24 lines
719 B
Python
24 lines
719 B
Python
import requests
|
|
import re
|
|
import csv
|
|
import json
|
|
|
|
header={
|
|
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36'
|
|
}
|
|
|
|
url='https://www.douban.com/doulist/3936288/'
|
|
print('开始爬取豆瓣电影Top250...')
|
|
response = requests.get(url,headers=header)
|
|
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)
|
|
print('电影名：',titles)
|
|
|
|
|
|
score_pattern=r'<span class="rating_nums">([^<]+)</span>'
|
|
scores=re.findall(score_pattern,html)
|
|
print('评分：',scores)
|