Python分割器怎么使用

这篇文章主要讲解了"Python分割器怎么使用"，文中的讲解内容简单清晰，易于学习与理解，下面请大家跟着小编的思路慢慢深入，一起来研究和学习"Python分割器怎么使用"吧！

1. # 将txt小说分割转换成多个HTML文件

2. # @author : GreatGhoul

3. # @email : greatghoul@gmail.com

4. # @blog : http://greatghoul.javaeye.com

5. import re

6. import os

7. # regex for the section title

8. # sec_re = re.compile(r'第.+卷\s+.+\s+第.+章\s+.+')

9. # txt book's path.

10. source_path = 'f:\\佣兵天下.txt'

11. path_pieces = os.path.split(source_path)

12. novel_title = re.sub(r'(\..*$)|($)', '', path_pieces[1])

13. target_path = '%s%s_html' % (path_pieces[0], novel_title)

14. section_re = re.compile(r'^\s*第.+卷\s+.*$')

15. section_head = '''''

22. %s

    去页尾

    ---

    '''

23. # escape xml/html

24. def escape_xml(code):

25. text = code

26. text = re.sub(r'<', '<', text)

27. text = re.sub(r'>', '>', text)

28. text = re.sub(r'&', '&', text)

29. text = re.sub(r'\t', '    ', text)

30. text = re.sub(r'\s', ' ', text)

31. return text

32. # entry of the script

33. def main():

34. # create the output folder

35. if not os.path.exists(target_path):

36. os.mkdir(target_path)

37. # open the source file

38. input = open(source_path, 'r')

39. sec_count = 0

40. sec_cache = []

41. idx_cache = []

42. output = open('%s\\%d.html' % (target_path, sec_count), 'w')

43. preface_title = '%s 前言' % novel_title

44. output.writelines([section_head % (preface_title,
    preface_title)])

45. idx_cache.append('

46. %s
'

47. % (sec_count, novel_title))

48. for line in input:

49. # is a chapter's title?

50. if line.strip() == '':

51. pass

52. elif re.match(section_re, line):

53. line = re.sub(r'\s+', ' ', line)

54. print 'converting %s...' % line

55. # write the section footer

56. sec_cache.append('

    ---

    ')

57. if sec_count == 0:

58. sec_cache.append('目录 | ')

59. sec_cache.append('下一篇 | '

60. % (sec_count + 1))

61. else:

62. sec_cache.append('上一篇 | '

63. % (sec_count - 1))

64. sec_cache.append('目录 | ')

65. sec_cache.append('下一篇 | '

66. % (sec_count + 1))

67. sec_cache.append('回页首

    ')

68. sec_cache.append('')

69. output.writelines(sec_cache)

70. output.flush()

71. output.close()

72. sec_cache = []

73. sec_count += 1

74. # create a new section

75. output = open('%s\\%d.html' % (target_path, sec_count), 'w')

76. output.writelines([section_head % (line, line)])

77. idx_cache.append('

78. %s
'

79. % (sec_count, line))

80. else:

81. sec_cache.append('

    %s

    '

82. % escape_xml(line))

83. # write rest lines

84. sec_cache.append('下一篇 | '

85. % (sec_count - 1))

86. sec_cache.append('目录 | ')

87. sec_cache.append('回页首

    ')

88. output.writelines(sec_cache)

89. output.flush()

90. output.close()

91. sec_cache = []

92. # write the menu

93. output = open('%s\\index.html' % (target_path), 'w')

94. menu_head = '%s 目录' % novel_title

95. output.writelines([section_head % (menu_head, menu_head),
    '

    '])

    • output.writelines(idx_cache)

    • output.writelines(['

    '])

96. output.flush()

97. output.close()

98. inx_cache = []

99. print 'completed. %d chapter(s) in total.' % sec_count

100. if __name__ == '__main__':

101. main()

感谢各位的阅读，以上就是"Python分割器怎么使用"的内容了，经过本文的学习后，相信大家对Python分割器怎么使用这一问题有了更深刻的体会，具体使用情况还需要大家实践验证。这里是，小编将为大家推送更多相关知识点的文章，欢迎关注！