111

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/.name

@@ -0,0 +1 @@
+dxq.py

.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 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8" 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/task-2-4-regular-expression.iml" filepath="$PROJECT_DIR$/.idea/task-2-4-regular-expression.iml" />
+    </modules>
+  </component>
+</project>

.idea/task-2-4-regular-expression.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="inheritedJdk" />
+    <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="" vcs="Git" />
+  </component>
+</project>

dxq.py

@@ -0,0 +1,29 @@
+import requests
+from bs4 import BeautifulSoup
+
+url = f"https://movie.douban.com/top250"
+
+headers = {
+    Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36
+    }
+
+print('开始爬取豆瓣电影Top250...')
+response = requests.get(url, headers=headers)
+print(f'状态码: {response.status_code}')
+print(f'内容长度: {len(response.text)} 字符')  
+
+# 找到所有电影标题
+html = response.text
+
+# 匹配 <span class="title">电影名</span>
+title_pattern = r'<span class="title">([^<]+)</span>'
+titles = re.findall(title_pattern, html)
+
+# 过滤掉英文名（以/开头）
+chinese_titles = [t for t in titles if not t.startswith('/')]
+
+print('电影名称（前10部）：')
+for i, title in enumerate(chinese_titles[:10], 1):
+    print(f'{i}. {title}')
+
+