class DocParser:
def __init__(self, name, book_properties):
self.name = name
self.book = Book(book_properties)
HTML_HEADER = """
<html>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<head>
Title
</head>
<body>
"""
def parse(self, output=""):
self.temp_dir = tempfile.mkdtemp()
if output == "":
output = self.temp_dir + "/tmp.html"
os.system(
PATH_TO_WV_WARE
+ "wvWare -x"
+ PATH_TO_WV_HTML
+ "/wvHtml.xml --charset=cp1251 %s > %s" % (self.name, output)
)
paragraphs = []
# temp_file = self.file.decode("utf-8")
file = open(self.temp_dir + "/tmp.html", "r")
temp_file = prettify.remove_spaces(file.read())
temp_file = prettify.remove_unnecessary_tags(temp_file)
soup = BeautifulSoup(temp_file)
temp_names = soup.findAll(align="center")
names = []
titles = []
for temp_name in temp_names:
if not re.match(r"^(<.*?>|\s+)*$", str(temp_name)):
names.append(re.sub(r"\s+", " ", str(temp_name)))
temp = re.sub(r"(<.*>|\s+)", " ", temp_name.prettify())
titles.append(re.sub(r"\s+", " ", temp))
temp_file = re.sub(r"\s+", " ", temp_file.decode("cp1251").encode("utf-8"))
out = open(self.temp_dir + "/tmp", "w")
out.write(temp_file)
out.write(" \n\n\n")
for name in names:
out.write(name + "\n\n\n")
out.close()
if not names:
print "not names"
file = open(self.temp_dir + "/0.html", "w")
file.write(temp_file)
file.close()
self.book.add_file(self.temp_dir + "/0.html", "c0", "")
for i, name in enumerate(names):
split_index = temp_file.find(name)
if i == 0:
paragraph = ""
else:
paragraph = self.HTML_HEADER
paragraph += temp_file[:split_index]
soup = BeautifulSoup(paragraph)
paragraph = soup.prettify()
paragraphs.append(paragraph)
temp_file = temp_file[split_index:]
# soup = BeautifulSoup(temp_file)
# temp_file = soup.prettify()
for i, paragraph in enumerate(paragraphs):
file = open(self.temp_dir + "/%d.html" % i, "w")
file.write(paragraph)
file.close()
self.book.add_file(self.temp_dir + "/%d.html" % i, "c%d" % i, titles[i])
# for i, image in enumerate(self.images):
# self.book.add_file(image, 'im%d' % i, title="", in_spine=False)
self.book.pack()
return True
def __init__(self, name, book_properties):
self.name = name
self.book = Book(book_properties)
def epub_form(request):
"""
Displays form for converting from txt files and adding into db
"""
messages = []
if request.method == "POST":
form = EpubAddForm(request.POST, request.FILES)
if form.is_valid():
cd = form.cleaned_data
book_name = cd['caption']
lang = cd['language']
tags = cd['tags']
subject = cd['subject']
description = cd['description']
type = cd['type']
date = cd['date']
rights = cd['rights']
temp_name = tempfile.mkstemp()[1]
properties = BookProperties(temp_name, book_name)
properties.language = lang
properties.subject = subject
properties.description = description
properties.genre = type
properties.date = date
properties.rights = rights
properties.author = request.user.first_name + " " + request.user.last_name
book = BookCreator(properties)
file = request.FILES['file']
toc = cd['toc']
if toc:
book.split_by_toc(toc, file.read())
else:
book.txt_to_html(file.read(), temp_name + "text.html")
book.add_file(temp_name + "text.html", "c1", "")
book.pack()
try:
language = Language.objects.get(short=lang)
except:
return render_response(request, "epub/epub_form.html",
{'errors': [_('No such language.')],
'user': request.user, 'menu_on': True,
'form': form})
lang_code = LANG_CODE[0]
for lang_code in LANG_CODE:
if lang_code[0] == lang:
break
book_model = Book.objects.create(language=language, pagelink="")
book_model.title = book_name
try:
author = Author.objects.get(name=request.user.first_name +
' ' + request.user.last_name)
except:
author = Author.objects.create(name=request.user.first_name +
' ' + request.user.last_name)
book_model.author = [author]
book_model.save()
ebook = EpubBook.objects.create(book = book_model)
exfile = _ExistingFile(temp_name)
ebook.name.save(book_name + ".epub", exfile)
print ebook.name
try:
book_file = BookFile(link="/" + MEDIA_URL + "/" + quote(str(ebook.name)))
book_file.type = 'epub'
book_file.save()
except Exception, e:
print e
return render_response(request, "epub/epub_form.html",
{'errors': [_("Book name should be unique")],
'menu_on': True, 'form': form})
book_model.book_file = [book_file]
book_model.save()
ebook.save()
messages += [_("Book successfully created.")]
hrr = HttpResponseRedirect("/book/id%d" % book_model.id)
return hrr
