上传文件至 /

q1.py

@@ -0,0 +1,51 @@
+import requests
+import json
+from bs4 import BeautifulSoup
+
+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"
+}
+
+response = requests.get(url, headers=headers)
+response.encoding = "utf-8"
+html_text = response.text
+
+with open("movies.html", "w", encoding="utf-8") as f:
+    f.write(html_text)
+
+soup = BeautifulSoup(html_text, "html.parser")
+
+movies_data = []
+data_id = ""
+
+table = soup.find("table")
+if table:
+    rows = table.find_all("tr")
+    for row in rows[1:]:
+        cols = row.find_all("td")
+        if len(cols) >= 8:
+            movie = {
+                "id": cols[0].text.strip(),
+                "title": cols[1].text.strip(),
+                "director": cols[2].text.strip(),
+                "year": int(cols[3].text.strip()),
+                "rating": float(cols[4].text.strip()),
+                "duration": int(cols[5].text.strip()),
+                "genre": cols[6].text.strip(),
+                "actors_count": int(cols[7].text.strip())
+            }
+            movies_data.append(movie)
+
+data_id_tag = soup.find("span", class_="data-id")
+if data_id_tag:
+    data_id = data_id_tag.text.strip()
+
+result = {
+    "data_id": data_id,
+    "movies": movies_data
+}
+
+with open("movies.json", "w", encoding="utf-8") as f:
+    json.dump(result, f, ensure_ascii=False, indent=4)

q2 (2).py

@@ -0,0 +1,32 @@
+import json
+
+with open("movies.json", "r", encoding="utf-8") as f:
+    data = json.load(f)
+movies = data["movies"]
+
+# 1.① 评分最高和最低
+max_rating_movie = max(movies, key=lambda x: x["rating"])
+min_rating_movie = min(movies, key=lambda x: x["rating"])
+print(max_rating_movie["title"], max_rating_movie["rating"])
+print(min_rating_movie["title"], min_rating_movie["rating"])
+
+# 2.② 各类型电影数量
+genre_count = {}
+for movie in movies:
+    genre = movie["genre"]
+    genre_count[genre] = genre_count.get(genre, 0) + 1
+print(genre_count)
+
+# 3.③ 各导演电影数量
+director_count = {}
+for movie in movies:
+    director = movie["director"]
+    director_count[director] = director_count.get(director, 0) + 1
+print(director_count)
+
+# 4.④ 2020年（含）以后电影数量
+count_2020_later = 0
+for movie in movies:
+    if movie["year"] >= 2020:
+        count_2020_later += 1
+print(count_2020_later)

q2.py

@@ -0,0 +1,32 @@
+import json
+
+with open("movies.json", "r", encoding="utf-8") as f:
+    data = json.load(f)
+movies = data["movies"]
+
+# 1.① 评分最高和最低
+max_rating_movie = max(movies, key=lambda x: x["rating"])
+min_rating_movie = min(movies, key=lambda x: x["rating"])
+print(max_rating_movie["title"], max_rating_movie["rating"])
+print(min_rating_movie["title"], min_rating_movie["rating"])
+
+# 2.② 各类型电影数量
+genre_count = {}
+for movie in movies:
+    genre = movie["genre"]
+    genre_count[genre] = genre_count.get(genre, 0) + 1
+print(genre_count)
+
+# 3.③ 各导演电影数量
+director_count = {}
+for movie in movies:
+    director = movie["director"]
+    director_count[director] = director_count.get(director, 0) + 1
+print(director_count)
+
+# 4.④ 2020年（含）以后电影数量
+count_2020_later = 0
+for movie in movies:
+    if movie["year"] >= 2020:
+        count_2020_later += 1
+print(count_2020_later)

q4_1.py

@@ -0,0 +1,19 @@
+import json
+import matplotlib.pyplot as plt
+
+with open("../q2_1_crawler/movies.json","r",encoding="utf-8") as f:
+    data = json.load(f)
+movies = data["movies"]
+
+genre_cnt = {}
+for m in movies:
+    g = m["genre"]
+    genre_cnt[g] = genre_cnt.get(g,0)+1
+
+x = list(genre_cnt.keys())
+y = list(genre_cnt.values())
+
+plt.bar(x,y)
+plt.tight_layout()
+plt.savefig("q4_1_bar.png",dpi=150)
+plt.close()

q4_2.py

@@ -0,0 +1,14 @@
+import json
+import matplotlib.pyplot as plt
+
+with open("../q2_1_crawler/movies.json","r",encoding="utf-8") as f:
+    data = json.load(f)
+movies = data["movies"]
+
+rating = [i["rating"] for i in movies]
+duration = [i["duration"] for i in movies]
+
+plt.scatter(duration,rating)
+plt.tight_layout()
+plt.savefig("q4_2_scatter.png",dpi=150)
+plt.close()