<分区>
我正在编写我的 xml 文件的 csv，其中包含 Date 、 ID 、 title 、 Abstract 当我运行我的代码时，它正在将所有行写在一列中作为列表它不单独写列它写的像 - ["123, 2018,abs,ABC"] ["123,2018,abs,ABC"] 一栏不分开
代码:
import os
import lxml.etree as ET
from itertools import izip_longest as zip_longest
import csv
path = '/home/shayez/Desktop/project/kk'
listfile = []
files = os.listdir(path)
for name in files:
listfile.append(name)
pmdata = []
for name2 in listfile:
full_file = os.path.abspath(os.path.join('project/kk',name2))
dom = ET.parse(full_file)
pmdat = dom.findall('PubmedArticle')
pmdata.append(pmdat)
def Print_Data ():
with open ('/home/shayez/Desktop/karim.csv','wt') as csvfile:
writer = csv.writer(csvfile, delimiter = "\t")
header = ['PMID','Date','Title','Abstract']
writer.writerow(header)
rows = []
row = zip_longest(*rows, fillvalue = '')
for d in pmdata:
for c in d :
PMID = c.find('MedlineCitation/PMID').text
title = c.find('MedlineCitation/Article/ArticleTitle').text
Date = c.find('MedlineCitation/Article/Journal/JournalIssue/PubDate/Year')
Date2 = c.find('MedlineCitation/Article/Journal/JournalIssue/PubDate/MedlineDate')
Abstract = c.find('MedlineCitation/Article/Abstract/AbstractText')
if Abstract is None :
pass
elif Date is None:
print PMID,"\t",Date2.text, "\t",title ,"\t",Abstract.text
rows.append([PMID,Date2.text,title,Abstract.text])
else :
print PMID,"\t",Date.text, "\t",title ,"\t",Abstract.text
rows.append([PMID,Date.text,title,Abstract.text])
writer.writerow(rows)
Print_Data()