30 lines
1.0 KiB
Python
30 lines
1.0 KiB
Python
import requests
|
||
import re
|
||
|
||
url = 'https://www.douban.com/doulist/3936288/'
|
||
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
|
||
response = requests.get(url, headers=headers)
|
||
response.encoding = 'utf-8'
|
||
html = response.text
|
||
|
||
# 1. 提取电影名
|
||
title_pattern = r'<span class="title">([^<]+)</span>'
|
||
titles = re.findall(title_pattern, html)
|
||
chinese_titles = [t for t in titles if not t.startswith('/')]
|
||
|
||
# 2. 提取评分
|
||
rating_pattern = r'<span class="rating_nums">([^<]+)</span>'
|
||
ratings = re.findall(rating_pattern, html)
|
||
|
||
# 3. 提取经典台词
|
||
quote_pattern = r'<span class="inq">([^<]+)</span>'
|
||
quotes = re.findall(quote_pattern, html)
|
||
|
||
# 合并打印（前10部）
|
||
print(f'{"排名":<4} {"电影名":<20} {"评分":<6} {"引言"}')
|
||
print('-' * 70)
|
||
for i in range(min(10, len(chinese_titles))):
|
||
title = chinese_titles[i]
|
||
rating = ratings[i] if i < len(ratings) else '无'
|
||
quote = f'"{quotes[i]}"' if i < len(quotes) else '无'
|
||
print(f'{i+1:<4} {title:<20} {rating:<6} {quote}') |