完成期末练习

q2_1_crawler/movie.html

@@ -0,0 +1,102 @@
+[
+  {
+    "id": "1",
+    "title": "阿甘正传",
+    "director": "Frank Darabont",
+    "year": "2023",
+    "rating": "8.5",
+    "duration": "112",
+    "genre": "科幻",
+    "actors_count": "4"
+  },
+  {
+    "id": "2",
+    "title": "忠犬八公的故事",
+    "director": "陈凯歌",
+    "year": "2023",
+    "rating": "6.9",
+    "duration": "102",
+    "genre": "动画",
+    "actors_count": "4"
+  },
+  {
+    "id": "3",
+    "title": "放牛班的春天",
+    "director": "Robert Zemeckis",
+    "year": "1993",
+    "rating": "7.6",
+    "duration": "175",
+    "genre": "动画",
+    "actors_count": "5"
+  },
+  {
+    "id": "4",
+    "title": "星际穿越",
+    "director": "James Cameron",
+    "year": "2024",
+    "rating": "9.1",
+    "duration": "92",
+    "genre": "喜剧",
+    "actors_count": "5"
+  },
+  {
+    "id": "5",
+    "title": "千与千寻",
+    "director": "宫崎骏",
+    "year": "2007",
+    "rating": "8.3",
+    "duration": "146",
+    "genre": "悬疑",
+    "actors_count": "4"
+  },
+  {
+    "id": "6",
+    "title": "肖申克的救赎",
+    "director": "Christopher Nolan",
+    "year": "1997",
+    "rating": "8.3",
+    "duration": "117",
+    "genre": "爱情",
+    "actors_count": "5"
+  },
+  {
+    "id": "7",
+    "title": "盗梦空间",
+    "director": "Lasse Hallström",
+    "year": "2001",
+    "rating": "7.5",
+    "duration": "131",
+    "genre": "悬疑",
+    "actors_count": "3"
+  },
+  {
+    "id": "8",
+    "title": "泰坦尼克号",
+    "director": "Rajkumar Hirani",
+    "year": "1994",
+    "rating": "6.8",
+    "duration": "163",
+    "genre": "喜剧",
+    "actors_count": "4"
+  },
+  {
+    "id": "9",
+    "title": "三傻大闹宝莱坞",
+    "director": "Christophe Barratier",
+    "year": "1997",
+    "rating": "6.8",
+    "duration": "107",
+    "genre": "冒险",
+    "actors_count": "5"
+  },
+  {
+    "id": "10",
+    "title": "霸王别姬",
+    "director": "Christopher Nolan",
+    "year": "2006",
+    "rating": "9.1",
+    "duration": "98",
+    "genre": "科幻",
+    "actors_count": "2"
+  }
+]

q2_1_crawler/movie.json

@@ -0,0 +1,102 @@
+[
+  {
+    "id": "1",
+    "title": "阿甘正传",
+    "director": "Frank Darabont",
+    "year": "2023",
+    "rating": "8.5",
+    "duration": "112",
+    "genre": "科幻",
+    "actors_count": "4"
+  },
+  {
+    "id": "2",
+    "title": "忠犬八公的故事",
+    "director": "陈凯歌",
+    "year": "2023",
+    "rating": "6.9",
+    "duration": "102",
+    "genre": "动画",
+    "actors_count": "4"
+  },
+  {
+    "id": "3",
+    "title": "放牛班的春天",
+    "director": "Robert Zemeckis",
+    "year": "1993",
+    "rating": "7.6",
+    "duration": "175",
+    "genre": "动画",
+    "actors_count": "5"
+  },
+  {
+    "id": "4",
+    "title": "星际穿越",
+    "director": "James Cameron",
+    "year": "2024",
+    "rating": "9.1",
+    "duration": "92",
+    "genre": "喜剧",
+    "actors_count": "5"
+  },
+  {
+    "id": "5",
+    "title": "千与千寻",
+    "director": "宫崎骏",
+    "year": "2007",
+    "rating": "8.3",
+    "duration": "146",
+    "genre": "悬疑",
+    "actors_count": "4"
+  },
+  {
+    "id": "6",
+    "title": "肖申克的救赎",
+    "director": "Christopher Nolan",
+    "year": "1997",
+    "rating": "8.3",
+    "duration": "117",
+    "genre": "爱情",
+    "actors_count": "5"
+  },
+  {
+    "id": "7",
+    "title": "盗梦空间",
+    "director": "Lasse Hallström",
+    "year": "2001",
+    "rating": "7.5",
+    "duration": "131",
+    "genre": "悬疑",
+    "actors_count": "3"
+  },
+  {
+    "id": "8",
+    "title": "泰坦尼克号",
+    "director": "Rajkumar Hirani",
+    "year": "1994",
+    "rating": "6.8",
+    "duration": "163",
+    "genre": "喜剧",
+    "actors_count": "4"
+  },
+  {
+    "id": "9",
+    "title": "三傻大闹宝莱坞",
+    "director": "Christophe Barratier",
+    "year": "1997",
+    "rating": "6.8",
+    "duration": "107",
+    "genre": "冒险",
+    "actors_count": "5"
+  },
+  {
+    "id": "10",
+    "title": "霸王别姬",
+    "director": "Christopher Nolan",
+    "year": "2006",
+    "rating": "9.1",
+    "duration": "98",
+    "genre": "科幻",
+    "actors_count": "2"
+  }
+]

