上传文件至 /

爬虫.py

@@ -0,0 +1,47 @@
+
+import requests
+from bs4 import BeautifulSoup
+import csv
+import time
+
+
+genre_dict = {
+    0:"剧情",
+    1:"喜剧",
+    2:"科幻",
+    3:"悬疑",
+    4:"动作",
+    5:"爱情",
+    6:"动画",
+    7:"犯罪",
+    8:"奇幻",
+    9:"记录",
+
+}
+url = 'https://movie.douban.com/top250'
+headers = {'User-Agent': 'Mozilla/5.0...'}
+response = requests.get(url, headers=headers)
+
+
+soup = BeautifulSoup(response.text, 'lxml')
+movies = []
+
+for item in soup.select('.item'):
+    title = item.select_one('.title').get_text()
+    rating = item.select_one('.rating_num').get_text()
+    quote = item.select_one('.inq').get_text() if item.select_one('.inq') else ''
+    
+    movies.append({
+        'title': title.strip(),
+        'rating': rating,
+        'quote': quote
+    })
+
+
+with open('movies.csv', 'w', newline='', encoding='utf-8') as f:
+    writer = csv.DictWriter(f, fieldnames=['title', 'rating', 'quote'])
+    writer.writeheader()
+    writer.writerows(movies)
+
+print(f'已保存 {len(movies)} 部电影到 movies.csv')
+print("类别编号1对应的类别:",genre_dict[1])