def _generate(self, article, style=None, extra_css=None):
content = article.content if article.content else ''
summary = article.summary if article.summary else ''
text = content if len(content) > len(summary) else summary
head = HEAD(TITLE(article.title))
if style:
head.append(STYLE(style, type='text/css'))
if extra_css:
head.append(STYLE(extra_css, type='text/css'))
if isbytestring(text):
text = text.decode('utf-8', 'replace')
elements = html.fragments_fromstring(text)
self.root = HTML(head,
BODY(H2(article.title), DIV()))
div = self.root.find('body').find('div')
if elements and isinstance(elements[0], unicode_type):
div.text = elements[0]
elements = list(elements)[1:]
for elem in elements:
if hasattr(elem, 'getparent'):
elem.getparent().remove(elem)
else:
elem = SPAN(elem)
div.append(elem)
def __init__(self,
path_or_stream,
dest_dir=None,
log=None,
notes_text=None):
self.docx = DOCX(path_or_stream, log=log)
self.log = self.docx.log
self.notes_text = notes_text or _('Notes')
self.dest_dir = dest_dir or os.getcwdu()
self.mi = self.docx.metadata
self.body = BODY()
self.styles = Styles()
self.images = Images()
self.tables = Tables()
self.object_map = OrderedDict()
self.html = HTML(
HEAD(
META(charset='utf-8'),
TITLE(self.mi.title or _('Unknown')),
LINK(rel='stylesheet', type='text/css', href='docx.css'),
), self.body)
self.html.text = '\n\t'
self.html[0].text = '\n\t\t'
self.html[0].tail = '\n'
for child in self.html[0]:
child.tail = '\n\t\t'
self.html[0][-1].tail = '\n\t'
self.html[1].text = self.html[1].tail = '\n'
lang = canonicalize_lang(self.mi.language)
if lang and lang != 'und':
lang = lang_as_iso639_1(lang)
if lang:
self.html.set('lang', lang)
def _generate(self, title, masthead, datefmt, feeds, extra_css=None, style=None):
self.IS_HTML = False
date = '%s, %s %s, %s' % (strftime('%A'), strftime('%B'), strftime('%d').lstrip('0'), strftime('%Y'))
masthead_p = etree.Element("p")
masthead_p.set("style","text-align:center")
masthead_img = etree.Element("img")
masthead_img.set("src",masthead)
masthead_img.set("alt","masthead")
masthead_p.append(masthead_img)
head = HEAD(TITLE(title))
if style:
head.append(STYLE(style, type='text/css'))
if extra_css:
head.append(STYLE(extra_css, type='text/css'))
toc = TABLE(CLASS('toc'),width="100%",border="0",cellpadding="3px")
for i, feed in enumerate(feeds):
if feed:
tr = TR()
tr.append(TD(CLASS('calibre_rescale_120'), A(feed.title, href='feed_%d/index.html'%i)))
tr.append(TD('%s' % len(feed.articles), style="text-align:right"))
toc.append(tr)
div = DIV(
masthead_p,
H3(CLASS('publish_date'),date),
DIV(CLASS('divider')),
toc)
self.root = HTML(head, BODY(div))
if self.html_lang:
self.root.set('lang', self.html_lang)
def _generate(self,
title,
masthead,
datefmt,
feeds,
extra_css=None,
style=None):
self.IS_HTML = False
date = strftime(datefmt)
head = HEAD(TITLE(title))
if style:
head.append(STYLE(style, type='text/css'))
if extra_css:
head.append(STYLE(extra_css, type='text/css'))
ul = UL(attrs('calibre_feed_list'))
for i, feed in enumerate(feeds):
if len(feed):
li = LI(A(
feed.title,
attrs('feed', rescale=120, href='feed_%d/index.html' % i)),
id='feed_%d' % i)
ul.append(li)
div = DIV(
PT(IMG(src=masthead, alt="masthead"), style='text-align:center'),
PT(date, style='text-align:right'), ul, attrs(rescale=100))
self.root = HTML(head, BODY(div))
if self.html_lang:
self.root.set('lang', self.html_lang)
def _generate(self,
bottom,
feed,
art,
number_of_articles_in_feed,
two_levels,
url,
