Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'py3' of https://github.com/eli-schwartz/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2019-05-28 07:42:30 +05:30
commit 015ff1611b
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
58 changed files with 230 additions and 204 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/ebooks/conversion/__init__.py
View File

@ -5,6 +5,8 @@ __license__ = 'GPL v3'
__copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
from polyglot.builtins import native_string_type
class ConversionUserFeedBack(Exception): class ConversionUserFeedBack(Exception):
@ -25,4 +27,4 @@ class ConversionUserFeedBack(Exception):
# Ensure exception uses fully qualified name as this is used to detect it in # Ensure exception uses fully qualified name as this is used to detect it in
# the GUI. # the GUI.
ConversionUserFeedBack.__name__ = str('calibre.ebooks.conversion.ConversionUserFeedBack') ConversionUserFeedBack.__name__ = native_string_type('calibre.ebooks.conversion.ConversionUserFeedBack')

1
src/calibre/ebooks/conversion/plugins/azw4_input.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>' __copyright__ = '2011, John Schember <john@nachtimwald.com>'

14
src/calibre/ebooks/conversion/plugins/chm_input.py
View File

@ -1,3 +1,5 @@
from __future__ import absolute_import, division, print_function, unicode_literals
''' CHM File decoding support ''' ''' CHM File decoding support '''
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>,' \ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>,' \
@ -64,7 +66,7 @@ class CHMInput(InputFormatPlugin):
metadata = Metadata(os.path.basename(chm_name)) metadata = Metadata(os.path.basename(chm_name))
encoding = self._chm_reader.get_encoding() or options.input_encoding or 'cp1252' encoding = self._chm_reader.get_encoding() or options.input_encoding or 'cp1252'
self._chm_reader.CloseCHM() self._chm_reader.CloseCHM()
# print tdir, mainpath # print((tdir, mainpath))
# from calibre import ipython # from calibre import ipython
# ipython() # ipython()
@ -117,10 +119,10 @@ class CHMInput(InputFormatPlugin):
strip_encoding_pats=True, resolve_entities=True)[0] strip_encoding_pats=True, resolve_entities=True)[0]
hhcroot = html.fromstring(hhcdata) hhcroot = html.fromstring(hhcdata)
toc = self._process_nodes(hhcroot) toc = self._process_nodes(hhcroot)
# print "=============================" # print("=============================")
# print "Printing hhcroot" # print("Printing hhcroot")
# print etree.tostring(hhcroot, pretty_print=True) # print(etree.tostring(hhcroot, pretty_print=True))
# print "=============================" # print("=============================")
log.debug('Found %d section nodes' % toc.count()) log.debug('Found %d section nodes' % toc.count())
htmlpath = os.path.splitext(hhcpath)[0] + ".html" htmlpath = os.path.splitext(hhcpath)[0] + ".html"
base = os.path.dirname(os.path.abspath(htmlpath)) base = os.path.dirname(os.path.abspath(htmlpath))
@ -183,7 +185,7 @@ class CHMInput(InputFormatPlugin):
p = node.xpath('ancestor::ul[1]/ancestor::li[1]/object[1]') p = node.xpath('ancestor::ul[1]/ancestor::li[1]/object[1]')
parent = p[0] if p else None parent = p[0] if p else None
toc = ancestor_map.get(parent, toc) toc = ancestor_map.get(parent, toc)
title = href = u'' title = href = ''
for param in node.xpath('./param'): for param in node.xpath('./param'):
if match_string(param.attrib['name'], 'name'): if match_string(param.attrib['name'], 'name'):
title = param.attrib['value'] title = param.attrib['value']

