From e609e4a9c2829f9454a326deb489e99cefb57f99 Mon Sep 17 00:00:00 2001
From: ph275ue6c <2370007971@qq.com>
Date: Mon, 17 Jun 2024 11:06:56 +0800
Subject: [PATCH] ADD file via upload

---
 豆瓣电影排行榜1.py | 44 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)
 create mode 100644 豆瓣电影排行榜1.py

diff --git a/豆瓣电影排行榜1.py b/豆瓣电影排行榜1.py
new file mode 100644
index 0000000..d268a72
--- /dev/null
+++ b/豆瓣电影排行榜1.py
@@ -0,0 +1,44 @@
+import requests
+from bs4 import BeautifulSoup
+import csv
+
+# 请求URL
+base_url = 'https://movie.douban.com/top250?start='
+# 请求头部
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
+}
+
+
+# 解析页面函数
+def parse_html(html):
+    soup = BeautifulSoup(html, 'lxml')
+    movie_list = soup.find('ol', class_='grid_view').find_all('li')
+    movies = []
+    for movie in movie_list:
+        title = movie.find('div', class_='hd').find('span', class_='title').get_text()
+        rating_num = movie.find('div', class_='star').find('span', class_='rating_num').get_text()
+        comment_num = movie.find('div', class_='star').find_all('span')[-1].get_text()
+        movies.append([title, rating_num, comment_num])
+    return movies
+
+
+# 保存数据函数
+def save_data():
+    with open('douban_movie_top250.csv', 'a', newline='', encoding='utf-8') as f:
+        writer = csv.writer(f)
+        writer.writerow(['电影名称', '评分', '评价人数'])
+        for i in range(10):
+            url = base_url + str(i * 25)
+            try:
+                response = requests.get(url, headers=headers)
+                response.raise_for_status()  # 如果请求失败，这里会抛出异常
+                movies = parse_html(response.text)
+                for movie in movies:
+                    writer.writerow(movie)
+            except requests.exceptions.RequestException as e:
+                print(f"请求失败: {e}")
+
+
+if __name__ == '__main__':
+    save_data()