border: 1px solid #eee; | |
| padding: 15px; | |
| margin-bottom: 15px; | |
| border-radius: 5px; | |
| background: white; | |
| transition: all 0.3s ease; | |
| opacity: 0; | |
| transform: translateY(20px); | |
| } | |
| .group.visible { | |
| opacity: 1; | |
| transform: translateY(0); | |
| } | |
| /* Buttons */ | |
| .primary-btn { | |
| background: #1f77b4 !important; | |
| border: none !important; | |
| color: #fff !important; | |
| border-radius: 5px !important; | |
| padding: 10px 20px !important; | |
| cursor: pointer !important; | |
| } | |
| .primary-btn:hover { | |
| background: #155a8c !important; | |
| } | |
| .secondary-btn { | |
| background: #f0f0f0 !important; | |
| border: 1px solid #ccc !important; | |
| color: #333 !important; | |
| border-radius: 5px !important; | |
| padding: 10px 20px !important; | |
| cursor: pointer !important; | |
| } | |
| .secondary-btn:hover { | |
| background: #e0e0e0 !important; | |
| } | |
| /* Input fields */ | |
| .textbox { | |
| border: 1px solid #ddd !important; | |
| border-radius: 4px !important; | |
| } | |
| /* Progress bar container */ | |
| .progress-container { | |
| position: fixed; | |
| top: 0; | |
| left: 0; | |
| width: 100%; | |
| height: 6px; | |
| background: #e0e0e0; | |
| z-index: 1000; | |
| } | |
| /* Progress bar */ | |
| .progress-bar { | |
| height: 100%; | |
| background: linear-gradient(90deg, #2196F3, #00BCD4); | |
| box-shadow: 0 0 10px rgba(33, 150, 243, 0.5); | |
| transition: width 0.3s ease; | |
| animation: progress-glow 1.5s ease-in-out infinite; | |
| } | |
| /* Progress text */ | |
| .progress-text { | |
| position: fixed; | |
| top: 8px; | |
| left: 50%; | |
| transform: translateX(-50%); | |
| background: #333; | |
| color: white; | |
| padding: 4px 12px; | |
| border-radius: 15px; | |
| font-size: 14px; | |
| z-index: 1001; | |
| box-shadow: 0 2px 5px rgba(0,0,0,0.2); | |
| } | |
| /* Progress bar animation */ | |
| @keyframes progress-glow { | |
| 0% { | |
| box-shadow: 0 0 5px rgba(33, 150, 243, 0.5); | |
| } | |
| 50% { | |
| box-shadow: 0 0 20px rgba(33, 150, 243, 0.8); | |
| } | |
| 100% { | |
| box-shadow: 0 0 5px rgba(33, 150, 243, 0.5); | |
| } | |
| } | |
| /* Loading state */ | |
| .loading { | |
| opacity: 0.7; | |
| pointer-events: none; | |
| transition: opacity 0.3s ease; | |
| } | |
| /* Responsive design for smaller screens */ | |
| @media (max-width: 768px) { | |
| .group { | |
| padding: 10px; | |
| margin-bottom: 15px; | |
| } | |
| .progress-text { | |
| font-size: 12px; | |
| padding: 3px 10px; | |
| } | |
| } | |
