Spaces:
Building
Building
File size: 13,854 Bytes
cce9aa5 9d3056e cce9aa5 e6ce983 cce9aa5 1abf4a9 e70c1dd 2c674f5 4227c16 2c674f5 e70c1dd 2c674f5 e70c1dd 2c674f5 e70c1dd 2c674f5 e70c1dd 2c674f5 e70c1dd 2c674f5 e70c1dd 2c674f5 e70c1dd 2c674f5 e70c1dd 2c674f5 e70c1dd 2c674f5 e70c1dd 2c674f5 e70c1dd 2c674f5 e70c1dd 1abf4a9 4227c16 1abf4a9 b58dbad 1abf4a9 cce9aa5 226d4fc 1abf4a9 226d4fc d5a7027 1abf4a9 4227c16 cce9aa5 0706733 70ba540 0706733 4227c16 0706733 9d3056e 1abf4a9 bec0a91 cce9aa5 bec0a91 1abf4a9 cce9aa5 70ba540 bec0a91 9d3056e 70ba540 9d3056e 33395c3 cce9aa5 1d30b8b 33395c3 1abf4a9 cce9aa5 70ba540 cce9aa5 1abf4a9 70ba540 cce9aa5 1abf4a9 cce9aa5 1d30b8b 33395c3 cce9aa5 70ba540 cce9aa5 1abf4a9 cce9aa5 1abf4a9 cce9aa5 1abf4a9 cce9aa5 1abf4a9 cce9aa5 1abf4a9 cce9aa5 1abf4a9 cce9aa5 980bf52 70ba540 980bf52 cce9aa5 70ba540 54328d4 1abf4a9 70ba540 cce9aa5 70ba540 cce9aa5 70ba540 cce9aa5 70ba540 54328d4 52196d9 1abf4a9 cce9aa5 1abf4a9 2072a11 1abf4a9 cce9aa5 70ba540 cce9aa5 70ba540 cce9aa5 70ba540 cce9aa5 54328d4 70ba540 54328d4 cce9aa5 54328d4 70ba540 54328d4 70ba540 cce9aa5 70ba540 cce9aa5 1abf4a9 cce9aa5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 |
import gradio as gr
import requests
import json
import os
from datetime import datetime, timedelta
from huggingface_hub import InferenceClient
API_KEY = os.getenv("SERPHOUSE_API_KEY")
# hf_client = InferenceClient("CohereForAI/c4ai-command-r-plus-08-2024", token=os.getenv("HF_TOKEN"))
# κ΅κ°λ³ μΈμ΄ μ½λ 맀ν
COUNTRY_LANGUAGES = {
"United States": "en",
"United Kingdom": "en",
"Taiwan": "zh-TW", # λλ§μ΄(λ²μ²΄ μ€κ΅μ΄)
"Canada": "en",
"Australia": "en",
"Germany": "de",
"France": "fr",
"Japan": "ja",
"South Korea": "ko",
"China": "zh",
"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": "hr",
"Slovakia": "sk",
"Bulgaria": "bg",
"Serbia": "sr",
"Estonia": "et",
"Latvia": "lv",
"Lithuania": "lt",
"Slovenia": "sl",
"Luxembourg": "fr",
"Malta": "mt",
"Cyprus": "el",
"Iceland": "is"
}
COUNTRY_LOCATIONS = {
"United States": "United States",
"United Kingdom": "United Kingdom",
"Taiwan": "Taiwan", # κ΅κ°λͺ
μ¬μ©
"Canada": "Canada",
"Australia": "Australia",
"Germany": "Germany",
"France": "France",
"Japan": "Japan",
"South Korea": "South Korea",
"China": "China",
"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": "Estonia",
"Latvia": "Latvia",
"Lithuania": "Lithuania",
"Slovenia": "Slovenia",
"Luxembourg": "Luxembourg",
"Malta": "Malta",
"Cyprus": "Cyprus",
"Iceland": "Iceland"
}
MAJOR_COUNTRIES = list(COUNTRY_LOCATIONS.keys())
def translate_query(query, country):
try:
# μμ΄ μ
λ ₯ νμΈ
if is_english(query):
print(f"μμ΄ κ²μμ΄ κ°μ§ - μλ³Έ μ¬μ©: {query}")
return query
# μ νλ κ΅κ°κ° λ²μ μ§μ κ΅κ°μΈ κ²½μ°
if country in COUNTRY_LANGUAGES:
# South Korea μ νμ νκΈ μ
λ ₯μ κ·Έλλ‘ μ¬μ©
if country == "South Korea":
print(f"νκ΅ μ ν - μλ³Έ μ¬μ©: {query}")
return query
target_lang = COUNTRY_LANGUAGES[country]
print(f"λ²μ μλ: {query} -> {country}({target_lang})")
url = f"https://translate.googleapis.com/translate_a/single"
params = {
"client": "gtx",
"sl": "auto",
"tl": target_lang,
"dt": "t",
"q": query
}
response = requests.get(url, params=params)
translated_text = response.json()[0][0][0]
print(f"λ²μ μλ£: {query} -> {translated_text} ({country})")
return translated_text
return query
except Exception as e:
print(f"λ²μ μ€λ₯: {str(e)}")
return query
def translate_to_korean(text):
try:
url = "https://translate.googleapis.com/translate_a/single"
params = {
"client": "gtx",
"sl": "auto",
"tl": "ko",
"dt": "t",
"q": text
}
response = requests.get(url, params=params)
translated_text = response.json()[0][0][0]
return translated_text
except Exception as e:
print(f"νκΈ λ²μ μ€λ₯: {str(e)}")
return text
def is_english(text):
return all(ord(char) < 128 for char in text.replace(' ', '').replace('-', '').replace('_', ''))
def is_korean(text):
return any('\uAC00' <= char <= '\uD7A3' for char in text)
def search_serphouse(query, country, page=1, num_result=10):
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)
print(f"Original query: {query}")
print(f"Translated query: {translated_query}")
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": "1",
"num": "10",
"date_range": date_range,
"sort_by": "date"
}
}
headers = {
"accept": "application/json",
"content-type": "application/json",
"authorization": f"Bearer {API_KEY}"
}
try:
response = requests.post(url, json=payload, headers=headers)
print("Request payload:", json.dumps(payload, indent=2, ensure_ascii=False))
print("Response status:", response.status_code)
response.raise_for_status()
return {"results": response.json(), "translated_query": translated_query}
except requests.RequestException as e:
return {"error": f"Error: {str(e)}", "translated_query": query}
def format_results_from_raw(response_data):
if "error" in response_data:
return "Error: " + 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 "κ²μ κ²°κ³Όκ° μμ΅λλ€.", []
articles = []
for idx, result in enumerate(news_results, 1):
articles.append({
"index": idx,
"title": result.get("title", "μ λͺ© μμ"),
"link": result.get("url", result.get("link", "#")),
"snippet": result.get("snippet", "λ΄μ© μμ"),
"channel": result.get("channel", result.get("source", "μ μ μμ")),
"time": result.get("time", result.get("date", "μ μ μλ μκ°")),
"image_url": result.get("img", result.get("thumbnail", "")),
"translated_query": translated_query
})
return "", articles
except Exception as e:
return f"κ²°κ³Ό μ²λ¦¬ μ€ μ€λ₯ λ°μ: {str(e)}", []
def serphouse_search(query, country):
response_data = search_serphouse(query, country)
return format_results_from_raw(response_data)
css = """
footer {visibility: hidden;}
"""
with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css, title="NewsAI μλΉμ€") as iface:
gr.Markdown("κ²μμ΄λ₯Ό μ
λ ₯νκ³ μνλ κ΅κ°(67κ°κ΅)λ₯Ό μ ννλ©΄, κ²μμ΄μ μΌμΉνλ 24μκ° μ΄λ΄ λ΄μ€λ₯Ό μ΅λ 100κ° μΆλ ₯ν©λλ€.")
gr.Markdown("κ΅κ° μ νν κ²μμ΄μ 'νκΈ'μ μ
λ ₯νλ©΄ νμ§ μΈμ΄λ‘ λ²μλμ΄ κ²μν©λλ€. μ: 'Taiwan' κ΅κ° μ νν 'μΌμ±' μ
λ ₯μ 'δΈζ'μΌλ‘ μλ κ²μ")
with gr.Column():
with gr.Row():
query = gr.Textbox(label="κ²μμ΄")
country = gr.Dropdown(MAJOR_COUNTRIES, label="κ΅κ°", value="South Korea")
# κ²μ μν λ©μμ§
status_message = gr.Markdown("", visible=True)
# λ²μ κ²°κ³Όλ₯Ό 보μ¬μ£Όλ μ»΄ν¬λνΈ
translated_query_display = gr.Markdown(visible=False)
search_button = gr.Button("κ²μ", variant="primary")
progress = gr.Progress()
articles_state = gr.State([])
article_components = []
for i in range(100):
with gr.Group(visible=False) as article_group:
title = gr.Markdown()
image = gr.Image(width=200, height=150)
snippet = gr.Markdown()
info = gr.Markdown()
article_components.append({
'group': article_group,
'title': title,
'image': image,
'snippet': snippet,
'info': info,
'index': i,
})
def search_and_display(query, country, articles_state, progress=gr.Progress()):
# κ²μ μν λ©μμ§ μ
λ°μ΄νΈ
status_msg = "κ²μμ μ§νμ€μ
λλ€. μ μλ§ κΈ°λ€λ¦¬μΈμ..."
progress(0, desc="κ²μμ΄ λ²μ μ€...")
# κ²μμ΄ λ²μ
translated_query = translate_query(query, country)
translated_display = f"**μλ³Έ κ²μμ΄:** {query}\n**λ²μλ κ²μμ΄:** {translated_query}" if translated_query != query else f"**κ²μμ΄:** {query}"
progress(0.2, desc="κ²μ μμ...")
error_message, articles = serphouse_search(query, country)
progress(0.5, desc="κ²°κ³Ό μ²λ¦¬ μ€...")
outputs = []
outputs.append(gr.update(value=status_msg, visible=True)) # μν λ©μμ§
outputs.append(gr.update(value=translated_display, visible=True)) # λ²μ κ²°κ³Ό
if error_message:
outputs.append(gr.update(value=error_message, visible=True))
for comp in article_components:
outputs.extend([
gr.update(visible=False), gr.update(), gr.update(),
gr.update(), gr.update()
])
articles_state = []
else:
outputs.append(gr.update(value="", visible=False))
total_articles = len(articles)
for idx, comp in enumerate(article_components):
progress((idx + 1) / total_articles, desc=f"κ²°κ³Ό νμ μ€... {idx + 1}/{total_articles}")
if idx < len(articles):
article = articles[idx]
image_url = article['image_url']
image_update = gr.update(value=image_url, visible=True) if image_url and not image_url.startswith('data:image') else gr.update(value=None, visible=False)
# μμ½ λ΄μ© νκΈ λ²μ
korean_summary = translate_to_korean(article['snippet'])
outputs.extend([
gr.update(visible=True),
gr.update(value=f"### [{article['title']}]({article['link']})"),
image_update,
gr.update(value=f"**μμ½:** {article['snippet']}\n\n**νκΈ μμ½:** {korean_summary}"),
gr.update(value=f"**μΆμ²:** {article['channel']} | **μκ°:** {article['time']}")
])
else:
outputs.extend([
gr.update(visible=False), gr.update(), gr.update(),
gr.update(), gr.update()
])
articles_state = articles
progress(1.0, desc="μλ£!")
outputs.append(articles_state)
# κ²μ μλ£ ν μν λ©μμ§ μ¨κΉ
outputs[0] = gr.update(value="", visible=False)
return outputs
search_outputs = [
status_message,
translated_query_display,
gr.Markdown(visible=False)
]
for comp in article_components:
search_outputs.extend([
comp['group'], comp['title'], comp['image'],
comp['snippet'], comp['info']
])
search_outputs.append(articles_state)
search_button.click(
search_and_display,
inputs=[query, country, articles_state],
outputs=search_outputs,
show_progress=True
)
iface.launch() |