11
src/calibre/ebooks/conversion/plugins/epub_input.py
View File

@ -1,4 +1,5 @@
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
@ -7,7 +8,7 @@ import os, re, posixpath
from itertools import cycle from itertools import cycle
from calibre.customize.conversion import InputFormatPlugin, OptionRecommendation from calibre.customize.conversion import InputFormatPlugin, OptionRecommendation
from polyglot.builtins import unicode_type, as_bytes, getcwd from polyglot.builtins import as_bytes, getcwd
ADOBE_OBFUSCATION = 'http://ns.adobe.com/pdf/enc#RC' ADOBE_OBFUSCATION = 'http://ns.adobe.com/pdf/enc#RC'
IDPF_OBFUSCATION = 'http://www.idpf.org/2008/embedding' IDPF_OBFUSCATION = 'http://www.idpf.org/2008/embedding'
@ -44,7 +45,7 @@ class EPUBInput(InputFormatPlugin):
import uuid, hashlib import uuid, hashlib
idpf_key = opf.raw_unique_identifier idpf_key = opf.raw_unique_identifier
if idpf_key: if idpf_key:
idpf_key = re.sub(u'[\u0020\u0009\u000d\u000a]', u'', idpf_key) idpf_key = re.sub('[\u0020\u0009\u000d\u000a]', '', idpf_key)
idpf_key = hashlib.sha1(idpf_key.encode('utf-8')).digest() idpf_key = hashlib.sha1(idpf_key.encode('utf-8')).digest()
key = None key = None
for item in opf.identifier_iter(): for item in opf.identifier_iter():
@ -269,7 +270,7 @@ class EPUBInput(InputFormatPlugin):
encfile = os.path.abspath(os.path.join('META-INF', 'encryption.xml')) encfile = os.path.abspath(os.path.join('META-INF', 'encryption.xml'))
opf = self.find_opf() opf = self.find_opf()
if opf is None: if opf is None:
for f in walk(u'.'): for f in walk('.'):
if f.lower().endswith('.opf') and '__MACOSX' not in f and \ if f.lower().endswith('.opf') and '__MACOSX' not in f and \
not os.path.basename(f).startswith('.'): not os.path.basename(f).startswith('.'):
opf = os.path.abspath(f) opf = os.path.abspath(f)
@ -369,7 +370,7 @@ class EPUBInput(InputFormatPlugin):
href = text = None href = text = None
for x in li.iterchildren(XHTML('a'), XHTML('span')): for x in li.iterchildren(XHTML('a'), XHTML('span')):
text = etree.tostring( text = etree.tostring(
x, method='text', encoding=unicode_type, with_tail=False).strip() or ' '.join( x, method='text', encoding='unicode', with_tail=False).strip() or ' '.join(
x.xpath('descendant-or-self::*/@title')).strip() x.xpath('descendant-or-self::*/@title')).strip()
href = x.get('href') href = x.get('href')
if href: if href:

4
src/calibre/ebooks/conversion/plugins/fb2_input.py
View File

@ -8,7 +8,7 @@ import os, re
from calibre.customize.conversion import InputFormatPlugin, OptionRecommendation from calibre.customize.conversion import InputFormatPlugin, OptionRecommendation
from calibre import guess_type from calibre import guess_type
from polyglot.builtins import iteritems, unicode_type, getcwd from polyglot.builtins import iteritems, getcwd
FB2NS = 'http://www.gribuser.ru/xml/fictionbook/2.0' FB2NS = 'http://www.gribuser.ru/xml/fictionbook/2.0'
FB21NS = 'http://www.gribuser.ru/xml/fictionbook/2.1' FB21NS = 'http://www.gribuser.ru/xml/fictionbook/2.1'
@ -71,7 +71,7 @@ class FB2Input(InputFormatPlugin):
stylesheets = doc.xpath('//*[local-name() = "stylesheet" and @type="text/css"]') stylesheets = doc.xpath('//*[local-name() = "stylesheet" and @type="text/css"]')
css = '' css = ''
for s in stylesheets: for s in stylesheets:
css += etree.tostring(s, encoding=unicode_type, method='text', css += etree.tostring(s, encoding='unicode', method='text',
with_tail=False) + '\n\n' with_tail=False) + '\n\n'
if css: if css:
import css_parser, logging import css_parser, logging

149
src/calibre/ebooks/conversion/plugins/fb2_output.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'
@ -67,80 +68,80 @@ class FB2Output(OutputFormatPlugin):
# Children's # Children's
'child_tale', # Fairy Tales 'child_tale', # Fairy Tales
'child_verse', # Verses 'child_verse', # Verses
'child_prose', # Prose 'child_prose', # Prose
'child_sf', # Science Fiction 'child_sf', # Science Fiction
'child_det', # Detectives & Thrillers 'child_det', # Detectives & Thrillers
'child_adv', # Adventures 'child_adv', # Adventures
'child_education', # Educational 'child_education', # Educational
'children', # Other 'children', # Other
# Poetry & Dramaturgy # Poetry & Dramaturgy
'poetry', # Poetry 'poetry', # Poetry
'dramaturgy', # Dramaturgy 'dramaturgy', # Dramaturgy
# Antique literature # Antique literature
'antique_ant', # Antique 'antique_ant', # Antique
'antique_european', # European 'antique_european', # European
'antique_russian', # Old russian 'antique_russian', # Old russian
'antique_east', # Old east 'antique_east', # Old east
'antique_myths', # Myths. Legends. Epos 'antique_myths', # Myths. Legends. Epos
'antique', # Other 'antique', # Other
# Scientific#educational # Scientific#educational
'sci_history', # History 'sci_history', # History
'sci_psychology', # Psychology 'sci_psychology', # Psychology
'sci_culture', # Cultural science 'sci_culture', # Cultural science
'sci_religion', # Religious studies 'sci_religion', # Religious studies
'sci_philosophy', # Philosophy 'sci_philosophy', # Philosophy
'sci_politics', # Politics 'sci_politics', # Politics
'sci_business', # Business literature 'sci_business', # Business literature
'sci_juris', # Jurisprudence 'sci_juris', # Jurisprudence
'sci_linguistic', # Linguistics 'sci_linguistic', # Linguistics
'sci_medicine', # Medicine 'sci_medicine', # Medicine
'sci_phys', # Physics 'sci_phys', # Physics
'sci_math', # Mathematics 'sci_math', # Mathematics
'sci_chem', # Chemistry 'sci_chem', # Chemistry
'sci_biology', # Biology 'sci_biology', # Biology
'sci_tech', # Technical 'sci_tech', # Technical
'science', # Other 'science', # Other
# Computers & Internet # Computers & Internet
'comp_www', # Internet 'comp_www', # Internet
'comp_programming', # Programming 'comp_programming', # Programming
'comp_hard', # Hardware 'comp_hard', # Hardware
'comp_soft', # Software 'comp_soft', # Software
'comp_db', # Databases 'comp_db', # Databases
'comp_osnet', # OS & Networking 'comp_osnet', # OS & Networking
'computers', # Other 'computers', # Other
# Reference # Reference
'ref_encyc', # Encyclopedias 'ref_encyc', # Encyclopedias
'ref_dict', # Dictionaries 'ref_dict', # Dictionaries
'ref_ref', # Reference 'ref_ref', # Reference
'ref_guide', # Guidebooks 'ref_guide', # Guidebooks
'reference', # Other 'reference', # Other
# Nonfiction # Nonfiction
'nonf_biography', # Biography & Memoirs 'nonf_biography', # Biography & Memoirs
'nonf_publicism', # Publicism 'nonf_publicism', # Publicism
'nonf_criticism', # Criticism 'nonf_criticism', # Criticism
'design', # Art & design 'design', # Art & design
'nonfiction', # Other 'nonfiction', # Other
# Religion & Inspiration # Religion & Inspiration
'religion_rel', # Religion 'religion_rel', # Religion
'religion_esoterics', # Esoterics 'religion_esoterics', # Esoterics
'religion_self', # Self#improvement 'religion_self', # Self#improvement
'religion', # Other 'religion', # Other
# Humor # Humor
'humor_anecdote', # Anecdote (funny stories) 'humor_anecdote', # Anecdote (funny stories)
'humor_prose', # Prose 'humor_prose', # Prose
'humor_verse', # Verses 'humor_verse', # Verses
'humor', # Other 'humor', # Other
# Home & Family # Home & Family
'home_cooking', # Cooking 'home_cooking', # Cooking
'home_pets', # Pets 'home_pets', # Pets
'home_crafts', # Hobbies & Crafts 'home_crafts', # Hobbies & Crafts
'home_entertain', # Entertaining 'home_entertain', # Entertaining
'home_health', # Health 'home_health', # Health
'home_garden', # Garden 'home_garden', # Garden
'home_diy', # Do it yourself 'home_diy', # Do it yourself
'home_sport', # Sports 'home_sport', # Sports
'home_sex', # Erotica & sex 'home_sex', # Erotica & sex
'home', # Other 'home', # Other
] ]
ui_data = { ui_data = {
'sectionize': { 'sectionize': {

2
src/calibre/ebooks/conversion/plugins/htmlz_output.py
View File

@ -100,7 +100,7 @@ class HTMLZOutput(OutputFormatPlugin):
for item in oeb_book.manifest: for item in oeb_book.manifest:
if item.media_type in OEB_IMAGES and item.href in images: if item.media_type in OEB_IMAGES and item.href in images:
if item.media_type == SVG_MIME: if item.media_type == SVG_MIME:
data = unicode_type(etree.tostring(item.data, encoding=unicode_type)) data = etree.tostring(item.data, encoding='unicode')
else: else:
data = item.data data = item.data
fname = os.path.join(tdir, u'images', images[item.href]) fname = os.path.join(tdir, u'images', images[item.href])

2
src/calibre/ebooks/conversion/plugins/lit_input.py
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'

2
src/calibre/ebooks/conversion/plugins/lit_output.py
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'

4
src/calibre/ebooks/conversion/plugins/lrf_input.py
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
@ -85,4 +85,4 @@ class LRFInput(InputFormatPlugin):
with open('content.opf', 'wb') as f: with open('content.opf', 'wb') as f:
f.write(result) f.write(result)
styles.write() styles.write()
return os.path.abspath(u'content.opf') return os.path.abspath('content.opf')