| /* Example section styling */ | |
| .examples-table { | |
| margin-top: 10px !important; | |
| margin-bottom: 20px !important; | |
| } | |
| .examples-table button { | |
| background-color: #f0f0f0 !important; | |
| border: 1px solid #ddd !important; | |
| border-radius: 4px !important; | |
| padding: 5px 10px !important; | |
| margin: 2px !important; | |
| transition: all 0.3s ease !important; | |
| } | |
| .examples-table button:hover { | |
| background-color: #e0e0e0 !important; | |
| transform: translateY(-1px) !important; | |
| box-shadow: 0 2px 5px rgba(0,0,0,0.1) !important; | |
| } | |
| .examples-table .label { | |
| font-weight: bold !important; | |
| color: #444 !important; | |
| margin-bottom: 5px !important; | |
| } | |
| """ | |
| # --- Gradio ์ธํฐํ์ด์ค (UI ๋ถ๋ถ) --- | |
| with gr.Blocks(css=css, title="NewsAI ์๋น์ค") as iface: | |
| # ๋ฐ์ดํฐ๋ฒ ์ด์ค ์ด๊ธฐํ (init_db() ํธ์ถ) | |
| init_db() | |
| gr.HTML("""<a href="https://visitorbadge.io/status?path=https%3A%2F%2Fopenfree-MoneyRadar.hf.space"> | |
| <img src="https://api.visitorbadge.io/api/visitors?path=https%3A%2F%2Fopenfree-MoneyRadar.hf.space&countColor=%23263759" /> | |
| </a>""") | |
| with gr.Tabs(): | |
| with gr.Tab("MoneyRadar"): | |
| # ์ฌ์ฉ ๋ฐฉ๋ฒ ๋ฐ ๊ธฐ๋ฅ ์ค๋ช (ํ๊ธ) | |
| gr.Markdown( | |
| """ | |
| ## MoneyRadar | |
| ์ต์ 24์๊ฐ ๋ด ์์ 100๊ฐ์ ์ฐ์ ์์ ๋ด์ค๋ฅผ ์๋์ผ๋ก ์ถ์ถํ์ฌ | |
| ์์ต ๊ธฐํ๋ฅผ ํฌ์ฐฉํฉ๋๋ค. | |
| **์๋น์ค ์ฌ์ฉ ๋ฐฉ๋ฒ**: | |
| 1. **์ฌ์ฉ์ ์ ์ ๊ฒ์**: ํค์๋๋ฅผ ์ ๋ ฅํ๊ณ ๋์ ๊ตญ๊ฐ๋ฅผ ์ ํํ์ฌ ์ต์ ๋ด์ค๋ฅผ ๊ฐ์ ธ์ต๋๋ค. | |
| ์์คํ ์ด ์๋์ผ๋ก ๊ฐ์ฑ ๋ถ์์ ์ํํ๊ณ ๊ฒฐ๊ณผ๋ฅผ ๋ฐ์ดํฐ๋ฒ ์ด์ค์ ์ ์ฅํฉ๋๋ค. | |
| 2. **์ ์ฒด ๋ถ์ ์ข ํฉ ๋ณด๊ณ ์ ์์ฑ**: ์๋ ์์ ์ ์๋์ผ๋ก ์ํํฉ๋๋ค. | |
| - ์ฌ์ ์ ์๋ ๋ชจ๋ ํ์ฌ๋ฅผ ๋ณ๋ ฌ๋ก ๊ฒ์ | |
| - ๊ธฐ์ฌ์ ๊ฐ์ฑ ๋ถ์ ๊ฒฐ๊ณผ๋ฅผ ๋ฐ์ดํฐ๋ฒ ์ด์ค์ ์ ์ฅ | |
| - ์ ์ฒด ๊ฒฐ๊ณผ๋ฅผ ์ข ํฉ ๋ณด๊ณ ์๋ก ํ์ | |
| 3. **๊ฐ๋ณ ํ์ฌ ๊ฒ์/๋ถ๋ฌ์ค๊ธฐ**: | |
| - **๊ฒ์**: ์ ํํ ํ์ฌ์ ๋ํด Google์์ ์ต์ ๋ด์ค๋ฅผ ๊ฒ์ ๋ฐ ๋ถ์ | |
| - **DB ๋ถ๋ฌ์ค๊ธฐ**: ๋ก์ปฌ ๋ฐ์ดํฐ๋ฒ ์ด์ค์์ ์ ์ฅ๋ ์ต์ ๋ด์ค์ ๊ฐ์ฑ ๋ถ์ ๊ฒฐ๊ณผ๋ฅผ ๋ถ๋ฌ์ต๋๋ค. | |
| **์ฃผ์ ๊ธฐ๋ฅ**: | |
| - **์ค์๊ฐ ๋ด์ค ์คํฌ๋ํ**: ์ฌ๋ฌ ์ง์ญ์์ ์ต์ ๊ธฐ์ฌ๋ฅผ ๊ฐ์ ธ์ต๋๋ค. | |
| - **๊ณ ๊ธ ๊ฐ์ฑ ๋ถ์**: ์ต์ NLP ๋ชจ๋ธ์ ํ์ฉํ ๊ฐ์ฑ ๋ถ์์ ์ํํฉ๋๋ค. | |
| - **๋ฐ์ดํฐ ์์์ฑ**: ๊ฒ์ ๊ฒฐ๊ณผ๋ฅผ SQLite ๋ฐ์ดํฐ๋ฒ ์ด์ค์ ์๋ ์ ์ฅ ๋ฐ ๋ถ๋ฌ์ค๊ธฐ. | |
| - **์ ์ฐ์ฑ**: ์ฌ์ ์ ์๋ ํค์๋๋ฟ ์๋๋ผ ์ํ๋ ํค์๋/๊ตญ๊ฐ ๊ฒ์์ด ๊ฐ๋ฅํฉ๋๋ค. | |
| **์ปค๋ฎค๋ํฐ**: https://discord.gg/openfreeai | |
| --- | |
| """ | |
| ) | |
| # ์ฌ์ฉ์ ์ ์ ๊ฒ์ ์น์ | |
| with gr.Group(): | |
| gr.Markdown("### ์ฌ์ฉ์ ์ ์ ๊ฒ์") | |
| with gr.Row(): | |
| with gr.Column(): | |
| user_input = gr.Textbox( | |
