View Single Post
Old 07-08-2011, 05:34 PM   #13
tylau0
Connoisseur
tylau0 began at the beginning.
 
Posts: 81
Karma: 10
Join Date: Oct 2010
Device: Kindle
Set a recipe that generates a typical e-book rather than a periodical

Sometimes, one may wish to use a recipe to generate a typical e-book rather than a periodical. You may make that possible by adding the following piece of code inside your recipe class.

Spoiler:
Code:
    def create_opf(self, feeds, dir=None):
        if dir is None:
            dir = self.output_dir
        title = self.short_title()
        if self.output_profile.periodical_date_in_title:
            title += strftime(self.timefmt)
        mi = MetaInformation(title, [__appname__])
        mi.publisher = __appname__
        mi.author_sort = __appname__
        mi.publication_type = self.publication_type+':'+self.short_title()
        mi.timestamp = nowf()
        mi.comments = self.description
        if not isinstance(mi.comments, unicode):
            mi.comments = mi.comments.decode('utf-8', 'replace')
        mi.pubdate = nowf()
        opf_path = os.path.join(dir, 'index.opf')
        ncx_path = os.path.join(dir, 'index.ncx')

        opf = OPFCreator(dir, mi)
        # Add mastheadImage entry to <guide> section
        mp = getattr(self, 'masthead_path', None)
        if mp is not None and os.access(mp, os.R_OK):
            from calibre.ebooks.metadata.opf2 import Guide
            ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu())
            ref.type = 'masthead'
            ref.title = 'Masthead Image'
            opf.guide.append(ref)

        manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))]
        manifest.append(os.path.join(dir, 'index.html'))
        manifest.append(os.path.join(dir, 'index.ncx'))

        # Get cover
        cpath = getattr(self, 'cover_path', None)
        if cpath is None:
            pf = open(os.path.join(dir, 'cover.jpg'), 'wb')
            if self.default_cover(pf):
                cpath =  pf.name
        if cpath is not None and os.access(cpath, os.R_OK):
            opf.cover = cpath
            manifest.append(cpath)

        # Get masthead
        mpath = getattr(self, 'masthead_path', None)
        if mpath is not None and os.access(mpath, os.R_OK):
            manifest.append(mpath)

        opf.create_manifest_from_files_in(manifest)
        for mani in opf.manifest:
            if mani.path.endswith('.ncx'):
                mani.id = 'ncx'
            if mani.path.endswith('mastheadImage.jpg'):
                mani.id = 'masthead-image'

        entries = ['index.html']
        toc = TOC(base_path=dir)
        self.play_order_counter = 0
        self.play_order_map = {}

        def feed_index(num, parent):
            f = feeds[num]
            for j, a in enumerate(f):
                if getattr(a, 'downloaded', False):
                    adir = 'feed_%d/article_%d/'%(num, j)
                    auth = a.author
                    if not auth:
                        auth = None
                    desc = a.text_summary
                    if not desc:
                        desc = None
                    else:
                        desc = self.description_limiter(desc)
                    entries.append('%sindex.html'%adir)
                    po = self.play_order_map.get(entries[-1], None)
                    if po is None:
                        self.play_order_counter += 1
                        po = self.play_order_counter
                    parent.add_item('%sindex.html'%adir, None, a.title if a.title else _('Untitled Article'),
                                    play_order=po, author=auth, description=desc)
                    last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep))
                    for sp in a.sub_pages:
                        prefix = os.path.commonprefix([opf_path, sp])
                        relp = sp[len(prefix):]
                        entries.append(relp.replace(os.sep, '/'))
                        last = sp

                    if os.path.exists(last):
                        with open(last, 'rb') as fi:
                            src = fi.read().decode('utf-8')
                        soup = BeautifulSoup(src)
                        body = soup.find('body')
                        if body is not None:
                            prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last))))
                            templ = self.navbar.generate(True, num, j, len(f),
                                            not self.has_single_feed,
                                            a.orig_url, __appname__, prefix=prefix,
                                            center=self.center_navbar)
                            elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div')
                            body.insert(len(body.contents), elem)
                            with open(last, 'wb') as fi:
                                fi.write(unicode(soup).encode('utf-8'))
        if len(feeds) == 0:
            raise Exception('All feeds are empty, aborting.')

        if len(feeds) > 1:
            for i, f in enumerate(feeds):
                entries.append('feed_%d/index.html'%i)
                po = self.play_order_map.get(entries[-1], None)
                if po is None:
                    self.play_order_counter += 1
                    po = self.play_order_counter
                auth = getattr(f, 'author', None)
                if not auth:
                    auth = None
                desc = getattr(f, 'description', None)
                if not desc:
                    desc = None
                feed_index(i, toc.add_item('feed_%d/index.html'%i, None,
                    f.title, play_order=po, description=desc, author=auth))

        else:
            entries.append('feed_%d/index.html'%0)
            feed_index(0, toc)

        for i, p in enumerate(entries):
            entries[i] = os.path.join(dir, p.replace('/', os.sep))
        opf.create_spine(entries)
        opf.set_toc(toc)

        with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
            opf.render(opf_file, ncx_file)


The above basically changes one line in the implementation of the following function of calibre.web.feeds.news
Code:
def create_opf(self, feeds, dir=None):
Turn the line
Code:
mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title()
to
Code:
mi.publication_type = self.publication_type+':'+self.short_title()
The keyword "periodical" in mi.publication_type is searched in the current Calibre program to determine if it should generate an e-book or a periodical.

For an example recipe, check the "Ming Pao - Hong Kong" recipe in your Calibre copy or here. You may also get insights on how to append the publication date in the e-book title, which could be useful for differentiating e-books generated on different dates.

Moderator Notice: The difference between a typical ebook and a "periodical" is relevant for a Kindle, but may not be relevant for other ebook readers.

Last edited by tylau0; 07-09-2011 at 10:32 AM.
tylau0 is offline   Reply With Quote