正则表达式：爬虫内容提取利器

0402+2509165015.JSON

@@ -0,0 +1,46 @@
+import requests
+from bs4 import BeautifulSoup
+import json
+import time
+
+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"
+}
+
+movies = []
+
+for start in range(0, 250, 25):
+    url = f"https://movie.douban.com/top250?start={start}"
+    res = requests.get(url, headers=headers)
+    soup = BeautifulSoup(res.text, "html.parser")
+    items = soup.find_all("div", class_="item")
+
+    for item in items:
+        rank = item.find("em").text
+        title = item.find("span", class_="title").text
+        rating = item.find("span", class_="rating_num").text
+        people = item.find("div", class_="star").find_all("span")[-1].text.replace("人评价", "")
+        quote = item.find("span", class_="inq").text if item.find("span", class_="inq") else "无"
+        info = item.find("p", class_="").text.strip().split("\n")
+        line1 = info[0].strip()
+        line2 = info[1].strip() if len(info) > 1 else ""
+
+        director = line1.split("导演: ")[1].split("主演: ")[0].strip() if "导演: " in line1 else "未知"
+        actor = line1.split("主演: ")[1].strip() if "主演: " in line1 else "未知"
+        parts = line2.split("/") if line2 else []
+        year = parts[0].strip() if len(parts) >= 1 else "未知"
+        area = parts[1].strip() if len(parts) >= 2 else "未知"
+        genre = parts[2].strip() if len(parts) >= 3 else "未知"
+
+        movies.append({
+            "排名": rank, "电影名": title, "评分": rating, "评价人数": people, "经典台词": quote,
+            "导演": director, "主演": actor, "年份": year, "地区": area, "类型": genre
+        })
+
+    time.sleep(1)
+    print(f"已爬取 {start + 25} 条")
+
+with open("douban_top250.json", "w", encoding="utf-8") as f:
+    json.dump(movies, f, ensure_ascii=False, indent=2)
+
+print("✅ JSON 导出完成")