Spaces:
Sleeping
Sleeping
File size: 21,077 Bytes
d5fb63f f9c1fca d5fb63f f9c1fca d5fb63f f9c1fca d5fb63f f9c1fca d5fb63f f9c1fca c850803 d5fb63f f9c1fca d5fb63f c850803 d5fb63f f9c1fca c850803 d5fb63f f9c1fca d5fb63f f9c1fca c850803 d5fb63f f9c1fca 2c541cf f9c1fca 2c541cf f9c1fca 2c541cf f9c1fca c850803 ce7fa06 c850803 f9c1fca c850803 d5fb63f f9c1fca 08f7932 f9c1fca 08f7932 f9c1fca 1a9c589 f9c1fca 1a9c589 f9c1fca 1a9c589 2c541cf f9c1fca 08f7932 f9c1fca 08f7932 f9c1fca 08f7932 f9c1fca 110447f f9c1fca 110447f ad33187 b3072ce 08f7932 b3072ce b06ebdb b3072ce b06ebdb b3072ce b06ebdb 08f7932 b3072ce b06ebdb b3072ce 110447f b3072ce 1a9c589 b3072ce 1a9c589 b06ebdb f9c1fca 110447f b3072ce d5fb63f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 |
import gradio as gr
import requests
import aiohttp
import asyncio
from bs4 import BeautifulSoup
import urllib.parse # iframe κ²½λ‘ λ³΄μ μ μν λͺ¨λ
import re
import logging
import tempfile
import pandas as pd
import mecab # pythonβmecabβko λΌμ΄λΈλ¬λ¦¬ μ¬μ©
import os
import time
import hmac
import hashlib
import base64
# λλ²κΉ
(λ‘κ·Έ)μ© ν¨μ
def debug_log(message: str):
print(f"[DEBUG] {message}")
# --- λ€μ΄λ² λΈλ‘κ·Έ μ€ν¬λν (λΉλκΈ° λ²μ ) ---
async def scrape_naver_blog(url: str) -> str:
debug_log("scrape_naver_blog ν¨μ μμ")
debug_log(f"μμ²λ°μ URL: {url}")
headers = {
"User-Agent": (
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/96.0.4664.110 Safari/537.36"
)
}
try:
async with aiohttp.ClientSession() as session:
async with session.get(url, headers=headers) as response:
debug_log("HTTP GET μμ²(λ©μΈ νμ΄μ§) μλ£")
if response.status != 200:
debug_log(f"μμ² μ€ν¨, μνμ½λ: {response.status}")
return f"μ€λ₯κ° λ°μνμ΅λλ€. μνμ½λ: {response.status}"
html = await response.text()
soup = BeautifulSoup(html, "html.parser")
debug_log("HTML νμ±(λ©μΈ νμ΄μ§) μλ£")
iframe = soup.select_one("iframe#mainFrame")
if not iframe:
debug_log("iframe#mainFrame νκ·Έλ₯Ό μ°Ύμ μ μμ΅λλ€.")
return "λ³Έλ¬Έ iframeμ μ°Ύμ μ μμ΅λλ€."
iframe_src = iframe.get("src")
if not iframe_src:
debug_log("iframe srcκ° μ‘΄μ¬νμ§ μμ΅λλ€.")
return "λ³Έλ¬Έ iframeμ srcλ₯Ό μ°Ύμ μ μμ΅λλ€."
parsed_iframe_url = urllib.parse.urljoin(url, iframe_src)
debug_log(f"iframe νμ΄μ§ μμ² URL: {parsed_iframe_url}")
async with aiohttp.ClientSession() as session:
async with session.get(parsed_iframe_url, headers=headers) as iframe_response:
debug_log("HTTP GET μμ²(iframe νμ΄μ§) μλ£")
if iframe_response.status != 200:
debug_log(f"iframe μμ² μ€ν¨, μνμ½λ: {iframe_response.status}")
return f"iframeμμ μ€λ₯κ° λ°μνμ΅λλ€. μνμ½λ: {iframe_response.status}"
iframe_html = await iframe_response.text()
iframe_soup = BeautifulSoup(iframe_html, "html.parser")
debug_log("HTML νμ±(iframe νμ΄μ§) μλ£")
title_div = iframe_soup.select_one('.se-module.se-module-text.se-title-text')
title = title_div.get_text(strip=True) if title_div else "μ λͺ©μ μ°Ύμ μ μμ΅λλ€."
debug_log(f"μΆμΆλ μ λͺ©: {title}")
content_div = iframe_soup.select_one('.se-main-container')
if content_div:
content = content_div.get_text("\n", strip=True)
else:
content = "λ³Έλ¬Έμ μ°Ύμ μ μμ΅λλ€."
debug_log("λ³Έλ¬Έ μΆμΆ μλ£")
result = f"[μ λͺ©]\n{title}\n\n[λ³Έλ¬Έ]\n{content}"
debug_log("μ λͺ©κ³Ό λ³Έλ¬Έ ν©μΉ¨ μλ£")
return result
except Exception as e:
debug_log(f"μλ¬ λ°μ: {str(e)}")
return f"μ€ν¬λν μ€ μ€λ₯κ° λ°μνμ΅λλ€: {str(e)}"
# --- λ€μ΄λ² κ²μ λ° κ΄κ³ API κ΄λ ¨ ---
def generate_signature(timestamp, method, uri, secret_key):
message = f"{timestamp}.{method}.{uri}"
digest = hmac.new(secret_key.encode("utf-8"), message.encode("utf-8"), hashlib.sha256).digest()
return base64.b64encode(digest).decode()
def get_header(method, uri, api_key, secret_key, customer_id):
timestamp = str(round(time.time() * 1000))
signature = generate_signature(timestamp, method, uri, secret_key)
return {
"Content-Type": "application/json; charset=UTF-8",
"X-Timestamp": timestamp,
"X-API-KEY": api_key,
"X-Customer": str(customer_id),
"X-Signature": signature
}
# --- μ°κ΄ ν€μλ μ‘°ν (λΉλκΈ°) ---
async def fetch_related_keywords(keyword):
debug_log(f"fetch_related_keywords νΈμΆ, ν€μλ: {keyword}")
API_KEY = os.environ["NAVER_API_KEY"]
SECRET_KEY = os.environ["NAVER_SECRET_KEY"]
CUSTOMER_ID = os.environ["NAVER_CUSTOMER_ID"]
BASE_URL = "https://api.naver.com"
uri = "/keywordstool"
method = "GET"
headers = get_header(method, uri, API_KEY, SECRET_KEY, CUSTOMER_ID)
params = {
"hintKeywords": [keyword],
"showDetail": "1"
}
async with aiohttp.ClientSession() as session:
async with session.get(BASE_URL + uri, headers=headers, params=params) as response:
data = await response.json()
if "keywordList" not in data:
return pd.DataFrame()
df = pd.DataFrame(data["keywordList"])
if len(df) > 100:
df = df.head(100)
def parse_count(x):
try:
return int(str(x).replace(",", ""))
except:
return 0
df["PCμκ²μλ"] = df["monthlyPcQcCnt"].apply(parse_count)
df["λͺ¨λ°μΌμκ²μλ"] = df["monthlyMobileQcCnt"].apply(parse_count)
df["ν νμκ²μλ"] = df["PCμκ²μλ"] + df["λͺ¨λ°μΌμκ²μλ"]
df.rename(columns={"relKeyword": "μ 보ν€μλ"}, inplace=True)
result_df = df[["μ 보ν€μλ", "PCμκ²μλ", "λͺ¨λ°μΌμκ²μλ", "ν νμκ²μλ"]]
debug_log("fetch_related_keywords μλ£")
return result_df
# --- λΈλ‘κ·Έ λ¬Έμμ μ‘°ν (λΉλκΈ°) ---
async def fetch_blog_count(keyword):
debug_log(f"fetch_blog_count νΈμΆ, ν€μλ: {keyword}")
client_id = os.environ["NAVER_SEARCH_CLIENT_ID"]
client_secret = os.environ["NAVER_SEARCH_CLIENT_SECRET"]
url = "https://openapi.naver.com/v1/search/blog.json"
headers = {
"X-Naver-Client-Id": client_id,
"X-Naver-Client-Secret": client_secret
}
params = {"query": keyword, "display": 1}
async with aiohttp.ClientSession() as session:
async with session.get(url, headers=headers, params=params) as response:
if response.status == 200:
data = await response.json()
debug_log(f"fetch_blog_count κ²°κ³Ό: {data.get('total', 0)}")
return data.get("total", 0)
