Pythoneksempler

transformasjon av filformater

[ HTML fra en enkel tekstfil ][ Transformasjon: CSV-XML ][ Transformasjon: CSV-HTML ][ Transformasjon: XML-HTML ]

Hva:

Demonstrasjon av noen momenter ved utvikling i Python

HTML fra en enkel tekstfil

Programmet leser inne en enkel tekstfil og plasserer innholdet i en pre-tag på en minimalistisk HTML-side. HTML-siden ligger som en tekst i programmet.

Input fil: http://www.ia.hiof.no/~borres/ml/python/frej1_txt.html
Output fil: http://www.ia.hiof.no/~borres/ml/python/frej1.html
Python koden:

"""
This is a modul that reads a textfil
wraps it in a HTML-skeleton and produce
a nice HTM-page
"""

#------------------------
# HTML-fragments
HTML_PAGE="""<html>
<head>
    <title>a page</title>
</head>
<body>
<h1> Farbror Frej:</h1>
<pre>
%s
</pre>
</body>
</html>
"""

#-----------------------
# filenames
infile='c:\\tull\\frej1.txt'
outfile='c:\\tull\\frej1.html'


#------------------------
# Read / write text files

def getTextFile(filename):
    try:
        file=open(filename,'r')
        res=file.read()
        file.close()
        return res
    except:
        print 'Trouble reading: '+filename
        return None

def storeTextFile(filename,txt):
    try:
        file=open(filename,'w')
        file.write(txt)
        file.close()
    except:
        print 'Trouble writing to: '+filename

#------------------------
# do the job

def doit():
    txt=getTextFile(infile)
    if txt!=None:
        txt=HTML_PAGE%txt
        #print txt
        storeTextFile(outfile,txt)

#doit()

Transformasjon: CSV-XML

Modulen boktoxml gjør noen av de grunnleggende operasjonene som inngår i å lage en XML-fil fra en kommaseparert fil:

åpner og leser en fil på en sivilisert måte
splitter innholdet opp i linjer, og forkaster meningsløse linjer
splitter hver linje i kommeseparete deler
bruker delene til å produsere XML-elementer
skriver alt tilbake til fil på en sivilisert måte

Input fil: http://www.ia.hiof.no/~borres/ml/python/bokliste_txt.html
Output fil:http://www.ia.hiof.no/~borres/ml/python/bokliste.xml
Pythonkoden:

# transform a commaseparated (CSV) file to XML
# Raw data as lines:
# title,author,publisher,year,isbn,pages,course,category,comment

#----------------------------
# XML-skeletons
# a template for a xml-fragment
XMLFragment="""
<book isbn="%s" pages="%s">
      <title>%s</title>
      <course>%s</course>
      <category>%s</category>
      <author>%s</author>
      <publisher>%s</publisher>
      <year>%s</year>
      <comment>%s</comment>
</book>
"""

# a template for a complete xml-file
XMLFile="""<?xml version="1.0" encoding="ISO-8859-1"?>
<booklist>
%s
</booklist>
"""
#-------------------------------------
# read / write text files
def getTextFile(filename):
    try:
        file=open(filename,'r')
        intext=file.read()
        file.close()
        return intext
    except:
        print 'Error reading file ',filename
        return ''

def storeTextFile(filename,txt):
    try:
        outfile=open(filename,'w')
        outfile.write(txt)
        outfile.close()
    except:
        print 'Error writing file ',filename
        
#--------------------------------
# produce and save XML
def makeXML(filename='c:\\articles\\ml\\python\\bokliste.txt'):
    # les en text fil
    text=getTextFile(filename)
    if(text==''):
        return
    content=''
    # plukk ut linjene
    lines=text.split('\n')
    for line in lines:
        line.strip()
        # drop tomme linjer og kommentarlinjer
        if(len(line)<2):
            continue
        if(line[0:2]=='//'):
            continue
        # har en boklinje, finn delene
        pcs=line.split(',')
        if(len(pcs)!=9):
            print 'ignore:' , line
            continue
        content+=XMLFragment%(pcs[4],pcs[5],pcs[0],pcs[6],
                              pcs[7],pcs[1],pcs[2],pcs[3],pcs[8])
    
    storeTextFile(filename.replace('.txt','.xml'),XMLFile%content)

