From 5a8416c1459569313c4028a3f9cebcb65890f67e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=9D=8E=E5=A4=A9=E8=B5=90?=
 <2509165007@student.example.com>
Date: Tue, 23 Jun 2026 11:18:32 +0800
Subject: [PATCH] =?UTF-8?q?=E4=B8=8A=E4=BC=A0=E6=96=87=E4=BB=B6=E8=87=B3?=
 =?UTF-8?q?=20=20q2=5F1=5Fcrawler?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
  q2_1_crawler/q2_1.py | 39 ++++++++++++++++++++++++++++++
  q2_1_crawler/q2_2.py | 55 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 94 insertions(+)
 create mode 100644  q2_1_crawler/q2_1.py
 create mode 100644  q2_1_crawler/q2_2.py

diff --git a/ q2_1_crawler/q2_1.py b/ q2_1_crawler/q2_1.py
new file mode 100644
index 0000000..df5ad89
--- /dev/null
+++ b/ q2_1_crawler/q2_1.py	
@@ -0,0 +1,39 @@
+import requests
+import json
+
+# 1. 配置请求头（测试头，满足题目要求）
+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",
+    "Accept-Language": "zh-CN,zh;q=0.9",
+    "Referer": "https://exam.detr.top/"
+}
+
+url = "https://exam.detr.top/exam-b/movies"
+
+# 2. 一次性请求获取全部数据（题目要求单次抓取）
+resp = requests.get(url, headers=headers)
+resp.raise_for_status()  # 捕获请求异常
+
+# 保存原始网页源码到 movies.html
+with open("movies.html", "w", encoding="utf-8") as f:
+    f.write(resp.text)
+
+# 解析接口返回的json数据
+movie_data = resp.json()
+
+# 筛选全部10部电影，校验字段：id, title, director, year, rating, duration, genre, actors_count
+valid_movies = []
+for item in movie_data:
+    needed_keys = ["id", "title", "director", "year", "rating", "duration", "genre", "actors_count"]
+    # 只保留包含全部要求键的电影
+    if all(k in item for k in needed_keys):
+        valid_movies.append(item)
+
+# 保存电影数据到 movies.json
+with open("movies.json", "w", encoding="utf-8") as f:
+    json.dump(valid_movies, f, ensure_ascii=False, indent=2)
+
+print("抓取完成：已生成 movies.html 和 movies.json")
+print(f"共抓取到 {len(valid_movies)} 部电影")
+
+
diff --git a/ q2_1_crawler/q2_2.py b/ q2_1_crawler/q2_2.py
new file mode 100644
index 0000000..7129447
--- /dev/null
+++ b/ q2_1_crawler/q2_2.py	
@@ -0,0 +1,55 @@
+import json
+from collections import defaultdict
+
+# 读取json文件
+with open("movies.json", "r", encoding="utf-8") as f:
+    movies = json.load(f)
+
+# ① 找出评分最高、最低电影
+def get_rating_extreme():
+    # 按rating排序
+    sorted_movies = sorted(movies, key=lambda x: x["rating"])
+    lowest = sorted_movies[0]
+    highest = sorted_movies[-1]
+    print("=== ① 评分极值 ===")
+    print(f"评分最低电影：{lowest['title']}，评分：{lowest['rating']}")
+    print(f"评分最高电影：{highest['title']}，评分：{highest['rating']}")
+    return highest, lowest
+
+# ② 统计各类型电影数量（genre为列表，拆分统计）
+def count_genre():
+    genre_count = defaultdict(int)
+    for movie in movies:
+        genres = movie["genre"]
+        for g in genres:
+            genre_count[g] += 1
+    print("\n=== ② 各类型电影数量（字典格式）===")
+    print(dict(genre_count))
+    return dict(genre_count)
+
+# ③ 统计各导演电影数量
+def count_director():
+    dir_count = defaultdict(int)
+    for movie in movies:
+        d = movie["director"]
+        dir_count[d] += 1
+    print("\n=== ③ 各导演电影数量（字典格式）===")
+    print(dict(dir_count))
+    return dict(dir_count)
+
+# ④ 统计2020年（含）以后上映电影数量
+def count_after_2020():
+    cnt = 0
+    for movie in movies:
+        if movie["year"] >= 2020:
+            cnt += 1
+    print("\n=== ④ 2020年（含）后上映电影数量 ===")
+    print(f"总数：{cnt}")
+    return cnt
+
+# 执行全部分析逻辑
+if __name__ == "__main__":
+    get_rating_extreme()
+    count_genre()
+    count_director()
+    count_after_2020()
\ No newline at end of file