Rosalind第16题——ros_bio16_MPRT

如果第一次阅读，请查看写在前面

import re
import requests

#通过compile设定N-糖基化模式
pattern = re.compile(r'N[^P][ST][^P]')

#读入蛋白名称
with open("../examples/ros_bio16_MPRT.txt") as f:
    id = f.read().rstrip()
id = id.split("\n")

#通过reques遍历访问各蛋白网站并读取蛋白序列
for i in id:
    url = 'http://www.uniprot.org/uniprot/' + i + '.fasta'
    r = requests.get(url)
    all = r.text.split("\n")
    protein = ''
    for line in all:
        lable = re.match(r'^>.*', line)
        if lable:
            continue
        else:
            protein += line
    #通过finditer方法获取匹配位置索引
    m = pattern.finditer(protein)
    index = ''
    for match in m:
        index = index + str(match.start() + 1) + ' '
    if index == '':
        continue
    else:
        print(i)
        print(index)