Transformasjon: CSV-HTML

Modulen boktohtml tar den samme tekst-fila som i eksempelet ovenfor og transformerer den til en htmlfil som viser en liste av bøker med forfatter

Input fil: http://www.ia.hiof.no/~borres/ml/python/bokliste_txt.html
Output fil: http://www.ia.hiof.no/~borres/ml/python/bokliste.html
Python koden:

# transform a commaseparated (CSV) file to HTML
# Raw data as lines:
# title,author,publisher,year,isbn,pages,course,category,comment

#----------------------------
# XML-skeletons
# a template for a complete html-file
HTMLFile=
"""<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
    <meta HTTP-EQUIV="Content-Type" 
          content="text/html; 
          charset=iso-8859-1">
    <title>books</title>
    <style>
     li{margin-top:10;}
     .fat{font-weight:bold; color:red}
    </style>
</head>
<body>
<h1>Bokliste</h1>
<ul>
%s
</ul>
</body>
</html>
"""

# a template for a xml-fragment
HTMLFragment="""
    <li>
        <div class="fat">%s</div>
        <div>%s</div>
    </li>
"""

#-------------------------------------
# read / write text files

def getTextFile(filename):
    try:
        file=open(filename,'r')
        intext=file.read()
        file.close()
        return intext
    except:
        print 'Error reading file ',filename
        return ''

def storeTextFile(filename,txt):
    try:
        outfile=open(filename,'w')
        outfile.write(txt)
        outfile.close()
    except:
        print 'Error writing file ',filename
        

#--------------------------------
# produce and save HTML
def makeHTML(filename='c:\\articles\\ml\\python\\bokliste.txt'):
    # les en text fil
    text=getTextFile(filename)
    if(text==''):
        return
    content=''
    # plukk ut linjene
    lines=text.split('\n')
    for line in lines:
        line.strip()
        # dropper tomme linjer
        if(len(line)<2):
            continue
        # dropper kommentarlinjer
        if(line[0:2]=='//'):
            continue
        # har en boklinje, finn delene
        pcs=line.split(',')
        if(len(pcs)!=9):
            print 'ignore:' , line
            continue
        content+=HTMLFragment%(pcs[0].strip(),pcs[1].strip())
    
    storeTextFile(filename.replace('.txt','.html'),
                  HTMLFile%content)

Transformasjon: XML-HTML

Modulen bokxmltohml tar xml-fila og transformerer den til html.

Input fil: http://www.ia.hiof.no/~borres/ml/python/bokliste.xml
Output fil: http://www.ia.hiof.no/~borres/ml/python/boklistefromxml.html
Pythonkode:

import xml.dom.minidom
#----------------------
# Produce a HTML-file from a XML-file
# http://www.ia.hiof.no/~borres/ml/python/p-python.html
# Input:
#<booklist>
#<book isbn="txt" pages="txt">
#<title>txt</title>
#<course>txt</course>
#<category>txt</category>
#<author>txt</author>
#<publisher>txt</publisher>
#<year>txt</year>
#<comment>txt</comment>
#</book>
#...
#</booklist>
#
# produce a html-file with same name, different ext
# Use: produceHTML(filename)
#--------------------------------------------------------------

#--------------------------------------
# skeleton for HTML-file
HTMLFile=
"""<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
    <html>
    <head>
    <META http-equiv="Content-Type" content="text/html; 
          charset=iso-8859-1\">
    <title>bokliste</title>
    <!-- produced by python -->
    </head>
    <body>
    <h2>Litteraturliste</h2>
    %s
    </body>
    </html>
    """

