站长资源脚本专栏

#!/usr/bin/python
# -*- coding: iso-8859-1 -*-
# Hello, this program is written in Python - http://python.org
programname = 'html2csv - version 2002-09-20 - http://sebsauvage.net'
import sys, getopt, os.path, glob, HTMLParser, re
try:  import psyco ; psyco.jit() # If present, use psyco to accelerate the program
except: pass
def usage(progname):
  ''' Display program usage. '''
  progname = os.path.split(progname)[1]
  if os.path.splitext(progname)[1] in ['.py','.pyc']: progname = 'python '+progname
  return '''%s
A coarse HTML tables to CSV (Comma-Separated Values) converter.
Syntax  : %s source.html
Arguments : source.html is the HTML file you want to convert to CSV.
      By default, the file will be converted to csv with the same
      name and the csv extension (source.html -> source.csv)
      You can use * and "'
    self.inTD = 1
  def end_td(self):
    if self.inTD:
      self.CSVrow += '",' 
      self.inTD = 0
  def handle_data(self, data):
    if self.inTD:
      self.CSVrow += self.re_multiplespaces.sub(' ',data.replace('\t',' ').replace('\n','').replace('\r','').replace('"','""'))
  def getCSV(self,purge=False):
    ''' Get output CSV.
      If purge is true, getCSV() will return all remaining data,
      even if <td> or <tr> are not properly closed.
      (You would typically call getCSV with purge=True when you do not have
      any more HTML to feed and you suspect dirty HTML (unclosed tags). '''
    if purge and self.inTR: self.end_tr() # This will also end_td and append last CSV row to output CSV.
    dataout = self.CSV[:]
    self.CSV = ''
    return dataout
if __name__ == "__main__":
  try: # Put getopt in place for future usage.
    opts, args = getopt.getopt(sys.argv[1:],None)
  except getopt.GetoptError:
    print usage(sys.argv[0]) # print help information and exit:
    sys.exit(2)
  if len(args) == 0:
    print usage(sys.argv[0]) # print help information and exit:
    sys.exit(2)    
  print programname
  html_files = glob.glob(args[0])
  for htmlfilename in html_files:
    outputfilename = os.path.splitext(htmlfilename)[0]+'.csv'
    parser = html2csv()
    print 'Reading %s, writing %s...' % (htmlfilename, outputfilename)
    try:
      htmlfile = open(htmlfilename, 'rb')
      csvfile = open( outputfilename, 'w+b')
      data = htmlfile.read(8192)
      while data:
        parser.feed( data )
        csvfile.write( parser.getCSV() )
        sys.stdout.write('%d CSV rows written.\r' % parser.rowCount)
        data = htmlfile.read(8192)
      csvfile.write( parser.getCSV(True) )
      csvfile.close()
      htmlfile.close()
    except:
      print 'Error converting %s    ' % htmlfilename
      try:  htmlfile.close()
      except: pass
      try:  csvfile.close()
      except: pass
  print 'All done. '