完成作业douban250

2026-03-31 11:27:41 +08:00
parent 34a14c904a
commit 4398d1ee78
3 changed files with 67 additions and 0 deletions
--- a/douban.txt/douban.txt
+++ b/douban.txt/douban.txt
@@ -0,0 +1,67 @@
+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(10):
+    start = page * 25
+    url = f"https://movie.douban.com/top250?start={start}&filter="
+
+    print(f"<22><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD> {page+1} ҳ <20><>")
+    resp = requests.get(url, headers=headers)
+    soup = BeautifulSoup(resp.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").t
+        score = item.find("span", class_="rating_num").text
+
+        info = item.find("div", class_="bd").p.text.strip()
+        lines = [line.strip() for line in info.split("\n") if line.strip()]
+
+        director_line = lines[0]
+        if "<22><><EFBFBD><EFBFBD>:" in director_line:
+            director = director_line.split("<22><><EFBFBD><EFBFBD>:")[1].split("<22><><EFBFBD><EFBFBD>:")[0].strip()
+        else:
+            director = "δ֪"
+
+        if len(lines) >= 2:
+            year_area_genre = lines[1].split("/")
+            year = year_area_genre[0].strip() if len(year_area_genre) > 0 else "δ֪"
+            area = year_area_genre[1].strip() if len(year_area_genre) > 1 else "δ֪"
+            genre = year_area_genre[2].strip() if len(year_area_genre) > 2 else "δ֪"
+        else:
+            year = area = genre = "δ֪"
+
+        movie = {
+            "<22><><EFBFBD><EFBFBD>": rank,
+            "Ƭ<><C6AC>": title,
+            "<22><><EFBFBD><EFBFBD>": director,
+            "<22><><EFBFBD><EFBFBD>": year,
+            "<22><><EFBFBD><EFBFBD>": area,
+            "<22><><EFBFBD><EFBFBD>": genre,
+            "<22><><EFBFBD><EFBFBD>": score
+        }
+        all_movies.append(movie)
+
+    time.sleep(1)  
+
+with open("douban_top250.txt", "w", encoding="utf-8") as f:
+    for m in all_movies:
+        f.write(f"<22><><EFBFBD><EFBFBD><EFBFBD><EFBFBD>{m['<27><><EFBFBD><EFBFBD>']}\n")
+        f.write(f"Ƭ<><C6AC><EFBFBD><EFBFBD>{m['Ƭ<><C6AC>']}\n")
+        f.write(f"<22><><EFBFBD>ݣ<EFBFBD>{m['<27><><EFBFBD><EFBFBD>']}\n")
+        f.write(f"<22><><EFBFBD>ݣ<EFBFBD>{m['<27><><EFBFBD><EFBFBD>']}\n")
+        f.write(f"<22><><EFBFBD><EFBFBD><EFBFBD><EFBFBD>{m['<27><><EFBFBD><EFBFBD>']}\n")
+        f.write(f"<22><><EFBFBD>ͣ<EFBFBD>{m['<27><><EFBFBD><EFBFBD>']}\n")
+        f.write(f"<22><><EFBFBD>֣<EFBFBD>{m['<27><><EFBFBD><EFBFBD>']}\n")
+        f.write("-" * 50 + "\n")
+
+print("ȫ<><C8AB><EFBFBD><EFBFBD><EFBFBD>꣡<EFBFBD>ѱ<EFBFBD><D1B1>浽 douban_top250.txt")