fix #694 按站点多次检索

This commit is contained in:
jxxghp
2023-09-29 08:20:55 +08:00
parent dbb3bead6b
commit 2e89eeca2c
5 changed files with 97 additions and 102 deletions

View File

@ -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()

View File

@ -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,

View File

@ -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": [],