上传文件至 /

COMMIT_EDITMSG

@@ -0,0 +1 @@
+完成作业六

config

@@ -0,0 +1,13 @@
+[core]
+	repositoryformatversion = 0
+	filemode = false
+	bare = false
+	logallrefupdates = true
+	symlinks = false
+	ignorecase = true
+[remote "origin"]
+	url = https://gitea.detr.top/2509165046/task-2-3-File-Operations.git
+	fetch = +refs/heads/*:refs/remotes/origin/*
+[branch "main"]
+	remote = origin
+	merge = refs/heads/main

description

@@ -0,0 +1 @@
+Unnamed repository; edit this file 'description' to name the repository.

爬电影.py

@@ -1,23 +1,23 @@
-
+
-
+
-headers = {
+headers = {
-    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
-}
+}
-
+
-url = 'https://movie.douban.com/top250'
+url = 'https://movie.douban.com/top250'
-
+
-print('开始爬取豆瓣电影Top250...')
+print('开始爬取豆瓣电影Top250...')
-response = requests.get(url, headers=headers)
+response = requests.get(url, headers=headers)
-print(f'状态码: {response.status_code}')
+print(f'状态码: {response.status_code}')
-print(f'内容长度: {len(response.text)} 字符')
+print(f'内容长度: {len(response.text)} 字符')
-
+
-html = response.text
+html = response.text
-
+
-title_pattern = r'<span class="title">([^<]+)</span>'
+title_pattern = r'<span class="title">([^<]+)</span>'
-titles = re.findall(title_pattern, html)
+titles = re.findall(title_pattern, html)
-
+
-chinese_titles = [t for t in titles if not t.startswith('/')]
+chinese_titles = [t for t in titles if not t.startswith('/')]
-
+
-print('电影名称（前10部）：')
+print('电影名称（前10部）：')
-for i, title in enumerate(chinese_titles[:10], 1):
+for i, title in enumerate(chinese_titles[:10], 1):
     print(f'{i}. {title}')