2007年6月25日星期一

批量下载后的文件名过滤

用FlashGet批量下载文件后面临一个文件名更改过滤的问题。我的解决方案是:
1.在批量下载时,同时下载该网页的HTML文件;
2.用Python来过滤出对应的HTML文件;
3.将过滤文件修补成Bat文件,运行后则可批量更改名称;
=====================================================================
Python过滤源代码
# -*- coding: cp936 -*-
# yankchina@gmail.com
# 2007-06-26 pass

from sgmllib import SGMLParser
class MyHtmlFilter(SGMLParser):
def reset(self):
SGMLParser.reset(self)
self.inValid = False
self.fileHrefs = []
self.fileNames = []

def start_a(self,attrs):
#idText = [ v for k, v in attrs if k == 'class' ]
fileHref = [ v for k, v in attrs if k == 'href' ]
#if idText == 'a01' :
self.inValid = True
self.fileHrefs.append( fileHref )
def end_a(self):
self.inValid = False


def handle_data(self, text ):
if self.inValid:
self.fileNames.append( text )


def FilteHtmlFile( inFileName,outFile ):
''' Filte Html File

'''
import os
if os.path.exists( inFileName ):
inFile = open( inFileName, "r")
parser = MyHtmlFilter()
parser.feed( inFile.read() )
inFile.close()
parser.close()
print len( parser.fileNames )
for i in range( len( parser.fileNames) ):
outFile.write( parser.fileHrefs[i][0] + " " + parser.fileNames[i]+ ".doc \n " )
print parser.fileNames[i]
print parser.fileHrefs[i]
print inFileName, len( parser.fileHrefs )

if __name__ == "__main__" :
outFileName = 'output.txt'
outFile = open( outFileName, "w" )
htmlFileName = "1.htm"
FilteHtmlFile(htmlFileName, outFile )
outFile.close()