完成作业一

爬虫/爬虫.py (2).txt

@@ -0,0 +1,30 @@
+import requests
+from bs4 import BeautifulSoup
+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"
+}
+
+all_movies = []
+
+for page in range(0, 250, 25):
+    url = f"https://movie.douban.com/top250?start={page}&filter="
+    print(f"<22><><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ȡ<EFBFBD><C8A1> {page//25 + 1} ҳ<><D2B3>{url}")
+
+    response = requests.get(url, headers=headers)
+    response.encoding = "utf-8"
+    soup = BeautifulSoup(response.text, "html.parser")
+
+   
+    items = soup.find_all("div", class_="item")
+    for item in items:
+        title = item.find("span", class_="title").get_text(strip=True)
+        all_movies.append(title)
+        print(title)
+
+    
+    time.sleep(1)
+
+
+print(f"\nһ<6E><D2BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ӱ<EFBFBD><D3B0>{len(all_movies)} <20><>")