#-------------------------------------
# read / write text files
def getTextFile(filename):
    try:
        file=open(filename,'r')
        intext=file.read()
        file.close()
        return intext
    except:
        print 'Error reading file ',filename
        return ''

def storeTextFile(filename,txt):
    try:
        outfile=open(filename,'w')
        outfile.write(txt)
        outfile.close()
    except:
        print 'Error writing file ',filename

#------------------------------------
# collect all text in a node
def getText(nodelist):
    rc = ''
    for node in nodelist:
        if node.nodeType == node.TEXT_NODE:
            t=node.data.encode('ISO-8859-1')
            rc += t
    return rc

def getStrippedText(nodelist):
    rc = ''
    for node in nodelist:
        if node.nodeType == node.TEXT_NODE:
            t=node.data
            t=t.strip()
            t=node.data.encode('ISO-8859-1')
            if t!='\n':
                rc += t.strip()
    return rc

#----------------------------------------
# Produce a fragment for one book
def makeBook(q):
    
    result=q.getElementsByTagName('title')[0]
    T='<h3>%s</h3>\n'%getText(result.childNodes)

    T+='<div>isbn:%s</div>\n'%q.getAttribute('isbn').encode('ISO-8859-1')

    result=q.getElementsByTagName('course')[0]
    T+='<div>%s</div>\n'%getText(result.childNodes)

    result=q.getElementsByTagName('category')[0]
    T+='<div>%s</div>\n'%getText(result.childNodes)

    result=q.getElementsByTagName('author')[0]
    T+='<div>%s</div>\n'%getText(result.childNodes)
    
    result=q.getElementsByTagName('publisher')[0]
    T+='<div>%s</div>\n'%getText(result.childNodes)

    result=q.getElementsByTagName('year')[0]
    T+='<div>%s</div>\n'%getText(result.childNodes)

    result=q.getElementsByTagName('comment')[0]
    T+='<div>%s</div>\n'%getText(result.childNodes)

    return T

#----------------------------------
# Produce the entire file and save it
def produceHTML(infile='c:\\articles\\ml\\python\\bokliste.xml'):
    # load xml-file
    document=getTextFile(infile)
    if document=='':
        return

    # and establish DOM-tree
    dom = xml.dom.minidom.parseString(document)
    
    # get a list of all books
    bliste=dom.getElementsByTagName('book')
    
    # doing the books
    T=''
    for b in bliste:
        T+=makeBook(b)

    # write the file
    storeTextFile(infile.replace('.xml','fromxml.html'),HTMLFile%T)
    
    # clean up
    dom.unlink()

Du kan sammenligne denne Pythonkoden med en XSLT-fil som gjør samme jobben:

<?xml version="1.0" encoding="ISO-8859-1"?>
<xsl:stylesheet version="1.0" 
                xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
    <xsl:output method="xml" 
     omit-xml-declaration="no"
     indent="yes" 
     doctype-public="-//W3C//DTD XHTML 1.0 Strict//EN" 
     doctype-system="http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd" 
     encoding="ISO-8859-1"/>

<xsl:template match="/">
    <html>
    <head>
    <title>bokliste</title>
    </head>
    
    <body>
    <h1>Litteratur</h1>
    <xsl:apply-templates select="booklist/book"/>
    </body>
    </html>
</xsl:template>

<xsl:template match="book">
   <h3><xsl:value-of select="title"/></h3>
   <div><xsl:value-of select="author"/></div>
   <div><xsl:value-of select="publisher"/>, 
   <xsl:value-of select="year"/></div>
   <div>Isbn: <xsl:value-of select="@isbn"/></div>
   <div class="kommentar"><xsl:value-of select="comment"/></div>
</xsl:template>

</xsl:stylesheet>

Referanser og eksempler:

Alle aktuelle filer fra eksemplene er sitert i teksten

Produksjon, kontroll og vedlikehold:

B.Stenseth, siste gang august 2006

Markup og web fra Høgskolen i Østfold: http://www.ia.hiof.no/~borres/ml/