挖掘DBLP作者合作关系，FP-Growth算法实践（2）：从DBLP数据集中

副标题#e#

上篇文章：http://www.voidcn.com/article/p-nsbrwwsu-zv.html?（挖掘DBLP作者合作关系，FP-Growth算法实践（1）：从DBLP数据集中提取目标信息（会议、作者等））

大家反映代码不能用，主要是太慢了，好吧，我也承认慢，在内存构造树，肯定的！

这次给出另外两种。

为了完整，先给出dom：

#do not use this code!
def DomParser():
    domTree=parse(fileName)
    dblp=domTree.documentElement
    inproceedingsList=dblp.getElementsByTagName("inproceedings")
    for inproceedings in inproceedingsList:
        
        year=inproceedings.getElementsByTagName("year")[0]
        yearStr=str(year.childNodes[0].data)
        if yearStr<fromYear:
            continue
        print "yearStr",yearStr,"=="*20
        
        booktitle=inproceedings.getElementsByTagName("booktitle")[0]
        booktitleStr=str(booktitle.childNodes[0].data)
        #for "<booktitle>ICML Unsupervised and Transfer Learning</booktitle>"
        booktitleStr=booktitleStr.split(" ")[0]
        if not confNameDict.has_key(booktitleStr):
            continue
        print "booktitleStr",booktitleStr,"^^"*20
        
        #allList=[] #"confName    \t    year    \t    title    \t    author1|author2|..|authorn"
        #authorDict={} #author: [frequence,yearStart,yearEnd]
        allContent=booktitleStr+"\t"+yearStr+"\t" #confName    \t    year    \t
        title=inproceedings.getElementsByTagName("title")[0]
        titleStr=str(title.childNodes[0].data)
        allContent+=titleStr+"\t" #title    \t
        authorList=inproceedings.getElementsByTagName("author")
        for i,author in enumerate(authorList):
            authorStr=str(author.childNodes[0].data)
            allContent+=authorStr+"|" #authori|
            if authorDict.has_key(authorStr):
                authorDict[authorStr][0]+=1
                if yearStr<authorDict[authorStr][1]:
                    authorDict[authorStr][1]=yearStr
                elif yearStr>authorDict[authorStr][2]:
                    authorDict[authorStr][2]=yearStr
            else:
                authorDict[authorStr]=[1,yearStr]
        allList.append(allContent)
    
    allContent="\n".join(allList)
    wf=open("allDB.txt","w")
    wf.write(allContent)
    wf.close()
    
    authorList=sorted(authorDict.items(),lambda x,y: cmp(x[1],y[1]),reverse=True)
    wf=open("authorDB.txt","w")
    allContent="\n".join([author+"\t"+str(frequence)+"\t"+yearStart+"\t"+yearEnd for author,(frequence,yearEnd) in authorList])
    wf.write(allContent)
    wf.close()

再给出sax：

class SAX_PARSER(xml.sax.ContentHandler):
    '''
    startDocument()方法
    文档启动的时候调用。
    endDocument()方法
    解析器到达文档结尾时调用。
    startElement(name,attrs)方法
    遇到XML开始标签时调用，name是标签的名字，attrs是标签的属性值字典。
    endElement(name)方法
    遇到XML结束标签时调用。
    
    characters(content)方法,调用时机：
    从行开始，遇到标签之前，存在字符，content的值为这些字符串。
    从一个标签，遇到下一个标签之前， 存在字符，content的值为这些字符串。
    从一个标签，遇到行结束符之前，存在字符，content的值为这些字符串。
    标签可以是开始标签，也可以是结束标签。
    '''
    
    def __init__(self):        
        self.authorList=""
        self.title=""
        self.year=""
        self.booktitle=""
        self.flag=0
        self.tag=""
        
    def startDocument(self):
         print "Document start","=="*20
         
    def endDocument(self):
         print "Document end","=="*20
    
    def startElement(self,tag,attributes):
        print "startElement","ss"*20,tag
        if tag=="inproceedings":
            self.flag=1
        elif self.flag==1: #tag!="inproceedings" and self.flag==1,we are now in a subtag of "inproceedings"
            self.tag=tag
        
    def endElement(self,tag):
        print "endElement","ee"*20,tag
        if self.flag==1 and tag=="inproceedings":
            if confNameDict.has_key(self.booktitle) and self.year>=fromYear:
                #allList=[] #"confName    \t    year    \t    title    \t    author1|author2|..|authorn"
                allContent=self.booktitle+"\t"+self.year+"\t"+self.title+"\t"+self.authorList[:-1]+"\n" #for the last "|"
                wf=open("allDB.txt","a")
                wf.write(allContent)
                wf.close()
            self.authorList=""
            self.title=""
            self.year=""
            self.booktitle=""
            self.flag=0
            self.tag=""
    
    def characters(self,content):
        print "characters","cc"*20,content
        if self.flag==1: #we are now in "inproceedings" tag
            print self.tag
            if self.tag=="author":
                self.authorList+=content+"|"
            elif self.tag=="title":
                self.title=content
            elif self.tag=="year":
                self.year=content
            elif self.tag=="booktitle":
                self.booktitle=content.split(" ")[0] #for "<booktitle>ICML Unsupervised and Transfer Learning</booktitle>"

最后给出string，把每行看成字符串来处理的方式：

#p#副标题#e##p#分页标题#e#

def XmlLineParser(fileName):
    rf=open(fileName,"r")
    for line in rf:
        #print "line [1]",line
        if line.startswith("<inproceedings"):
            print "line [1]",line
            booktitle=""
            year=""
            title=""
            authorList=""
            for line in rf:
                print "line [2]",line
                if line.startswith("<author"):
                    authorList+=line
                if line.startswith("<title"):
                    title=line
                elif line.startswith("<year"):
                    year=line[6:10]
                    if year<fromYear:
                        break
                elif line.startswith("<booktitle"):
                    booktitle=((line[11:]).split("</")[0]).split(" ")[0]
                    if not confNameDict.has_key(booktitle):
                        break
                elif line.startswith("</inproceedings"):
                    #tranList=[] #"confName    \t    year    \t    title    \t    author1|author2|..|authorn"
                    localTran=booktitle+"\t"+year+"\t"+(title[7:]).split("</")[0]+"\t"
                    for authorLine in authorList.split("\n"):
                        for author in re.findall(re.compile(r'<author>(.*)</author>',re.S),authorLine):
                            localTran+=author+"|"
                    wf=open("tranDB.txt","a")
                    wf.write(localTran[:-1]+"\n") #remove last "|"
                    wf.close()
                    break #do not forget
    rf.close()

调用直接：

XmlLineParser(fileName)

拿走不谢，代码写得有点水，见谅。