else:
debug_log(f"fetch_blog_count μ€λ₯, μνμ½λ: {response.status}")
return 0
def create_excel_file(df):
with tempfile.NamedTemporaryFile(suffix=".xlsx", delete=False) as tmp:
excel_path = tmp.name
df.to_excel(excel_path, index=False, engine='openpyxl')
debug_log(f"Excel νμΌ μμ±λ¨: {excel_path}")
return excel_path
# --- ν€μλ κ²μ (λΉλκΈ°) ---
async def process_keyword(keywords: str, include_related: bool):
debug_log(f"process_keyword νΈμΆ, ν€μλλ€: {keywords}, μ°κ΄κ²μμ΄ ν¬ν¨: {include_related}")
input_keywords = [k.strip() for k in keywords.splitlines() if k.strip()]
result_dfs = []
for idx, kw in enumerate(input_keywords):
df_kw = await fetch_related_keywords(kw)
if df_kw.empty:
continue
row_kw = df_kw[df_kw["μ 보ν€μλ"] == kw]
if not row_kw.empty:
result_dfs.append(row_kw)
else:
result_dfs.append(df_kw.head(1))
if include_related and idx == 0:
df_related = df_kw[df_kw["μ 보ν€μλ"] != kw]
if not df_related.empty:
result_dfs.append(df_related)
if result_dfs:
result_df = pd.concat(result_dfs, ignore_index=True)
result_df.drop_duplicates(subset=["μ 보ν€μλ"], inplace=True)
else:
result_df = pd.DataFrame(columns=["μ 보ν€μλ", "PCμκ²μλ", "λͺ¨λ°μΌμκ²μλ", "ν νμκ²μλ"])
# λΈλ‘κ·Έ λ¬Έμμ μ‘°νλ₯Ό λ³λ ¬λ‘ μ²λ¦¬
tasks = [fetch_blog_count(kw) for kw in result_df["μ 보ν€μλ"]]
counts = await asyncio.gather(*tasks)
result_df["λΈλ‘κ·Έλ¬Έμμ"] = counts
result_df.sort_values(by="ν νμκ²μλ", ascending=False, inplace=True)
debug_log("process_keyword μλ£")
return result_df, create_excel_file(result_df)
# --- ννμ λΆμ (μ°Έκ³ μ½λ-1, λκΈ°) ---
def analyze_text(text: str):
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)
logger.debug("μλ³Έ ν
μ€νΈ: %s", text)
filtered_text = re.sub(r'[^κ°-ν£]', '', text)
logger.debug("νν°λ§λ ν
μ€νΈ: %s", filtered_text)
if not filtered_text:
logger.debug("μ ν¨ν νκ΅μ΄ ν
μ€νΈκ° μμ.")
return pd.DataFrame(columns=["λ¨μ΄", "λΉλμ"]), ""
mecab_instance = mecab.MeCab()
tokens = mecab_instance.pos(filtered_text)
logger.debug("ννμ λΆμ κ²°κ³Ό: %s", tokens)
freq = {}
for word, pos in tokens:
if word and word.strip() and pos.startswith("NN"):
freq[word] = freq.get(word, 0) + 1
logger.debug("λ¨μ΄: %s, νμ¬: %s, λΉλ: %d", word, pos, freq[word])
sorted_freq = sorted(freq.items(), key=lambda x: x[1], reverse=True)
logger.debug("μ λ ¬λ λ¨μ΄ λΉλ: %s", sorted_freq)
df = pd.DataFrame(sorted_freq, columns=["λ¨μ΄", "λΉλμ"])
logger.debug("ννμ λΆμ DataFrame μμ±λ¨, shape: %s", df.shape)
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx")
df.to_excel(temp_file.name, index=False, engine='openpyxl')
temp_file.close()
logger.debug("Excel νμΌ μμ±λ¨: %s", temp_file.name)
return df, temp_file.name
# --- ννμ λΆμκ³Ό κ²μλ/λΈλ‘κ·Έλ¬Έμμ λ³ν© (λΉλκΈ°) ---
async def morphological_analysis_and_enrich(text: str, remove_freq1: bool):
debug_log("morphological_analysis_and_enrich ν¨μ μμ")
df_freq, _ = analyze_text(text)
if df_freq.empty:
debug_log("ννμ λΆμ κ²°κ³Όκ° λΉ λ°μ΄ν°νλ μμ
λλ€.")