__appname__,
prefix='',
center=True,
extra_css=None,
style=None):
head = HEAD(TITLE('navbar'))
if style:
head.append(STYLE(style, type='text/css'))
if extra_css:
head.append(STYLE(extra_css, type='text/css'))
if prefix and not prefix.endswith('/'):
prefix += '/'
align = 'center' if center else 'left'
navbar = DIV(
attrs('calibre_navbar', rescale=70, style='text-align:' + align))
if bottom:
if not url.startswith('file://'):
navbar.append(HR())
text = 'This article was downloaded by '
p = PT(
text,
STRONG(__appname__),
A(url, href=url, rel='calibre-downloaded-from'),
style='text-align:left; max-width: 100%; overflow: hidden;'
)
p[0].tail = ' from '
navbar.append(p)
navbar.append(BR())
navbar.append(BR())
else:
next_art = 'feed_%d'%(feed+1) if art == number_of_articles_in_feed - 1 \
else 'article_%d'%(art+1)
up = '../..' if art == number_of_articles_in_feed - 1 else '..'
href = '%s%s/%s/index.html' % (prefix, up, next_art)
navbar.text = '| '
navbar.append(A(_('Next'), href=href))
href = '%s../index.html#article_%d' % (prefix, art)
next(navbar.iterchildren(reversed=True)).tail = ' | '
navbar.append(A(_('Section menu'), href=href))
href = '%s../../index.html#feed_%d' % (prefix, feed)
next(navbar.iterchildren(reversed=True)).tail = ' | '
navbar.append(A(_('Main menu'), href=href))
if art > 0 and not bottom:
href = '%s../article_%d/index.html' % (prefix, art - 1)
next(navbar.iterchildren(reversed=True)).tail = ' | '
navbar.append(A(_('Previous'), href=href))
next(navbar.iterchildren(reversed=True)).tail = ' | '
if not bottom:
navbar.append(HR())
self.root = HTML(head, BODY(navbar))
def _generate(self,
title,
masthead,
datefmt,
feeds,
extra_css=None,
style=None):
self.IS_HTML = False
if isinstance(datefmt, unicode):
datefmt = datefmt.encode(preferred_encoding)
date = strftime(datefmt)
head = HEAD(TITLE(title))
if style:
head.append(STYLE(style, type='text/css'))
if extra_css:
head.append(STYLE(extra_css, type='text/css'))
ul = UL(CLASS('calibre_feed_list'))
for i, feed in enumerate(feeds):
if feed:
li = LI(A(
feed.title,
CLASS('feed',
'calibre_rescale_120',
href='feed_%d/index.html' % i)),
id='feed_%d' % i)
ul.append(li)
div = DIV(
PT(IMG(src=masthead, alt="masthead"), style='text-align:center'),
PT(date, style='text-align:right'), ul,
CLASS('calibre_rescale_100'))
self.root = HTML(head, BODY(div))
if self.html_lang:
self.root.set('lang', self.html_lang)
def _generate(self,
bottom,
feed,
art,
number_of_articles_in_feed,
two_levels,
url,
__appname__,
prefix='',
center=True,
extra_css=None,
style=None):
head = HEAD(TITLE('navbar'))
if style:
head.append(STYLE(style, type='text/css'))
if extra_css:
head.append(STYLE(extra_css, type='text/css'))
navbar = DIV()
navbar_t = TABLE(CLASS('touchscreen_navbar'))
navbar_tr = TR()
# | Previous
if art > 0:
link = A(CLASS('article_link'),
_('Previous'),
href='%s../article_%d/index.html' % (prefix, art - 1))
navbar_tr.append(TD(CLASS('article_prev'), link))
else:
navbar_tr.append(TD(CLASS('article_prev'), ''))
# | Articles | Sections |
link = A(CLASS('articles_link'),
_('Articles'),
href='%s../index.html#article_%d' % (prefix, art))
navbar_tr.append(TD(CLASS('article_articles_list'), link))
link = A(CLASS('sections_link'),
_('Sections'),
href='%s../../index.html#feed_%d' % (prefix, feed))
navbar_tr.append(TD(CLASS('article_sections_list'), link))
# | Next
next = 'feed_%d'%(feed+1) if art == number_of_articles_in_feed - 1 \
else 'article_%d'%(art+1)
up = '../..' if art == number_of_articles_in_feed - 1 else '..'
