diff --git a/app/modules/indexer/spider/mtorrent.py b/app/modules/indexer/spider/mtorrent.py index 54e292c2..27b0f53c 100644 --- a/app/modules/indexer/spider/mtorrent.py +++ b/app/modules/indexer/spider/mtorrent.py @@ -267,9 +267,9 @@ class MTorrentSpider: base64_str = base64.b64encode(json.dumps(params).encode('utf-8')).decode('utf-8') return f"[{base64_str}]{url}" - def parse_subtitle_links(self, page_url: str) -> List[str]: + def get_subtitle_links(self, page_url: str) -> List[str]: """ - 解析指定页面的字幕下载链接 + 获取指定页面的字幕下载链接 :param page_url: 种子详情页网址 :type page_url: str diff --git a/app/modules/subtitle/__init__.py b/app/modules/subtitle/__init__.py index 5b437aeb..e515b4a5 100644 --- a/app/modules/subtitle/__init__.py +++ b/app/modules/subtitle/__init__.py @@ -8,9 +8,13 @@ from lxml import etree from app.chain.storage import StorageChain from app.core.config import settings from app.core.context import Context +from app.db.site_oper import SiteOper +from app.helper.sites import SitesHelper # noqa from app.helper.torrent import TorrentHelper from app.log import logger from app.modules import _ModuleBase +from app.modules.indexer.spider.mtorrent import MTorrentSpider +from app.schemas import TorrentInfo from app.schemas.file import FileURI from app.schemas.types import ModuleType, OtherModulesType from app.utils.http import RequestUtils @@ -65,6 +69,52 @@ class SubtitleModule(_ModuleBase): def test(self): pass + def _get_subtitle_links(self, torrent: TorrentInfo): + """ + 获取字幕链接 + """ + # API请求方式的站点需要特殊处理 + if torrent.site is not None: + site = SiteOper().get(torrent.site) + if indexer := SitesHelper().get_indexer(site.domain): + if indexer.get("parser") == "mTorrent": + return MTorrentSpider(indexer).get_subtitle_links( + torrent.page_url + ) + # TODO 其它采用API访问的站点 + # 普通站点通过解析网站代码的方式获取 + request = RequestUtils(cookies=torrent.site_cookie, ua=torrent.site_ua) + res = request.get_res(torrent.page_url) + if res and res.status_code == 200: + if not res.text: + logger.warn(f"读取页面代码失败：{torrent.page_url}") + return [] + html = etree.HTML(res.text) + try: + sublink_list = [] + for xpath in self._SITE_SUBTITLE_XPATH: + sublinks = html.xpath(xpath) + if sublinks: + for sublink in sublinks: + if not sublink: + continue + if not sublink.startswith("http"): + base_url = StringUtils.get_base_url(torrent.page_url) + if sublink.startswith("/"): + sublink = "%s%s" % (base_url, sublink) + else: + sublink = "%s/%s" % (base_url, sublink) + sublink_list.append(sublink) + return sublink_list + finally: + if html is not None: + del html + elif res is not None: + logger.warn(f"连接 {torrent.page_url} 失败，状态码：{res.status_code}") + else: + logger.warn(f"无法打开链接：{torrent.page_url}") + return None + def download_added(self, context: Context, download_dir: Path, torrent_content: Union[str, bytes] = None): """ 添加下载任务成功后，从站点下载字幕，保存到下载目录 @@ -117,83 +167,56 @@ class SubtitleModule(_ModuleBase): logger.error(f"下载目录不存在，无法保存字幕：{download_dir / folder_name}") return # 读取网站代码 + sublink_list = self._get_subtitle_links(torrent) + if not sublink_list: + logger.warn(f"{torrent.page_url} 页面未找到字幕下载链接") + return + # 下载所有字幕文件 request = RequestUtils(cookies=torrent.site_cookie, ua=torrent.site_ua) - res = request.get_res(torrent.page_url) - if res and res.status_code == 200: - if not res.text: - logger.warn(f"读取页面代码失败：{torrent.page_url}") - return - html = etree.HTML(res.text) - try: - sublink_list = [] - for xpath in