app.py

import requests
from bs4 import BeautifulSoup
import gradio as gr

def scrape_naver_blog(url):
    try:
        # 디버깅 로그: URL 확인
        print(f"[DEBUG] Scraping URL: {url}")

        # 네이버 블로그 HTML 가져오기
        headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36"}
        response = requests.get(url, headers=headers)

        # HTTP 상태 코드 확인
        print(f"[DEBUG] HTTP Response Status Code: {response.status_code}")
        if response.status_code != 200:
            return f"Error: Unable to access the page. HTTP Status Code: {response.status_code}"

        # HTML 파싱
        soup = BeautifulSoup(response.text, "html.parser")

        # 제목과 내용 스크래핑
        title_xpath = "div > div > div > div:nth-of-type(10) > div:nth-of-type(1) > div > table:nth-of-type(2) > tbody > tr > td:nth-of-type(2) > div > div > div > div:nth-of-type(1) > div > div > div:nth-of-type(2)"
        content_xpath = "div > div > div > div:nth-of-type(10) > div:nth-of-type(1) > div > table:nth-of-type(2) > tbody > tr > td:nth-of-type(2) > div > div > div > div:nth-of-type(2) > div:nth-of-type(2) > div > div"

        # CSS 선택자 변환
        title_element = soup.select_one(title_xpath.replace(" > ", " > "))
        content_element = soup.select_one(content_xpath.replace(" > ", " > "))

        if not title_element or not content_element:
            return "Error: Unable to locate title or content using the provided XPaths."

        # 텍스트 추출
        title = title_element.get_text(strip=True)
        content = content_element.get_text(strip=True)

        # 결과 반환
        return f"제목: {title}\n내용: {content}"

    except Exception as e:
        # 디버깅 로그: 예외 발생 시
        print(f"[DEBUG] Exception occurred: {str(e)}")
        return f"An error occurred: {str(e)}"

# Gradio 인터페이스 설정
def gradio_interface(url):
    return scrape_naver_blog(url)

iface = gr.Interface(
    fn=gradio_interface,
    inputs=gr.Textbox(label="Naver Blog URL"),
    outputs=gr.Textbox(label="Scraped Content"),
    title="Naver Blog Scraper",
    description="Enter a Naver Blog URL to scrape the title and content.",
)

if __name__ == "__main__":
    iface.launch()