1
This commit is contained in:
2509165028
152
q2_1_crawler/movies.html
Normal file
152
q2_1_crawler/movies.html
Normal file
@@ -0,0 +1,152 @@
|
|||||||
|
<!-- exam_fingerprint: B-20260623-8741 -->
|
||||||
|
<!-- server_time: 2026-06-23 10:13:12 -->
|
||||||
|
<!-- 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-20260623-8741</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>盗梦空间</td>
|
||||||
|
<td>Frank Darabont</td>
|
||||||
|
<td>2024</td>
|
||||||
|
<td>7.1</td>
|
||||||
|
<td>126</td>
|
||||||
|
<td>悬疑</td>
|
||||||
|
<td>2</td>
|
||||||
|
</tr>
|
||||||
|
|
||||||
|
<tr>
|
||||||
|
<td>2</td>
|
||||||
|
<td>放牛班的春天</td>
|
||||||
|
<td>陈凯歌</td>
|
||||||
|
<td>2013</td>
|
||||||
|
<td>7.8</td>
|
||||||
|
<td>162</td>
|
||||||
|
<td>悬疑</td>
|
||||||
|
<td>3</td>
|
||||||
|
</tr>
|
||||||
|
|
||||||
|
<tr>
|
||||||
|
<td>3</td>
|
||||||
|
<td>三傻大闹宝莱坞</td>
|
||||||
|
<td>Robert Zemeckis</td>
|
||||||
|
<td>2004</td>
|
||||||
|
<td>9.1</td>
|
||||||
|
<td>179</td>
|
||||||
|
<td>爱情</td>
|
||||||
|
<td>2</td>
|
||||||
|
</tr>
|
||||||
|
|
||||||
|
<tr>
|
||||||
|
<td>4</td>
|
||||||
|
<td>泰坦尼克号</td>
|
||||||
|
<td>James Cameron</td>
|
||||||
|
<td>2006</td>
|
||||||
|
<td>8.1</td>
|
||||||
|
<td>172</td>
|
||||||
|
<td>爱情</td>
|
||||||
|
<td>4</td>
|
||||||
|
</tr>
|
||||||
|
|
||||||
|
<tr>
|
||||||
|
<td>5</td>
|
||||||
|
<td>肖申克的救赎</td>
|
||||||
|
<td>宫崎骏</td>
|
||||||
|
<td>2002</td>
|
||||||
|
<td>6.0</td>
|
||||||
|
<td>153</td>
|
||||||
|
<td>冒险</td>
|
||||||
|
<td>5</td>
|
||||||
|
</tr>
|
||||||
|
|
||||||
|
<tr>
|
||||||
|
<td>6</td>
|
||||||
|
<td>千与千寻</td>
|
||||||
|
<td>Christopher Nolan</td>
|
||||||
|
<td>2017</td>
|
||||||
|
<td>8.0</td>
|
||||||
|
<td>163</td>
|
||||||
|
<td>爱情</td>
|
||||||
|
<td>3</td>
|
||||||
|
</tr>
|
||||||
|
|
||||||
|
<tr>
|
||||||
|
<td>7</td>
|
||||||
|
<td>星际穿越</td>
|
||||||
|
<td>Lasse Hallström</td>
|
||||||
|
<td>2021</td>
|
||||||
|
<td>9.5</td>
|
||||||
|
<td>148</td>
|
||||||
|
<td>冒险</td>
|
||||||
|
<td>3</td>
|
||||||
|
</tr>
|
||||||
|
|
||||||
|
<tr>
|
||||||
|
<td>8</td>
|
||||||
|
<td>忠犬八公的故事</td>
|
||||||
|
<td>Rajkumar Hirani</td>
|
||||||
|
<td>2006</td>
|
||||||
|
<td>7.3</td>
|
||||||
|
<td>115</td>
|
||||||
|
<td>动画</td>
|
||||||
|
<td>3</td>
|
||||||
|
</tr>
|
||||||
|
|
||||||
|
<tr>
|
||||||
|
<td>9</td>
|
||||||
|
<td>霸王别姬</td>
|
||||||
|
<td>Christophe Barratier</td>
|
||||||
|
<td>2010</td>
|
||||||
|
<td>6.6</td>
|
||||||
|
<td>136</td>
|
||||||
|
<td>喜剧</td>
|
||||||
|
<td>2</td>
|
||||||
|
</tr>
|
||||||
|
|
||||||
|
<tr>
|
||||||
|
<td>10</td>
|
||||||
|
<td>阿甘正传</td>
|
||||||
|
<td>Christopher Nolan</td>
|
||||||
|
<td>2001</td>
|
||||||
|
<td>9.1</td>
|
||||||
|
<td>107</td>
|
||||||
|
<td>喜剧</td>
|
||||||
|
<td>4</td>
|
||||||
|
</tr>
|
||||||
|
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
22
q2_1_crawler/movies.json
Normal file
22
q2_1_crawler/movies.json
Normal file
@@ -0,0 +1,22 @@
|
|||||||
|
[
|
||||||
|
{
|
||||||
|
"id": "1",
|
||||||
|
"title": "示例电影A",
|
||||||
|
"director": "导演A",
|
||||||
|
"year": 2022,
|
||||||
|
"rating": 8.5,
|
||||||
|
"duration": 120,
|
||||||
|
"genre": "动作",
|
||||||
|
"actors_count": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "2",
|
||||||
|
"title": "示例电影B",
|
||||||
|
"director": "导演B",
|
||||||
|
"year": 2019,
|
||||||
|
"rating": 6.0,
|
||||||
|
"duration": 95,
|
||||||
|
"genre": "喜剧",
|
||||||
|
"actors_count": 6
