def createCSV(phdThesis): columns=['id','author','mDate','month','title','year'] with open ("phdThesis.csv", 'a') as csvfile: header = columns writeFiles = csv.Dict(csvfile, delimiter=',', lineterminator='\n',fieldnames=header) for i in phdThesis: context = etree.iterparse(i, load_dtd=True,html=True) result=parseData(context) result1=arrangeFormat(result) df=pd.DataFrame(data=np.asarray(result1).reshape(1,len(columns))) with open('phdThesis.csv', 'a') as f: df.to_csv(f, header=False,index=False)
def createCSV(inproceeding): columns=['id','author','bookTitle','cite','Mdate','publisher','title','year','url'] with open ("inproceeding.csv", 'a') as csvfile: header = columns writeFiles = csv.Dict(csvfile, delimiter=',', lineterminator='\n',fieldnames=header) for i in inproceeding: context = etree.iterparse(i, load_dtd=True,html=True) result=parseData(context) result1=arrangeFormat(result) df=pd.DataFrame(data=np.asarray(result1).reshape(1,len(columns))) with open('inproceeding.csv', 'a') as f: df.to_csv(f, header=False,index=False)