2018-01-25 TIL WPS Homework 멜론 노래 상세정보 가져오기

def get_song_id():
    path_module = os.path.abspath(__name__)
    root_dir = os.path.dirname(path_module)
    path_data_dir = os.path.join(root_dir, 'data')

    file_path = os.path.join(path_data_dir, 'chart_realtime.html')
    with open(file_path, 'rt') as f:
        source = f.read()

    FIND_SONG_ID = re.compile(r'<a href="javascript:melon.link.goSongDetail\(\'(.*?)\'\)', re.S)



    for idx, i in enumerate(re.finditer(FIND_SONG_ID, source)):
        result = i.group(1)
        print('순위:' ,idx+1, 'ID:', result)



def get_song_detail(song_id):

    SONG_DETAIL = 'https://www.melon.com/song/detail.htm?songId='+str(song_id)
    response = requests.get(SONG_DETAIL)
    source = response.text

    soup = BeautifulSoup(source, 'lxml')
    result = []

    FIND_DATE = re.compile(r'.*(\d{4}\.\d{2}\.\d{2})')
    FIND_NAME = re.compile(r'\\t(\w+)\\r', re.S)
    FIND_GENRE = re.compile(r'<dt>장르</dt><dd>(\w+)*?</dd>\s*?', re.S)


    for tr in soup.find_all('div', id='conts'):
        find_song_name = tr.find('div', class_='song_name').text
        song_name = re.search(FIND_NAME, find_song_name)

        artist = tr.find('div', class_='artist').find('a').find('span').text
        album = tr.find('div', class_='meta').find('a').text
        meta_information = tr.find('div', class_='meta').find_all('dd')
        release_date = re.findall(FIND_DATE, str(meta_information))
        genre = re.search(FIND_GENRE, str(meta_information))
        lyric = tr.find('div', class_='lyric').text
        writer = tr.find('div', class_='ellipsis artist').find('a').text
        composer = tr.find('div', class_='ellipsis artist').find('a').text

        result.append({
            'song name': song_name,
            'artist': artist,
            'album': album,
            'release date' : release_date,
            'genre' : genre,
            'lyric' : lyric,
            'writer' : writer,
            'composer' : composer,
        })

    print(result)