2505155046/4-2-image-labeling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

上传文件至 /

Browse Source
This commit is contained in:
张兴宇
2026-06-23 11:30:01 +08:00
parent 4e16fa131b
commit bc7e68bcdd
3 changed files with 349 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

152
movies.html Normal file
View File

@@ -0,0 +1,152 @@
<!-- exam_fingerprint: B-20260623-4783 -->
<!-- server_time: 2026-06-23 10:31:48 -->
<!-- exam_paper: B -->
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<title>电影列表</title>
<style>
body { font-family: "Microsoft YaHei", sans-serif; margin: 20px; background: #f5f5f5; }
h1 { color: #c0392b; }
.meta { color: #999; font-size: 12px; margin-bottom: 15px; }
.meta code { background: #e9ecef; padding: 2px 6px; border-radius: 3px; }
table { width: 100%; border-collapse: collapse; background: white; box-shadow: 0 1px 3px rgba(0,0,0,0.1); }
th, td { padding: 10px; text-align: left; border-bottom: 1px solid #ddd; }
th { background: #c0392b; color: white; }
tr:hover { background: #fef5f4; }
</style>
</head>
<body>
<h1>电影列表</h1>
<p class="meta">数据编号：<code>B-20260623-4783</code></p>
<table>
<thead>
<tr>
<th>编号</th>
<th>电影名</th>
<th>导演</th>
<th>上映年份</th>
<th>评分</th>
<th>时长(分钟)</th>
<th>类型</th>
<th>主演数</th>
</tr>
</thead>
<tbody>
<tr>
<td>1</td>
<td>千与千寻</td>
<td>Frank Darabont</td>
<td>2001</td>
<td>8.4</td>
<td>91</td>
<td>悬疑</td>
<td>2</td>
</tr>
<tr>
<td>2</td>
<td>霸王别姬</td>
<td>陈凯歌</td>
<td>2002</td>
<td>9.3</td>
<td>125</td>
<td>悬疑</td>
<td>2</td>
</tr>
<tr>
<td>3</td>
<td>阿甘正传</td>
<td>Robert Zemeckis</td>
<td>1999</td>
<td>9.3</td>
<td>99</td>
<td>喜剧</td>
<td>4</td>
</tr>
<tr>
<td>4</td>
<td>放牛班的春天</td>
<td>James Cameron</td>
<td>2012</td>
<td>6.3</td>
<td>100</td>
<td>爱情</td>
<td>3</td>
</tr>
<tr>
<td>5</td>
<td>星际穿越</td>
<td>宫崎骏</td>
<td>2024</td>
<td>6.5</td>
<td>166</td>
<td>爱情</td>
<td>3</td>
</tr>
<tr>
<td>6</td>
<td>泰坦尼克号</td>
<td>Christopher Nolan</td>
<td>2003</td>
<td>7.3</td>
<td>127</td>
<td>动画</td>
<td>5</td>
</tr>
<tr>
<td>7</td>
<td>盗梦空间</td>
<td>Lasse Hallström</td>
<td>1993</td>
<td>9.2</td>
<td>118</td>
<td>喜剧</td>
<td>4</td>
</tr>
<tr>
<td>8</td>
<td>忠犬八公的故事</td>
<td>Rajkumar Hirani</td>
<td>2003</td>
<td>8.9</td>
<td>118</td>
<td>动画</td>
<td>4</td>
</tr>
<tr>
<td>9</td>
<td>三傻大闹宝莱坞</td>
<td>Christophe Barratier</td>
<td>2010</td>
<td>8.3</td>
<td>137</td>
<td>动画</td>
<td>2</td>
</tr>
<tr>
<td>10</td>
<td>肖申克的救赎</td>
<td>Christopher Nolan</td>
<td>1999</td>
<td>8.2</td>
<td>178</td>
<td>爱情</td>
<td>2</td>
</tr>
</tbody>
</table>
</body>
</html>

