API tools faq
paste
Advertisement
AgvirtheSilent

Process Index Light Novels

AgvirtheSilent
Apr 15th, 2012
137
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 10.20 KB | None | 0 0
raw download clone embed print report
  1. #!/usr/bin/python
  2. import codecs, glob, os, re, subprocess, sys
  3.  
  4. irfanview_bin_path = '"C:\Program Files (x86)\IrfanView\i_view32.exe"'
  5. cover_file_top = u"<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n\
  6. <!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\"\n\
  7.  \"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">\n\
  8. \n\
  9. <html xmlns=\"http://www.w3.org/1999/xhtml\">\n\
  10. <head>\n\
  11.  <title>Cover</title>\n\
  12.  <link href=\"../Styles/stylesheet.css\" rel=\"stylesheet\" type=\"text/css\" />\n\
  13. </head>\n\
  14. \n\
  15. <body>\n\
  16.  <p class=\"cover\"><img alt=\"\" class=\"imagefit\" src=\"../Images/"
  17. cover_file_bottom = u"\" /></p>\n\
  18. </body>\n\
  19. </html>\n"
  20. illustrations_file_top = u"<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n\
  21. <!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\"\n\
  22.  \"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">\n\
  23. \n\
  24. <html xmlns=\"http://www.w3.org/1999/xhtml\">\n\
  25. <head>\n\
  26.  <title>Illustrations</title>\n\
  27.  <link href=\"../Styles/stylesheet.css\" rel=\"stylesheet\" type=\"text/css\" />\n\
  28. </head>\n\
  29. \n\
  30. <body>\n"
  31. illustrations_file_bottom = u"</body>\n\
  32. </html>\n"
  33. illustrations_insert_front = u"<p class=\"illustration\"><img alt=\"\" class=\"imagefit\" src=\"../Images/"
  34. illustrations_insert_back = u"\" /></p>\n"
  35. stylesheet_file = u".cover {\n\
  36.    display: block\n\
  37.    }\n\
  38. .illustration {\n\
  39.    display: block\n\
  40.    }\n\
  41. .imagefit {\n\
  42.    max-height: 100%;\n\
  43.    max-width: 100%\n\
  44.    }"
  45.  
  46. delete = raw_input("Overwrite existing converted files? (Y/N) ")
  47. if not re.match(r'Y|N$', delete):
  48.     sys.stderr.write("ERROR: Input not valid! Press Enter to exit.")
  49.     raw_input()
  50.     sys.exit(1)
  51.  
  52. # Process all files by directory
  53. for i in range(1, len(sys.argv)):
  54.     # Process passed argument
  55.     first_pass = True
  56.     if os.path.isdir(sys.argv[i]):
  57.         this_dir = sys.argv[i]
  58.         # Process all files by directory, if any, and recurse subdir
  59.         for dirpath, dirnames, filenames in os.walk(this_dir):
  60.             if first_pass:
  61.                 # First pass
  62.                 sys.stderr.write("Processing folder " + dirpath + "\n")
  63.                 first_pass = False
  64.                 # Create converted HTML dir
  65.                 try:
  66.                     os.mkdir(os.path.normpath(dirpath + os.sep + "Converted HTML"))
  67.                 except:
  68.                     if delete == "N":
  69.                         sys.exit(1)
  70.                     elif delete == "Y":
  71.                         old_files = glob.glob(os.path.normpath(dirpath + os.sep + "Converted HTML" + os.sep + '*'))
  72.                         if old_files:
  73.                             for f in old_files:
  74.                                 os.unlink(f)
  75.                 # Create stylesheet
  76.                 sys.stderr.write("Generating CSS stylesheet file\n")
  77.                 output = open(os.path.normpath(dirpath + os.sep + "Converted HTML" + os.sep + "stylesheet.css"), 'w')
  78.                 output.write(stylesheet_file)
  79.                 output.close()
  80.                 for file in filenames:
  81.                     if os.path.splitext(file)[1] == ".htm":
  82.                         # Process HTML file(s)
  83.                         sys.stderr.write("Formatting HTML file " + file + "\n")
  84.                         if re.search('(?<=Toaru Majutsu no Index )(.+)(?= - Baka-Tsuki.htm)', file):
  85.                             name_match = re.search('(?<=Toaru Majutsu no Index )(.+)(?= - Baka-Tsuki.htm)', file)
  86.                             file_name = name_match.group(1)
  87.                         elif re.search('(?<=To Aru Majutsu no Index )(.+)(?= - Baka-Tsuki.htm)', file):
  88.                             name_match = re.search('(?<=To Aru Majutsu no Index )(.+)(?= - Baka-Tsuki.htm)', file)
  89.                             file_name = name_match.group(1)
  90.                         file_name = re.sub(r'NT Volume\d+ |SS Norse Mythology |RailgunSS\d+ |Volume\d+ |Volume SP |SSVolume\d+ ', '', file_name)
