import os
import requests
import pandas as pd
from bs4 import BeautifulSoup


def fetch_search_results(search_term):
    # URL 설정
    base_url = 'http://aha-dic.com/View.asp?word='
    url = f"{base_url}{search_term}"

    # HTTP GET 요청을 보내고 응답을 가져옴
    response = requests.get(url)
    response.raise_for_status()

    return response.text


def parse_results(html, download_folder):
    soup = BeautifulSoup(html, 'html.parser')
    results = []

    # 결과를 포함하는 div를 찾기
    result_div = soup.find('div', id='result')
    if result_div:
        # class 'word' 텍스트 추출
        word_span = result_div.find('span', class_='word')
        word = word_span.get_text(strip=True) if word_span else ''

        # class 'phoneticKor' 텍스트 추출
        phonetic_kor_span = result_div.find('span', class_='phoneticKor')
        phonetic_kor = phonetic_kor_span.get_text(strip=True) if phonetic_kor_span else ''

        # class 'playSound middle'에서 mp3 url 추출
        play_sound = result_div.find('span', class_='playSound middle')
        mp3_url = play_sound['mp3'] if play_sound else ''

        if mp3_url:
            full_mp3_url = f"http://aha-dic.com{mp3_url}"
            mp3_filename = os.path.join(download_folder, os.path.basename(mp3_url))
            download_file(full_mp3_url, mp3_filename)
        else:
            full_mp3_url = ''

        # ul li HTML 코드 추출 및 예제 품사 추출
        ul = result_div.find('ul')
        li_elements = ul.find_all('li') if ul else []
        meanings = [li.get_text(strip=True) for li in li_elements]

        # 예문 및 품사 패널 내용 추출
        panels = result_div.find_all('fieldset', class_='panel')
        example_sentence = ''
        part_of_speech = ''
        for panel in panels:
            legend = panel.find('legend')
            span = panel.find('span')
            if legend and span:
                if '예문' in legend.get_text(strip=True):
                    example_sentence = span.get_text(strip=True)
                elif '품사' in legend.get_text(strip=True):
                    part_of_speech = span.get_text(strip=True)

        results.append({
            'Word': word,
            'PhoneticKor': phonetic_kor,
            'MP3_URL': full_mp3_url,
            'Meanings': '; '.join(meanings),
            'ExampleSentence': example_sentence,
            'PartOfSpeech': part_of_speech
        })

    return results


def download_file(url, local_filename):
    # MP3 파일을 다운로드하여 지정된 경로에 저장
    try:
        with requests.get(url, stream=True) as r:
            r.raise_for_status()
            with open(local_filename, 'wb') as f:
                for chunk in r.iter_content(chunk_size=8192):
                    f.write(chunk)
        print(f"Downloaded: {local_filename}")
    except Exception as e:
        print(f"Failed to download {url}: {e}")


def main():
    # 검색어가 포함된 CSV 파일 경로
    search_terms_file = 'search_terms.csv'  # CSV 파일 경로 설정
    download_folder = 'D:\\downloads'  # 다운로드할 폴더 경로 설정

    if not os.path.exists(download_folder):
        os.makedirs(download_folder)

    # CSV 파일에서 검색어 불러오기
    search_terms_df = pd.read_csv(search_terms_file)
    print("CSV 파일의 내용:")
    print(search_terms_df.head())  # CSV 파일 내용 확인
    if 'search_term' not in search_terms_df.columns:
        raise KeyError("CSV 파일에 'search_term' 열이 없습니다.")

    search_terms = search_terms_df['search_term'].tolist()[:5]  # 테스트용으로 첫 5개의 검색어만 가져옴

    all_results = []

    # 검색어 루프 돌면서 검색 및 결과 저장
    for i, search_term in enumerate(search_terms, start=1):
        print(f"Processing {i}/{len(search_terms)}: {search_term}")
        try:
            html = fetch_search_results(search_term)
            results = parse_results(html, download_folder)
            all_results.extend(results)
            print(f"Finished processing {search_term}")
        except Exception as e:
            print(f"Error processing {search_term}: {e}")

    # 결과를 CSV 파일로 저장
    output_filename = 'search_results.csv'
    df = pd.DataFrame(all_results)
    df.to_csv(output_filename, index=False, encoding='utf-8')
    print(f'All results have been saved to {output_filename}')


if __name__ == '__main__':
    main()