From 29f21480abe99cf00844024b0e5a1f95127ecebf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9E=97=E6=AA=8E?= Date: Sat, 4 Mar 2017 15:37:30 +0800 Subject: [PATCH 1/2] Reuse original code logic. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit iteration loop dc:* add dc:language removal of bookmeta[‘comments’] , reusing bootmeta[‘description’] --- cps/book_formats.py | 2 -- cps/epub.py | 39 +++++++++++++++++++-------------------- cps/uploader.py | 2 +- cps/web.py | 2 +- 4 files changed, 21 insertions(+), 24 deletions(-) diff --git a/cps/book_formats.py b/cps/book_formats.py index 934638fc..a88e5e0e 100644 --- a/cps/book_formats.py +++ b/cps/book_formats.py @@ -64,7 +64,6 @@ def default_meta(tmp_file_path, original_file_name, original_file_extension): tags="", series="", series_id="", - comments="", languages="") @@ -94,7 +93,6 @@ def pdf_meta(tmp_file_path, original_file_name, original_file_extension): tags="", series="", series_id="", - comments="", languages="") diff --git a/cps/epub.py b/cps/epub.py index b800250d..ccbe9cad 100644 --- a/cps/epub.py +++ b/cps/epub.py @@ -41,31 +41,31 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension): p = tree.xpath('/pkg:package/pkg:metadata', namespaces=ns)[0] 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) if len(tmp) > 0: epub_metadata[s] = p.xpath('dc:%s/text()' % s, namespaces=ns)[0] else: epub_metadata[s] = "Unknown" - #detect lang need futher modification in web.py /upload - try:#maybe dc:language isn't present, less possible but possible - lang = p.xpath('dc:language/text()', namespaces=ns)[0] - lang = lang.split('-', 1)[0] - lang.lower() - if len(lang) == 2: - epub_metadata['languages'] = isoLanguages.get(part1=lang).name - elif len(lang) == 3: - epub_metadata['languages'] = isoLanguages.get(part3=lang).name + + if epub_metadata['description'] == "Unknown": + description = tree.xpath("//*[local-name() = 'description']/text()") + if len(description) > 0: + epub_metadata['description'] = description else: - epub_metadata['languages'] = "" - except: - epub_metadata['languages'] = "" + epub_metadata['description'] = "" + + if epub_metadata['language'] == "Unknown": + epub_metadata['language'] == "" + else: + lang = epub_metadata['language'].split('-', 1)[0].lower() + if len(lang) == 2: + epub_metadata['language'] = isoLanguages.get(part1=lang).name + elif len(lang) == 3: + epub_metadata['language'] = isoLanguages.get(part3=lang).name + else: + epub_metadata['language'] = "" coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href", namespaces=ns) coverfile = None @@ -107,5 +107,4 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension): tags="", series="", series_id="", - comments=epub_metadata['comments'], - languages=epub_metadata['languages']) + languages=epub_metadata['language']) diff --git a/cps/uploader.py b/cps/uploader.py index 18e4bd43..2772e033 100644 --- a/cps/uploader.py +++ b/cps/uploader.py @@ -7,7 +7,7 @@ import hashlib from collections import namedtuple import book_formats -BookMeta = namedtuple('BookMeta', 'file_path, extension, title, author, cover, description, tags, series, series_id, comments, languages') +BookMeta = namedtuple('BookMeta', 'file_path, extension, title, author, cover, description, tags, series, series_id, languages') """ :rtype: BookMeta diff --git a/cps/web.py b/cps/web.py index 5687d604..d28ae70b 100755 --- a/cps/web.py +++ b/cps/web.py @@ -2234,7 +2234,7 @@ def upload(): db.session.add(db_book) db.session.flush()# flush content get db_book.id avalible #add comment - upload_comment = Markup(meta.comments).unescape() + upload_comment = Markup(meta.description).unescape() db_comment = None if upload_comment != "": db_comment = db.Comments(upload_comment, db_book.id) 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 2/2] 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: