支持作品 id 为 BJ 或 VJ 开头的音声

yodhcn · Apr 19, 2023 · a9d0b9c · a9d0b9c
1 parent 9c8d392
commit a9d0b9c
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 7 deletions.
diff --git a/scaner/scaner.py b/scaner/scaner.py
@@ -13,7 +13,7 @@ def scan(self, root_path: str, _depth=0):
         """
         if os.path.isdir(root_path):  # 检查是否是文件夹
             folder = os.path.basename(root_path)
-            rjcode = Dlsite.parse_rjcode(folder)
+            rjcode = Dlsite.parse_workno(folder)
             if rjcode:  # 检查文件夹名称中是否含RJ号
                 yield rjcode, root_path
             elif _depth < self.__max_depth:

diff --git a/scraper/dlsite.py b/scraper/dlsite.py
@@ -21,14 +21,15 @@ def _load_translations():
 
 class Dlsite(object):
     TRANSLATIONS: Final = _load_translations()
+    WORKNO_PATTERN: Final = re.compile(r'[RBV]J(\d{6}|\d{8})(?!\d+)')
     RJCODE_PATTERN: Final = re.compile(r'RJ(\d{6}|\d{8})(?!\d+)')
     RGCODE_PATTERN: Final = re.compile(r'RG(\d{5})(?!\d+)')
     SRICODE_PATTERN: Final = re.compile(r'SRI(\d{10})(?!\d+)')
 
-    # 提取字符串中的 rjcode
+    # 提取字符串中的 workno
     @staticmethod
-    def parse_rjcode(string: str):
-        match = Dlsite.RJCODE_PATTERN.search(string.upper())
+    def parse_workno(string: str):
+        match = Dlsite.WORKNO_PATTERN.search(string.upper())
         if match:
             return match.group()
         else:

diff --git a/scraper/scraper.py b/scraper/scraper.py
@@ -156,15 +156,15 @@ def __parse_metadata(self, html: str, rjcode: str):
 
     def scrape_metadata(self, rjcode: str):
         rjcode = rjcode.upper()
-        if not Dlsite.RJCODE_PATTERN.fullmatch(rjcode):
+        if not Dlsite.WORKNO_PATTERN.fullmatch(rjcode):
             raise ValueError
         # html = self.__request_work_page(rjcode)
         # metadata = self.__parse_metadata(html, rjcode)
         metadata = self.__scrape_metadata_from_product_api(rjcode)
         return metadata
 
-    def __scrape_metadata_from_product_api(self, rjcode: str):
-        product_info = self.__request_product_api(rjcode)
+    def __scrape_metadata_from_product_api(self, workno: str):
+        product_info = self.__request_product_api(workno)
 
         metadata: WorkMetadata = {
             'rjcode': product_info['workno'],