def run(bk):
if any(bk.selected_iter()):
on_selected = True
else:
on_selected = False
for file_id, file_href in files_iter(bk, on_selected):
xhtml_file = bk.readfile(file_id)
xhtml_soup = sigil_bs4.BeautifulSoup(xhtml_file, 'lxml')
if xhtml_soup.h1:
header = xhtml_soup.h1.text
elif xhtml_soup.h2:
header = xhtml_soup.h2.text
elif xhtml_soup.h3:
header = xhtml_soup.h3.text
elif xhtml_soup.h4:
header = xhtml_soup.h4.text
elif xhtml_soup.h5:
header = xhtml_soup.h5.text
elif xhtml_soup.h6:
header = xhtml_soup.h6.text
else:
header = ''
if not xhtml_soup.head.title:
title = xhtml_soup.new_tag("title")
xhtml_soup.head.append(title)
xhtml_soup.head.title.string = header
bk.writefile(file_id, xhtml_soup.prettyprint_xhtml(indent_chars=" "))
return 0
def parse(text, **kwargs):
with gumboc.parse(text, **kwargs) as output:
soup = sigil_bs4.BeautifulSoup('', "html.parser")
_add_document(soup, output.contents.document.contents)
for node in output.contents.document.contents.children:
soup.append(_add_node(soup, node))
_add_next_prev_pointers(soup.html)
return soup
def getCoverImageID(bk):
# get cover image id from metadata
coverImgID = ''
metadata = bk.getmetadataxml()
stinx = sigil_bs4.BeautifulSoup(metadata, 'xml')
for node in stinx.find_all('meta'):
if node.get('name') == 'cover':
coverImgID = node.get('content')
break
return coverImgID
def editIdentifierInToC(bk, BookId):
# read toc file contents
tocManifestId = bk.gettocid()
tocXml = bk.readfile(tocManifestId)
tocSoup = sigil_bs4.BeautifulSoup(tocXml, 'xml')
metaNode = tocSoup.find('head')
# change the content of the identifier
for node in metaNode.find_all('meta'):
if node.get('name') == "dtb:uid":
node['content'] = BookId
print('Setting identifier in ToC: %s' % node)
# write back
bk.writefile(tocManifestId, tocSoup.prettify())
def setCoverImageID(bk, coverImgID):
# set metadata: cover
metadata_xml = bk.getmetadataxml()
metadata_soup = sigil_bs4.BeautifulSoup(metadata_xml, 'xml')
metadata_node = metadata_soup.find('metadata')
if coverImgID:
for node in metadata_node.find_all('meta'): # remove existing info
if node.get('name') == 'cover':
node.decompose()
meta_cover_tag = metadata_soup.new_tag('meta')
meta_cover_tag['name'] = 'cover'
meta_cover_tag['content'] = coverImgID
metadata_node.append(meta_cover_tag)
bk.setmetadataxml(str(metadata_soup))
def run(bk):
print('start')
for (file_id, _) in bk.text_iter():
modified = False
html = bk.readfile(file_id)
soup = sigil_bs4.BeautifulSoup(html)
# br tag will cause p tag cannot be found
for elem in soup.findAll(['p', 'div', 'span'],
text=re.compile('(\d+)')):
modified = True
text = elem.string
for key in conversionDict:
text = re.sub(key, conversionDict[key], text)
elem.string.replace_with(text)
# print(elem.string)
if modified:
print("Modifed File -> ", id)
bk.writefile(file_id, fixSelfCloseTags(str(soup)))
return 0
def run(bk):
if any(bk.selected_iter()):
on_selected = True
else:
on_selected = False
for file_id, file_href in files_iter(bk, on_selected):
xhtml_file = bk.readfile(file_id)
xhtml_soup = sigil_bs4.BeautifulSoup(xhtml_file, 'lxml')
# There's a typo in bk.href_to_basename until version 0.9.5 of Sigil
if bk.launcher_version() <= 20160325:
file_name = href_to_basename(file_href)
else:
file_name = bk.href_to_basename(file_href)
if xhtml_soup.head.title:
xhtml_soup.head.title.string = file_name[:file_name.rindex(".")]