link = A(CLASS('article_link'),
_('Next'),
href='%s%s/%s/index.html' % (prefix, up, next))
navbar_tr.append(TD(CLASS('article_next'), link))
navbar_t.append(navbar_tr)
navbar.append(navbar_t)
#print "\n%s\n" % etree.tostring(navbar, pretty_print=True)
self.root = HTML(head, BODY(navbar))
def document_from_json(self, page_json, label_list):
return HTML(
HEAD(
TITLE(page_json['title']),
META(name='date', content=page_json['history']['createdDate']),
META(name='modified', content=page_json['version']['when']),
META(name='tags',
content=','.join([
l for l in label_list if l not in ('hidden', 'menu')
])),
META(name='authors',
content=page_json['history']['createdBy']['username'])),
BODY(
*lxml.html.fromstring(page_json['body']['export_view']['value']
or '<p>Nothing yet.</p>')))
def _generate(self, f, feeds, cutoff, extra_css=None, style=None):
from calibre.utils.cleantext import clean_xml_chars
feed = feeds[f]
head = HEAD(TITLE(feed.title))
if style:
head.append(STYLE(style, type='text/css'))
if extra_css:
head.append(STYLE(extra_css, type='text/css'))
body = BODY()
body.append(self.get_navbar(f, feeds))
div = DIV(
H2(feed.title,
CLASS('calibre_feed_title', 'calibre_rescale_160')),
CLASS('calibre_rescale_100')
)
body.append(div)
if getattr(feed, 'image', None):
div.append(DIV(IMG(
alt=feed.image_alt if feed.image_alt else '',
src=feed.image_url
),
CLASS('calibre_feed_image')))
if getattr(feed, 'description', None):
d = DIV(clean_xml_chars(feed.description), CLASS('calibre_feed_description',
'calibre_rescale_80'))
d.append(BR())
div.append(d)
ul = UL(CLASS('calibre_article_list'))
for i, article in enumerate(feed.articles):
if not getattr(article, 'downloaded', False):
continue
li = LI(
A(article.title, CLASS('article calibre_rescale_120',
href=article.url)),
SPAN(article.formatted_date, CLASS('article_date')),
CLASS('calibre_rescale_100', id='article_%d'%i,
style='padding-bottom:0.5em')
)
if article.summary:
li.append(DIV(clean_xml_chars(cutoff(article.text_summary)),
CLASS('article_description', 'calibre_rescale_70')))
ul.append(li)
div.append(ul)
div.append(self.get_navbar(f, feeds, top=False))
self.root = HTML(head, body)
if self.html_lang:
self.root.set('lang', self.html_lang)
def _generate(self, bottom, feed, art, number_of_articles_in_feed,
two_levels, url, __appname__, prefix='', center=True,
extra_css=None, style=None):
head = HEAD(TITLE('navbar'))
if style:
head.append(STYLE(style, type='text/css'))
if extra_css:
head.append(STYLE(extra_css, type='text/css'))
navbar = DIV()
navbar_t = TABLE(CLASS('touchscreen_navbar'))
navbar_tr = TR()
if bottom and not url.startswith('file://'):
navbar.append(HR())
text = 'This article was downloaded by '
p = PT(text, STRONG(__appname__), A(url, href=url, rel='calibre-downloaded-from'),
style='text-align:left; max-width: 100%; overflow: hidden;')
p[0].tail = ' from '
navbar.append(p)
navbar.append(BR())
# | Previous
if art > 0:
link = A(CLASS('article_link'),_('Previous'),href='%s../article_%d/index.html'%(prefix, art-1))
navbar_tr.append(TD(CLASS('article_prev'),link))
else:
navbar_tr.append(TD(CLASS('article_prev'),''))
# | Articles | Sections |
link = A(CLASS('articles_link'),_('Articles'), href='%s../index.html#article_%d'%(prefix, art))
navbar_tr.append(TD(CLASS('article_articles_list'),link))
link = A(CLASS('sections_link'),_('Sections'), href='%s../../index.html#feed_%d'%(prefix, feed))
navbar_tr.append(TD(CLASS('article_sections_list'),link))
# | Next
next = 'feed_%d'%(feed+1) if art == number_of_articles_in_feed - 1 \
else 'article_%d'%(art+1)
up = '../..' if art == number_of_articles_in_feed - 1 else '..'
