根据年份提取dblp内容

#!/usr/bin/python
# use xml.sax, because it support external entity expansion
# this program will extract all article elements in dblp.xml into inProceedings.xml
import xml.sax
import codecs
from xml.sax.saxutils import escape


# a handler class  for xml.sax.parse(source,handler)
class dblpHandler(xml.sax.handler.ContentHandler):
    def __init__(self):
        # xml.sax.ContentHandler.__init__(self)
        self.isArticle = 0
        self.outfile = codecs.open('data/article.xml', 'w', 'utf-8')
        self.outfile.write('n')
        self.outfile.write('n')
        self.outfile.write('nn')

    # starting tag of an element
    def startElement(self, name, attrs):
        if name == 'article':
            self.isArticle = 1
            self.outfile.write('n')
        elif self.isArticle == 1:
            self.outfile.write('<' + name + '>')

    # ending tag of an element
    def endElement(self, name):
        if name == 'article':
            self.outfile.write('

和老师进行讨论之后，只需要提取article和inproceedings类型文章。将上述提取article类型的代码改成提取inproceeding

代码如下：

#!/usr/bin/python
#use xml.sax, because it support external entity expansion
#this program will extract all article elements in dblp.xml into inProceedings.xml
import xml.sax
import codecs
from xml.sax.saxutils import escape
from multiprocessing import Pool


# a handler class  for xml.sax.parse(source,handler)
class dblpHandler(xml.sax.handler.ContentHandler):
    def __init__(self,year):
        #xml.sax.ContentHandler.__init__(self)
        self.isArticle = 0
        self.buffer = '' 
        self.isYear = 0
        self.year = year
        self.currentYear = 0   # year for current parsing article paper
        #self.outfile = codecs.open('data/inProceedings.xml','w','utf-8')
        self.outfile = codecs.open('data/'+str(year)+'article.xml','w','utf-8')
        self.outfile.write('n')
        self.outfile.write('n')
        self.outfile.write('nn')


    #starting tag of an element
    def startElement(self, name, attrs):
        if name == 'article':
            self.isArticle = 1
            #self.outfile.write('n')
            self.buffer += 'n'
        elif self.isArticle == 1:    # name != inproceedings and isInProceedings == 1
            #self.outfile.write('<'+name+'>')
            self.buffer += '<'+name+'>'
            if name == 'year':
                self.isYear = 1


    #ending tag of an element
    def endElement(self,name):
        if name == 'article':
            #self.outfile.write('nn')
            self.buffer += 'nn'
            if self.currentYear == self.year:
                self.outfile.write(self.buffer)
            self.buffer = ''
            self.isArticle = 0
        elif self.isArticle == 1:
            #self.outfile.write('n')
            self.buffer += 'n'
            if name == 'year':
                self.isYear = 0


    #write content in  and 
    def characters(self,content):
        if self.isArticle == 1:
            if not content.isspace():
                #self.outfile.write(escape(content))
                self.buffer += escape(content)
        if self.isYear == 1:
            self.currentYear = int(content)


    #write the ending file tag for inProceeding.xml and close the written file
    def close_file(self):
        self.outfile.write('')
        self.outfile.close()


if __name__ == '__main__':
    for year in reversed(range(1970,2009)):
        dblp = dblpHandler(year)
        source = open('./data/article.xml','r',encoding='utf-8')
        xml.sax.parse(source, dblp)
        dblp.close_file()
        print("compelete!")

最后，会得到article1970--article2008和inproceedings1970--inproceedings2008的xml文件。

本次代码是根据GitHub上相关代码改编的，可能不是很有效，但是最后还是得到清洗后的数据，下次要进行作者提取。