39 lines
1.3 KiB
Python
39 lines
1.3 KiB
Python
import requests
|
||
from bs4 import BeautifulSoup
|
||
|
||
headers = {
|
||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
||
'Referer': 'https://movie.douban.com/'
|
||
}
|
||
|
||
all_movies = [] # 存放全部250部电影
|
||
|
||
# TOP250 共 10 页，每页 25 条
|
||
for page in range(10):
|
||
start = page * 25
|
||
url = f'https://movie.douban.com/top250?start={start}&filter='
|
||
|
||
try:
|
||
response = requests.get(url, headers=headers, timeout=15)
|
||
response.encoding = 'utf-8'
|
||
print(f'正在爬取第 {page+1}/10 页...')
|
||
|
||
soup = BeautifulSoup(response.text, 'html.parser')
|
||
items = soup.find_all('div', class_='item') # 每部电影的父容器
|
||
|
||
for item in items:
|
||
# 提取电影名
|
||
title_tag = item.find('span', class_='title')
|
||
if title_tag:
|
||
title = title_tag.get_text(strip=True)
|
||
if title not in all_movies: # 去重
|
||
all_movies.append(title)
|
||
|
||
except Exception as e:
|
||
print(f'第 {page+1} 页爬取异常：', e)
|
||
|
||
# 输出结果
|
||
print(f'\n✅ 成功爬取 {len(all_movies)} 部电影（TOP250 完整数据）')
|
||
print('='*30)
|
||
for idx, movie in enumerate(all_movies, 1):
|
||
print(f'{idx}. {movie}') |