利用python的xml包，對kegg的xml數(shù)據(jù)進(jìn)行提取谨胞。根據(jù)這些數(shù)據(jù)固歪，可以實現(xiàn)代謝路徑的數(shù)據(jù)整合、重構(gòu)或解析胯努。

# -*- coding: utf-8 -*-
"""
Created on Fri Jan 18 09:05:39 2019

@author: Menglei-Xia
@email:mlxia@tust.edu.cn
@Please Feel free to contact
"""

import xml.etree.ElementTree as ET
import os
import openpyxl

from tkinter import Tk
import tkinter.filedialog as tf

Tk().withdraw()
b=tf.askopenfilename()


tree = ET.ElementTree(file=b)
root=tree.getroot()


wb = openpyxl.Workbook()


sheet1=wb.create_sheet('化合物信息');
row_xia=1
for elem in tree.iter(tag='entry'):
    key_xia=list(elem.attrib.keys())
    value_xia=list(elem.attrib.values())
    if 'compound' in value_xia:
        row_xia=row_xia+1
        colum_xia=0
        key_xia2=list(elem[0].attrib.keys())
        value_xia2=list(elem[0].attrib.values())       
        for ii in key_xia2:
            colum_xia=colum_xia+1
            sheet1.cell(row=row_xia,column=colum_xia).value=value_xia2[colum_xia-1]
sheet1.cell(row=1,column=1).value='Name'
sheet1.cell(row=1,column=2).value='x'
sheet1.cell(row=1,column=3).value='height'
sheet1.cell(row=1,column=4).value='y'
sheet1.cell(row=1,column=5).value='width'
sheet1.cell(row=1,column=6).value='fgcolor'
sheet1.cell(row=1,column=7).value='type'
sheet1.cell(row=1,column=8).value='bgcolor'


sheet2=wb.create_sheet('gene');
row_xia=1
for elem in tree.iter(tag='entry'):
    key_xia=list(elem.attrib.keys())
    value_xia=list(elem.attrib.values())
    if 'gene' in value_xia:
        row_xia=row_xia+1
        colum_xia=0
        key_xia2=list(elem[0].attrib.keys())
        value_xia2=list(elem[0].attrib.values())       
        for ii in key_xia2:
            colum_xia=colum_xia+1
            sheet2.cell(row=row_xia,column=colum_xia).value=value_xia2[colum_xia-1]
sheet2.cell(row=1,column=1).value='fgcolor'
sheet2.cell(row=1,column=2).value='name'
sheet2.cell(row=1,column=3).value='type'
sheet2.cell(row=1,column=4).value='bgcolor'
sheet2.cell(row=1,column=5).value='coords'





         
sheet3=wb.create_sheet('ortholog');
row_xia=1
for elem in tree.iter(tag='entry'):
    key_xia=list(elem.attrib.keys())
    value_xia=list(elem.attrib.values())
    if 'ortholog' in value_xia:
        row_xia=row_xia+1
        colum_xia=0
        key_xia2=list(elem[0].attrib.keys())
        value_xia2=list(elem[0].attrib.values())       
        for ii in key_xia2:
            colum_xia=colum_xia+1
            sheet3.cell(row=row_xia,column=colum_xia).value=value_xia2[colum_xia-1]
sheet3.cell(row=1,column=1).value='fgcolor'
sheet3.cell(row=1,column=2).value='name'
sheet3.cell(row=1,column=3).value='type'
sheet3.cell(row=1,column=4).value='bgcolor'
sheet3.cell(row=1,column=5).value='coords'


sheet4=wb.create_sheet('reaction');
row_xia=1
for elem in tree.iter(tag='reaction'): 
    row_xia=row_xia+1
    sheet4.cell(row=row_xia,column=5).value=elem.attrib['type']
    sheet4.cell(row=row_xia,column=1).value=elem[0].attrib['id']
    sheet4.cell(row=row_xia,column=2).value=elem[0].attrib['name']
    sheet4.cell(row=row_xia,column=3).value=elem[1].attrib['id']
    sheet4.cell(row=row_xia,column=4).value=elem[1].attrib['name']    

sheet4.cell(row=1,column=5).value='type'
sheet4.cell(row=1,column=1).value='Source_id'
sheet4.cell(row=1,column=2).value='Source_name'
sheet4.cell(row=1,column=3).value='Target_id'
sheet4.cell(row=1,column=4).value='Target_name'  
          
wb.save('data3.xlsx')

在這里沒有對ElementTree的用法進(jìn)行系統(tǒng)的解析牢裳。具體用法可以參考以下博文：
Reference
【1】深入解讀Python解析XML的幾種方式 及 ElementTree模塊的使用