Spaces:
Sleeping
Sleeping
File size: 13,255 Bytes
d5fb63f 771fcfc f8570dc d5fb63f 771fcfc d5fb63f 771fcfc d5fb63f 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc d5fb63f 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc f8570dc 771fcfc d5fb63f f8570dc c850803 d5fb63f 771fcfc d5fb63f f8570dc d5fb63f 771fcfc d5fb63f 771fcfc d5fb63f c850803 d5fb63f f8570dc c850803 d5fb63f f8570dc d5fb63f f8570dc c850803 d5fb63f f8570dc 2c541cf 771fcfc 2c541cf f8570dc 2c541cf 771fcfc 2c541cf 771fcfc f8570dc 2c541cf 989a45c fb6f347 c850803 771fcfc fb6f347 771fcfc c850803 771fcfc f8570dc c850803 771fcfc c850803 771fcfc c850803 d5fb63f 989a45c 771fcfc 989a45c d5fb63f 771fcfc |
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 |
import gradio as gr
import requests
from bs4 import BeautifulSoup
import urllib.parse # iframe ๊ฒฝ๋ก ๋ณด์ ์ ์ํ ๋ชจ๋
import re
import logging
import tempfile
import pandas as pd
import mecab # pythonโmecabโko ๋ผ์ด๋ธ๋ฌ๋ฆฌ ์ฌ์ฉ
import os
import time
import hmac
import hashlib
import base64
# ๋๋ฒ๊น
(๋ก๊ทธ)์ฉ ํจ์
def debug_log(message: str):
print(f"[DEBUG] {message}")
# [๊ธฐ๋ณธ์ฝ๋] - ๋ค์ด๋ฒ ๋ธ๋ก๊ทธ ์คํฌ๋ํ ๊ธฐ๋ฅ
def scrape_naver_blog(url: str) -> str:
debug_log("scrape_naver_blog ํจ์ ์์")
debug_log(f"์์ฒญ๋ฐ์ 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:
# 1) ๋ค์ด๋ฒ ๋ธ๋ก๊ทธ '๋ฉ์ธ' ํ์ด์ง ์์ฒญ
response = requests.get(url, headers=headers)
debug_log("HTTP GET ์์ฒญ(๋ฉ์ธ ํ์ด์ง) ์๋ฃ")
if response.status_code != 200:
debug_log(f"์์ฒญ ์คํจ, ์ํ์ฝ๋: {response.status_code}")
return f"์ค๋ฅ๊ฐ ๋ฐ์ํ์ต๋๋ค. ์ํ์ฝ๋: {response.status_code}"
# 2) ๋ฉ์ธ ํ์ด์ง ํ์ฑ
soup = BeautifulSoup(response.text, "html.parser")
debug_log("HTML ํ์ฑ(๋ฉ์ธ ํ์ด์ง) ์๋ฃ")
# 3) iframe ํ๊ทธ ์ฐพ๊ธฐ
iframe = soup.select_one("iframe#mainFrame")
if not iframe:
debug_log("iframe#mainFrame ํ๊ทธ๋ฅผ ์ฐพ์ ์ ์์ต๋๋ค.")
return "๋ณธ๋ฌธ iframe์ ์ฐพ์ ์ ์์ต๋๋ค."
iframe_src = iframe.get("src")
if not iframe_src:
debug_log("iframe src๊ฐ ์กด์ฌํ์ง ์์ต๋๋ค.")
return "๋ณธ๋ฌธ iframe์ src๋ฅผ ์ฐพ์ ์ ์์ต๋๋ค."
# 4) iframe src ๋ณด์ (์ ๋๊ฒฝ๋ก ์ฒ๋ฆฌ)
parsed_iframe_url = urllib.parse.urljoin(url, iframe_src)
debug_log(f"iframe ํ์ด์ง ์์ฒญ URL: {parsed_iframe_url}")
# 5) iframe ํ์ด์ง ์์ฒญ ๋ฐ ํ์ฑ
iframe_response = requests.get(parsed_iframe_url, headers=headers)
debug_log("HTTP GET ์์ฒญ(iframe ํ์ด์ง) ์๋ฃ")
if iframe_response.status_code != 200:
debug_log(f"iframe ์์ฒญ ์คํจ, ์ํ์ฝ๋: {iframe_response.status_code}")
return f"iframe์์ ์ค๋ฅ๊ฐ ๋ฐ์ํ์ต๋๋ค. ์ํ์ฝ๋: {iframe_response.status_code}"
iframe_soup = BeautifulSoup(iframe_response.text, "html.parser")
debug_log("HTML ํ์ฑ(iframe ํ์ด์ง) ์๋ฃ")
# 6) ์ ๋ชฉ๊ณผ ๋ณธ๋ฌธ ์ถ์ถ
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 "์ ๋ชฉ์ ์ฐพ์ ์ ์์ต๋๋ค."
