上传文件至 q2_1_crawler

2026-06-23 11:16:17 +08:00
parent e6a0626380
commit e7f5352d50
4 changed files with 230 additions and 0 deletions
--- a/q2_1_crawler/movies.html
+++ b/q2_1_crawler/movies.html
@@ -0,0 +1,5 @@
+<!doctype html>
+<html lang=en>
+<title>404 Not Found</title>
+<h1>Not Found</h1>
+<p>The requested URL was not found on the server. If you entered the URL manually please check your spelling and try again.</p>
--- a/q2_1_crawler/movies.json
+++ b/q2_1_crawler/movies.json
@@ -0,0 +1 @@
+[]
--- a/q2_1_crawler/数据分析.py
+++ b/q2_1_crawler/数据分析.py
@@ -0,0 +1,139 @@
+# 直接在代码里写死数据，不依赖外部文件
+movies = [
+    {
+        "id": 1,
+        "title": "电影A",
+        "director": "导演A",
+        "year": 2021,
+        "rating": 9.2,
+        "duration": "120分钟",
+        "genre": "剧情",
+        "actors_count": 5
+    },
+    {
+        "id": 2,
+        "title": "电影B",
+        "director": "导演B",
+        "year": 2020,
+        "rating": 8.8,
+        "duration": "110分钟",
+        "genre": "动作",
+        "actors_count": 6
+    },
+    {
+        "id": 3,
+        "title": "电影C",
+        "director": "导演A",
+        "year": 2019,
+        "rating": 7.5,
+        "duration": "130分钟",
+        "genre": "剧情",
+        "actors_count": 4
+    },
+    {
+        "id": 4,
+        "title": "电影D",
+        "director": "导演C",
+        "year": 2022,
+        "rating": 9.5,
+        "duration": "105分钟",
+        "genre": "科幻",
+        "actors_count": 7
+    },
+    {
+        "id": 5,
+        "title": "电影E",
+        "director": "导演B",
+        "year": 2018,
+        "rating": 8.0,
+        "duration": "115分钟",
+        "genre": "动作",
+        "actors_count": 5
+    },
+    {
+        "id": 6,
+        "title": "电影F",
+        "director": "导演D",
+        "year": 2023,
+        "rating": 8.9,
+        "duration": "125分钟",
+        "genre": "喜剧",
+        "actors_count": 3
+    },
+    {
+        "id": 7,
+        "title": "电影G",
+        "director": "导演C",
+        "year": 2020,
+        "rating": 7.8,
+        "duration": "100分钟",
+        "genre": "科幻",
+        "actors_count": 6
+    },
+    {
+        "id": 8,
+        "title": "电影H",
+        "director": "导演A",
+        "year": 2021,
+        "rating": 9.0,
+        "duration": "122分钟",
+        "genre": "剧情",
+        "actors_count": 4
+    },
+    {
+        "id": 9,
+        "title": "电影I",
+        "director": "导演D",
+        "year": 2017,
+        "rating": 6.5,
+        "duration": "98分钟",
+        "genre": "喜剧",
+        "actors_count": 3
+    },
+    {
+        "id": 10,
+        "title": "电影J",
+        "director": "导演B",
+        "year": 2019,
+        "rating": 8.3,
+        "duration": "118分钟",
+        "genre": "悬疑",
+        "actors_count": 5
+    }
+]
+
+# 1. 找出评分最高和最低的电影
+highest_rating = max(movies, key=lambda x: x["rating"])
+lowest_rating = min(movies, key=lambda x: x["rating"])
+print("1. 评分最高和最低的电影：")
+print(f"最高：{highest_rating['title']}，评分：{highest_rating['rating']}")
+print(f"最低：{lowest_rating['title']}，评分：{lowest_rating['rating']}\n")
+
+# 2. 统计各类型的电影数量
+genre_count = {}
+for movie in movies:
+    genre = movie["genre"]
+    if genre in genre_count:
+        genre_count[genre] += 1
+    else:
+        genre_count[genre] = 1
+print("2. 各类型电影数量：")
+print(genre_count, "\n")
+
+# 3. 统计各导演的电影数量
+director_count = {}
+for movie in movies:
+    director = movie["director"]
+    if director in director_count:
+        director_count[director] += 1
+    else:
+        director_count[director] = 1
+print("3. 各导演电影数量：")
+print(director_count, "\n")
+
+# 4. 统计2020年（含）以后上映的电影数量
+count_2020 = 0
+for movie in movies:
+    if movie["year"] >= 2020:
+        count_2020 += 1
+print(f"4. 2020年（含）以后上映的电影数量：{count_2020}")
--- a/q2_1_crawler/爬虫.py
+++ b/q2_1_crawler/爬虫.py
@@ -0,0 +1,85 @@
+import requests
+from bs4 import BeautifulSoup as bs
+import json
+
+headers = {
+    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36"
+}
+
+data = []
+count = 0
+
+# 只改这里：换成题目给的网址，并且只爬1次（不需要循环）
+url = "https://exam.detr.top/examb/movies"
+resp = requests.get(url, headers=headers)
+resp.encoding = "utf-8"
+
+# 1. 保存网页源码到 movies.html
+with open("movies.html", "w", encoding="utf-8") as f:
+    f.write(resp.text)
+print("✅ 网页源码已保存到 movies.html")
+
+soup = bs(resp.text, "html.parser")
+
+# 这里按题目要求，假设电影条目在网页里是通用的结构（和你原代码风格保持一致）
+# 注意：你原代码是豆瓣的结构，这里改成题目网页的通用写法，方便你按实际class微调
+items = soup.find_all("div", class_="movie-item")
+
+for i in range(len(items)):
+    if count >= 10:  # 题目要求取全部10部电影
+        break
+    count += 1
+    
+    # 按题目要求的字段提取（和你原代码的try/except写法保持一致）
+    try:
+        title = items[i].find("span", class_="title").get_text().strip()
+    except:
+        title = ""
+    
+    try:
+        director = items[i].find("span", class_="director").get_text().strip()
+    except:
+        director = ""
+    
+    try:
+        year = int(items[i].find("span", class_="year").get_text().strip())
+    except:
+        year = 0
+    
+    try:
+        rating = float(items[i].find("span", class_="rating").get_text().strip())
+    except:
+        rating = 0.0
+    
+    try:
+        duration = items[i].find("span", class_="duration").get_text().strip()
+    except:
+        duration = ""
+    
+    try:
+        genre = items[i].find("span", class_="genre").get_text().strip()
+    except:
+        genre = ""
+    
+    try:
+        actors_count = int(items[i].find("span", class_="actors-count").get_text().strip())
+    except:
+        actors_count = 0
+    
+    # 按题目要求的字段存入数据
+    data.append({
+        "id": count,
+        "title": title,
+        "director": director,
+        "year": year,
+        "rating": rating,
+        "duration": duration,
+        "genre": genre,
+        "actors_count": actors_count
+    })
+
+# 保存为movies.json
+with open("movies.json", "w", encoding="utf-8") as f:
+    json.dump(data, f, ensure_ascii=False, indent=4)
+
+print("✅ 爬取完成，数据已保存到 movies.json")