diff --git a/app/chain/__init__.py b/app/chain/__init__.py index cd281904..7850dc0e 100644 --- a/app/chain/__init__.py +++ b/app/chain/__init__.py @@ -197,21 +197,19 @@ class ChainBase(metaclass=ABCMeta): return self.run_module("search_medias", meta=meta) def search_torrents(self, site: CommentedMap, - mediainfo: MediaInfo, - keyword: str = None, - page: int = 0, - area: str = "title") -> List[TorrentInfo]: + keywords: List[str], + mtype: MediaType = None, + page: int = 0) -> List[TorrentInfo]: """ 搜索一个站点的种子资源 :param site: 站点 - :param mediainfo: 识别的媒体信息 - :param keyword: 搜索关键词，如有按关键词搜索，否则按媒体信息名称搜索 + :param keywords: 搜索关键词列表 + :param mtype: 媒体类型 :param page: 页码 - :param area: 搜索区域 :reutrn: 资源列表 """ - return self.run_module("search_torrents", mediainfo=mediainfo, site=site, - keyword=keyword, page=page, area=area) + return self.run_module("search_torrents", site=site, keywords=keywords, + mtype=mtype, page=page) def refresh_torrents(self, site: CommentedMap) -> List[TorrentInfo]: """ diff --git a/app/chain/search.py b/app/chain/search.py index 671b3d6c..6f09913c 100644 --- a/app/chain/search.py +++ b/app/chain/search.py @@ -62,7 +62,7 @@ class SearchChain(ChainBase): else: logger.info(f'开始浏览资源，站点：{site} ...') # 搜索 - return self.__search_all_sites(keyword=title, sites=[site] if site else None, page=page) or [] + return self.__search_all_sites(keywords=[title], sites=[site] if site else None, page=page) or [] def last_search_results(self) -> List[Context]: """ @@ -117,16 +117,12 @@ class SearchChain(ChainBase): else: keywords = [mediainfo.title] # 执行搜索 - torrents: List[TorrentInfo] = [] - for keyword in keywords: - torrents = self.__search_all_sites( - mediainfo=mediainfo, - keyword=keyword, - sites=sites, - area=area - ) - if torrents: - break + torrents: List[TorrentInfo] = self.__search_all_sites( + mediainfo=mediainfo, + keywords=keywords, + sites=sites, + area=area + ) if not torrents: logger.warn(f'{keyword or mediainfo.title} 未搜索到资源') return [] @@ -241,15 +237,15 @@ class SearchChain(ChainBase): # 返回 return contexts - def __search_all_sites(self, mediainfo: Optional[MediaInfo] = None, - keyword: str = None, + def __search_all_sites(self, keywords: List[str], + mediainfo: Optional[MediaInfo] = None, sites: List[int] = None, page: int = 0, area: str = "title") -> Optional[List[TorrentInfo]]: """ 多线程搜索多个站点 :param mediainfo: 识别的媒体信息 - :param keyword: 搜索关键词，如有按关键词搜索，否则按媒体信息名称搜索 + :param keywords: 搜索关键词列表 :param sites: 指定站点ID列表，如有则只搜索指定站点，否则搜索所有站点 :param page: 搜索页码 :param area: 搜索区域 title or imdbid @@ -291,8 +287,18 @@ class SearchChain(ChainBase): executor = ThreadPoolExecutor(max_workers=len(indexer_sites)) all_task = [] for site in indexer_sites: - task = executor.submit(self.search_torrents, mediainfo=mediainfo, - site=site, keyword=keyword, page=page, area=area) + if area == "imdbid": + # 搜索IMDBID + task = executor.submit(self.search_torrents, site=site, + keywords=[mediainfo.imdb_id] if mediainfo else None, + mtype=mediainfo.type if mediainfo else None, + page=page) + else: + # 搜索标题 + task = executor.submit(self.search_torrents, site=site, + keywords=keywords, + mtype=mediainfo.type if mediainfo else None, + page=page) all_task.append(task) # 结果集 results = [] @@ -303,7 +309,7 @@ class SearchChain(ChainBase): results.extend(result) logger.info(f"站点搜索进度：{finish_count} / {total_num}") self.progress.update(value=finish_count / total_num * 100, - text=f"正在搜索{keyword or ''}，已完成 {finish_count} / {total_num} 