diff --git a/33ljh.py b/33ljh.py new file mode 100644 index 0000000..95c405c --- /dev/null +++ b/33ljh.py @@ -0,0 +1,28 @@ +import requests +import re + +headers = { + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36' +} +url = 'https://movie.douban.com/top250' + +response = requests.get(url, headers=headers) +html = response.text + + +pattern = r'([^<&]+)' +titles = re.findall(pattern, html) + + +chinese_titles = [t for t in titles if not t.startswith('/')] + +top10 = chinese_titles[:10] + +with open('movies.txt', 'w', encoding='utf-8') as f: + for i, title in enumerate(top10, 1): + f.write(f'{i}. {title}\n') + +print('已保存前10部电影到 movies.txt') + +with open('movies.txt', 'r', encoding='utf-8') as f: + print(f.read()) \ No newline at end of file