ncbi爬虫geneID注释

import urllib.request
import pandas as pd
import re

# 1.逐行读取xls文件列名并获取基因ID
def read_xlsx(path, sheetname,i):
    sheet = pd.read_excel(path, sheetname)
    geneID = []
    for row in sheet.index.values:
        geneID.append(sheet.iloc[row, i-1])
    return geneID

# 2.NCBI搜索基因ID，找到注释信息
def get_infoID(GeneID):
    infoID = []
    for i in GeneID:
        url = f'https://www.ncbi.nlm.nih.gov/gene/?term={i}'  # 查找基因的网址
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36"
        }
        request = urllib.request.Request(url, headers=headers)
        response = urllib.request.urlopen(request)
        content = response.read().decode('utf-8')
        p = re.findall('<dd>(.*?)<span class="prov">', content)[0]# (.*?)为正则表达式的目标区域
        infoID.append(p)
    retur