From 64b551a31638f550408c384f19439838ae4546eb Mon Sep 17 00:00:00 2001
From: 2509165020 <2509165020@student.edu.cn>
Date: Thu, 2 Apr 2026 15:51:57 +0800
Subject: [PATCH] =?UTF-8?q?=E6=AD=A3=E5=88=99=E8=A1=A8=E8=BE=BE=E5=BC=8F?=
 =?UTF-8?q?=EF=BC=9A=E7=88=AC=E8=99=AB=E5=86=85=E5=AE=B9=E6=8F=90=E5=8F=96?=
 =?UTF-8?q?=E5=88=A9=E5=99=A8?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 260402+2509165020/1.py        | 69 +++++++++++++++++++++++++++++++++++
 260402+2509165020/movies.csv  |  1 +
 260402+2509165020/movies.json |  1 +
 260402+2509165020/movies.txt  |  0
 4 files changed, 71 insertions(+)
 create mode 100644 260402+2509165020/1.py
 create mode 100644 260402+2509165020/movies.csv
 create mode 100644 260402+2509165020/movies.json
 create mode 100644 260402+2509165020/movies.txt

diff --git a/260402+2509165020/1.py b/260402+2509165020/1.py
new file mode 100644
index 0000000..18c8524
--- /dev/null
+++ b/260402+2509165020/1.py
@@ -0,0 +1,69 @@
+import requests
+import re
+import csv
+import json
+
+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/114.0.0.0 Safari/537.36"
+}
+
+response = requests.get(url, headers=headers)
+html = response.text
+
+pattern = re.compile(
+    r'<em class="">(\d+)</em>.*?'
+    r'<span class="title">(.*?)</span>.*?'
+    r'<span class="other">(.*?)</span>.*?'
+    r'<span class="rating_num".*?>(.*?)</span>.*?'
+    r'<span>(\d+人评价)</span>.*?'  
+    r'<span class="inq">(.*?)</span>?',
+    re.S
+)
+
+movies = pattern.findall(html)[:10]
+
+movie_list = []
+for m in movies:
+    rank = m[0]
+    title = m[1]
+    en_title = m[2].replace("/", "").strip()
+    rating = m[3]
+    people = m[4]       
+    quote = m[5] if len(m) > 5 else ""  
+    movie_list.append({
+        "rank": int(rank),
+        "title": title,
+        "en_title": en_title,
+        "rating": rating,
+        "people": people,  
+        "quote": quote      
+    })
+
+with open("movies.txt", "w", encoding="utf-8") as f:
+    for m in movie_list:
+        f.write(m["title"] + " | " + m["quote"] + "\n")  
+print("✅ 练习1完成：已保存中文名+评语到 movies.txt")
+
+with open("movies.csv", "w", encoding="utf-8-sig", newline="") as f:
+    writer = csv.writer(f)
+
+    writer.writerow(["排名", "中文名", "英文名", "评分", "评价人数", "经典评语"])
+    for m in movie_list:
+        writer.writerow([m["rank"], m["title"], m["en_title"], m["rating"], m["people"], m["quote"]])
+print("✅ 练习2完成：已保存到 movies.csv")
+
+with open("movies.json", "w", encoding="utf-8") as f:
+    json.dump(movie_list, f, ensure_ascii=False, indent=4)
+print("✅ 练习3完成：已保存到 movies.json")
+
+print("\n--- 练习4：筛选评分>9.5的电影 ---")
+with open("movies.csv", "r", encoding="utf-8-sig") as f:
+    reader = csv.DictReader(f)
+    for row in reader:
+        if float(row["评分"]) > 9.5:
+            print(row)
+
+print("\n--- 练习5：JSON统计 ---")
+with open("movies.json", "r", encoding="utf-8") as f:
+    data = json.load(f)
diff --git a/260402+2509165020/movies.csv b/260402+2509165020/movies.csv
new file mode 100644
index 0000000..dc55a4d
--- /dev/null
+++ b/260402+2509165020/movies.csv
@@ -0,0 +1 @@
+排名,中文名,英文名,评分,评价人数,经典评语
diff --git a/260402+2509165020/movies.json b/260402+2509165020/movies.json
new file mode 100644
index 0000000..0637a08
--- /dev/null
+++ b/260402+2509165020/movies.json
@@ -0,0 +1 @@
+[]
\ No newline at end of file
diff --git a/260402+2509165020/movies.txt b/260402+2509165020/movies.txt
new file mode 100644
index 0000000..e69de29