105
movies.json Normal file
View File

@@ -0,0 +1,105 @@
{
"data_id": null,
"movies": [
{
"id": 1,
"title": "千与千寻",
"director": "Frank Darabont",
"year": 2001,
"rating": 8.4,
"duration": 91,
"genre": "悬疑",
"actors_count": 2
},
{
"id": 2,
"title": "霸王别姬",
"director": "陈凯歌",
"year": 2002,
"rating": 9.3,
"duration": 125,
"genre": "悬疑",
"actors_count": 2
},
{
"id": 3,
"title": "阿甘正传",
"director": "Robert Zemeckis",
"year": 1999,
"rating": 9.3,
"duration": 99,
"genre": "喜剧",
"actors_count": 4
},
{
"id": 4,
"title": "放牛班的春天",
"director": "James Cameron",
"year": 2012,
"rating": 6.3,
"duration": 100,
"genre": "爱情",
"actors_count": 3
},
{
"id": 5,
"title": "星际穿越",
"director": "宫崎骏",
"year": 2024,
"rating": 6.5,
"duration": 166,
"genre": "爱情",
"actors_count": 3
},
{
"id": 6,
"title": "泰坦尼克号",
"director": "Christopher Nolan",
"year": 2003,
"rating": 7.3,
"duration": 127,
"genre": "动画",
"actors_count": 5
},
{
"id": 7,
"title": "盗梦空间",
"director": "Lasse Hallström",
"year": 1993,
"rating": 9.2,
"duration": 118,
"genre": "喜剧",
"actors_count": 4
},
{
"id": 8,
"title": "忠犬八公的故事",
"director": "Rajkumar Hirani",
"year": 2003,
"rating": 8.9,
"duration": 118,
"genre": "动画",
"actors_count": 4
},
{
"id": 9,
"title": "三傻大闹宝莱坞",
"director": "Christophe Barratier",
"year": 2010,
"rating": 8.3,
"duration": 137,
"genre": "动画",
"actors_count": 2
},
{
"id": 10,
"title": "肖申克的救赎",
"director": "Christopher Nolan",
"year": 1999,
"rating": 8.2,
"duration": 178,
"genre": "爱情",
"actors_count": 2
}
]
}

92
爬虫.py Normal file
View File

@@ -0,0 +1,92 @@
import requests
import json
from bs4 import BeautifulSoup
# 题目强制要求请求头
url = "https://exam.detr.top/exam-b/movies"
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
# 仅一次请求，符合题目要求
resp = requests.get(url, headers=headers)
resp.encoding = "utf-8"
html_text = resp.text
# 保存原始网页 movies.html
with open("movies.html", "w", encoding="utf-8") as f:
f.write(html_text)
print("✅ 已保存网页源码 movies.html")
# 解析表格页面
soup = BeautifulSoup(html_text, "html.parser")
# 提取页面data_id（页面顶部/body标签，没有则留空）
data_id = None
if soup.body and "data-id" in soup.body.attrs:
data_id = soup.body["data-id"]
print(f"页面data_id: {data_id}")
# 提取表格所有数据行 <tr>，跳过表头第一行
all_tr = soup.find_all("tr")
movie_list = []
# 表头是第0行，电影从第1行开始遍历
for tr in all_tr[1:]:
td_list = tr.find_all("td")
# 表格列顺序：id、title、director、year、rating、duration、genre、actors_count
if len(td_list) >= 8:
movie = {
"id": int(td_list[0].get_text(strip=True)),
"title": td_list[1].get_text(strip=True),
"director": td_list[2].get_text(strip=True),
"year": int(td_list[3].get_text(strip=True)),
"rating": float(td_list[4].get_text(strip=True)),
"duration": int(td_list[5].get_text(strip=True)),
"genre": td_list[6].get_text(strip=True),
"actors_count": int(td_list[7].get_text(strip=True))
}
movie_list.append(movie)
print(f"一共抓取到 {len(movie_list)} 部电影")
# 组装并保存 movies.json
save_data = {
"data_id": data_id,
"movies": movie_list
}
with open("movies.json", "w", encoding="utf-8") as f:
json.dump(save_data, f, ensure_ascii=False, indent=2)
print("✅ movies.json 写入完成")
# ====================== 第2题数据分析（防止空列表报错） ======================
if len(movie_list) == 0:
print("❌ 未抓取到任何电影数据，请检查表格解析逻辑！")
else:
# ① 找出评分最高、最低电影
sorted_movies = sorted(movie_list, key=lambda x: x["rating"])
lowest_movie = sorted_movies[0]
highest_movie = sorted_movies[-1]
print("\n① 评分最高&最低电影：")
print(f"评分最低：{lowest_movie['title']} {lowest_movie['rating']}")
print(f"评分最高：{highest_movie['title']} {highest_movie['rating']}")
# ② 统计各类型电影数量（字典输出）
genre_count = {}
for m in movie_list:
g = m["genre"]
genre_count[g] = genre_count.get(g, 0) + 1
print("\n② 各类型电影数量：", genre_count)
# ③ 统计各导演电影数量（字典输出）
director_count = {}
for m in movie_list:
d = m["director"]
director_count[d] = director_count.get(d, 0) + 1
print("\n③ 各导演电影数量：", director_count)
# ④ 统计2020年（含）以后上映电影
count_2020 = 0
for m in movie_list:
if m["year"] >= 2020:
count_2020 += 1
print(f"\n④ 2020年(含)后上映电影总数：{count_2020}")