def concat_books():
for book in TEST_FILES:
print book
e = _load_epub(book, verbose=True)
e.parse_meta()
e.parse_opf()
e.parse_ncx()
lang = e.find_language() or 'UND'
doc = epub.new_doc(lang=lang)
for ID in e.spine:
fn, mimetype = e.manifest[ID]
print fn
if mimetype.startswith('image'):
tree = epub.new_doc(guts='<img src="%s" alt="" />' % fn)
else:
tree = e.gettree(fn, parse=_html_parse)
add_marker(doc, 'espri-new-page-%s' % ID, fn)
add_guts(tree, doc)
f = open('tests/xhtml/' + os.path.basename(book) + '.html', 'w')
print >> f, lxml.etree.tostring(doc, encoding='utf-8', method='html').replace(' ', '')#.encode('utf-8')
f.close()
def concat_chapters(fn):
e = epub.Epub()
e.load(open(fn).read())
e.parse_meta()
e.parse_opf()
e.parse_ncx()
lang = e.find_language() or 'UND'
chapter_depth, toc_points = e.find_probable_chapters()
doc = epub.new_doc(lang=lang)
for ID in e.order:
fn, mimetype = e.manifest[ID]
print fn
if mimetype.startswith('image'):
tree = epub.new_doc(guts='<img src="%s" alt="" />' % fn)
else:
tree = e.gettree(fn, parse=_html_parse)
add_marker(doc, 'espri-new-page-%s' % ID, fn)
add_guts(tree, doc)
return doc
def test_new_doc():
#XXX not very comprehensive.
for guts in ('', "hello", "<h1>HELLO!</h1>"):
doc = epub.new_doc(guts=guts)
try:
body = doc.iter(epub.XHTMLNS + 'body').next()
print "got %s" % body
except StopIteration:
body = doc.iter('body').next()
guts2 = body.text or ''
for x in body:
guts2 += lxml.etree.tostring(x)
if body.tail is not None:
guts2 += body.tail
assert guts == guts2