return df_freq, ""
if remove_freq1:
before_shape = df_freq.shape
df_freq = df_freq[df_freq["λΉλμ"] != 1]
debug_log(f"λΉλμ 1 μ κ±° μ μ©λ¨. {before_shape} -> {df_freq.shape}")
keywords = "\n".join(df_freq["λ¨μ΄"].tolist())
debug_log(f"λΆμλ ν€μλ: {keywords}")
df_keyword_info, _ = await process_keyword(keywords, include_related=False)
debug_log("κ²μλ λ° λΈλ‘κ·Έλ¬Έμμ μ‘°ν μλ£")
merged_df = pd.merge(df_freq, df_keyword_info, left_on="λ¨μ΄", right_on="μ 보ν€μλ", how="left")
merged_df.drop(columns=["μ 보ν€μλ"], inplace=True)
merged_excel_path = create_excel_file(merged_df)
debug_log("morphological_analysis_and_enrich ν¨μ μλ£")
return merged_df, merged_excel_path
# --- μ§μ ν€μλ λΆμ (λ¨λ
λΆμ, λΉλκΈ°) ---
async def direct_keyword_analysis(text: str, keyword_input: str):
debug_log("direct_keyword_analysis ν¨μ μμ")
keywords = re.split(r'[\n,]+', keyword_input)
keywords = [kw.strip() for kw in keywords if kw.strip()]
debug_log(f"μ
λ ₯λ ν€μλ λͺ©λ‘: {keywords}")
results = []
for kw in keywords:
count = text.count(kw)
results.append((kw, count))
debug_log(f"ν€μλ '{kw}'μ λΉλμ: {count}")
# μ§μ μ
λ ₯ ν€μλκ° λ³Έλ¬Έμ μμΌλ©΄ μΆκ° μ‘°ν
if kw not in text:
df_direct, _ = await process_keyword(kw, include_related=False)
if (not df_direct.empty) and (kw in df_direct["μ 보ν€μλ"].values):
row = df_direct[df_direct["μ 보ν€μλ"] == kw].iloc[0]
pc = row.get("PCμκ²μλ", None)
mobile = row.get("λͺ¨λ°μΌμκ²μλ", None)
total = row.get("ν νμκ²μλ", None)
blog_count = row.get("λΈλ‘κ·Έλ¬Έμμ", None)
else:
pc = mobile = total = blog_count = None
# κ²°κ³Όμ μ ν μΆκ°
results.append((kw, count))
df = pd.DataFrame(results, columns=["ν€μλ", "λΉλμ"])
excel_path = create_excel_file(df)
debug_log("direct_keyword_analysis ν¨μ μλ£")
return df, excel_path
# --- ν΅ν© λΆμ (ννμ λΆμ + μ§μ ν€μλ λΆμ, λΉλκΈ°) ---
async def combined_analysis(blog_text: str, remove_freq1: bool, direct_keyword_input: str):
debug_log("combined_analysis ν¨μ μμ")
merged_df, _ = await morphological_analysis_and_enrich(blog_text, remove_freq1)
if "μ§μ μ
λ ₯" not in merged_df.columns:
merged_df["μ§μ μ
λ ₯"] = ""
direct_keywords = re.split(r'[\n,]+', direct_keyword_input)
direct_keywords = [kw.strip() for kw in direct_keywords if kw.strip()]
debug_log(f"μ
λ ₯λ μ§μ ν€μλ: {direct_keywords}")
for dk in direct_keywords:
if dk in merged_df["λ¨μ΄"].values:
merged_df.loc[merged_df["λ¨μ΄"] == dk, "μ§μ μ
λ ₯"] = "μ§μ μ
λ ₯"
else:
freq = blog_text.count(dk)
df_direct, _ = await process_keyword(dk, include_related=False)
if (not df_direct.empty) and (dk in df_direct["μ 보ν€μλ"].values):
row = df_direct[df_direct["μ 보ν€μλ"] == dk].iloc[0]
pc = row.get("PCμκ²μλ", None)
mobile = row.get("λͺ¨λ°μΌμκ²μλ", None)
total = row.get("ν νμκ²μλ", None)
blog_count = row.get("λΈλ‘κ·Έλ¬Έμμ", None)
else:
pc = mobile = total = blog_count = None
new_row = {
"λ¨μ΄": dk,
"λΉλμ": freq,
"PCμκ²μλ": pc,
"λͺ¨λ°μΌμκ²μλ": mobile,
"ν νμκ²μλ": total,
"λΈλ‘κ·Έλ¬Έμμ": blog_count,
"μ§μ μ