4
src/calibre/ebooks/conversion/plugins/lrf_output.py
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
@ -188,7 +188,7 @@ class LRFOutput(OutputFormatPlugin):
self.flatten_toc() self.flatten_toc()
from calibre.ptempfile import TemporaryDirectory from calibre.ptempfile import TemporaryDirectory
with TemporaryDirectory(u'_lrf_output') as tdir: with TemporaryDirectory('_lrf_output') as tdir:
from calibre.customize.ui import plugin_for_output_format from calibre.customize.ui import plugin_for_output_format
oeb_output = plugin_for_output_format('oeb') oeb_output = plugin_for_output_format('oeb')
oeb_output.convert(oeb, tdir, input_plugin, opts, log) oeb_output.convert(oeb, tdir, input_plugin, opts, log)

10
src/calibre/ebooks/conversion/plugins/mobi_input.py
View File

@ -1,4 +1,5 @@
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
@ -29,13 +30,13 @@ class MOBIInput(InputFormatPlugin):
mr = MobiReader(stream, log, options.input_encoding, mr = MobiReader(stream, log, options.input_encoding,
options.debug_pipeline) options.debug_pipeline)
if mr.kf8_type is None: if mr.kf8_type is None:
mr.extract_content(u'.', parse_cache) mr.extract_content('.', parse_cache)
except: except:
mr = MobiReader(stream, log, options.input_encoding, mr = MobiReader(stream, log, options.input_encoding,
options.debug_pipeline, try_extra_data_fix=True) options.debug_pipeline, try_extra_data_fix=True)
if mr.kf8_type is None: if mr.kf8_type is None:
mr.extract_content(u'.', parse_cache) mr.extract_content('.', parse_cache)
if mr.kf8_type is not None: if mr.kf8_type is not None:
log('Found KF8 MOBI of type %r'%mr.kf8_type) log('Found KF8 MOBI of type %r'%mr.kf8_type)
@ -52,7 +53,8 @@ class MOBIInput(InputFormatPlugin):
if raw: if raw:
if isinstance(raw, unicode_type): if isinstance(raw, unicode_type):
raw = raw.encode('utf-8') raw = raw.encode('utf-8')
open(u'debug-raw.html', 'wb').write(raw) with open('debug-raw.html', 'wb') as f:
f.write(raw)
from calibre.ebooks.oeb.base import close_self_closing_tags from calibre.ebooks.oeb.base import close_self_closing_tags
for f, root in parse_cache.items(): for f, root in parse_cache.items():
raw = html.tostring(root, encoding='utf-8', method='xml', raw = html.tostring(root, encoding='utf-8', method='xml',

2
src/calibre/ebooks/conversion/plugins/mobi_output.py
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'

3
src/calibre/ebooks/conversion/plugins/odt_input.py
View File

@ -1,4 +1,5 @@
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'

3
src/calibre/ebooks/conversion/plugins/oeb_output.py
View File

@ -1,4 +1,5 @@
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'

1
src/calibre/ebooks/conversion/plugins/pdb_input.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

1
src/calibre/ebooks/conversion/plugins/pdb_output.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

15
src/calibre/ebooks/conversion/plugins/pdf_input.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'
@ -38,7 +39,7 @@ class PDFInput(InputFormatPlugin):
with open(u'index.xml', 'rb') as f: with open(u'index.xml', 'rb') as f:
xml = clean_ascii_chars(f.read()) xml = clean_ascii_chars(f.read())
PDFDocument(xml, self.opts, self.log) PDFDocument(xml, self.opts, self.log)
return os.path.join(getcwd(), u'metadata.opf') return os.path.join(getcwd(), 'metadata.opf')
def convert(self, stream, options, file_ext, log, def convert(self, stream, options, file_ext, log,
accelerators): accelerators):
@ -57,7 +58,7 @@ class PDFInput(InputFormatPlugin):
mi = get_metadata(stream, 'pdf') mi = get_metadata(stream, 'pdf')
opf = OPFCreator(getcwd(), mi) opf = OPFCreator(getcwd(), mi)
manifest = [(u'index.html', None)] manifest = [('index.html', None)]
images = os.listdir(getcwd()) images = os.listdir(getcwd())
images.remove('index.html') images.remove('index.html')
@ -66,16 +67,16 @@ class PDFInput(InputFormatPlugin):
log.debug('Generating manifest...') log.debug('Generating manifest...')
opf.create_manifest(manifest) opf.create_manifest(manifest)
opf.create_spine([u'index.html']) opf.create_spine(['index.html'])
log.debug('Rendering manifest...') log.debug('Rendering manifest...')
with open(u'metadata.opf', 'wb') as opffile: with open('metadata.opf', 'wb') as opffile:
opf.render(opffile) opf.render(opffile)
if os.path.exists(u'toc.ncx'): if os.path.exists('toc.ncx'):
ncxid = opf.manifest.id_for_path('toc.ncx') ncxid = opf.manifest.id_for_path('toc.ncx')
if ncxid: if ncxid:
with open(u'metadata.opf', 'r+b') as f: with open('metadata.opf', 'r+b') as f:
raw = f.read().replace(b'<spine', b'<spine toc="%s"' % as_bytes(ncxid)) raw = f.read().replace(b'<spine', b'<spine toc="%s"' % as_bytes(ncxid))
f.seek(0) f.seek(0)
f.write(raw) f.write(raw)
return os.path.join(getcwd(), u'metadata.opf') return os.path.join(getcwd(), 'metadata.opf')

