17 lines
542 B
Python
17 lines
542 B
Python
import requests
|
|
import re
|
|
import csv
|
|
import json
|
|
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
|
|
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')
|
|
html = response.text
|
|
title_pattern = r'<span class="title">([^<]+)</span>'
|
|
titles = re.findall(title_pattern, html) |