λ ₯": "μ§μ μ
λ ₯"
}
merged_df = pd.concat([merged_df, pd.DataFrame([new_row])], ignore_index=True)
merged_df = merged_df.sort_values(by="λΉλμ", ascending=False).reset_index(drop=True)
combined_excel = create_excel_file(merged_df)
debug_log("combined_analysis ν¨μ μλ£")
return merged_df, combined_excel
# --- λΆμ νΈλ€λ¬ (λΉλκΈ°) ---
async def analysis_handler(blog_text: str, remove_freq1: bool, direct_keyword_input: str, direct_keyword_only: bool):
debug_log("analysis_handler ν¨μ μμ")
if direct_keyword_only:
return await direct_keyword_analysis(blog_text, direct_keyword_input)
else:
return await combined_analysis(blog_text, remove_freq1, direct_keyword_input)
# --- μ€ν¬λν μ€ν νΈλ€λ¬ (λΉλκΈ°) ---
async def fetch_blog_content(url: str):
debug_log("fetch_blog_content ν¨μ μμ")
content = await scrape_naver_blog(url)
debug_log("fetch_blog_content ν¨μ μλ£")
return content
# --- Custom CSS ---
custom_css = """
/* μ 체 컨ν
μ΄λ μ€νμΌ */
.gradio-container {
max-width: 960px;
margin: auto;
font-family: 'Helvetica Neue', Arial, sans-serif;
background: #f5f7fa;
padding: 2rem;
}
/* ν€λ μ€νμΌ */
.custom-header {
text-align: center;
font-size: 2.5rem;
font-weight: bold;
margin-bottom: 1.5rem;
color: #333;
}
/* κ·Έλ£Ή λ°μ€ μ€νμΌ */
.custom-group {
background: #ffffff;
border-radius: 8px;
padding: 1.5rem;
box-shadow: 0 2px 8px rgba(0,0,0,0.1);
margin-bottom: 1.5rem;
}
/* λ²νΌ μ€νμΌ */
.custom-button {
background-color: #007bff;
color: #fff;
border: none;
border-radius: 4px;
padding: 0.6rem 1.2rem;
font-size: 1rem;
cursor: pointer;
transition: background-color 0.3s;
}
.custom-button:hover {
background-color: #0056b3;
}
/* 체ν¬λ°μ€ μ€νμΌ */
.custom-checkbox {
margin-right: 1rem;
font-size: 1rem;
font-weight: bold;
}
/* κ²°κ³Ό ν
μ΄λΈ λ° λ€μ΄λ‘λ λ²νΌ */
.custom-result {
margin-top: 1.5rem;
}
/* κ°μ΄λ° μ λ ¬ */
.centered {
display: flex;
justify-content: center;
align-items: center;
}
/* μ¬μ©μ€λͺ
μ€νμΌ */
.usage-instructions {
font-size: 1.1rem;
line-height: 1.6;
color: #555;
background: #fff;
padding: 1.5rem;
border-radius: 8px;
box-shadow: 0 2px 8px rgba(0,0,0,0.1);
margin-top: 2rem;
}
.usage-instructions h2 {
font-size: 1.8rem;
font-weight: bold;
margin-bottom: 1rem;
color: #333;
}
.usage-instructions ul {
list-style: disc;
margin-left: 2rem;
}
"""
# --- Gradio μΈν°νμ΄μ€ κ΅¬μ± ---
with gr.Blocks(title="λ€μ΄λ² λΈλ‘κ·Έ ννμ λΆμ μλΉμ€", css=custom_css) as demo:
gr.HTML("<div class='custom-header'>λ€μ΄λ² λΈλ‘κ·Έ ννμ λΆμ μλΉμ€ π</div>")
with gr.Group(elem_classes="custom-group"):
with gr.Row():
blog_url_input = gr.Textbox(label="λ€μ΄λ² λΈλ‘κ·Έ λ§ν¬", placeholder="μ: https://blog.naver.com/ssboost/222983068507", lines=1)
with gr.Row(elem_classes="centered"):
scrape_button = gr.Button("μ€ν¬λν μ€ν", elem_classes="custom-button")
with gr.Group(elem_classes="custom-group"):
blog_content_box = gr.Textbox(label="λΈλ‘κ·Έ λ΄μ© (μμ κ°λ₯)", lines=10, placeholder="μ€ν¬λνλ λΈλ‘κ·Έ λ΄μ©μ΄ μ¬κΈ°μ νμλ©λλ€.")
with gr.Group(elem_classes="custom-group"):
with gr.Row():
remove_freq_checkbox = gr.Checkbox(label="λΉλμ1 μ κ±°", value=True, elem_classes="custom-checkbox")
with gr.Row():
direct_keyword_only_checkbox = gr.Checkbox(label="μ§μ ν€μλ μ
λ ₯λ§ λΆμ", value=False, elem_classes="custom-checkbox")
with gr.Row():
direct_keyword_box = gr.Textbox(label="μ§μ ν€μλ μ
λ ₯ (μν° λλ ','λ‘ κ΅¬λΆ)", lines=2, placeholder="μ: ν€μλ1, ν€μλ2\nν€μλ3")
with gr.Group(elem_classes="custom-group"):
with gr.Row(elem_classes="centered"):
analyze_button = gr.Button("λΆμ μ€ν", elem_classes="custom-button")
with gr.Group(elem_classes="custom-group custom-result"):
result_df = gr.Dataframe(label="ν΅ν© λΆμ κ²°κ³Ό (λ¨μ΄, λΉλμ, κ²μλ, λΈλ‘κ·Έλ¬Έμμ, μ§μ μ
λ ₯)", interactive=True)
with gr.Group(elem_classes="custom-group"):
excel_file = gr.File(label="Excel λ€μ΄λ‘λ")
with gr.Group(elem_classes="custom-group"):
usage_html = gr.HTML("""
<div class="usage-instructions">
<h2>μ¬μ© μ€λͺ
π</h2>
<ul>
<li>π <strong>λ€μ΄λ² λΈλ‘κ·Έ λ§ν¬</strong>: λΆμν λ€μ΄λ² λΈλ‘κ·Έμ URLμ μ
λ ₯νμΈμ.</li>
<li>βοΈ <strong>μ€ν¬λν μ€ν</strong>: λ§ν¬ μ
λ ₯ ν λ²νΌμ ν΄λ¦νλ©΄ λΈλ‘κ·Έμ μ λͺ©κ³Ό λ³Έλ¬Έμ΄ μλμΌλ‘ λΆλ¬μμ§λλ€.</li>
<li>π <strong>λΈλ‘κ·Έ λ΄μ© (μμ κ°λ₯)</strong>: λΆλ¬μ¨ λΈλ‘κ·Έ λ΄μ©μ΄ νμλλ©°, νμμ λ°λΌ μ§μ μμ ν μ μμ΅λλ€.</li>
<li>βοΈ <strong>μ΅μ
μ€μ </strong>:
<ul>
<li><em>λΉλμ1 μ κ±°</em>: κΈ°λ³Έ μ νλμ΄ μμΌλ©°, λΉλμκ° 1μΈ λ¨μ΄λ κ²°κ³Όμμ μ μΈν©λλ€.</li>
<li><em>μ§μ ν€μλ μ
λ ₯λ§ λΆμ</em>: μ΄ μ΅μ
μ μ ννλ©΄, λΈλ‘κ·Έ λ³Έλ¬Έμμ μ§μ μ
λ ₯ν ν€μλλ§ λΆμν©λλ€.</li>
</ul>
</li>
<li>π€ <strong>μ§μ ν€μλ μ
λ ₯</strong>: μν° λλ μΌν(,)λ‘ κ΅¬λΆνμ¬ λΆμν ν€μλλ₯Ό μ
λ ₯νμΈμ.</li>
<li>π <strong>λΆμ μ€ν</strong>: μ€μ ν μ΅μ
μ λ°λΌ ννμ λΆμ λ° ν€μλ λΆμμ΄ μνλμ΄ κ²°κ³Όκ° νμ Excel νμΌλ‘ μΆλ ₯λ©λλ€.</li>
<li>π₯ <strong>Excel λ€μ΄λ‘λ</strong>: λΆμ κ²°κ³Όλ₯Ό Excel νμΌλ‘ λ€μ΄λ‘λν μ μμ΅λλ€.</li>
</ul>
<p><strong>Tip:</strong> λΆμ κ²°κ³Όλ μ€μκ°μΌλ‘ μ
λ°μ΄νΈλλ©°, νμμ μμ ν λ€μ λΆμν μ μμ΅λλ€. μ¦κ±°μ΄ λΆμ λμΈμ! π</p>
</div>
""")
# μ΄λ²€νΈ μ°κ²° (λΉλκΈ° ν¨μ μ¬μ©)
scrape_button.click(fn=fetch_blog_content, inputs=blog_url_input, outputs=blog_content_box)
analyze_button.click(fn=analysis_handler,
inputs=[blog_content_box, remove_freq_checkbox, direct_keyword_box, direct_keyword_only_checkbox],
outputs=[result_df, excel_file])
if __name__ == "__main__":
debug_log("Gradio μ± μ€ν μμ")
demo.launch()
debug_log("Gradio μ± μ€ν μ’
λ£")
|