From a850e64bfbb58066d060cb27d5f2377e1f4ad904 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9E=97=E6=AA=8E?= Date: Sat, 4 Mar 2017 15:48:59 +0800 Subject: [PATCH] Refactor cover detection MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit obsolate hardcode %cover_id%= ‘cover’ in now %cover_id% retrieve from --- cps/epub.py | 36 ++++++++++++++++-------------------- 1 file changed, 16 insertions(+), 20 deletions(-) diff --git a/cps/epub.py b/cps/epub.py index ccbe9cad..446efe9b 100644 --- a/cps/epub.py +++ b/cps/epub.py @@ -72,26 +72,22 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension): if len(coversection) > 0: coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path) 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] - 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: - 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) - + meta_cover = tree.xpath("/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content", namespaces=ns) + if len(meta_cover) > 0: + coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='"+meta_cover[0]+"']/@href", namespaces=ns) + if len(coversection) > 0: + 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) + if epub_metadata['title'] is None: title = original_file_name else: