From 0612dbd39f268e0816cd7e1cd5bc95e12938dc51 Mon Sep 17 00:00:00 2001
From: JoeamAmier <yonglelolu@gmail.com>
Date: Mon, 28 Aug 2023 21:39:44 +0800
Subject: [PATCH] =?UTF-8?q?=E6=96=B0=E5=A2=9E=E4=BD=9C=E5=93=81=E9=93=BE?=
 =?UTF-8?q?=E6=8E=A5=E6=A0=BC=E5=BC=8F=E5=88=A4=E6=96=AD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main.py            | 2 ++
 source/__init__.py | 8 ++++++++
 2 files changed, 10 insertions(+)

diff --git a/main.py b/main.py
index 9a96cea..8b50a71 100644
--- a/main.py
+++ b/main.py
@@ -4,6 +4,7 @@ from source import XHS
 def example():
     """使用示例"""
     # 测试链接
+    error_demo = "https://www.xiaohongshu.com/explore/"
     image_demo = "https://www.xiaohongshu.com/explore/64d1b406000000000103ee8d"
     video_demo = "https://www.xiaohongshu.com/explore/64c05652000000000c0378e7"
     # 实例对象
@@ -26,6 +27,7 @@ def example():
     # 无需区分图文和视频作品
     # 返回作品详细数据，包括下载地址
     download = True  # 启用自动下载作品文件
+    print(xhs.extract(error_demo))  # 获取数据失败时返回空字典
     print(xhs.extract(image_demo, download=download))
     print(xhs.extract(video_demo, download=download))
 
diff --git a/source/__init__.py b/source/__init__.py
index 1b0792d..a155421 100644
--- a/source/__init__.py
+++ b/source/__init__.py
@@ -1,3 +1,5 @@
+from re import compile
+
 from .Download import Download
 from .Explore import Explore
 from .Html import Html
@@ -11,6 +13,7 @@ class XHS:
         "Referer": "https://www.xiaohongshu.com/",
         "Cookie": "abRequestId=27dafe41-28af-5b33-9f22-fe05d8c4ac2f; xsecappid=xhs-pc-web; a1=18a363d90c9gw7eaz2krqhj4cx2gtwgotul1wur8950000289463; webId=27fb29ed7ff41eadd4bc58197a465b63; websectiga=cffd9dcea65962b05ab048ac76962acee933d26157113bb213105a116241fa6c; sec_poison_id=3a1e34ee-3535-4ee9-8186-4d574da5291e; web_session=030037a3d84590608f6da85793234a9a6588ed; gid=yY0qKqfd2Y9qyY0qKqfj877FSjkEWd0uJTFA1YjxV4SCJy28k9EklE888JYj4Kq82242dKiY; webBuild=3.6.0; cache_feeds=[]",
     }
+    links = compile(r"https://www.xiaohongshu.com/explore/[0-9a-z]+")
 
     def __init__(
             self,
@@ -44,6 +47,8 @@ class XHS:
         container["下载地址"] = url
 
     def extract(self, url: str, download=False) -> dict:
+        if not self.check(url):
+            return {}
         html = self.html.get_html(url)
         if not html:
             return {}
@@ -53,3 +58,6 @@ class XHS:
         else:
             self.get_image(data, html, download)
         return data
+
+    def check(self, url: str):
+        return self.links.match(url)