else:
title = xhtml_soup.new_tag("title")
title.string = file_name[:file_name.rindex(".")]
xhtml_soup.head.append(title)
bk.writefile(file_id, xhtml_soup.prettyprint_xhtml(indent_chars=" "))
return 0
def parse_xml(bk: 'BookContainer', collector: XHTMLAttributes,
prefs: MutableMapping) -> XHTMLAttributes:
fragid_container_attrs = prefs[
'fragid_container_attrs'] or collector.fragid_container_attrs
xhtml_files = set(id_ for id_, href in bk.text_iter())
for file_id, href, mime in bk.manifest_iter():
# if file is xhtml or not xml, skip ahead
if file_id in xhtml_files or not re.search(r'[/+]xml\b', mime):
continue
try:
soup = sigil_bs4.BeautifulSoup(bk.readfile(file_id), 'lxml-xml')
except Exception as E:
raise XMLParsingError('Error in {}: {}'.format(
utils.href_to_basename(href), E))
for elem in soup.find_all(True):
# gather fragment identifiers, if present
for attr in fragid_container_attrs:
fragid = get_fragid(elem, attr)
if fragid:
collector.fragment_identifier.add(fragid)
return collector
def newIdentifierInMetadata(bk):
metadata_xml = bk.getmetadataxml()
metadata_soup = sigil_bs4.BeautifulSoup(metadata_xml, 'xml')
metadata_node = metadata_soup.find('metadata')
# remove the old identifier
for node in metadata_node.find_all('identifier'):
if node.get('id') == "BookId":
node.decompose()
# print('Creating a new BookID.')
BookId = uuid.uuid4().urn
id_node = metadata_soup.new_tag('dc:identifier')
id_node['id'] = "BookId"
id_node['opf:scheme'] = "UUID"
id_node.string = BookId
metadata_node.append(id_node)
print('Setting metadata: %s' % id_node)
bk.setmetadataxml(str(metadata_soup))
return BookId
def run(bk):
# get python plugin path
global plugin_path
plugin_path = os.path.join(bk._w.plugin_dir, plugin_name)
for (textID, textHref) in bk.text_iter():
print('\nProcessing text file: %s' % textHref)
textContents = bk.readfile(
textID) # Read the section into textContents
if not isinstance(
textContents, text_type
): # If the section is not str then sets its type to 'utf-8'
textContents = text_type(textContents, 'utf-8')
soup = sigil_bs4.BeautifulSoup(textContents, "xml")
# TODO: near square image?
# done in getSvgForImage. not yet backport to baka-epub
useImgForLandscape = False
svgSizePercent = 98
removeMe = []
for divNode in soup.find_all("div"):
if divNode.has_attr('class') and "svg_outer" in divNode['class']:
for imgNode in divNode.find_all(["img", "svg"]):
if imgNode.name == 'img':
imgSrc = imgNode['src']
else:
imgSrc = imgNode.image['xlink:href']
if imgSrc.startswith('../'): imgSrc = imgSrc[3:]
imgID = bk.href_to_id(imgSrc)
if imgID: # image file exists
print('Found image: ' + imgSrc)
if (len(bk.readfile(imgID)) == 0):
print('Zero-length file. Removing...')
removeMe.append(divNode)
else:
_useImg = useImgForLandscape
if "svg_yes" in divNode['class']:
_useImg = False
_svgSizePercent = svgSizePercent
if "svg_100" in divNode['class']:
_svgSizePercent = 100
svgNode = sigil_bs4.BeautifulSoup(
getSvgForImage(bk,
imgID,
svgSizePercent=_svgSizePercent,
useImgForLandscape=_useImg,
dontWrapInDiv=True), "xml")
imgNode.replace_with(svgNode)
else:
print('404 error: ' + imgSrc + '. Removing...')
removeMe.append(divNode)
for element in removeMe:
element.decompose()
textContents = str(soup)
textContents = '<?xml version="1.0" encoding="utf-8"?>' + re.sub(
'<\?xml\s.*?\?>', '', textContents)
bk.writefile(textID, textContents)
print('Done.')
return 0