link = A(CLASS('article_link'), _('Next'), href='%s%s/%s/index.html'%(prefix, up, next))
navbar_tr.append(TD(CLASS('article_next'),link))
navbar_t.append(navbar_tr)
navbar.append(navbar_t)
# print "\n%s\n" % etree.tostring(navbar, pretty_print=True)
self.root = HTML(head, BODY(navbar))
def __init__(self,
path_or_stream,
dest_dir=None,
log=None,
detect_cover=True,
notes_text=None,
notes_nopb=False,
nosupsub=False):
self.docx = DOCX(path_or_stream, log=log)
self.namespace = self.docx.namespace
self.ms_pat = re.compile(r'\s{2,}')
self.ws_pat = re.compile(r'[\n\r\t]')
self.log = self.docx.log
self.detect_cover = detect_cover
self.notes_text = notes_text or _('Notes')
self.notes_nopb = notes_nopb
self.nosupsub = nosupsub
self.dest_dir = dest_dir or os.getcwdu()
self.mi = self.docx.metadata
self.body = BODY()
self.theme = Theme(self.namespace)
self.settings = Settings(self.namespace)
self.tables = Tables(self.namespace)
self.fields = Fields(self.namespace)
self.styles = Styles(self.namespace, self.tables)
self.images = Images(self.namespace, self.log)
self.object_map = OrderedDict()
self.html = HTML(
HEAD(
META(charset='utf-8'),
TITLE(self.mi.title or _('Unknown')),
LINK(rel='stylesheet', type='text/css', href='docx.css'),
), self.body)
self.html.text = '\n\t'
self.html[0].text = '\n\t\t'
self.html[0].tail = '\n'
for child in self.html[0]:
child.tail = '\n\t\t'
self.html[0][-1].tail = '\n\t'
self.html[1].text = self.html[1].tail = '\n'
lang = html_lang(self.mi.language)
if lang:
self.html.set('lang', lang)
self.doc_lang = lang
else:
self.doc_lang = None
def toc_as_html(toc, pdf, opts):
pdf = pdf.engine.pdf
indents = []
for i in range(1, 7):
indents.extend((i, 1.4*i))
html = HTML(
HEAD(
STYLE(
'''
.calibre-pdf-toc table { width: 100%% }
.calibre-pdf-toc table tr td:last-of-type { text-align: right }
.calibre-pdf-toc .level-0 {
font-size: larger;
}
.calibre-pdf-toc .level-%d td:first-of-type { padding-left: %.1gem }
.calibre-pdf-toc .level-%d td:first-of-type { padding-left: %.1gem }
.calibre-pdf-toc .level-%d td:first-of-type { padding-left: %.1gem }
.calibre-pdf-toc .level-%d td:first-of-type { padding-left: %.1gem }
.calibre-pdf-toc .level-%d td:first-of-type { padding-left: %.1gem }
.calibre-pdf-toc .level-%d td:first-of-type { padding-left: %.1gem }
''' % tuple(indents) + (opts.extra_css or '')
)
),
BODY(
H2(opts.toc_title or _('Table of Contents')),
TABLE(),
)
)
body = html[1]
body.set('class', 'calibre-pdf-toc')
process_children(toc, body[1], 0, pdf)
return tostring(html, pretty_print=True, include_meta_content_type=True, encoding='utf-8')
def build_index(books, num, search, sort, order, start, total, url_base, CKEYS,
prefix):
logo = DIV(IMG(src=prefix + '/static/calibre.png', alt=__appname__),
id='logo')
search_box = build_search_box(num, search, sort, order, prefix)
navigation = build_navigation(start, num, total, prefix + url_base)
navigation2 = build_navigation(start, num, total, prefix + url_base)
bookt = TABLE(id='listing')
body = BODY(logo, search_box, navigation, HR(CLASS('spacer')), bookt,
HR(CLASS('spacer')), navigation2)
# Book list {{{
for book in books:
thumbnail = TD(
IMG(type='image/jpeg',
border='0',
src=prefix + '/get/thumb/%s' % book['id']), CLASS('thumbnail'))
data = TD()
for fmt in book['formats'].split(','):
if not fmt or fmt.lower().startswith('original_'):
continue
a = quote(ascii_filename(book['authors']))
t = quote(ascii_filename(book['title']))
s = SPAN(
A(fmt.lower(),
href=prefix + '/get/%s/%s-%s_%d.%s' %
(fmt, a, t, book['id'], fmt.lower())), CLASS('button'))
s.tail = u''
data.append(s)
div = DIV(CLASS('data-container'))
data.append(div)
series = u'[%s - %s]'%(book['series'], book['series_index']) \
if book['series'] else ''
tags = u'Tags=[%s]' % book['tags'] if book['tags'] else ''
ctext = ''
for key in CKEYS:
val = book.get(key, None)
if val:
ctext += '%s=[%s] ' % tuple(val.split(':#:'))
first = SPAN(
u'\u202f%s %s by %s' % (book['title'], series, book['authors']),
CLASS('first-line'))
div.append(first)
second = SPAN(
u'%s - %s %s %s' % (book['size'], book['timestamp'], tags, ctext),
CLASS('second-line'))
div.append(second)
bookt.append(TR(thumbnail, data))
# }}}
body.append(
DIV(A(_('Switch to the full interface (non-mobile interface)'),
href=prefix + "/browse",
style="text-decoration: none; color: blue",
title=_('The full interface gives you many more features, '
'but it may not work well on a small screen')),
style="text-align:center"))
return HTML(
HEAD(
TITLE(__appname__ + ' Library'),
LINK(rel='icon',
href='http://calibre-ebook.com/favicon.ico',
type='image/x-icon'),
LINK(rel='stylesheet',
type='text/css',
href=prefix + '/mobile/style.css'),
LINK(rel='apple-touch-icon',
href="/static/calibre.png")), # End head
body) # End html
def _generate(self, f, feeds, cutoff, extra_css=None, style=None):
from calibre.utils.cleantext import clean_xml_chars
def trim_title(title,clip=18):
if len(title)>clip:
tokens = title.split(' ')
new_title_tokens = []
new_title_len = 0
if len(tokens[0]) > clip:
return tokens[0][:clip] + '...'
for token in tokens:
if len(token) + new_title_len < clip:
new_title_tokens.append(token)
new_title_len += len(token)
else:
new_title_tokens.append('...')
