Python文件操作完全指南

260331+2509165020 作业/movies.csv

@@ -0,0 +1 @@
+排名,中文名,英文名,评分

260331+2509165020 作业/movies.json

@@ -0,0 +1 @@
+[]

260331+2509165020 作业/movies.txt

@@ -0,0 +1,10 @@
+肖申克的救赎
+霸王别姬
+泰坦尼克号
+阿甘正传
+千与千寻
+美丽人生
+星际穿越
+这个杀手不太冷
+盗梦空间
+楚门的世界

260331+2509165020 作业/test1.py

@@ -0,0 +1,31 @@
+import requests
+import re
+
+headers = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36"
+}
+
+url = "https://movie.douban.com/top250"
+
+try:
+    response = requests.get(url=url, headers=headers, timeout=10)
+    response.raise_for_status()  
+    page_source = response.text
+    print("页面请求成功！")
+except Exception as e:
+    print(f"请求失败：{e}")
+    exit()
+
+pattern = re.compile(r'<span class="title">([^&]+?)</span>', re.S)
+movie_names = pattern.findall(page_source)
+
+target_names = movie_names[:10]
+with open("movies.txt", "w", encoding="utf-8") as f:
+    for name in target_names:
+        f.write(name + "\n")
+
+print(f"成功爬取{len(target_names)}部电影名，已保存到movies.txt！")
+
+print("\n爬取结果预览：")
+for i, name in enumerate(target_names, 1):
+    print(f"{i}. {name}")

260331+2509165020 作业/test2.py

@@ -0,0 +1,27 @@
+import requests
+import re
+import csv
+
+url = "https://movie.douban.com/top250"
+headers = {"User-Agent": "Mozilla/5.0"}
+resp = requests.get(url, headers=headers)
+html = resp.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>',
+    re.S
+)
+movies = pattern.findall(html)[:10]
+
+with open("movies.csv", "w", encoding="utf-8-sig", newline="") as f:
+    w = csv.writer(f)
+    w.writerow(["排名", "中文名", "英文名", "评分"])
+    for m in movies:
+        rank, title, en, rating = m
+        en = en.replace("/", "").strip()
+        w.writerow([rank, title, en, rating])
+
+print("已保存到 movies.csv")

260331+2509165020 作业/test3.py

@@ -0,0 +1,33 @@
+import requests
+import re
+import json
+
+url = "https://movie.douban.com/top250"
+headers = {"User-Agent": "Mozilla/5.0"}
+resp = requests.get(url, headers=headers)
+html = resp.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 class="inq">(.*?)</span>?',
+    re.S
+)
+movies = pattern.findall(html)[:10]
+
+result = []
+for m in movies:
+    result.append({
+        "rank": int(m[0]),
+        "title": m[1],
+        "en_title": m[2].replace("/", "").strip(),
+        "rating": m[3],
+        "quote": m[4] if len(m) > 4 else ""
+    })
+
+with open("movies.json", "w", encoding="utf-8") as f:
+    json.dump(result, f, ensure_ascii=False, indent=4)
+
+print("已保存到 movies.json")