前段时间写了个简单的
TXT2HTML小说转换器HTA版,现在拿python再实现一遍,自动按章节分割成多个HTML文件,并建立目录,方便阅读。
效果图:
脚本代码:
# encoding: gbk
#
# 将txt小说分割转换成多个HTML文件
#
# @author : GreatGhoul
# @email : [email protected]
# @blog : http://greatghoul.iteye.com
import re
import os
# regex for the section title
# sec_re = re.compile(r'第.+卷\s+.+\s+第.+章\s+.+')
# txt book's path.
source_path = 'f:\\佣兵天下.txt'
path_pieces = os.path.split(source_path)
novel_title = re.sub(r'(\..*$)|($)', '', path_pieces[1])
target_path = '%s%s_html' % (path_pieces[0], novel_title)
section_re = re.compile(r'^\s*第.+卷\s+.*$')
section_head = '''
<html>
<head>
<meta http-equiv="Content-Type" content="GBK"/>
<title>%s</title>
</head>
<body style="font-family:楷体,宋体;font-size:16px; margin:0;
padding: 20px; background:#FAFAD2;color:#2B4B86;text-align:center;">
<h2>%s</h2><a href="#bottom">去页尾</a><hr/>'''
# escape xml/html
def escape_xml(code):
text = code
text = re.sub(r'<', '<', text)
text = re.sub(r'>', '>', text)
text = re.sub(r'&', '&', text)
text = re.sub(r'\t', ' ', text)
text = re.sub(r'\s', ' ', text)
return text
# entry of the script
def main():
# create the output folder
if not os.path.exists(target_path):
os.mkdir(target_path)
# open the source file
input = open(source_path, 'r')
sec_count = 0
sec_cache = []
idx_cache = []
output = open('%s\\%d.html' % (target_path, sec_count), 'w')
preface_title = '%s 前言' % novel_title
output.writelines([section_head % (preface_title, preface_title)])
idx_cache.append('<li><a href="%d.html">%s</a></li>'
% (sec_count, novel_title))
for line in input:
# is a chapter's title?
if line.strip() == '':
pass
elif re.match(section_re, line):
line = re.sub(r'\s+', ' ', line)
print 'converting %s...' % line
# write the section footer
sec_cache.append('<hr/><p>')
if sec_count == 0:
sec_cache.append('<a href="index.html">目录</a> | ')
sec_cache.append('<a href="%d.html">下一篇</a> | '
% (sec_count + 1))
else:
sec_cache.append('<a href="%d.html">上一篇</a> | '
% (sec_count - 1))
sec_cache.append('<a href="index.html">目录</a> | ')
sec_cache.append('<a href="%d.html">下一篇</a> | '
% (sec_count + 1))
sec_cache.append('<a name="bottom" href="#">回页首</a></p>')
sec_cache.append('</body></html>')
output.writelines(sec_cache)
output.flush()
output.close()
sec_cache = []
sec_count += 1
# create a new section
output = open('%s\\%d.html' % (target_path, sec_count), 'w')
output.writelines([section_head % (line, line)])
idx_cache.append('<li><a href="%d.html">%s</a></li>'
% (sec_count, line))
else:
sec_cache.append('<p style="text-align:left;">%s</p>'
% escape_xml(line))
# write rest lines
sec_cache.append('<a href="%d.html">下一篇</a> | '
% (sec_count - 1))
sec_cache.append('<a href="index.html">目录</a> | ')
sec_cache.append('<a name="bottom" href="#">回页首</a></p></body></html>')
output.writelines(sec_cache)
output.flush()
output.close()
sec_cache = []
# write the menu
output = open('%s\\index.html' % (target_path), 'w')
menu_head = '%s 目录' % novel_title
output.writelines([section_head % (menu_head, menu_head), '<ul style="text-align:left">'])
output.writelines(idx_cache)
output.writelines(['</ul><body></html>'])
output.flush()
output.close()
inx_cache = []
print 'completed. %d chapter(s) in total.' % sec_count
if __name__ == '__main__':
main()
将其中的
引用
source_path = 'f:\\佣兵天下.txt'
修改成TXT小说的路径,再根据情况,稍微修改下匹配章节标题的正则
引用
section_re = re.compile(r'^\s*第.+卷\s+.*$')
即可。脚本会在小说所在目录生成一个"文件名_html"的文件夹用于存放节割后的文件。
刚刚接触python,感觉写的代码很不精简,请大家帮忙改进下。