|
||||||
|
}
|
||||||
|
]
|
||||||
44
q2_1_crawler/q2_1.py
Normal file
44
q2_1_crawler/q2_1.py
Normal file
@@ -0,0 +1,44 @@
|
|||||||
|
import requests
|
||||||
|
import json
|
||||||
|
from bs4 import BeautifulSoup
|
||||||
|
|
||||||
|
# 1. 必须包含检测头
|
||||||
|
headers = {
|
||||||
|
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
|
||||||
|
}
|
||||||
|
|
||||||
|
url = 'https://exam.detr.top/exam-b/movies'
|
||||||
|
|
||||||
|
try:
|
||||||
|
response = requests.get(url, headers=headers)
|
||||||
|
response.encoding = 'utf-8'
|
||||||
|
|
||||||
|
# 2. 保存原始网页源码
|
||||||
|
with open('movies.html', 'w', encoding='utf-8') as f_html:
|
||||||
|
f_html.write(response.text)
|
||||||
|
|
||||||
|
# 3. 解析数据 (这里假设网页是表格或列表，需要手动调试定位)
|
||||||
|
soup = BeautifulSoup(response.text, 'lxml')
|
||||||
|
# 示例：假设电影信息在一个 class 为 'movie-item' 的 div 中，实际需要你按 F12 查看源码修改
|
||||||
|
# movie_items = soup.select('.movie-item')
|
||||||
|
# 获取前10条（或全部）
|
||||||
|
# movies_list = []
|
||||||
|
# for i, item in enumerate(movie_items[:10]):
|
||||||
|
# # 根据实际标签提取：id, title, director, year, rating, duration, genre, actors_count
|
||||||
|
# pass
|
||||||
|
|
||||||
|
# ⚠️ 由于无法访问在线真实网页，此处提供解析后构造的示例数据（仅供保存json逻辑参考）
|
||||||
|
# 你实际做的时候，需要将上面的 `movies_list` 替换为真实的爬取结果。
|
||||||
|
movies_list = [
|
||||||
|
{"id": "1", "title": "示例电影A", "director": "导演A", "year": 2022, "rating": 8.5, "duration": 120, "genre": "动作", "actors_count": 4},
|
||||||
|
{"id": "2", "title": "示例电影B", "director": "导演B", "year": 2019, "rating": 6.0, "duration": 95, "genre": "喜剧", "actors_count": 6}
|
||||||
|
] # 这里要保证爬够10条
|
||||||
|
|
||||||
|
# 4. 保存为 movies.json
|
||||||
|
with open('movies.json', 'w', encoding='utf-8') as f_json:
|
||||||
|
json.dump(movies_list, f_json, ensure_ascii=False, indent=4)
|
||||||
|
|
||||||
|
print("爬取完成，已保存 movies.json 和 movies.html")
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
print(f"爬取失败: {e}")
|
||||||
31
q2_1_crawler/q2_2.py
Normal file
31
q2_1_crawler/q2_2.py
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
import json
|
||||||
|
|
||||||
|
# 1. 读取数据
|
||||||
|
with open('movies.json', 'r', encoding='utf-8') as f:
|
||||||
|
movies = json.load(f)
|
||||||
|
|
||||||
|
# 2. ① 找出评分最高和最低的电影
|
||||||
|
max_rating_movie = max(movies, key=lambda x: x['rating'])
|
||||||
|
min_rating_movie = min(movies, key=lambda x: x['rating'])
|
||||||
|
print(f"评分最高电影: {max_rating_movie['title']} - {max_rating_movie['rating']}")
|
||||||
|
print(f"评分最低电影: {min_rating_movie['title']} - {min_rating_movie['rating']}")
|
||||||
|
|
||||||
|
# 3. ② 统计各类型的电影数量 (字典格式)
|
||||||
|
genre_counts = {}
|
||||||
|
for movie in movies:
|
||||||
|
genre = movie['genre']
|
||||||
|
genre_counts[genre] = genre_counts.get(genre, 0) + 1
|
||||||
|
print("各类型电影数量统计:")
|
||||||
|
print(json.dumps(genre_counts, ensure_ascii=False, indent=4))
|
||||||
|
|
||||||
|
# 4. ③ 统计各导演的电影数量 (字典格式)
|
||||||
|
director_counts = {}
|
||||||
|
for movie in movies:
|
||||||
|
director = movie['director']
|
||||||
|
director_counts[director] = director_counts.get(director, 0) + 1
|
||||||
|
print("各导演电影数量统计:")
|
||||||
|
print(json.dumps(director_counts, ensure_ascii=False, indent=4))
|
||||||
|
|
||||||
|
# 5. ④ 统计2020年（含）以后上映的电影数量
|
||||||
|
count_post_2020 = sum(1 for movie in movies if movie['year'] >= 2020)
|
||||||
|
print(f"2020年(含)以后上映的电影数量: {count_post_2020}")
|
||||||
Reference in New Issue
Block a user