  91.                         if re.search('(Chapter|Main|Sub|Period)[\s\.]?(\d+)', file_name):
  92.                             chapter_match = re.search('(Chapter|Main|Sub|Period)[\s\.]?(\d+)', file_name)
  93.                             name = chapter_match.group(1)
  94.                             number = chapter_match.group(2)
  95.                             file_name = name + "_" + number.zfill(2)
  96.                         file_name = os.path.splitext(file_name)[0] + ".xhtml"
  97.                         input = codecs.open(os.path.normpath(dirpath + os.sep + file), 'r', 'utf-8')
  98.                         output = codecs.open(os.path.normpath(dirpath + os.sep + "Converted HTML" + os.sep + file_name), 'w', 'utf-8')
  99.                         # Read in file and apply regexs
  100.                         entire_file = input.read()
  101.                         input.close()
  102.                         # Strip out <head>
  103.                         pattern = re.compile(u'(?<=<head>\n).+(?=</head>)', re.DOTALL)
  104.                         entire_file = re.sub(pattern, u'  <title>' + unicode(os.path.splitext(file_name)[0]) + u'</title>\n  <link href="../Styles/stylesheet.css" rel="stylesheet" type="text/css" />\n', entire_file)
  105.                         # Fix stray References header level
  106.                         entire_file = re.sub(ur'<h2>[^\n]*(<span class="mw-headline" id="References">\s*References\s*</span>)</h2>', u'<h3>\g<1></h3>', entire_file)
  107.                         # Fix malformatted References header
  108.                         entire_file = re.sub(ur'<h2>[^\n]*<span class="mw-headline" id="refs">\s*refs\s*</span></h2>', u'<h3><span class="mw-headline" id="References">References</span></h3>', entire_file)
  109.                         # Fix stray Notes header level
  110.                         entire_file = re.sub(ur'<h2>[^\n]*(<span class="mw-headline" id="Notes">\s*Notes\s*</span>)</h2>', u'<h3>\g<1></h3>', entire_file)
  111.                         # Strip out body before chapter header
  112.                         pattern = re.compile(u'\s+<div id="mw-page-base" class="noprint"></div>.+(<!-- bodytext -->\s+|</table>\s+|[^\n]+Please read[^\n]+Template:PREVIEW.+)(?=<h2>\s?<span class="mw-headline")', re.DOTALL)
  113.                         entire_file = re.sub(pattern, u'\n', entire_file)
  114.                         pattern = re.compile(u'\s+<div id="mw-page-base" class="noprint"></div>.+(<!-- bodytext -->\s+|</table>\s+|[^\n]+Please read[^\n]+Template:PREVIEW.+)([^\n]*<h2>)<span class="editsection">[^\n]+(?=<span class="mw-headline")', re.DOTALL)
  115.                         entire_file = re.sub(pattern, u'\n\g<2>', entire_file)
  116.                         pattern = re.compile(u'\s+<div id="mw-page-base" class="noprint"></div>.+<!-- bodytext -->', re.DOTALL)
  117.                         entire_file = re.sub(pattern, u'\n<h2 class="mw-headline" id="' + unicode(os.path.splitext(file_name)[0]) + u'">' + unicode(os.path.splitext(file_name)[0]) + u'</h2>', entire_file)
  118.                         # Strip out edit sections
  119.                         entire_file = re.sub(ur'<span class="editsection">\[<a href="[^"]+" title="[^"]+">edit</a>]</span>', u'', entire_file)
  120.                         # Strip out bottom of file
  121.                         pattern = re.compile(u'(<table class="wikitable"|<table border="1").+(?=</body>)', re.DOTALL)
  122.                         entire_file = re.sub(pattern, u'', entire_file)
  123.                         pattern = re.compile(u'<!--\s*NewPP limit report.+(?=</body>)', re.DOTALL)
  124.                         entire_file = re.sub(pattern, u'', entire_file)
  125.                         entire_file = re.sub(ur'<!-- Cached \d+ -->', u'', entire_file)
  126.                         # Strip colons out of id for NCNAME spec
  127.                         id_matches = re.findall(ur'(id="[^"]+")', entire_file)
  128.                         if len(id_matches) > 0:
  129.                             for id in id_matches:
  130.                                 strip_invalid = re.sub(ur':', u'', id)
  131.                                 entire_file = re.sub(re.escape(unicode(id)), unicode(strip_invalid), entire_file)
  132.                         # Purge illustration blocks (already have illustrations)
  133.                         if re.search(u'<h2>\s*<span class="mw-headline" id="Illustrations">\s*Illustrations\s*</span></h2>\n', entire_file):
  134.                             # Remove gallery blocks (don't convert)