q2_1_crawler/q2_1.py

@@ -0,0 +1,48 @@
+import requests
+from bs4 import BeautifulSoup as bs
+import json
+
+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/149.0.0.0 Safari/537.36 Edg/149.0.0.0',
+    'Referer':'https://exam.detr.top/exam-b/movies'}
+req = requests.get(url, headers=headers)
+req.encoding="utf-8"
+
+data=[]
+
+soup=bs(req.text,"html.parser")
+# print(soup)
+#id, title, director, year, rating, duration, genre, actors-count
+
+items=soup.select('.item-row')
+# movie_list=[]
+for i in range(len(items)):
+    id=items[i].find("td",class_="item-id").get_text()
+    title=items[i].find("td",class_="item-title").get_text().strip()
+    director=items[i].find("td",class_="item-director").get_text().strip()
+    year=items[i].find("td",class_="item-year").get_text()
+    rating=items[i].find("td",class_="item-rating").get_text()
+    duration=items[i].find("td",class_="item-duration").get_text()
+    genre=items[i].find("td",class_="item-genre").get_text()
+    actors_count=items[i].find("td",class_="item-actors-count").get_text()
+
+    data.append({
+        "id":id,
+        "title":title,
+        "director":director,
+        "year":year,
+        "rating":rating,
+        "duration":duration,
+        "genre":genre,
+        "actors_count":actors_count
+        
+    })
+
+print(data)
+
+
+with open('movie.json', 'w', encoding='utf-8') as f:
+    json.dump(data, f, ensure_ascii=False, indent=2)
+
+with open("movie.html","w",encoding='utf-8') as f:
+     json.dump(data, f, ensure_ascii=False, indent=2)

q2_1_crawler/q2_2.py

@@ -0,0 +1,43 @@
+# ① 找出评分最高和最低的电影，打印电影名 + 评分。
+# ② 统计各类型的电影数量，用字典格式输出。
+# ③ 统计各导演的电影数量，用字典格式输出。
+# ④ 统计 2020 年（含）以后上映的电影数量。
+
+import json
+
+
+
+with open('movie.json', 'r', encoding='utf-8') as f:
+    data=json.load(f)
+    # print(data)
+   
+
+sort_movie=sorted(data,key=lambda x:x["rating"])
+min=sort_movie[0]
+max=sort_movie[-1]
+print("评分最低的电影",min["title"],min["rating"])
+print("评分最高的电影",max["title"],max["rating"])
+
+genre_shu={}
+for g in data:
+    ge=g["genre"]
+    if ge in genre_shu:
+        genre_shu[ge]+=1
+    else:
+        genre_shu[ge]=1
+print("各类型的电影数量",genre_shu)
+
+director_shu={}
+for d in data:
+    di=d["director"]
+    if di in director_shu:
+        director_shu[di]+=1
+    else:
+        director_shu[di]=1
+print("各导演的电影数量",director_shu)
+
+a=0
+for y in data:
+    if int(y["year"]) >= 2020:
+        a+=1
+print("2020 年（含）以后上映的电影数量",a)

q3/q3_3_质量自评.md

@@ -0,0 +1,9 @@
+标注质量自评
+1.标注前准备
+本次文本情感分类标注规范：仅设置（正面）（负面）俩类标签，一条评论只能标注单一情感，无中立标签；判断依据以用户核心情绪、评价倾向为准，忽略无关客观描述。标注前查看2条示例评论，明确极端好评、差评的区别边界，统一判定标准。
+
+2.标注过程
+困难：部分评论同时存在优缺点混合描述，情感倾向模糊。解决方法：抓取句子核心总结、整体推荐态度，以最终情绪导向判定；不确定样本反复重读全文，不随意打标签，保证标签唯一。
+
+3.标注后检查
+逐条核对5条评论，确保每条都存在id、text、sentiment字段，无漏标数据；没有导入重复数据，全部素材仅标注一次，导出JSON校验字段格式符合作业要求，无缺失、错标。

