Python分割器在我们进行文章分割的时候会经常用到。当然一篇相当长的文章会让你有些头疼。看完下面的代码希望大家能够熟练的使用Python分割器进行文章分割。
- # 将txt小说分割转换成多个HTML文件
- # @author : GreatGhoul
- # @email : greatghoul@gmail.com
- # @blog : http://greatghoul.javaeye.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 = '''''
%s - margin:0;
- padding: 20px; background:#FAFAD2;color:#2B4B86;text
-align:center;">%s
去页尾
'''- # 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('
- %s
'- % (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('
')
- if sec_count == 0:
- sec_cache.append('目录 | ')
- sec_cache.append('下一篇 | '
- % (sec_count + 1))
- else:
- sec_cache.append('上一篇 | '
- % (sec_count - 1))
- sec_cache.append('目录 | ')
- sec_cache.append('下一篇 | '
- % (sec_count + 1))
- sec_cache.append('回页首')
- sec_cache.append('')
- 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('
- %s
'- % (sec_count, line))
- else:
- sec_cache.append('
%s
'- % escape_xml(line))
- # write rest lines
- sec_cache.append('下一篇 | '
- % (sec_count - 1))
- sec_cache.append('目录 | ')
- sec_cache.append('#">回页首