From 0c97163a248d78279285b96132cb9f31ec0a381f Mon Sep 17 00:00:00 2001
From: xingzhibang <775288271@qq.com>
Date: Mon, 24 Aug 2026 14:25:37 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BC=98=E5=8C=96?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 text.py | 37 ++++++++++++++++++++++++++++++++-----
 1 file changed, 32 insertions(+), 5 deletions(-)

diff --git a/text.py b/text.py
index 0728fd6..cd7ea29 100644
--- a/text.py
+++ b/text.py
@@ -9,15 +9,42 @@ class SpiderBiQuGe(object):
         self.headers = {
             "User-Agent":UserAgent().random
         }
+        self.area = "https://www.bqgie.cc"
         # 根目录
         self.BASE_DIR = os.path.dirname(__file__)
         # 源码文件目录,存储爬取到的每一页的源码数据
         self.SOURCE_DIR = os.path.join(self.BASE_DIR,"novel","source")
         # 文档目录，存储解析到小说的内容
         self.NOVEL_DIR = os.path.join(self.BASE_DIR,"novel","novel")
-
-    def handler(self,file_name,mode="a",encoding="utf-8",tag="source"):
+    def create_tree(self,target_url):
+        # 发起请求
+        response = requests.get(url=target_url,headers=self.headers)
+        # 获取响应
+        page_text = response.text
+        return  etree.HTML(page_text)
+    # 负责写入和读取本地文件数据的
+    def handler(self,file_name,novel_name,data="",mode="a",encoding="utf-8",tag="source"):
         if tag == "source":
-            file_path = os.path.join(self.SOURCE_DIR,f"{file_name.html}")
-
-
+            file_dir = os.path.join(self.SOURCE_DIR,novel_name)
+        elif tag == "novel":
+            file_dir= os.path.join(self.NOVEL_DIR,novel_name)
+        else:
+            file_dir = self.SOURCE_DIR
+        os.makedirs(file_dir,exist_ok=True)
+        file_path = os.path.join(file_dir,f"{file_name.html}")
+        with open(file=file_path,mode=mode,encoding=encoding) as fp:
+            if mode == "a" or mode == "w":
+                fp.write(data)
+            else:
+                data = fp.read()
+        return  data
+    # 抓取小说主页
+    def Spier_index(self):
+        # 定义目标地址
+        target_url = f"{self.area}/book/43278/"
+        tree = self.create_tree(target_url=target_url)
+        #print(page_text)
+        self.handler(file_name="index",novel_name=)
+if __name__ == '__main__':
+    spider = SpiderBiQuGe()
+    spider.Spier_index()