fix: 修复项目功能异常

1. 修复 ScannerError 错误
2. 优化作品数据提取逻辑
3. 移除 Cookie 参数

Closes #124
Closes #126

locale/en_GB/LC_MESSAGES/xhs.po

@@ -226,9 +226,6 @@ msgstr "If XHS-Downloader is helpful to you, please consider giving it Star. Tha
 msgid "作者的其他开源项目"
 msgstr "Other open-source projects of the author"
 
-msgid "文件 {0} 请求失败，响应码 {1}"
-msgstr "File {0} request failed with response code {1}"
-
 msgid "视频作品下载功能已关闭，跳过下载"
 msgstr "The video download function has been turned off, skip download"
 

locale/zh_CN/LC_MESSAGES/xhs.po

@@ -226,9 +226,6 @@ msgstr ""
 msgid "作者的其他开源项目"
 msgstr ""
 
-msgid "文件 {0} 请求失败，响应码 {1}"
-msgstr ""
-
 msgid "视频作品下载功能已关闭，跳过下载"
 msgstr ""
 

source/application/download.py

@@ -117,11 +117,7 @@ class Download:
         temp = self.temp.joinpath(f"{name}.{format_}")
         try:
             async with self.client.stream("GET", url, ) as response:
-                if response.status_code != 200:
-                    logging(
-                        log, self.message("链接 {0} 请求失败，响应码 {1}").format(
-                            url, response.status_code), style=ERROR)
-                    return False
+                response.raise_for_status()
                 suffix = self.__extract_type(
                     response.headers.get("Content-Type")) or format_
                 real = path.joinpath(f"{name}.{suffix}")

source/application/request.py

@@ -27,8 +27,7 @@ class Html:
                 url,
                 **kwargs,
             )
-            if response.status_code != 200:
-                return ""
+            response.raise_for_status()
             return response.text if content else str(response.url)
         except HTTPError as error:
             logging(log, str(error), ERROR)

source/expansion/converter.py

@@ -7,7 +7,7 @@ __all__ = ["Converter"]
 
 
 class Converter:
-    INITIAL_STATE = "(//script)[last()]/text()"
+    INITIAL_STATE = "//script/text()"
     KEYS_LINK = (
         "note",
         "noteDetailMap",
@@ -16,22 +16,23 @@ class Converter:
     )
 
     def run(self, content: str) -> dict:
-        return self.__filter_object(
-            self.__convert_object(
-                self.__extract_object(content)))
+        return self._filter_object(
+            self._convert_object(
+                self._extract_object(content)))
 
-    def __extract_object(self, html: str) -> str:
+    def _extract_object(self, html: str) -> str:
         if not html:
             return ""
         html_tree = HTML(html)
-        return d[0] if (d := html_tree.xpath(self.INITIAL_STATE)) else ""
+        scripts = html_tree.xpath(self.INITIAL_STATE)
+        return self.get_script(scripts)
 
     @staticmethod
-    def __convert_object(text: str) -> dict:
+    def _convert_object(text: str) -> dict:
         return safe_load(text.lstrip("window.__INITIAL_STATE__="))
 
     @classmethod
-    def __filter_object(cls, data: dict) -> dict:
+    def _filter_object(cls, data: dict) -> dict:
         return cls.deep_get(data, cls.KEYS_LINK) or {}
 
     @classmethod
@@ -55,3 +56,11 @@ class Converter:
         elif isinstance(data, list | tuple | set):
             return data[index]
         raise TypeError
+
+    @staticmethod
+    def get_script(scripts: list) -> str:
+        scripts.reverse()
+        for script in scripts:
+            if script.startswith("window.__INITIAL_STATE__"):
+                return script
+        return ""

source/module/manager.py

@@ -77,7 +77,7 @@ class Manager:
             "Sec-Ch-Ua": sec_ch_ua or SEC_CH_UA,
             "Sec-Ch-Ua-Platform": sec_ch_ua_platform or SEC_CH_UA_PLATFORM,
         }
-        self.headers = self.blank_headers | {"Cookie": cookie}
+        self.headers = self.blank_headers | {"Cookie": ""}
         self.retry = retry
         self.chunk = chunk
         self.name_format = self.__check_name_format(name_format)