self._SITE_SUBTITLE_XPATH: - sublinks = html.xpath(xpath) - if sublinks: - for sublink in sublinks: - if not sublink: - continue - if not sublink.startswith("http"): - base_url = StringUtils.get_base_url(torrent.page_url) - if sublink.startswith("/"): - sublink = "%s%s" % (base_url, sublink) - else: - sublink = "%s/%s" % (base_url, sublink) - sublink_list.append(sublink) - finally: - if html is not None: - del html - # 下载所有字幕文件 - for sublink in sublink_list: - logger.info(f"找到字幕下载链接：{sublink}，开始下载...") - # 下载 - ret = request.get_res(sublink) - if ret and ret.status_code == 200: - # 保存ZIP - file_name = TorrentHelper.get_url_filename(ret, sublink) - if not file_name: - logger.warn(f"链接不是字幕文件：{sublink}") - continue - if file_name.lower().endswith(".zip"): - # ZIP包 - zip_file = settings.TEMP_PATH / file_name - # 保存 - zip_file.write_bytes(ret.content) - # 解压路径 - zip_path = zip_file.with_name(zip_file.stem) - # 解压文件 - shutil.unpack_archive(zip_file, zip_path, format='zip') - # 遍历转移文件 - for sub_file in SystemUtils.list_files(zip_path, settings.RMT_SUBEXT): - target_sub_file = Path(working_dir_item.path) / Path(sub_file.name) - if storageChain.get_file_item(storage, target_sub_file): - logger.info(f"字幕文件已存在：{target_sub_file}") - continue - logger.info(f"转移字幕 {sub_file} 到 {target_sub_file} ...") - storageChain.upload_file(working_dir_item, sub_file) - # 删除临时文件 - try: - shutil.rmtree(zip_path) - zip_file.unlink() - except Exception as err: - logger.error(f"删除临时文件失败：{str(err)}") - else: - sub_file = settings.TEMP_PATH / file_name - # 保存 - sub_file.write_bytes(ret.content) + for sublink in sublink_list: + logger.info(f"找到字幕下载链接：{sublink}，开始下载...") + # 下载 + ret = request.get_res(sublink) + if ret and ret.status_code == 200: + # 保存ZIP + file_name = TorrentHelper.get_url_filename(ret, sublink) + if not file_name: + logger.warn(f"链接不是字幕文件：{sublink}") + continue + if file_name.lower().endswith(".zip"): + # ZIP包 + zip_file = settings.TEMP_PATH / file_name + # 保存 + zip_file.write_bytes(ret.content) + # 解压路径 + zip_path = zip_file.with_name(zip_file.stem) + # 解压文件 + shutil.unpack_archive(zip_file, zip_path, format='zip') + # 遍历转移文件 + for sub_file in SystemUtils.list_files(zip_path, settings.RMT_SUBEXT): target_sub_file = Path(working_dir_item.path) / Path(sub_file.name) if storageChain.get_file_item(storage, target_sub_file): logger.info(f"字幕文件已存在：{target_sub_file}") continue logger.info(f"转移字幕 {sub_file} 到 {target_sub_file} ...") storageChain.upload_file(working_dir_item, sub_file) + # 删除临时文件 + try: + shutil.rmtree(zip_path) + zip_file.unlink() + except Exception as err: + logger.error(f"删除临时文件失败：{str(err)}") else: - logger.error(f"下载字幕文件失败：{sublink}") - continue - if sublink_list: - logger.info(f"{torrent.page_url} 页面字幕下载完成") + sub_file = settings.TEMP_PATH / file_name + # 保存 + sub_file.write_bytes(ret.content) + target_sub_file = Path(working_dir_item.path) / Path(sub_file.name) + if storageChain.get_file_item(storage, target_sub_file): + logger.info(f"字幕文件已存在：{target_sub_file}") + continue + logger.info(f"转移字幕 {sub_file} 到 {target_sub_file} ...") + storageChain.upload_file(working_dir_item, sub_file) else: - logger.warn(f"{torrent.page_url} 页面未找到字幕下载链接") - elif res is not None: - logger.warn(f"连接 {torrent.page_url} 失败，状态码：{res.status_code}") - else: - logger.warn(f"无法打开链接：{torrent.page_url}") + logger.error(f"下载字幕文件失败：{sublink}") + continue + logger.info(f"{torrent.page_url} 页面字幕下载完成")