个站点 ...", + text=f"正在搜索{keywords or ''}，已完成 {finish_count} / {total_num} 个站点 ...", key=ProgressKey.Search) # 计算耗时 end_time = datetime.now() diff --git a/app/modules/indexer/__init__.py b/app/modules/indexer/__init__.py index 7830fa81..16feaa82 100644 --- a/app/modules/indexer/__init__.py +++ b/app/modules/indexer/__init__.py @@ -3,7 +3,7 @@ from typing import List, Optional, Tuple, Union from ruamel.yaml import CommentedMap -from app.core.context import MediaInfo, TorrentInfo +from app.core.context import TorrentInfo from app.log import logger from app.modules import _ModuleBase from app.modules.indexer.mtorrent import MTorrentSpider @@ -28,69 +28,71 @@ class IndexerModule(_ModuleBase): def init_setting(self) -> Tuple[str, Union[str, bool]]: return "INDEXER", "builtin" - def search_torrents(self, site: CommentedMap, mediainfo: MediaInfo = None, - keyword: str = None, page: int = 0, area: str = "title") -> List[TorrentInfo]: + def search_torrents(self, site: CommentedMap, + keywords: List[str] = None, + mtype: MediaType = None, + page: int = 0) -> List[TorrentInfo]: """ 搜索一个站点 - :param mediainfo: 识别的媒体信息 :param site: 站点 - :param keyword: 搜索关键词，如有按关键词搜索，否则按媒体信息名称搜索 + :param keywords: 搜索关键词列表 + :param mtype: 媒体类型 :param page: 页码 - :param area: 搜索区域 title or imdbid :return: 资源列表 """ # 确认搜索的名字 - if keyword: - search_word = keyword - elif mediainfo: - search_word = mediainfo.title - else: - search_word = None - - if search_word \ - and site.get('language') == "en" \ - and StringUtils.is_chinese(search_word): - # 不支持中文 - logger.warn(f"{site.get('name')} 不支持中文搜索") - return [] - - # 去除搜索关键字中的特殊字符 - if search_word: - search_word = StringUtils.clear(search_word, replace_word=" ", allow_space=True) + if not keywords: + # 浏览种子页 + keywords = [None] # 开始索引 result_array = [] # 开始计时 start_time = datetime.now() - try: - imdbid = mediainfo.imdb_id if mediainfo and area == "imdbid" else None - if site.get('parser') == "TNodeSpider": - error_flag, result_array = TNodeSpider(site).search( - keyword=search_word, - imdbid=imdbid, - page=page - ) - elif site.get('parser') == "TorrentLeech": - error_flag, result_array = TorrentLeech(site).search( - keyword=search_word, - page=page - ) - elif site.get('parser') == "mTorrent": - error_flag, result_array = MTorrentSpider(site).search( - keyword=search_word, - mtype=mediainfo.type if mediainfo else None, - page=page - ) - else: - error_flag, result_array = self.__spider_search( - keyword=search_word, - imdbid=imdbid, - indexer=site, - mtype=mediainfo.type if mediainfo else None, - page=page - ) - except Exception as err: - logger.error(f"{site.get('name')} 搜索出错：{err}") + + # 搜索多个关键字 + for search_word in keywords: + # 可能为关键字或ttxxxx + if search_word \ + and site.get('language') == "en" \ + and StringUtils.is_chinese(search_word): + # 不支持中文 + logger.warn(f"{site.get('name')} 不支持中文搜索") + continue + + # 去除搜索关键字中的特殊字符 + if search_word: + search_word = StringUtils.clear(search_word, replace_word=" ", allow_space=True) + + try: + if site.get('parser') == "TNodeSpider": + error_flag, result_array = TNodeSpider(site).search( + keyword=search_word, + page=page + ) + elif site.get('parser') == "TorrentLeech": + error_flag, result_array = TorrentLeech(site).search( + keyword=search_word, + page=page + ) + elif site.get('parser') == "mTorrent": + error_flag, result_array = MTorrentSpider(site).search( + keyword=search_word, + mtype=mtype, + page=page + ) + else: + error_flag, result_array = self.