debug_log(f"์ถ์ถ๋ ์ ๋ชฉ: {title}")
content_div = iframe_soup.select_one('.se-main-container')
if content_div:
content = content_div.get_text("\n", strip=True)
else:
content = "๋ณธ๋ฌธ์ ์ฐพ์ ์ ์์ต๋๋ค."
debug_log("๋ณธ๋ฌธ ์ถ์ถ ์๋ฃ")
result = f"[์ ๋ชฉ]\n{title}\n\n[๋ณธ๋ฌธ]\n{content}"
debug_log("์ ๋ชฉ๊ณผ ๋ณธ๋ฌธ์ ํฉ์ณ ๋ฐํ ์ค๋น ์๋ฃ")
return result
except Exception as e:
debug_log(f"์๋ฌ ๋ฐ์: {str(e)}")
return f"์คํฌ๋ํ ์ค ์ค๋ฅ๊ฐ ๋ฐ์ํ์ต๋๋ค: {str(e)}"
# [์ฐธ์กฐ์ฝ๋-1] ํํ์ ๋ถ์ ๊ธฐ๋ฅ
def analyze_text(text: str):
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)
logger.debug("์๋ณธ ํ
์คํธ: %s", text)
# 1. ํ๊ตญ์ด๋ง ๋จ๊ธฐ๊ธฐ (๊ณต๋ฐฑ, ์์ด, ๊ธฐํธ ๋ฑ ์ ๊ฑฐ)
filtered_text = re.sub(r'[^๊ฐ-ํฃ]', '', text)
logger.debug("ํํฐ๋ง๋ ํ
์คํธ (ํ๊ตญ์ด๋ง, ๊ณต๋ฐฑ ์ ๊ฑฐ): %s", filtered_text)
if not filtered_text:
logger.debug("์ ํจํ ํ๊ตญ์ด ํ
์คํธ๊ฐ ์์.")
return pd.DataFrame(columns=["๋จ์ด", "๋น๋์"]), ""
# 2. Mecab์ ์ด์ฉํ ํํ์ ๋ถ์ (๋ช
์ฌ์ ๋ณตํฉ๋ช
์ฌ๋ง ์ถ์ถ)
mecab_instance = mecab.MeCab()
tokens = mecab_instance.pos(filtered_text)
logger.debug("ํํ์ ๋ถ์ ๊ฒฐ๊ณผ: %s", tokens)
freq = {}
for word, pos in tokens:
if word and word.strip():
if pos.startswith("NN"):
freq[word] = freq.get(word, 0) + 1
logger.debug("๋จ์ด: %s, ํ์ฌ: %s, ํ์ฌ ๋น๋: %d", word, pos, freq[word])
# 3. ๋น๋์๋ฅผ ๋ด๋ฆผ์ฐจ์ ์ ๋ ฌ
sorted_freq = sorted(freq.items(), key=lambda x: x[1], reverse=True)
logger.debug("๋ด๋ฆผ์ฐจ์ ์ ๋ ฌ๋ ๋จ์ด ๋น๋: %s", sorted_freq)
# 4. ๊ฒฐ๊ณผ DataFrame ์์ฑ
df = pd.DataFrame(sorted_freq, columns=["๋จ์ด", "๋น๋์"])
logger.debug("๊ฒฐ๊ณผ DataFrame ์์ฑ๋จ, shape: %s", df.shape)
# 5. Excel ํ์ผ ์์ฑ (์์ ํ์ผ)
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx")
df.to_excel(temp_file.name, index=False, engine='openpyxl')
temp_file.close()
logger.debug("Excel ํ์ผ ์์ฑ๋จ: %s", temp_file.name)
return df, temp_file.name
# [์ฐธ์กฐ์ฝ๋-2] ๋ค์ด๋ฒ ๊ด๊ณ API ๋ฐ ๊ฒ์๋/๋ธ๋ก๊ทธ๋ฌธ์์ ์กฐํ ๊ธฐ๋ฅ
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
}
def fetch_related_keywords(keyword):
debug_log(f"fetch_related_keywords ํธ์ถ, ํค์๋: {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"
}
response = requests.get(BASE_URL + uri, params=params, headers=headers)
data = 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["PC์๊ฒ์๋"] = df["monthlyPcQcCnt"].apply(parse_count)
df["๋ชจ๋ฐ์ผ์๊ฒ์๋"] = df["monthlyMobileQcCnt"].apply(parse_count)
df["ํ ํ์๊ฒ์๋"] = df["PC์๊ฒ์๋"] + df["๋ชจ๋ฐ์ผ์๊ฒ์๋"]
df.rename(columns={"relKeyword": "์ ๋ณดํค์๋"}, inplace=True)
result_df = df[["์ ๋ณดํค์๋", "PC์๊ฒ์๋", "๋ชจ๋ฐ์ผ์๊ฒ์๋", "ํ ํ์๊ฒ์๋"]]
debug_log("fetch_related_keywords ์๋ฃ")
return result_df
def fetch_blog_count(keyword):
debug_log(f"fetch_blog_count ํธ์ถ, ํค์๋: {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}
response = requests.get(url, headers=headers, params=params)
if response.status_code == 200:
data = response.json()
debug_log(f"fetch_blog_count ๊ฒฐ๊ณผ: {data.get('total', 0)}")
return data.get("total", 0)
else:
debug_log(f"fetch_blog_count ์ค๋ฅ, ์ํ์ฝ๋: {response.status_code}")
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)
debug_log(f"Excel ํ์ผ ์์ฑ๋จ: {excel_path}")
return excel_path
def process_keyword(keywords: str, include_related: bool):
debug_log(f"process_keyword ํธ์ถ, ํค์๋๋ค: {keywords}, ์ฐ๊ด๊ฒ์์ด ํฌํจ: {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 = fetch_related_keywords(kw)
if df_kw.empty:
continue
row_kw = df_kw[df_kw["์ ๋ณดํค์๋"] == 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["์ ๋ณดํค์๋"] != 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=["์ ๋ณดํค์๋"], inplace=True)
else:
result_df = pd.DataFrame(columns=["์ ๋ณดํค์๋", "PC์๊ฒ์๋", "๋ชจ๋ฐ์ผ์๊ฒ์๋", "ํ ํ์๊ฒ์๋"])
result_df["๋ธ๋ก๊ทธ๋ฌธ์์"] = result_df["์ ๋ณดํค์๋"].apply(fetch_blog_count)
result_df.sort_values(by="ํ ํ์๊ฒ์๋", ascending=False, inplace=True)
debug_log("process_keyword ์๋ฃ")
return result_df, create_excel_file(result_df)
# [์ฐธ์กฐ์ฝ๋-1] ๋ฐ [์ฐธ์กฐ์ฝ๋-2]๋ฅผ ํ์ฉํ ํํ์ ๋ถ์ ๋ฐ ๊ฒ์๋, ๋ธ๋ก๊ทธ๋ฌธ์์ ์ถ๊ฐ (๋น๋์1 ์ ๊ฑฐ ์ต์
ํฌํจ)
def morphological_analysis_and_enrich(text: str, remove_freq1: bool):
debug_log("morphological_analysis_and_enrich ํจ์ ์์")
df_freq, _ = analyze_text(text)
if df_freq.empty:
debug_log("ํํ์ ๋ถ์ ๊ฒฐ๊ณผ๊ฐ ๋น ๋ฐ์ดํฐํ๋ ์์
๋๋ค.")
