今天是简略的一篇,简单小实验
import requests
from bs4 import BeautifulSoup
# 模拟浏览器的构成(请求头)
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36 Edg/123.0.0.0"
}
for start_num in range(0,250,25):
# 获取豆瓣top榜上前250部电影的响应内容
response = requests.get(f"https://movie.douban.com/top250?start={start_num}", headers=headers)
html = response.text
# 传入方法,指定解析器为html.parser"
soup = BeautifulSoup(html, "html.parser")
all_titles=soup.findAll("span",attrs={"class":"title"})
for title in all_titles:
title_string=title.string
if "/" not in title_string:
print(title_string)
读取: