笔趣阁初始化

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.11 (py3119)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (test_env)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/pythonProject1.iml" filepath="$PROJECT_DIR$/.idea/pythonProject1.iml" />
+    </modules>
+  </component>
+</project>

.idea/pythonProject1.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.8 (test_env)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

text.py

@@ -0,0 +1,23 @@
+import os.path
+
+import  requests
+from lxml import  etree
+from fake_useragent import  UserAgent
+
+class SpiderBiQuGe(object):
+    def __init__(self):
+        self.headers = {
+            "User-Agent":UserAgent().random
+        }
+        # 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"):
+        if tag == "source":
+            file_path = os.path.join(self.SOURCE_DIR,f"{file_name.html}")
+
+