更新无水印图片采集逻辑

README.md

@@ -20,6 +20,8 @@
 <h1>📸 程序截图</h1>
 <br>
 <img src="static/程序截图.png" alt="">
+<h1>🪟 关于终端</h1>
+<p>⭐ 推荐使用 <a href="https://learn.microsoft.com/zh-cn/windows/terminal/install">Windows 终端</a> （Windows 11 自带默认终端）运行程序以便获得最佳显示效果！</p>
 <h1>🥣 使用方法</h1>
 <p>如果仅需下载作品文件，选择 <b>直接运行</b> 或者 <b>源码运行</b> 均可，如果需要获取作品信息，则需要进行二次开发进行调用。</p>
 <h2>🖱 直接运行</h2>

main.py

@@ -44,6 +44,7 @@ def example():
 
 
 class XHSDownloader(App):
+    VERSION = 1.5
     CSS_PATH = "static/XHS_Downloader.tcss"
     BINDINGS = [
         Binding(key="q", action="quit", description="退出程序"),
@@ -63,7 +64,7 @@ def compose(self) -> ComposeResult:
         yield Footer()
 
     def on_mount(self) -> None:
-        self.title = "小红书作品采集工具"
+        self.title = f"小红书作品采集工具 V{self.VERSION}"
 
     def on_button_pressed(self, event: Button.Pressed) -> None:
         if event.button.id == "solo":

source/Image.py

@@ -1,13 +1,12 @@
 from json import loads
 from re import compile
-
-from .Html import Html
-
 __all__ = ['Image']
 
 
 class Image:
     IMAGE_INFO = compile(r'("infoList":\[\{.*?}])')
+    IMAGE_TOKEN = compile(
+        r"http://sns-webpic-qc.xhscdn.com/\d+/\w+/(\w+)!")
 
     def get_image_link(self, html: str) -> list:
         data = self.__extract_image_data(html)
@@ -22,11 +21,18 @@ def __format_image_data(data: list[str]) -> list[dict]:
         return [loads(f"{{{i}}}") for i in data]
 
     @staticmethod
-    def __extract_image_urls(data: list[dict]) -> list[str]:
+    def __generate_image_link(token: str) -> str:
+        return f"https://ci.xiaohongshu.com/{token}?imageView2/2/w/format/png"
+
+    def __extract_image_token(self, url: str) -> str:
+        return self.__generate_image_link(token[0]) if len(
+            token := self.IMAGE_TOKEN.findall(url)) == 1 else ""
+
+    def __extract_image_urls(self, data: list[dict]) -> list[str]:
         urls = []
         for i in data:
             for j in i.get("infoList", []):
                 if j.get("imageScene", "").startswith("CRD_WM_"):
-                    urls.append(j.get("url", ""))
+                    urls.append(self.__extract_image_token(j.get("url", "")))
                     break
-        return [Html.format_url(i) for i in urls if i]
+        return [i for i in urls if i]

source/__init__.py

@@ -17,13 +17,11 @@ class XHS:
     headers = {
         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome"
                       "/116.0.0.0 Safari/537.36",
-        "Cookie": "abRequestId=8bf8c305-4e5b-52dd-a723-e9a5343ab42d; webBuild=3.11.3; xsecappid=xhs-pc-web"
-                  "; a1=18b5003660f88kld0gicpx2on2oksepl5y3r9htmn50000247235; webId=a2b049d2fa82434385976a4"
-                  "9814085b0; websectiga=16f444b9ff5e3d7e258b5f7674489196303a0b160e16647c6c2b4dcb609f4134; s"
-                  "ec_poison_id=3d97668d-1e50-42a7-89c0-7b46aa0183a5; web_session=030037a2006067cf0a2b5f724b"
-                  "224a1819eb36; gid=yYD288qW4824yYD288qKKvx98iYYT1f8k3SUq6ICJlIJlF28TMdU1j888J4WJq28fqDJiqq"
-                  "0; unread={%22ub%22:%22650533d4000000001302862b%22%2C%22ue%22:%2265015857000000001e021a5e"
-                  "%22%2C%22uc%22:42}",
+        "Cookie": "abRequestId=c76828f5-4f37-5b3b-8cc3-036eb91b2edb; webBuild=3.14.1; xsecappid=xhs-pc-web; "
+                  "a1=18ba9b2b23co9uwihz4adkebwsw05g8upycgsldyj50000141248; webId=23ee7745020025247828cf8d6d0decff; "
+                  "websectiga=6169c1e84f393779a5f7de7303038f3b47a78e47be716e7bec57ccce17d45f99; "
+                  "sec_poison_id=ae001863-a9db-4463-ad78-ede3aac4e5b1; gid=yYD0jDJDWyU4yYD0jDJDJv1fqSlj7E3xu40fSvVTd"
+                  "DEMEk2882kY7M888y4yJ4Y8D8SK0iiK; web_session=030037a2797dde5008c3e66f32224a8af75429; ",
     }
     links = compile(r"https://www.xiaohongshu.com/explore/[0-9a-z]+")