title = ' '.join(new_title_tokens)
break
return title
self.IS_HTML = False
feed = feeds[f]
# Construct the navbar
navbar_t = TABLE(CLASS('touchscreen_navbar'))
navbar_tr = TR()
# Previous Section
link = ''
if f > 0:
link = A(CLASS('feed_link'),
trim_title(feeds[f-1].title),
href='../feed_%d/index.html' % int(f-1))
navbar_tr.append(TD(CLASS('feed_prev'),link))
# Up to Sections
link = A(_('Sections'), href="../index.html")
navbar_tr.append(TD(CLASS('feed_up'),link))
# Next Section
link = ''
if f < len(feeds)-1:
link = A(CLASS('feed_link'),
trim_title(feeds[f+1].title),
href='../feed_%d/index.html' % int(f+1))
navbar_tr.append(TD(CLASS('feed_next'),link))
navbar_t.append(navbar_tr)
top_navbar = navbar_t
bottom_navbar = copy.copy(navbar_t)
# print "\n%s\n" % etree.tostring(navbar_t, pretty_print=True)
# Build the page
head = HEAD(TITLE(feed.title))
if style:
head.append(STYLE(style, type='text/css'))
if extra_css:
head.append(STYLE(extra_css, type='text/css'))
body = BODY()
div = DIV(
top_navbar,
H2(feed.title, CLASS('feed_title'))
)
body.append(div)
if getattr(feed, 'image', None):
div.append(DIV(IMG(
alt=feed.image_alt if feed.image_alt else '',
src=feed.image_url
),
CLASS('calibre_feed_image')))
if getattr(feed, 'description', None):
d = DIV(clean_xml_chars(feed.description), CLASS('calibre_feed_description',
'calibre_rescale_80'))
d.append(BR())
div.append(d)
for i, article in enumerate(feed.articles):
if not getattr(article, 'downloaded', False):
continue
div_td = DIV(CLASS('article_summary'),
A(article.title, CLASS('summary_headline','calibre_rescale_120',
href=article.url)))
if article.author:
div_td.append(DIV(article.author,
CLASS('summary_byline', 'calibre_rescale_100')))
if article.summary:
div_td.append(DIV(cutoff(article.text_summary),
CLASS('summary_text', 'calibre_rescale_100')))
div.append(div_td)
div.append(bottom_navbar)
self.root = HTML(head, body)
if self.html_lang:
self.root.set('lang', self.html_lang)
def _create_html_root(self, hhcpath, log, encoding):
from lxml import html
from polyglot.urllib import unquote as _unquote
from calibre.ebooks.oeb.base import urlquote
from calibre.ebooks.chardet import xml_to_unicode
hhcdata = self._read_file(hhcpath)
hhcdata = hhcdata.decode(encoding)
hhcdata = xml_to_unicode(hhcdata,
verbose=True,
strip_encoding_pats=True,
resolve_entities=True)[0]
hhcroot = html.fromstring(hhcdata)
toc = self._process_nodes(hhcroot)
# print("=============================")
# print("Printing hhcroot")
# print(etree.tostring(hhcroot, pretty_print=True))
# print("=============================")
log.debug('Found %d section nodes' % toc.count())
htmlpath = os.path.splitext(hhcpath)[0] + ".html"
base = os.path.dirname(os.path.abspath(htmlpath))
def unquote(x):
if isinstance(x, unicode_type):
x = x.encode('utf-8')
return _unquote(x).decode('utf-8')
def unquote_path(x):
y = unquote(x)
if (not os.path.exists(os.path.join(base, x))
and os.path.exists(os.path.join(base, y))):
x = y
return x
def donode(item, parent, base, subpath):
for child in item:
title = child.title
if not title:
continue
raw = unquote_path(child.href or '')
rsrcname = os.path.basename(raw)
rsrcpath = os.path.join(subpath, rsrcname)
if (not os.path.exists(os.path.join(base, rsrcpath))
and os.path.exists(os.path.join(base, raw))):
rsrcpath = raw
if '%' not in rsrcpath:
rsrcpath = urlquote(rsrcpath)
if not raw:
rsrcpath = ''
c = DIV(A(title, href=rsrcpath))
donode(child, c, base, subpath)
parent.append(c)
with open(htmlpath, 'wb') as f:
if toc.count() > 1:
from lxml.html.builder import HTML, BODY, DIV, A
path0 = toc[0].href
path0 = unquote_path(path0)
subpath = os.path.dirname(path0)
base = os.path.dirname(f.name)
root = DIV()
donode(toc, root, base, subpath)
raw = html.tostring(HTML(BODY(root)),
encoding='utf-8',
pretty_print=True)
f.write(raw)
else:
f.write(as_bytes(hhcdata))
return htmlpath, toc