15
src/calibre/ebooks/conversion/plugins/pdf_output.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2012, Kovid Goyal <kovid at kovidgoyal.net>' __copyright__ = '2012, Kovid Goyal <kovid at kovidgoyal.net>'
@ -30,7 +31,7 @@ class PDFMetadata(object): # {{{
from calibre.ebooks.metadata import authors_to_string from calibre.ebooks.metadata import authors_to_string
self.title = _(u'Unknown') self.title = _(u'Unknown')
self.author = _(u'Unknown') self.author = _(u'Unknown')
self.tags = u'' self.tags = ''
self.mi = mi self.mi = mi
if mi is not None: if mi is not None:
@ -39,7 +40,7 @@ class PDFMetadata(object): # {{{
if mi.authors: if mi.authors:
self.author = authors_to_string(mi.authors) self.author = authors_to_string(mi.authors)
if mi.tags: if mi.tags:
self.tags = u', '.join(mi.tags) self.tags = ', '.join(mi.tags)
self.title = force_unicode(self.title) self.title = force_unicode(self.title)
self.author = force_unicode(self.author) self.author = force_unicode(self.author)
@ -242,16 +243,16 @@ class PDFOutput(OutputFormatPlugin):
elif iswindows and rule.type == rule.STYLE_RULE: elif iswindows and rule.type == rule.STYLE_RULE:
from tinycss.fonts3 import parse_font_family, serialize_font_family from tinycss.fonts3 import parse_font_family, serialize_font_family
s = rule.style s = rule.style
f = s.getProperty(u'font-family') f = s.getProperty('font-family')
if f is not None: if f is not None:
font_families = parse_font_family(css_text(f.propertyValue)) font_families = parse_font_family(css_text(f.propertyValue))
ff = [x for x in font_families if x.lower() != u'courier'] ff = [x for x in font_families if x.lower() != 'courier']
if len(ff) != len(font_families): if len(ff) != len(font_families):
if 'courier' not in self.filtered_font_warnings: if 'courier' not in self.filtered_font_warnings:
# See https://bugs.launchpad.net/bugs/1665835 # See https://bugs.launchpad.net/bugs/1665835
self.filtered_font_warnings.add(u'courier') self.filtered_font_warnings.add('courier')
self.log.warn(u'Removing courier font family as it does not render on windows') self.log.warn('Removing courier font family as it does not render on windows')
f.propertyValue.cssText = serialize_font_family(ff or [u'monospace']) f.propertyValue.cssText = serialize_font_family(ff or ['monospace'])
def convert_text(self, oeb_book): def convert_text(self, oeb_book):
from calibre.ebooks.metadata.opf2 import OPF from calibre.ebooks.metadata.opf2 import OPF

