From 7972b987d4a79b64c7c1689b14d1240a82d50054 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9E=97=E6=AA=8E?= Date: Wed, 1 Mar 2017 13:18:14 +0800 Subject: [PATCH 1/2] Read img tag of cover file if cover is (x)html MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit for example ‘ 0: - coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path) + filetype = coversection[0].rsplit('.',1)[-1] + if filetype == "xhtml" or filetype == "html": #if cover is (x)html format + markup = zip.read(os.path.join(coverpath,coversection[0])) + markupTree = etree.fromstring(markup) + #no matter xhtml or html with no namespace + imgsrc = markupTree.xpath( "//*[local-name() = 'img']/@src") + #imgsrc maybe startwith "../"" so fullpath join then relpath to cwd + filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(coverpath,coversection[0])),imgsrc[0])) + coverfile = extractCover(zip, filename, "", tmp_file_path) + else: + coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path) else: coverfile = None From 9a2877ebd50d39d6772f4cf87f5e5f563921dac4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9E=97=E6=AA=8E?= Date: Wed, 1 Mar 2017 14:36:31 +0800 Subject: [PATCH 2/2] situation when opf file content is --- cps/epub.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/cps/epub.py b/cps/epub.py index 26dc839c..62520aa3 100644 --- a/cps/epub.py +++ b/cps/epub.py @@ -54,7 +54,7 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension): else: coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover']/@href", namespaces=ns) if len(coversection) > 0: - filetype = coversection[0].rsplit('.',1)[-1] + filetype = coversection[0].rsplit('.',1)[-1] if filetype == "xhtml" or filetype == "html": #if cover is (x)html format markup = zip.read(os.path.join(coverpath,coversection[0])) markupTree = etree.fromstring(markup) @@ -66,7 +66,13 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension): else: coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path) else: - coverfile = None + meta_cover = tree.xpath("/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content", namespaces=ns) + 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) + else: + coverfile = None if epub_metadata['title'] is None: title = original_file_name