__spider_search( + search_word=search_word, + indexer=site, + mtype=mtype, + page=page + ) + # 有结果后停止 + if result_array: + break + except Exception as err: + logger.error(f"{site.get('name')} 搜索出错：{err}") # 索引花费的时间 seconds = round((datetime.now() - start_time).seconds, 1) @@ -112,15 +114,13 @@ class IndexerModule(_ModuleBase): @staticmethod def __spider_search(indexer: CommentedMap, - keyword: str = None, - imdbid: str = None, + search_word: str = None, mtype: MediaType = None, page: int = 0) -> (bool, List[dict]): """ 根据关键字搜索单个站点 :param: indexer: 站点配置 - :param: keyword: 关键字 - :param: imdbid: imdbid + :param: search_word: 关键字 :param: page: 页码 :param: mtype: 媒体类型 :param: timeout: 超时时间 @@ -128,8 +128,7 @@ class IndexerModule(_ModuleBase): """ _spider = TorrentSpider(indexer=indexer, mtype=mtype, - keyword=keyword, - imdbid=imdbid, + keyword=search_word, page=page) return _spider.is_error, _spider.get_torrents() diff --git a/app/modules/indexer/spider.py b/app/modules/indexer/spider.py index 0b4ae684..ea80db3e 100644 --- a/app/modules/indexer/spider.py +++ b/app/modules/indexer/spider.py @@ -40,8 +40,6 @@ class TorrentSpider: referer: str = None # 搜索关键字 keyword: str = None - # 搜索IMDBID - imdbid: str = None # 媒体类型 mtype: MediaType = None # 搜索路径、方式配置 @@ -68,7 +66,6 @@ class TorrentSpider: def __init__(self, indexer: CommentedMap, keyword: [str, list] = None, - imdbid: str = None, page: int = 0, referer: str = None, mtype: MediaType = None): @@ -76,7 +73,6 @@ class TorrentSpider: 设置查询参数 :param indexer: 索引器 :param keyword: 搜索关键字，如果数组则为批量搜索 - :param imdbid: IMDB ID :param page: 页码 :param referer: Referer :param mtype: 媒体类型 @@ -84,7 +80,6 @@ class TorrentSpider: if not indexer: return self.keyword = keyword - self.imdbid = imdbid self.mtype = mtype self.indexerid = indexer.get('id') self.indexername = indexer.get('name') @@ -159,20 +154,17 @@ class TorrentSpider: # 搜索URL indexer_params = self.search.get("params") or {} if indexer_params: - # 支持IMDBID时优先使用IMDBID搜索 - search_area = indexer_params.get("search_area") or 0 - if self.imdbid and search_area: - search_word = self.imdbid - else: - search_word = self.keyword - # 不启用IMDBID搜索时需要将search_area移除 - if search_area: - indexer_params.pop('search_area') + search_area = indexer_params.get('search_area') + # search_area非0表示支持imdbid搜索 + if (search_area and + (not self.keyword or not self.keyword.startswith('tt'))): + # 支持imdbid搜索，但关键字不是imdbid时，不启用imdbid搜索 + indexer_params.pop('search_area') # 变量字典 inputs_dict = { "keyword": search_word } - # 查询参数 + # 查询参数，默认查询标题 params = { "search_mode": search_mode, "search_area": 0, diff --git a/app/modules/indexer/tnode.py b/app/modules/indexer/tnode.py index f9d57c01..2d7f89d9 100644 --- a/app/modules/indexer/tnode.py +++ b/app/modules/indexer/tnode.py @@ -49,16 +49,16 @@ class TNodeSpider: if csrf_token: self._token = csrf_token.group(1) - def search(self, keyword: str, imdbid: str = None, page: int = 0) -> Tuple[bool, List[dict]]: + def search(self, keyword: str, page: int = 0) -> Tuple[bool, List[dict]]: if not self._token: logger.warn(f"{self._name} 未获取到token，无法搜索") return True, [] - search_type = "imdbid" if imdbid else "title" + search_type = "imdbid" if (keyword and keyword.startswith('tt')) else "title" params = { "page": int(page) + 1, "size": self._size, "type": search_type, - "keyword": imdbid or keyword or "", + "keyword": keyword or "", "sorter": "id", "order": "desc", "tags": [],