Created
October 31, 2011 14:48
-
-
Save esehara/1327644 to your computer and use it in GitHub Desktop.
Project Euler (Japanese Translation) -> Epub
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import os | |
import urllib2 | |
import BeautifulSoup | |
import re | |
import zipfile | |
class Epub_maker(object): | |
def __init__(self,filename,title,author,identi,workspace='./temp/',): | |
""" | |
Initialize :: Create Directory and File.Epub needs there. | |
./(workspace)/ | |
./(workspace)/mimetype | |
./(workspace)/META-INF/container.xml | |
""" | |
self.filename = filename | |
self.title = title | |
self.author = author | |
self.identi = identi | |
workdir = workspace + filename + "/" | |
#Create Directory | |
os.mkdir(workdir) | |
os.mkdir(workdir + "OEBPS") | |
os.mkdir(workdir + "META-INF") | |
#Create Minetype | |
mimetype = open(workdir + "mimetype","w") | |
mimetype.write("application/epub+zip\n") | |
mimetype.close() | |
#Create xml | |
container_xml = open(workdir + 'META-INF/container.xml','w') | |
make_xml = """<?xml version='1.0' encoding="UTF-8"?> | |
<container xmlns="urn:oasis:names:tc:opendocument:xmlns:container" version="1.0"> | |
<rootfiles> | |
<rootfile full-path="content.opf" media-type="application/oebps-package+xml" /> | |
</rootfiles> | |
</container> | |
""" | |
container_xml.write(make_xml) | |
container_xml.close() | |
self.workdir = workdir | |
def make_opf(self): | |
xml_header = u"""<?xml version="1.0" encoding="UTF-8"?> | |
<package version="2.0" xmlns="http://www.idpf.org/2007/opf" unique-identifier="BookId"> | |
<metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf"> | |
<dc:title>%s</dc:title> | |
<dc:creator opf:role="aut">%s</dc:creator> | |
<dc:language>ja</dc:language> | |
<dc:publisher>Epub Maker (Python) </dc:publisher> | |
<dc:identifier id="BookId">%s</dc:identifier> | |
</metadata> | |
""" % (self.title,self.author,self.identi) | |
xml_manifest_header = u""" | |
<manifest> | |
<item id="ncx" href="toc.ncx" media-type="application/x-dtbncx+xml" /> | |
""" | |
xml_manifest_body = u"" | |
filelist = os.listdir(self.workdir + '/OEBPS/') | |
filelist.pop(0) | |
filelist.sort() | |
for number,file in enumerate(filelist): | |
xml_manifest_body += u"<item id='file%d' href='%s' media-type='application/xhtml+xml' /> " % (number + 1,str(number + 1) + '.xhtml') | |
xml_manifest_body += u'</manifest>' | |
xml_fooder = u""" | |
<spine toc="ncx"> | |
""" | |
for number,file in enumerate(filelist): | |
xml_fooder += u"""<itemref idref="file%d" />""" % (number + 1) | |
xml_fooder += u""" | |
</spine> | |
</package> | |
""" | |
print "[DEBUG] ---- Output OPF File ----" | |
opffile = open(self.workdir + 'content.opf','w') | |
print xml_header | |
opffile.write(xml_header.encode('utf-8')) | |
print xml_manifest_header | |
opffile.write(xml_manifest_header.encode('utf-8')) | |
print xml_manifest_body | |
opffile.write(xml_manifest_body.encode('utf-8')) | |
print xml_fooder | |
opffile.write(xml_fooder.encode('utf-8')) | |
opffile.close() | |
self.filelist = filelist | |
def make_ncx(self): | |
xml_header = u"""<?xml version="1.0" encoding="UTF-8" ?> | |
<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1"> | |
<head> | |
<meta name='dtb:uid' content="%s" /> | |
<meta name='dtb:depth' content="1" /> | |
<meta name='dtb:totalPageCount' content="0" /> | |
<meta name='dtb:maxPageNumber' content="0" /> | |
</head> | |
<docTitle> | |
<text>%s</text> | |
</docTitle> | |
<docAuthor> | |
<text>%s</text> | |
</docAuthor> | |
""" % (self.identi,self.title,self.author) | |
xml_navMap = u"<navMap>" | |
for number,files in enumerate(self.filelist): | |
xml_navMap += u"""<navPoint id='file%d' playOrder='%d'> | |
<navLabel> | |
<text>%s</text> | |
</navLabel> | |
<content src="%s" /> | |
</navPoint> | |
""" % (number + 1,number + 1,number + 1,"OEBPS/" + str(number) + '.xhtml') | |
xml_navMap += u"</navMap>" | |
xml_navMap += u"</ncx>" | |
ncxfile = open(self.workdir + 'toc.ncx','w') | |
print "[DEBUG] ---- Output Ncx File ----" | |
print xml_header | |
ncxfile.write(xml_header.encode('utf-8')) | |
print xml_navMap | |
ncxfile.write(xml_navMap.encode('utf-8')) | |
ncxfile.close() | |
def make_zip(self): | |
epub_zip = zipfile.ZipFile(re.sub(' ','',self.filename) + '.epub','w',zipfile.ZIP_DEFLATED) | |
filelist = os.listdir(self.workdir) | |
for file in filelist: | |
epub_zip.write(self.workdir + file,file) | |
filelist = os.listdir(self.workdir + 'META-INF') | |
for file in filelist: | |
epub_zip.write(self.workdir + 'META-INF/' + file,'./META-INF/' + file) | |
filelist = os.listdir(self.workdir + 'OEBPS') | |
for file in filelist: | |
epub_zip.write(self.workdir + 'OEBPS/' + file,'./OEBPS/' + file) | |
epub_zip.close() | |
class ProjectEular(object): | |
def gen(self): | |
opener = urllib2.build_opener() | |
epub = Epub_maker(filename = "peuler", | |
title = "Project Euler", | |
author = "Project Euler", | |
identi = "http://odz.sakura.ne.jp/projecteuler/index.php") | |
html = opener.open("http://odz.sakura.ne.jp/projecteuler/index.php").read() | |
mainsoup = BeautifulSoup.BeautifulSoup(html) | |
subsoup = mainsoup.findAll("ul",{"class":"list1"})[2].findAll("a") | |
for num,soup in enumerate(subsoup): | |
print soup.text | |
print soup["href"] | |
gen_file = open(epub.workdir + "OEBPS/" + str(num) + ".xhtml","w") | |
gen_file.write(self.gen_xml(soup["href"]).encode("utf-8")) | |
gen_file.close() | |
epub.make_opf() | |
epub.make_ncx() | |
epub.make_zip() | |
def gen_xml(self,page): | |
opener = urllib2.build_opener() | |
header = '''<?xml version="1.0" encoding="UTF-8"?> | |
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//JP" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"> | |
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="ja" lang="ja"> | |
<head> | |
''' | |
target_page = opener.open(page).read() | |
soup = BeautifulSoup.BeautifulSoup(target_page) | |
title = soup.find("h1").text | |
body_str = "" | |
for num,body_soup in enumerate(soup.findAll("p")): | |
if num + 1 == len(soup.findAll("p")): | |
break | |
body_str += "<p>%s</p>\n" % body_soup.text | |
header += ''' | |
<title>%s</title> | |
</head> | |
<body> | |
''' % title | |
body = ''' | |
<h1>%s</h1> | |
%s | |
''' % (title,body_str) | |
fooder = ''' | |
</body> | |
</html> | |
''' | |
return (header + body + fooder) | |
if __name__ == "__main__":ProjectEular().gen() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment