|
|
@ -41,57 +41,53 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
|
|
|
|
p = tree.xpath('/pkg:package/pkg:metadata', namespaces=ns)[0]
|
|
|
|
p = tree.xpath('/pkg:package/pkg:metadata', namespaces=ns)[0]
|
|
|
|
|
|
|
|
|
|
|
|
epub_metadata = {}
|
|
|
|
epub_metadata = {}
|
|
|
|
try:#maybe description isn't present
|
|
|
|
|
|
|
|
comments = tree.xpath("//*[local-name() = 'description']/text()")[0]
|
|
|
|
|
|
|
|
epub_metadata['comments'] = comments
|
|
|
|
|
|
|
|
except:
|
|
|
|
|
|
|
|
epub_metadata['comments'] = ""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
for s in ['title', 'description', 'creator']:
|
|
|
|
for s in ['title', 'description', 'creator', 'language']:
|
|
|
|
tmp = p.xpath('dc:%s/text()' % s, namespaces=ns)
|
|
|
|
tmp = p.xpath('dc:%s/text()' % s, namespaces=ns)
|
|
|
|
if len(tmp) > 0:
|
|
|
|
if len(tmp) > 0:
|
|
|
|
epub_metadata[s] = p.xpath('dc:%s/text()' % s, namespaces=ns)[0]
|
|
|
|
epub_metadata[s] = p.xpath('dc:%s/text()' % s, namespaces=ns)[0]
|
|
|
|
else:
|
|
|
|
else:
|
|
|
|
epub_metadata[s] = "Unknown"
|
|
|
|
epub_metadata[s] = "Unknown"
|
|
|
|
#detect lang need futher modification in web.py /upload
|
|
|
|
|
|
|
|
try:#maybe dc:language isn't present, less possible but possible
|
|
|
|
if epub_metadata['description'] == "Unknown":
|
|
|
|
lang = p.xpath('dc:language/text()', namespaces=ns)[0]
|
|
|
|
description = tree.xpath("//*[local-name() = 'description']/text()")
|
|
|
|
lang = lang.split('-', 1)[0]
|
|
|
|
if len(description) > 0:
|
|
|
|
lang.lower()
|
|
|
|
epub_metadata['description'] = description
|
|
|
|
|
|
|
|
else:
|
|
|
|
|
|
|
|
epub_metadata['description'] = ""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if epub_metadata['language'] == "Unknown":
|
|
|
|
|
|
|
|
epub_metadata['language'] == ""
|
|
|
|
|
|
|
|
else:
|
|
|
|
|
|
|
|
lang = epub_metadata['language'].split('-', 1)[0].lower()
|
|
|
|
if len(lang) == 2:
|
|
|
|
if len(lang) == 2:
|
|
|
|
epub_metadata['languages'] = isoLanguages.get(part1=lang).name
|
|
|
|
epub_metadata['language'] = isoLanguages.get(part1=lang).name
|
|
|
|
elif len(lang) == 3:
|
|
|
|
elif len(lang) == 3:
|
|
|
|
epub_metadata['languages'] = isoLanguages.get(part3=lang).name
|
|
|
|
epub_metadata['language'] = isoLanguages.get(part3=lang).name
|
|
|
|
else:
|
|
|
|
else:
|
|
|
|
epub_metadata['languages'] = ""
|
|
|
|
epub_metadata['language'] = ""
|
|
|
|
except:
|
|
|
|
|
|
|
|
epub_metadata['languages'] = ""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href", namespaces=ns)
|
|
|
|
coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href", namespaces=ns)
|
|
|
|
coverfile = None
|
|
|
|
coverfile = None
|
|
|
|
if len(coversection) > 0:
|
|
|
|
if len(coversection) > 0:
|
|
|
|
coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path)
|
|
|
|
coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path)
|
|
|
|
else:
|
|
|
|
else:
|
|
|
|
coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover']/@href", namespaces=ns)
|
|
|
|
meta_cover = tree.xpath("/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content", namespaces=ns)
|
|
|
|
if len(coversection) > 0:
|
|
|
|
if len(meta_cover) > 0:
|
|
|
|
filetype = coversection[0].rsplit('.',1)[-1]
|
|
|
|
coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='"+meta_cover[0]+"']/@href", namespaces=ns)
|
|
|
|
if filetype == "xhtml" or filetype == "html": #if cover is (x)html format
|
|
|
|
if len(coversection) > 0:
|
|
|
|
markup = zip.read(os.path.join(coverpath,coversection[0]))
|
|
|
|
filetype = coversection[0].rsplit('.',1)[-1]
|
|
|
|
markupTree = etree.fromstring(markup)
|
|
|
|
if filetype == "xhtml" or filetype == "html": #if cover is (x)html format
|
|
|
|
#no matter xhtml or html with no namespace
|
|
|
|
markup = zip.read(os.path.join(coverpath,coversection[0]))
|
|
|
|
imgsrc = markupTree.xpath("//*[local-name() = 'img']/@src")
|
|
|
|
markupTree = etree.fromstring(markup)
|
|
|
|
#imgsrc maybe startwith "../"" so fullpath join then relpath to cwd
|
|
|
|
#no matter xhtml or html with no namespace
|
|
|
|
filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(coverpath, coversection[0])), imgsrc[0]))
|
|
|
|
imgsrc = markupTree.xpath("//*[local-name() = 'img']/@src")
|
|
|
|
coverfile = extractCover(zip, filename, "", tmp_file_path)
|
|
|
|
#imgsrc maybe startwith "../"" so fullpath join then relpath to cwd
|
|
|
|
else:
|
|
|
|
filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(coverpath, coversection[0])), imgsrc[0]))
|
|
|
|
coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path)
|
|
|
|
coverfile = extractCover(zip, filename, "", tmp_file_path)
|
|
|
|
else:
|
|
|
|
else:
|
|
|
|
meta_cover = tree.xpath("/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content", namespaces=ns)
|
|
|
|
coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path)
|
|
|
|
if len(meta_cover) > 0:
|
|
|
|
|
|
|
|
meta_cover_content = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='"+meta_cover[0]+"']/@href", namespaces=ns)
|
|
|
|
|
|
|
|
if len(meta_cover_content) > 0:
|
|
|
|
|
|
|
|
coverfile = extractCover(zip, meta_cover_content[0], coverpath, tmp_file_path)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if epub_metadata['title'] is None:
|
|
|
|
if epub_metadata['title'] is None:
|
|
|
|
title = original_file_name
|
|
|
|
title = original_file_name
|
|
|
|
else:
|
|
|
|
else:
|
|
|
@ -107,5 +103,4 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
|
|
|
|
tags="",
|
|
|
|
tags="",
|
|
|
|
series="",
|
|
|
|
series="",
|
|
|
|
series_id="",
|
|
|
|
series_id="",
|
|
|
|
comments=epub_metadata['comments'],
|
|
|
|
languages=epub_metadata['language'])
|
|
|
|
languages=epub_metadata['languages'])
|
|
|
|
|
|
|
|