return df_freq, ""
if remove_freq1:
before_shape = df_freq.shape
df_freq = df_freq[df_freq["๋น๋์"] != 1]
debug_log(f"๋น๋์ 1 ์ ๊ฑฐ ์ ์ฉ๋จ. {before_shape} -> {df_freq.shape}")
# ํํ์ ๋ถ์ ๊ฒฐ๊ณผ์์ ํค์๋ ์ถ์ถ (๊ฐ ๋จ์ด๋ฅผ ์ํฐ๋ก ๊ตฌ๋ถ)
keywords = "\n".join(df_freq["๋จ์ด"].tolist())
debug_log(f"๋ถ์๋ ํค์๋: {keywords}")
# [์ฐธ์กฐ์ฝ๋-2]๋ฅผ ํ์ฉํ์ฌ ๊ฐ ํค์๋์ ๊ฒ์๋ ๋ฐ ๋ธ๋ก๊ทธ๋ฌธ์์ ์กฐํ (์ฐ๊ด๊ฒ์์ด ๋ฏธํฌํจ)
df_keyword_info, _ = process_keyword(keywords, include_related=False)
debug_log("๊ฒ์๋ ๋ฐ ๋ธ๋ก๊ทธ๋ฌธ์์ ์กฐํ ์๋ฃ")
# ํํ์ ๋ถ์ ๊ฒฐ๊ณผ์ ๊ฒ์๋ ์ ๋ณด๋ฅผ ๋ณํฉ (ํค์๋ ๊ธฐ์ค)
merged_df = pd.merge(df_freq, df_keyword_info, left_on="๋จ์ด", right_on="์ ๋ณดํค์๋", how="left")
merged_df.drop(columns=["์ ๋ณดํค์๋"], inplace=True)
# ๋ณํฉ ๊ฒฐ๊ณผ Excel ํ์ผ ์์ฑ
merged_excel_path = create_excel_file(merged_df)
debug_log("morphological_analysis_and_enrich ํจ์ ์๋ฃ")
return merged_df, merged_excel_path
# ์๋กญ๊ฒ ์ถ๊ฐ๋ ๊ธฐ๋ฅ: ์
๋ ฅํ ๋ธ๋ก๊ทธ ๋งํฌ๋ก๋ถํฐ ์คํฌ๋ํํ์ฌ ์์ ๊ฐ๋ฅํ ํ
์คํธ ๋ฐ์ค์ ์ถ๋ ฅ
def fetch_blog_content(url: str):
debug_log("fetch_blog_content ํจ์ ์์")
content = scrape_naver_blog(url)
debug_log("fetch_blog_content ํจ์ ์๋ฃ")
return content
# Gradio ์ธํฐํ์ด์ค ๊ตฌ์ฑ (๋จ์ผ ํญ)
with gr.Blocks(title="๋ค์ด๋ฒ ๋ธ๋ก๊ทธ ํํ์ ๋ถ์ ์คํ์ด์ค", css=".gradio-container { max-width: 960px; margin: auto; }") as demo:
gr.Markdown("# ๋ค์ด๋ฒ ๋ธ๋ก๊ทธ ํํ์ ๋ถ์ ์คํ์ด์ค")
with gr.Row():
blog_url_input = gr.Textbox(label="๋ค์ด๋ฒ ๋ธ๋ก๊ทธ ๋งํฌ", placeholder="์: https://blog.naver.com/ssboost/222983068507", lines=1)
with gr.Row():
scrape_button = gr.Button("์คํฌ๋ํ ์คํ")
with gr.Row():
blog_content_box = gr.Textbox(label="๋ธ๋ก๊ทธ ๋ด์ฉ (์์ ๊ฐ๋ฅ)", lines=10, placeholder="์คํฌ๋ํ๋ ๋ธ๋ก๊ทธ ๋ด์ฉ์ด ์ฌ๊ธฐ์ ํ์๋ฉ๋๋ค.")
with gr.Row():
remove_freq_checkbox = gr.Checkbox(label="๋น๋์1 ์ ๊ฑฐ", value=False)
with gr.Row():
analyze_button = gr.Button("๋ถ์ ์คํ")
with gr.Row():
analysis_result = gr.Dataframe(label="๋ถ์ ๊ฒฐ๊ณผ (๋จ์ด, ๋น๋์, ๊ฒ์๋, ๋ธ๋ก๊ทธ๋ฌธ์์ ๋ฑ)")
with gr.Row():
analysis_excel = gr.File(label="Excel ๋ค์ด๋ก๋")
# ์คํฌ๋ํ ์คํ ์ URL๋ก๋ถํฐ ๋ธ๋ก๊ทธ ๋ณธ๋ฌธ ์คํฌ๋ํ ํ ์์ ๊ฐ๋ฅํ ํ
์คํธ ๋ฐ์ค์ ์ถ๋ ฅ
scrape_button.click(fn=fetch_blog_content, inputs=blog_url_input, outputs=blog_content_box)
# ๋ถ์ ์คํ ์ ์์ ๋ ๋ธ๋ก๊ทธ ๋ด์ฉ์ ๋์์ผ๋ก ํํ์ ๋ถ์ ๋ฐ ๊ฒ์๋/๋ธ๋ก๊ทธ๋ฌธ์์ ์กฐํ ์งํ
analyze_button.click(fn=morphological_analysis_and_enrich, inputs=[blog_content_box, remove_freq_checkbox], outputs=[analysis_result, analysis_excel])
if __name__ == "__main__":
debug_log("Gradio ์ฑ ์คํ ์์")
demo.launch()
debug_log("Gradio ์ฑ ์คํ ์ข
๋ฃ")
|