python爬取InBase网站中的intein序列

一、爬取

(ML) mrc@mrc-Precision-3660:request$ cat request_intein.py
import requests
from bs4 import BeautifulSoup

# 基础URL
base_url = "https://inbase.ligsciss.com/iwai/InBase/tools.neb.com/inbase/"

# 目标页面
url = base_url + "list_prop.html"

# 获取网页内容
response = requests.get(url)
response.encoding = 'utf-8'  # 设置编码
soup = BeautifulSoup(response.text, 'html.parser')

# 获取所有Intein链接
intein_links = soup.find_all('a')

# 存储Intein名称和对应的序列
intein_sequences = {}

for link in intein_links:
    # 检查<a>标签是否有href属性
    if 'href' in link.attrs:
        intein_name = link.text.strip()
        intein_url = base_url + link['href']
        
        # 获取Intein详细信息页面内容
        intein_response = requests.get(intein_url)
        i