jitashe.py

from requests_html import HTMLSession, requests
from typing import Union
from pathlib import Path
import logging


class JitasheDownloader:
    BASE_URL = 'https://www.jitashe.org'

    def __init__(self):
        self.session = HTMLSession()

    def _search(self, keyword) -> Union[str, None]:
        """ 查询页，如有查询结果返回第一个，否则返回 None """

        search_req = self.session.get(f'{self.BASE_URL}/search/tab/{keyword}')
        search_first = search_req.html.find('#threadlist > div > div.text > a', first=True)
        first_elem_url = search_first and self.BASE_URL + search_first.element.attrib['href']
        return first_elem_url

    def _download(self, keyword, out_dir) -> None:
        """ 根据查询页返回结果下载乐谱 """

        search_url = self._search(keyword)
        if search_url:
            score_req = self.session.get(search_url)
            title = score_req.html.find('h1.gb-title', first=True).text
            scores_url = [url.split('!')[0] for url in score_req.html.xpath(
                '//ignore_js_op/picture/img/@src')]

            if scores_url:
                download_path = Path(out_dir) / title
                download_path.mkdir(parents=True, exist_ok=True)
                filename_width = len(str(len(scores_url)))
                for i, url in enumerate(scores_url, 1):
                    file = download_path / f'{title}-{i:0{filename_width}}.jpg'
                    logging.debug(f'下载中 - {file.name}')
                    file.write_bytes(self.session.get(url).content)

                logging.info(f'完成下载：{title}')
            else:
                logging.info(f'无图片谱: {keyword}')
        else:
            logging.info(f'搜索词「{keyword}」下无对应结果')

        logging.debug('')

    def download(self, keyword, out_dir='./output', max_retry=3) -> None:
        """ 下载乐谱（支持重试） """

        for i in range(max_retry):
            try:
                self._download(keyword, out_dir=out_dir)
                break
            except requests.RequestException:
                logging.error(f'重试第{i + 1}次下载 - {keyword}')
                continue
        else:
            logging.error(f'{max_retry}次尝试下载失败 - {keyword}')


if __name__ == '__main__':
    logging.basicConfig(
        format='[%(asctime)s] [%(levelname)-5s] %(message)s',
        level=logging.INFO,
        datefmt='%Y-%m-%d %T'
    )

    logging.getLogger("urllib3.connectionpool").setLevel(logging.CRITICAL)

    downloader = JitasheDownloader()
    song_list = [
        '同桌的你', '十年', '蓝莲花', '千千阙歌', '大海',
        '月亮代表我的心', '童话', '爱情转移', '外婆的澎湖湾',
        '笨小孩', '上海滩', '红日', '我们的爱', '雨一直下',
        '江南','孤勇者', '孤勇者1', '孤勇者2'
    ]
    for song in song_list:
        downloader.download(song)