上传文件至 /

2026-04-02 2509165011.py

@@ -0,0 +1,66 @@
+import requests
+import re
+import time
+import random
+import csv
+from bs4 import BeautifulSoup
+
+# 保存到 CSV
+def save_to_csv(data, filename="douban_top250_with_comments.csv"):
+    with open(filename, "w", encoding="utf-8-sig", newline="") as f:
+        writer = csv.DictWriter(f, fieldnames=["排名", "片名", "评分", "评分人数", "热门评语"])
+        writer.writeheader()
+        writer.writerows(data)
+
+# 爬取豆瓣 Top250
+def crawl_douban_top250():
+    base_url = "https://movie.douban.com/top250"
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36",
+        "Referer": "https://movie.douban.com/",
+    }
+    movie_list = []
+
+    # 爬 10 页
+    for start in range(0, 250, 25):
+        url = f"{base_url}?start={start}"
+        try:
+            resp = requests.get(url, headers=headers, timeout=10)
+            soup = BeautifulSoup(resp.text, "html.parser")
+            items = soup.find_all("div", class_="item")
+
+            for item in items:
+                # 排名
+                rank = item.find("em").text.strip()
+                # 片名pip
+                title = item.find("span", class_="title").text.strip()
+                # 评分
+                rating = item.find("span", class_="rating_num").text.strip()
+                # 评分人数
+                eval_text = item.find("div", class_="star").find_all("span")[-1].text
+                eval_num = re.search(r"(\d+)人评价", eval_text).group(1)
+                # 评语（热门短评）
+                comment_tag = item.find("span", class_="inq")
+                comment = comment_tag.text.strip() if comment_tag else "无评语"
+
+                movie_list.append({
+                    "排名": rank,
+                    "片名": title,
+                    "评分": rating,
+                    "评分人数": eval_num,
+                    "热门评语": comment
+                })
+
+                print(f"{rank}. {title} | 评分：{rating} | 评价：{eval_num} | 评语：{comment[:20]}...")
+
+            time.sleep(random.uniform(1, 2.5))  # 防封
+
+        except Exception as e:
+            print(f"爬取失败：{e}")
+            continue
+
+    return movie_list
+
+if __name__ == "__main__":
+    data = crawl_douban_top250()
+    save_to_csv(data)