| label="ํค์๋๋ฅผ ์ ๋ ฅํ์ธ์", | |
| placeholder="์: Apple, Samsung ๋ฑ", | |
| elem_classes="textbox" | |
| ) | |
| with gr.Column(): | |
| country_selection = gr.Dropdown( | |
| choices=list(COUNTRY_LOCATIONS.keys()), | |
| value="United States", | |
| label="๊ตญ๊ฐ ์ ํ" | |
| ) | |
| with gr.Column(): | |
| custom_search_btn = gr.Button( | |
| "๊ฒ์", | |
| variant="primary", | |
| elem_classes="primary-btn" | |
| ) | |
| custom_search_output = gr.Markdown() | |
| custom_search_btn.click( | |
| fn=search_custom, | |
| inputs=[user_input, country_selection], | |
| outputs=custom_search_output | |
| ) | |
| # ์ ์ฒด ๋ณด๊ณ ์ ์์ฑ์ ์ํ ๋ฒํผ | |
| with gr.Row(): | |
| full_report_btn = gr.Button( | |
| "์ ์ฒด ๋ถ์ ์ข ํฉ ๋ณด๊ณ ์ ์์ฑ", | |
| variant="primary", | |
| elem_classes="primary-btn" | |
| ) | |
| full_report_display = gr.Markdown() | |
| full_report_btn.click( | |
| fn=full_summary_report, | |
| outputs=full_report_display | |
| ) | |
| # ๊ฐ๋ณ ํ์ฌ์ ๋ํ ๊ฒ์/๋ถ๋ฌ์ค๊ธฐ | |
| with gr.Column(): | |
| for i in range(0, len(KOREAN_COMPANIES), 2): | |
| with gr.Row(): | |
| # ์ผ์ชฝ ์ปฌ๋ผ | |
| with gr.Column(): | |
| company = KOREAN_COMPANIES[i] | |
| with gr.Group(): | |
| gr.Markdown(f"### {company}") | |
| with gr.Row(): | |
| search_btn = gr.Button( | |
| "๊ฒ์", | |
| variant="primary", | |
| elem_classes="primary-btn" | |
| ) | |
| load_btn = gr.Button( | |
| "DB ๋ถ๋ฌ์ค๊ธฐ", | |
| variant="secondary", | |
| elem_classes="secondary-btn" | |
| ) | |
| result_display = gr.Markdown() | |
| search_btn.click( | |
| fn=lambda c=company: search_company(c), | |
| outputs=result_display | |
| ) | |
| load_btn.click( | |
| fn=lambda c=company: load_company(c), | |
| outputs=result_display | |
| ) | |
| # ์ค๋ฅธ์ชฝ ์ปฌ๋ผ (์กด์ฌํ ๊ฒฝ์ฐ) | |
| if i + 1 < len(KOREAN_COMPANIES): | |
| with gr.Column(): | |
| company = KOREAN_COMPANIES[i + 1] | |
| with gr.Group(): | |
| gr.Markdown(f"### {company}") | |
| with gr.Row(): | |
| search_btn = gr.Button( | |
| "๊ฒ์", | |
| variant="primary", | |
| elem_classes="primary-btn" | |
| ) | |
| load_btn = gr.Button( | |
| "DB ๋ถ๋ฌ์ค๊ธฐ", | |
| variant="secondary", | |
| elem_classes="secondary-btn" | |
| ) | |
| result_display = gr.Markdown() | |
| search_btn.click( | |
| fn=lambda c=company: search_company(c), | |
| outputs=result_display | |
| ) | |
| load_btn.click( | |
| fn=lambda c=company: load_company(c), | |
| outputs=result_display | |
| ) | |
| # Gradio ์ธํฐํ์ด์ค ์คํ | |
| iface.launch( | |
| server_name="0.0.0.0", | |
| server_port=7860, | |
| share=True, | |
| ssl_verify=False, | |
| show_error=True | |
| ) | |