  135.                             pattern = re.compile(u'<h2>\s*<span class="mw-headline" id="Illustrations">\s*Illustrations\s*</span></h2>\s+<ul class="gallery">(\s*<li[^\n]+\n|\s*<div[^\n]+\n|\s*<p[^\n]+\n|\s*</li[^\n]+\n|\s*</div[^\n]+\n|\s*</p[^\n]+\n)+</ul>', re.DOTALL)
  136.                             entire_file = re.sub(pattern, u'', entire_file)
  137.                         # Convert <img>
  138.                         entire_file = re.sub(ur'<div class="thumb[^\n]+File:([^"]+)[^\n]+</div></div></div></div>', u'<p class="illustration"><img alt="" class="imagefit" src="../Images/\g<1>" /></p>', entire_file)
  139.                         # Convert <img> in <ul class="gallery">
  140.                         entire_file = re.sub(ur'\s+<ul class=gallery>\n|</ul>', u'', entire_file)
  141.                         entire_file = re.sub(ur'\s+<li class="gallerybox"[^\n]+\n[^\n]+File:([^"]+)[^\n]+\s+<div class="gallerytext">\s+</div>\s+</div></li>', u'<p class="illustration"><img alt="" class="imagefit" src="../Images/\g<1>" /></p>', entire_file)
  142.                         # Write out conversion to file
  143.                         output.write(entire_file)
  144.                         output.close()
  145.                     elif os.path.splitext(file)[1] == ".png":
  146.                         # Generate cover
  147.                         sys.stderr.write("Generating cover page for " + file + "\n")
  148.                         cover_file = cover_file_top + unicode(file) + cover_file_bottom
  149.                         output = codecs.open(os.path.normpath(dirpath + os.sep + "Converted HTML" + os.sep + "Cover.xhtml"), 'w', 'utf-8')
  150.                         output.write(cover_file)
  151.                         output.close()
  152.             elif os.path.basename(dirpath) == "Images":
  153.                 # Generate illustrations
  154.                 sys.stderr.write("Generating illustrations page for " + os.path.dirname(dirpath) + "\n")
  155.                 sorted_images = sorted(filenames)
  156.                 image_check = [x for x in sorted_images if re.match(ur'\w+[_\-](000|008)\w*\.\w+', x)]
  157.                 sys.stderr.write(', '.join(image_check) + "\n")
  158.                 illustrations_file = illustrations_file_top
  159.                 if len(image_check) == 2:
  160.                     # Grab images _000.jpg through _008.jpg
  161.                     for image in sorted_images:
  162.                         illustrations_file = illustrations_file + illustrations_insert_front + unicode(image) + illustrations_insert_back
  163.                         if re.match(ur'\w+[_\-]008\w*\.\w+', image):
  164.                             break
  165.                 else:
  166.                     # Grab all images
  167.                     for image in sorted_images:
  168.                         illustrations_file = illustrations_file + illustrations_insert_front + unicode(image) + illustrations_insert_back
  169.                 illustrations_file = illustrations_file + illustrations_file_bottom
  170.                 output = open(os.path.normpath(os.path.dirname(dirpath) + os.sep + "Converted HTML" + os.sep + "Illustrations.xhtml"), 'w')
  171.                 output.write(illustrations_file)
  172.                 output.close()
  173.                 # Resize images
  174.                 sys.stderr.write("Resizing images for " + os.path.dirname(dirpath) + "\n")
  175.                 try:
  176.                     os.mkdir(os.path.normpath(os.path.dirname(dirpath) + os.sep + "Converted Images"))
  177.                 except:
  178.                     if delete == "N":
  179.                         sys.exit(1)
  180.                     elif delete == "Y":
  181.                         old_files = glob.glob(os.path.normpath(os.path.dirname(dirpath) + os.sep + "Converted Images" + os.sep + '*'))
  182.                         if old_files:
  183.                             for f in old_files:
  184.                                 os.unlink(f)
  185.                 for image in sorted(filenames):
  186.                     commands = [irfanview_bin_path, '"' + os.path.normpath(dirpath + os.sep + image) + '"', "/resize=(1000,1000)", "/resample", "/aspectratio", "/convert=" + '"' + os.path.normpath(os.path.dirname(dirpath) + os.sep + "Converted Images" + os.sep + image) + '"']
  187.                     subprocess.call(" ".join(commands))
  188.  
  189. sys.stderr.write("Conversion complete! Press Enter to exit.")
  190. raw_input()
  191. sys.exit(0)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!