23
src/calibre/ebooks/conversion/plugins/pml_input.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'
@ -73,9 +74,9 @@ class PMLInput(InputFormatPlugin):
imgs = glob.glob(os.path.join(tdir, os.path.splitext(os.path.basename(stream.name))[0] + '_img', '*.png')) imgs = glob.glob(os.path.join(tdir, os.path.splitext(os.path.basename(stream.name))[0] + '_img', '*.png'))
# No images in Dropbook location try generic images directory # No images in Dropbook location try generic images directory
if not imgs: if not imgs:
imgs = glob.glob(os.path.join(os.path.join(tdir, u'images'), u'*.png')) imgs = glob.glob(os.path.join(os.path.join(tdir, 'images'), '*.png'))
if imgs: if imgs:
os.makedirs(os.path.join(getcwd(), u'images')) os.makedirs(os.path.join(getcwd(), 'images'))
for img in imgs: for img in imgs:
pimg_name = os.path.basename(img) pimg_name = os.path.basename(img)
pimg_path = os.path.join(getcwd(), 'images', pimg_name) pimg_path = os.path.join(getcwd(), 'images', pimg_name)
@ -99,11 +100,11 @@ class PMLInput(InputFormatPlugin):
if file_ext == 'pmlz': if file_ext == 'pmlz':
log.debug('De-compressing content to temporary directory...') log.debug('De-compressing content to temporary directory...')
with TemporaryDirectory(u'_unpmlz') as tdir: with TemporaryDirectory('_unpmlz') as tdir:
zf = ZipFile(stream) zf = ZipFile(stream)
zf.extractall(tdir) zf.extractall(tdir)
pmls = glob.glob(os.path.join(tdir, u'*.pml')) pmls = glob.glob(os.path.join(tdir, '*.pml'))
for pml in pmls: for pml in pmls:
html_name = os.path.splitext(os.path.basename(pml))[0]+'.html' html_name = os.path.splitext(os.path.basename(pml))[0]+'.html'
html_path = os.path.join(getcwd(), html_name) html_path = os.path.join(getcwd(), html_name)
@ -114,8 +115,8 @@ class PMLInput(InputFormatPlugin):
toc += ttoc toc += ttoc
images = self.get_images(stream, tdir, True) images = self.get_images(stream, tdir, True)
else: else:
toc = self.process_pml(stream, u'index.html') toc = self.process_pml(stream, 'index.html')
pages.append(u'index.html') pages.append('index.html')
if hasattr(stream, 'name'): if hasattr(stream, 'name'):
images = self.get_images(stream, os.path.abspath(os.path.dirname(stream.name))) images = self.get_images(stream, os.path.abspath(os.path.dirname(stream.name)))
@ -131,14 +132,14 @@ class PMLInput(InputFormatPlugin):
log.debug('Reading metadata from input file...') log.debug('Reading metadata from input file...')
mi = get_metadata(stream, 'pml') mi = get_metadata(stream, 'pml')
if 'images/cover.png' in images: if 'images/cover.png' in images:
mi.cover = u'images/cover.png' mi.cover = 'images/cover.png'
opf = OPFCreator(getcwd(), mi) opf = OPFCreator(getcwd(), mi)
log.debug('Generating manifest...') log.debug('Generating manifest...')
opf.create_manifest(manifest_items) opf.create_manifest(manifest_items)
opf.create_spine(pages) opf.create_spine(pages)
opf.set_toc(toc) opf.set_toc(toc)
with open(u'metadata.opf', 'wb') as opffile: with open('metadata.opf', 'wb') as opffile:
with open(u'toc.ncx', 'wb') as tocfile: with open('toc.ncx', 'wb') as tocfile:
opf.render(opffile, tocfile, u'toc.ncx') opf.render(opffile, tocfile, 'toc.ncx')
return os.path.join(getcwd(), u'metadata.opf') return os.path.join(getcwd(), 'metadata.opf')

1
src/calibre/ebooks/conversion/plugins/pml_output.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

1
src/calibre/ebooks/conversion/plugins/rb_input.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

1
src/calibre/ebooks/conversion/plugins/rb_output.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

12
src/calibre/ebooks/conversion/plugins/recipe_input.py
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
@ -65,7 +65,8 @@ class RecipeInput(InputFormatPlugin):
zf = ZipFile(recipe_or_file, 'r') zf = ZipFile(recipe_or_file, 'r')
zf.extractall() zf.extractall()
zf.close() zf.close()
self.recipe_source = open(u'download.recipe', 'rb').read() with open('download.recipe', 'rb') as f:
self.recipe_source = f.read()
recipe = compile_recipe(self.recipe_source) recipe = compile_recipe(self.recipe_source)
recipe.needs_subscription = False recipe.needs_subscription = False
self.recipe_object = recipe(opts, log, self.report_progress) self.recipe_object = recipe(opts, log, self.report_progress)
@ -87,7 +88,8 @@ class RecipeInput(InputFormatPlugin):
self.recipe_source = self.recipe_source.encode('utf-8') self.recipe_source = self.recipe_source.encode('utf-8')
recipe = compile_recipe(self.recipe_source) recipe = compile_recipe(self.recipe_source)
elif os.access(recipe_or_file, os.R_OK): elif os.access(recipe_or_file, os.R_OK):
self.recipe_source = open(recipe_or_file, 'rb').read() with open(recipe_or_file, 'rb') as f:
self.recipe_source = f.read()
recipe = compile_recipe(self.recipe_source) recipe = compile_recipe(self.recipe_source)
log('Using custom recipe') log('Using custom recipe')
else: else:
@ -140,11 +142,11 @@ class RecipeInput(InputFormatPlugin):
for key, val in self.recipe_object.conversion_options.items(): for key, val in self.recipe_object.conversion_options.items():
setattr(opts, key, val) setattr(opts, key, val)
for f in os.listdir(u'.'): for f in os.listdir('.'):
if f.endswith('.opf'): if f.endswith('.opf'):
return os.path.abspath(f) return os.path.abspath(f)
for f in walk(u'.'): for f in walk('.'):
if f.endswith('.opf'): if f.endswith('.opf'):
return os.path.abspath(f) return os.path.abspath(f)

1
src/calibre/ebooks/conversion/plugins/rtf_output.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

1
src/calibre/ebooks/conversion/plugins/tcr_input.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

1
src/calibre/ebooks/conversion/plugins/tcr_output.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

