From a4318a04a88495c6d478a84ea4ea4d22792e918f Mon Sep 17 00:00:00 2001
From: 2505140092 <2505140092@student.edu.cn>
Date: Thu, 2 Apr 2026 16:04:03 +0800
Subject: [PATCH] 111

---
 .idea/.gitignore                              |  3 ++
 .idea/.name                                   |  1 +
 .../inspectionProfiles/profiles_settings.xml  |  6 ++++
 .idea/misc.xml                                |  4 +++
 .idea/modules.xml                             |  8 +++++
 .idea/task-2-4-regular-expression.iml         |  8 +++++
 .idea/vcs.xml                                 |  6 ++++
 dxq.py                                        | 29 +++++++++++++++++++
 8 files changed, 65 insertions(+)
 create mode 100644 .idea/.gitignore
 create mode 100644 .idea/.name
 create mode 100644 .idea/inspectionProfiles/profiles_settings.xml
 create mode 100644 .idea/misc.xml
 create mode 100644 .idea/modules.xml
 create mode 100644 .idea/task-2-4-regular-expression.iml
 create mode 100644 .idea/vcs.xml
 create mode 100644 dxq.py

diff --git a/.idea/.gitignore b/.idea/.gitignore
new file mode 100644
index 0000000..26d3352
--- /dev/null
+++ b/.idea/.gitignore
@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml
diff --git a/.idea/.name b/.idea/.name
new file mode 100644
index 0000000..7602925
--- /dev/null
+++ b/.idea/.name
@@ -0,0 +1 @@
+dxq.py
\ No newline at end of file
diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml
new file mode 100644
index 0000000..105ce2d
--- /dev/null
+++ b/.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>
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
new file mode 100644
index 0000000..d1e22ec
--- /dev/null
+++ b/.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>
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
new file mode 100644
index 0000000..2dbaab4
--- /dev/null
+++ b/.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>
\ No newline at end of file
diff --git a/.idea/task-2-4-regular-expression.iml b/.idea/task-2-4-regular-expression.iml
new file mode 100644
index 0000000..d0876a7
--- /dev/null
+++ b/.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>
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100644
index 0000000..35eb1dd
--- /dev/null
+++ b/.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>
\ No newline at end of file
diff --git a/dxq.py b/dxq.py
new file mode 100644
index 0000000..0e29844
--- /dev/null
+++ b/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}')
+
+    
\ No newline at end of file