q4/q4_1/q4_1.py

@@ -0,0 +1,40 @@
+import matplotlib.pyplot as plt
+import json
+
+
+with open(r'D:\桌面\期末考试\simulated-examination\q2_1_crawler\movie.json', 'r', encoding='utf-8') as f:
+    data=json.load(f)
+    # print(data)
+    
+genre_shu={}
+for g in data:
+    ge=g["genre"]
+    if ge in genre_shu:
+        genre_shu[ge]+=1
+    else:
+        genre_shu[ge]=1
+# print("各类型的电影数量",genre_shu)
+
+genre_lei=list(genre_shu.keys())
+genre_liang=list(genre_shu.values())
+
+print(genre_liang)
+
+plt.figure(figsize=(14, 12))
+plt.bar(genre_lei,  genre_liang,      
+        width=0.6)            
+      
+# 标题和标签
+plt.title('类型电影数量分布', fontsize=14)
+plt.xlabel('类型名称', fontsize=12)
+plt.ylabel('电影数量', fontsize=12)
+
+
+import os
+save_path = os.path.join(os.path.dirname(__file__),"q4_1_bar.png")
+plt.savefig(save_path, dpi=150,format='png')
+plt.show()
+
+
+
+#with open('movie.json', 'r', encoding='utf-8') as f:

q4/q4_2/q4_2.py

@@ -0,0 +1,28 @@
+import matplotlib.pyplot as plt
+import json
+
+rating=[]
+duration=[]
+
+with open(r'D:\桌面\期末考试\simulated-examination\q2_1_crawler\movie.json', 'r', encoding='utf-8') as f:
+    data=json.load(f)
+    # print(data)
+    for i in data:
+        rating.append(i["rating"])
+        duration.append(i["duration"])
+plt.figure(figsize=(12, 8))
+plt.scatter(duration, rating,
+            c='red',
+            s=80,                      # 点的大小
+            alpha=0.6,                 # 透明度
+            edgecolors='white')         # 点的边框
+plt.title('时长与评分关系散点图', fontsize=14)
+plt.xlabel('时长', fontsize=12)
+plt.ylabel('评分', fontsize=12)
+plt.grid(True, linestyle='--', alpha=0.5)
+
+
+import os
+save_path = os.path.join(os.path.dirname(__file__),"q4_2_scatter.png")
+plt.savefig(save_path, dpi=150,format='png')
+plt.show()

q4/q4_3a/q4_3a.py

@@ -0,0 +1,24 @@
+import matplotlib.pyplot as plt
+import json
+
+rating=[]
+
+with open(r'D:\桌面\期末考试\simulated-examination\q2_1_crawler\movie.json', 'r', encoding='utf-8') as f:
+    data=json.load(f)
+    # print(data)
+    for i in data:
+        rating.append(i["rating"])
+
+plt.figure(figsize=(12,8))
+plt.hist(rating,                     # 数据
+         bins=10,                    # 分成几个柱子
+         color='#3498DB',            # 颜色
+         edgecolor='white')          # 柱子边框颜色
+plt.title('评分分布', fontsize=14)
+plt.xlabel('评分', fontsize=13)
+plt.grid(True, linestyle='--', alpha=0.5, axis='y')
+
+import os
+save_path = os.path.join(os.path.dirname(__file__),"q4_3a_hist.png")
+plt.savefig(save_path, dpi=150,format='png')
+plt.show()

q4/q4_3b/q4_3b.py

@@ -0,0 +1,24 @@
+import matplotlib.pyplot as plt
+import json
+duration=[]
+
+with open(r'D:\桌面\期末考试\simulated-examination\q2_1_crawler\movie.json', 'r', encoding='utf-8') as f:
+    data=json.load(f)
+    # print(data)
+    for i in data:
+       duration.append(i["duration"])
+
+plt.figure(figsize=(12,8))
+plt.hist( duration,                     # 数据
+         bins=10,                    # 分成几个柱子
+         color='#3498DB',            # 颜色
+         edgecolor='white')          # 柱子边框颜色
+plt.title('时长分布', fontsize=14)
+plt.xlabel('时长（分钟）', fontsize=13)
+plt.grid(True, linestyle='--', alpha=0.5, axis='y')
+
+
+import os
+save_path = os.path.join(os.path.dirname(__file__),"q4_3b_hist.png")
+plt.savefig(save_path, dpi=150,format='png')
+plt.show()