1
src/calibre/ebooks/conversion/plugins/txt_output.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

10
src/calibre/ebooks/conversion/plumber.py
View File

@ -1,4 +1,6 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
@ -20,7 +22,7 @@ from calibre import (extract, walk, isbytestring, filesystem_encoding,
from calibre.constants import __version__ from calibre.constants import __version__
from polyglot.builtins import unicode_type, string_or_bytes, map from polyglot.builtins import unicode_type, string_or_bytes, map
DEBUG_README=u''' DEBUG_README=b'''
This debug directory contains snapshots of the e-book as it passes through the This debug directory contains snapshots of the e-book as it passes through the
various stages of conversion. The stages are: various stages of conversion. The stages are:
@ -848,7 +850,7 @@ OptionRecommendation(name='search_replace',
rec = self.get_option_by_name(name) rec = self.get_option_by_name(name)
help = getattr(rec, 'help', None) help = getattr(rec, 'help', None)
if help is not None: if help is not None:
return help.replace('%default', str(rec.recommended_value)) return help.replace('%default', unicode_type(rec.recommended_value))
def get_all_help(self): def get_all_help(self):
ans = {} ans = {}
@ -1061,8 +1063,8 @@ OptionRecommendation(name='search_replace',
self.opts.debug_pipeline = os.path.abspath(self.opts.debug_pipeline) self.opts.debug_pipeline = os.path.abspath(self.opts.debug_pipeline)
if not os.path.exists(self.opts.debug_pipeline): if not os.path.exists(self.opts.debug_pipeline):
os.makedirs(self.opts.debug_pipeline) os.makedirs(self.opts.debug_pipeline)
open(os.path.join(self.opts.debug_pipeline, 'README.txt'), with open(os.path.join(self.opts.debug_pipeline, 'README.txt'), 'wb') as f:
'wb').write(DEBUG_README.encode('utf-8')) f.write(DEBUG_README)
for x in ('input', 'parsed', 'structure', 'processed'): for x in ('input', 'parsed', 'structure', 'processed'):
x = os.path.join(self.opts.debug_pipeline, x) x = os.path.join(self.opts.debug_pipeline, x)
if os.path.exists(x): if os.path.exists(x):

