40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
import requests
|
||
from bs4 import BeautifulSoup
|
||
import re
|
||
import csv
|
||
import json
|
||
import time
|
||
|
||
# 设置请求头，模拟浏览器访问
|
||
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
|
||
|
||
url = 'https://movie.douban.com/top250'
|
||
|
||
print('开始爬取豆瓣电影Top250...')
|
||
response = requests.get(url, headers=headers)
|
||
print(f'状态码: {response.status_code}')
|
||
print(f'内容长度: {len(response.text)} 字符')
|
||
|
||
# 找到所有电影标题
|
||
html = response.text
|
||
|
||
# 匹配 <span class="title">电影名</span>
|
||
title_pattern = r'<span class="title">([^<]+)</span>'
|
||
titles = re.findall(title_pattern, html)
|
||
|
||
# 过滤掉英文名（以/开头）
|
||
chinese_titles = [t for t in titles if not t.startswith('/')]
|
||
|
||
print('电影名称（前10部）：')
|
||
for i, title in enumerate(chinese_titles[:10], 1):
|
||
print(f'{i}. {title}')
|
||
|
||
|
||
abstract_pattern = r'<span class="abstract">([^<]+)</span>'
|
||
abstract = re.findall(abstract_pattern, html)
|
||
|
||
chinese_abstract = [t for t in abstract if not t.startswith('/')]
|
||
|
||
print('电影的导演（前10部）：')
|
||
for i, abstract in enumerate(chinese_abstract[:10], 1):
|
||
print(f'{i}. {abstract}') |