Update app.py

app.py

@@ -5,98 +5,6 @@ import re
 from huggingface_hub import InferenceClient
 from fpdf import FPDF
 from datetime import datetime
-import requests
-from bs4 import BeautifulSoup
-from requests.adapters import HTTPAdapter
-from requests.packages.urllib3.util.retry import Retry
-import time
-
-def setup_session():
-    try:
-        session = requests.Session()
-        retries = Retry(total=5, backoff_factor=1, status_forcelist=[502, 503, 504])
-        session.mount('https://', HTTPAdapter(max_retries=retries))
-        return session
-    except Exception as e:
-        return None
-
-def generate_naver_search_url(query):
-    base_url = "https://search.naver.com/search.naver?"
-    params = {"ssc": "tab.blog.all", "sm": "tab_jum", "query": query}
-    url = base_url + "&".join(f"{key}={value}" for key, value in params.items())
-    return url
-
-def crawl_blog_content(url, session):
-    try:
-        headers = {
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3",
-            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
-            "Accept-Language": "ko-KR,ko;q=0.9,en-US;q=0.8,en;q=0.7",
-            "Accept-Encoding": "gzip, deflate, br",
-            "Connection": "keep-alive",
-            "Referer": "https://search.naver.com/search.naver",
-        }
-        
-        delay = random.uniform(1, 2)
-        time.sleep(delay)
-
-        response = session.get(url, headers=headers)
-        if response.status_code != 200:
-            return ""
-        
-        soup = BeautifulSoup(response.content, "html.parser")
-        content = soup.find("div", attrs={'class': 'se-main-container'})
-        
-        if content:
-            return clean_text(content.get_text())
-        else:
-            return ""
-    except Exception as e:
-        return ""
-
-def crawl_naver_search_results(url, session):
-    try:
-        headers = {
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3",
-            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
-            "Accept-Language": "ko-KR,ko;q=0.9,en-US;q=0.8,en;q=0.7",
-            "Accept-Encoding": "gzip, deflate, br",
-            "Connection": "keep-alive",
-            "Referer": "https://search.naver.com/search.naver",
-        }
-        response = session.get(url, headers=headers)
-        if response.status_code != 200:
-            return []
-
-        soup = BeautifulSoup(response.content, "html.parser")
-        results = []
-        count = 0
-        for li in soup.find_all("li", class_=re.compile("bx.*")):
-            if count >= 10:
-                break
-            for div in li.find_all("div", class_="detail_box"):
-                for div2 in div.find_all("div", class_="title_area"):
-                    title = div2.text.strip()
-                    for a in div2.find_all("a", href=True):
-                        link = a["href"]
-                        if "blog.naver" in link:
-                            link = link.replace("https://", "https://m.")
-                            results.append({"제목": title, "링크": link})
-                            count += 1
-                            if count >= 10:
-                                break
-                if count >= 10:
-                    break
-            if count >= 10:
-                break
-        
-        return results
-    except Exception as e:
-        return []
-
-def clean_text(text):
-    text = re.sub(r'\s+', ' ', text).strip()
-    return text
 
 def create_client(model_name):
     return InferenceClient(model_name, token=os.getenv("HF_TOKEN"))
@@ -133,22 +41,6 @@ def generate_blog_post(category, style, topic, references1, references2, referen
     formatted_text = modified_text.replace('\n', '\n\n')
     return formatted_text
 
-def fetch_references(topic):
-    search_url = generate_naver_search_url(topic)
-    session = setup_session()
-    if session is None:
-        return "Failed to set up session.", "", "", ""
-    results = crawl_naver_search_results(search_url, session)
-    if not results:
-        return "No results found.", "", "", ""
-    
-    selected_results = random.sample(results, 3)
-    references1_content = f"제목: {selected_results[0]['제목']}\n내용: {crawl_blog_content(selected_results[0]['링크'], session)}"
-    references2_content = f"제목: {selected_results[1]['제목']}\n내용: {crawl_blog_content(selected_results[1]['링크'], session)}"
-    references3_content = f"제목: {selected_results[2]['제목']}\n내용: {crawl_blog_content(selected_results[2]['링크'], session)}"
-    
-    return "참고글 생성 완료", references1_content, references2_content, references3_content
-
 def get_title_prompt(category):
     if (category == "고객반응형"):
         return """
@@ -399,7 +291,7 @@ with gr.Blocks() as demo:
     gr.Markdown(f"# {title}")
     
     gr.Markdown("### 1단계: 포스팅 카테고리를 지정해주세요", elem_id="step-title")
-    category = gr.Radio(choices=["고객반응형"], label="포스팅 카테고리", value="고객반응형")
+    category = gr.Radio(choices=["고객반응형","기능집중형(1개 기능)"], label="포스팅 카테고리", value="고객반응형")
     
     gr.Markdown("---\n\n")
 
@@ -419,17 +311,6 @@ with gr.Blocks() as demo:
     references2 = gr.Textbox(label="참고 글 2", placeholder="참고할 글을 복사하여 붙여넣으세요", lines=10, visible=True)
     references3 = gr.Textbox(label="참고 글 3", placeholder="참고할 글을 복사하여 붙여넣으세요", lines=10, visible=True)
 
-    # 진행 상황 표시를 위한 출력 텍스트박스
-    progress_output = gr.Textbox(label="진행 상황", lines=2, visible=True)
-    
-    # 참고글 가져오기 버튼
-    fetch_references_btn = gr.Button("참고글 생성하기")
-    fetch_references_btn.click(fn=fetch_references, inputs=[topic], outputs=[progress_output, references1, references2, references3])
-    
-    # 참고글 다시 넣기 버튼
-    refill_btn = gr.Button("참고글 다시 넣기")
-    refill_btn.click(fn=fetch_references, inputs=[topic], outputs=[progress_output, references1, references2, references3])
-
     gr.Markdown("---\n\n")
 
     gr.Markdown("### 5단계: 블로그 제목을 입력하세요", elem_id="step-title")