diff --git a/q2_1_crawler/movies.html b/q2_1_crawler/movies.html
new file mode 100644
index 0000000..2e24df0
--- /dev/null
+++ b/q2_1_crawler/movies.html
@@ -0,0 +1,152 @@
+
+
+
+
+
+
+
+ 电影列表
+
+
+
+ 电影列表
+ 数据编号：B-20260623-2074
+
+
+
+
+ | 编号 |
+ 电影名 |
+ 导演 |
+ 上映年份 |
+ 评分 |
+ 时长(分钟) |
+ 类型 |
+ 主演数 |
+
+
+
+
+
+ | 1 |
+ 放牛班的春天 |
+ Frank Darabont |
+ 2019 |
+ 8.2 |
+ 134 |
+ 爱情 |
+ 2 |
+
+
+
+ | 2 |
+ 忠犬八公的故事 |
+ 陈凯歌 |
+ 2010 |
+ 6.7 |
+ 130 |
+ 爱情 |
+ 4 |
+
+
+
+ | 3 |
+ 星际穿越 |
+ Robert Zemeckis |
+ 2010 |
+ 7.7 |
+ 109 |
+ 动画 |
+ 2 |
+
+
+
+ | 4 |
+ 阿甘正传 |
+ James Cameron |
+ 2005 |
+ 9.2 |
+ 98 |
+ 爱情 |
+ 4 |
+
+
+
+ | 5 |
+ 肖申克的救赎 |
+ 宫崎骏 |
+ 2022 |
+ 8.9 |
+ 111 |
+ 冒险 |
+ 4 |
+
+
+
+ | 6 |
+ 霸王别姬 |
+ Christopher Nolan |
+ 2005 |
+ 9.4 |
+ 169 |
+ 悬疑 |
+ 5 |
+
+
+
+ | 7 |
+ 千与千寻 |
+ Lasse Hallström |
+ 2000 |
+ 9.2 |
+ 106 |
+ 冒险 |
+ 4 |
+
+
+
+ | 8 |
+ 盗梦空间 |
+ Rajkumar Hirani |
+ 2014 |
+ 8.0 |
+ 101 |
+ 悬疑 |
+ 2 |
+
+
+
+ | 9 |
+ 泰坦尼克号 |
+ Christophe Barratier |
+ 1996 |
+ 9.2 |
+ 93 |
+ 喜剧 |
+ 5 |
+
+
+
+ | 10 |
+ 三傻大闹宝莱坞 |
+ Christopher Nolan |
+ 2003 |
+ 7.9 |
+ 114 |
+ 冒险 |
+ 4 |
+
+
+
+
+
+
\ No newline at end of file
diff --git a/q2_1_crawler/movies.json b/q2_1_crawler/movies.json
new file mode 100644
index 0000000..0241519
--- /dev/null
+++ b/q2_1_crawler/movies.json
@@ -0,0 +1,102 @@
+[
+ {
+ "id": "1",
+ "title": "放牛班的春天",
+ "director": "Frank Darabont",
+ "year": 2019,
+ "rating": 8.2,
+ "duration": 134,
+ "genre": "爱情",
+ "actors_count": 2
+ },
+ {
+ "id": "2",
+ "title": "忠犬八公的故事",
+ "director": "陈凯歌",
+ "year": 2010,
+ "rating": 6.7,
+ "duration": 130,
+ "genre": "爱情",
+ "actors_count": 4
+ },
+ {
+ "id": "3",
+ "title": "星际穿越",
+ "director": "Robert Zemeckis",
+ "year": 2010,
+ "rating": 7.7,
+ "duration": 109,
+ "genre": "动画",
+ "actors_count": 2
+ },
+ {
+ "id": "4",
+ "title": "阿甘正传",
+ "director": "James Cameron",
+ "year": 2005,
+ "rating": 9.2,
+ "duration": 98,
+ "genre": "爱情",
+ "actors_count": 4
+ },
+ {
+ "id": "5",
+ "title": "肖申克的救赎",
+ "director": "宫崎骏",
+ "year": 2022,
+ "rating": 8.9,
+ "duration": 111,
+ "genre": "冒险",
+ "actors_count": 4
+ },
+ {
+ "id": "6",
+ "title": "霸王别姬",
+ "director": "Christopher Nolan",
+ "year": 2005,
+ "rating": 9.4,
+ "duration": 169,
+ "genre": "悬疑",
+ "actors_count": 5
+ },
+ {
+ "id": "7",
+ "title": "千与千寻",
+ "director": "Lasse Hallström",
+ "year": 2000,
+ "rating": 9.2,
+ "duration": 106,
+ "genre": "冒险",
+ "actors_count": 4
+ },
+ {
+ "id": "8",
+ "title": "盗梦空间",
+ "director": "Rajkumar Hirani",
+ "year": 2014,
+ "rating": 8.0,
+ "duration": 101,
+ "genre": "悬疑",
+ "actors_count": 2
+ },
+ {
+ "id": "9",
+ "title": "泰坦尼克号",
+ "director": "Christophe Barratier",
+ "year": 1996,
+ "rating": 9.2,
+ "duration": 93,
+ "genre": "喜剧",
+ "actors_count": 5
+ },
+ {
+ "id": "10",
+ "title": "三傻大闹宝莱坞",
+ "director": "Christopher Nolan",
+ "year": 2003,
+ "rating": 7.9,
+ "duration": 114,
+ "genre": "冒险",
+ "actors_count": 4
+ }
+]
\ No newline at end of file
diff --git a/q2_1_crawler/q2_1.py b/q2_1_crawler/q2_1.py
new file mode 100644
index 0000000..caae0d4
--- /dev/null
+++ b/q2_1_crawler/q2_1.py
@@ -0,0 +1,46 @@
+import requests
+import json
+from bs4 import BeautifulSoup
+
+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'
+ html_content = response.text
+ with open('movies.html', 'w', encoding='utf-8') as f_html:
+ f_html.write(html_content)
+ soup = BeautifulSoup(html_content, 'html.parser')
+ table = soup.find('table')
+ tbody = table.find('tbody')
+ rows = tbody.find_all('tr')
+
+ movies_data = []
+
+ for row in rows:
+ tds = row.find_all('td')
+ if len(tds) >= 8:
+ movie = {
+ "id": tds[0].text.strip(),
+ "title": tds[1].text.strip(),
+ "director": tds[2].text.strip(),
+ "year": int(tds[3].text.strip()),
+ "rating": float(tds[4].text.strip()),
+ "duration": int(tds[5].text.strip()),
+ "genre": tds[6].text.strip(),
+ "actors_count": int(tds[7].text.strip())
+ }
+ movies_data.append(movie)
+
+ with open('movies.json', 'w', encoding='utf-8') as f_json:
+ json.dump(movies_data, f_json, ensure_ascii=False, indent=4)
+
+ print(f"爬取成功！共获取 {len(movies_data)} 条电影数据。")
+ print("文件 movies.html 和 movies.json 已保存。")
+
+except Exception as e:
+ print(f"爬取或解析失败，错误信息：{e}")
diff --git a/q2_1_crawler/q2_2.py b/q2_1_crawler/q2_2.py
new file mode 100644
index 0000000..f8f1ea8
--- /dev/null
+++ b/q2_1_crawler/q2_2.py
@@ -0,0 +1,37 @@
+import json
+
+with open('q2_1_crawler\movies.json', 'r', encoding='utf-8') as f:
+ movies = json.load(f)
+
+if movies:
+ sorted_by_rating = sorted(movies, key=lambda x: x['rating'])
+ lowest_movie = sorted_by_rating[0]
+ highest_movie = sorted_by_rating[-1]
+
+ print("2.1 最高评分电影:")
+ print(f"电影名: {highest_movie['title']}, 评分: {highest_movie['rating']}")
+ print("\n最低评分电影:")
+ print(f"电影名: {lowest_movie['title']}, 评分: {lowest_movie['rating']}")
+
+genre_counts = {}
+for movie in movies:
+ genre = movie['genre']
+ genre_counts[genre] = genre_counts.get(genre, 0) + 1
+
+print("\n2.2 各类型电影数量字典:")
+print(genre_counts)
+
+director_counts = {}
+for movie in movies:
+ director = movie['director']
+ director_counts[director] = director_counts.get(director, 0) + 1
+
+print("\n2.3 各导演电影数量字典:")
+print(director_counts)
+
+count_2020_later = 0
+for movie in movies:
+ if movie['year'] >= 2020:
+ count_2020_later += 1
+
+print(f"\n2.4 2020年（含）以后上映的电影数量: {count_2020_later} 部")
\ No newline at end of file