python : 书签转换为 HTML-CSDN博客

bm2htm.py mybatis.txt


# -*- coding: cp936 -*-
# 先将 bookmark 转码: unicode -> gbk
import os, sys
import re

if len(sys.argv) ==2:
    f1 = sys.argv[1]
else:
    print 'usage: bm2htm.py file1.txt '
    sys.exit(4)

if not os.path.exists(f1):
    print 'ERROR: %s not found\n' % f1
    sys.exit(4)

fn,ext = os.path.splitext(f1)
if ext !='.txt':
    print 'ERROR: %s ext is not .txt\n' % f1
    sys.exit(4)

fp = open(f1,'r')
f2 = fn +'.htm'
fp2 = open(f2,'w')
fp2.write('<html>\n')
fp2.write('  <head>\n')
fp2.write('   <base target="top"/>\n')
fp2.write('    <meta http-equiv="Content-Type" content="text/html; charset=GBK">\n')
fp2.write('    <title>深入浅出 MyBatis技术原理与实战 </title>\n')
fp2.write('  </head>\n')
fp2.write('<body>\n')
# set 参数
path ='mybatis'
pre ='m'  # prefix
pat = re.compile("^[1-9A-Z]")
end = 272 # page max value

for line in fp:
    t = line.strip().replace('　',' ').split()  # A1A1
    if line.strip() =='':
        fp2.write('\n')
        continue
    if re.match(pat,line):        
        if len(t)>=3:
            d = int(t[-1])
            aline = '  <li>%s  %s  <a href="get.php?dir=%s&pre=%s&end=%d&i=%d">%s</a></li>\n' % (t[0],t[1],path,pre,end,d,t[-1])
        else:
            aline = '  <li>%s  %s </li>\n' % (t[0],t[1])            
        fp2.write(aline)
    elif len(t)==2:
        d = int(t[-1])
        aline = '  <li>%s <a href="get.php?dir=%s&pre=%s&end=%d&i=%d">%s</a></li>\n' % (t[0],path,pre,end,d,t[1])
        fp2.write(aline)
    elif len(t)>=3:
        d = int(t[-1])
        aline = '</ul>\n<ul>%s  %s  <a href="get.php?dir=%s&pre=%s&end=%d&i=%d">%s</a>\n' % (t[0],t[1],path,pre,end,d,t[-1])
        fp2.write(aline)    
    else:
        aline = '</ul>\n<ul>'+line
        fp2.write(aline)
#
fp.close()
fp2.write('</ul>\n')
fp2.write('</body>\n')
fp2.write('</html>\n')
fp2.close()