38
src/calibre/ebooks/conversion/preprocess.py
View File

@ -75,8 +75,8 @@ def smarten_punctuation(html, log=None):
from calibre.ebooks.conversion.utils import HeuristicProcessor from calibre.ebooks.conversion.utils import HeuristicProcessor
preprocessor = HeuristicProcessor(log=log) preprocessor = HeuristicProcessor(log=log)
from uuid import uuid4 from uuid import uuid4
start = 'calibre-smartypants-'+str(uuid4()) start = 'calibre-smartypants-'+unicode_type(uuid4())
stop = 'calibre-smartypants-'+str(uuid4()) stop = 'calibre-smartypants-'+unicode_type(uuid4())
html = html.replace('<!--', start) html = html.replace('<!--', start)
html = html.replace('-->', stop) html = html.replace('-->', stop)
html = preprocessor.fix_nbsp_indents(html) html = preprocessor.fix_nbsp_indents(html)
@ -152,20 +152,20 @@ class DocAnalysis(object):
maxLineLength=1900 # Discard larger than this to stay in range maxLineLength=1900 # Discard larger than this to stay in range
buckets=20 # Each line is divided into a bucket based on length buckets=20 # Each line is divided into a bucket based on length
# print "there are "+str(len(lines))+" lines" # print("there are "+unicode_type(len(lines))+" lines")
# max = 0 # max = 0
# for line in self.lines: # for line in self.lines:
# l = len(line) # l = len(line)
# if l > max: # if l > max:
# max = l # max = l
# print "max line found is "+str(max) # print("max line found is "+unicode_type(max))
# Build the line length histogram # Build the line length histogram
hRaw = [0 for i in range(0,buckets)] hRaw = [0 for i in range(0,buckets)]
for line in self.lines: for line in self.lines:
l = len(line) l = len(line)
if l > minLineLength and l < maxLineLength: if l > minLineLength and l < maxLineLength:
l = int(l/100) l = int(l // 100)
# print "adding "+str(l) # print("adding "+unicode_type(l))
hRaw[l]+=1 hRaw[l]+=1
# Normalize the histogram into percents # Normalize the histogram into percents
@ -174,8 +174,8 @@ class DocAnalysis(object):
h = [float(count)/totalLines for count in hRaw] h = [float(count)/totalLines for count in hRaw]
else: else:
h = [] h = []
# print "\nhRaw histogram lengths are: "+str(hRaw) # print("\nhRaw histogram lengths are: "+unicode_type(hRaw))
# print " percents are: "+str(h)+"\n" # print(" percents are: "+unicode_type(h)+"\n")
# Find the biggest bucket # Find the biggest bucket
maxValue = 0 maxValue = 0
@ -184,10 +184,10 @@ class DocAnalysis(object):
maxValue = h[i] maxValue = h[i]
if maxValue < percent: if maxValue < percent:
# print "Line lengths are too variable. Not unwrapping." # print("Line lengths are too variable. Not unwrapping.")
return False return False
else: else:
# print str(maxValue)+" of the lines were in one bucket" # print(unicode_type(maxValue)+" of the lines were in one bucket")
return True return True
@ -232,7 +232,7 @@ class Dehyphenator(object):
if len(firsthalf) > 4 and self.prefixes.match(firsthalf) is None: if len(firsthalf) > 4 and self.prefixes.match(firsthalf) is None:
lookupword = self.removeprefix.sub('', lookupword) lookupword = self.removeprefix.sub('', lookupword)
if self.verbose > 2: if self.verbose > 2:
self.log("lookup word is: "+str(lookupword)+", orig is: " + str(hyphenated)) self.log("lookup word is: "+lookupword+", orig is: " + hyphenated)
try: try:
searchresult = self.html.find(lookupword.lower()) searchresult = self.html.find(lookupword.lower())
except: except:
@ -240,33 +240,33 @@ class Dehyphenator(object):
if self.format == 'html_cleanup' or self.format == 'txt_cleanup': if self.format == 'html_cleanup' or self.format == 'txt_cleanup':
if self.html.find(lookupword) != -1 or searchresult != -1: if self.html.find(lookupword) != -1 or searchresult != -1:
if self.verbose > 2: if self.verbose > 2:
self.log(" Cleanup:returned dehyphenated word: " + str(dehyphenated)) self.log(" Cleanup:returned dehyphenated word: " + dehyphenated)
return dehyphenated return dehyphenated
elif self.html.find(hyphenated) != -1: elif self.html.find(hyphenated) != -1:
if self.verbose > 2: if self.verbose > 2:
self.log(" Cleanup:returned hyphenated word: " + str(hyphenated)) self.log(" Cleanup:returned hyphenated word: " + hyphenated)
return hyphenated return hyphenated
else: else:
if self.verbose > 2: if self.verbose > 2:
self.log(" Cleanup:returning original text "+str(firsthalf)+" + linefeed "+str(secondhalf)) self.log(" Cleanup:returning original text "+firsthalf+" + linefeed "+secondhalf)
return firsthalf+'\u2014'+wraptags+secondhalf return firsthalf+'\u2014'+wraptags+secondhalf
else: else:
if self.format == 'individual_words' and len(firsthalf) + len(secondhalf) <= 6: if self.format == 'individual_words' and len(firsthalf) + len(secondhalf) <= 6:
if self.verbose > 2: if self.verbose > 2:
self.log("too short, returned hyphenated word: " + str(hyphenated)) self.log("too short, returned hyphenated word: " + hyphenated)
return hyphenated return hyphenated
if len(firsthalf) <= 2 and len(secondhalf) <= 2: if len(firsthalf) <= 2 and len(secondhalf) <= 2:
if self.verbose > 2: if self.verbose > 2:
self.log("too short, returned hyphenated word: " + str(hyphenated)) self.log("too short, returned hyphenated word: " + hyphenated)
return hyphenated return hyphenated
if self.html.find(lookupword) != -1 or searchresult != -1: if self.html.find(lookupword) != -1 or searchresult != -1:
if self.verbose > 2: if self.verbose > 2:
self.log(" returned dehyphenated word: " + str(dehyphenated)) self.log(" returned dehyphenated word: " + dehyphenated)
return dehyphenated return dehyphenated
else: else:
if self.verbose > 2: if self.verbose > 2:
self.log(" returned hyphenated word: " + str(hyphenated)) self.log(" returned hyphenated word: " + hyphenated)
return hyphenated return hyphenated
def __call__(self, html, format, length=1): def __call__(self, html, format, length=1):
@ -595,7 +595,7 @@ class HTMLPreProcessor(object):
docanalysis = DocAnalysis('pdf', html) docanalysis = DocAnalysis('pdf', html)
length = docanalysis.line_length(getattr(self.extra_opts, 'unwrap_factor')) length = docanalysis.line_length(getattr(self.extra_opts, 'unwrap_factor'))
if length: if length:
# print "The pdf line length returned is " + str(length) # print("The pdf line length returned is " + unicode_type(length))
# unwrap em/en dashes # unwrap em/en dashes
end_rules.append((re.compile( end_rules.append((re.compile(
r'(?<=.{%i}[–—])\s*<p>\s*(?=[\[a-z\d])' % length), lambda match: '')) r'(?<=.{%i}[–—])\s*<p>\s*(?=[\[a-z\d])' % length), lambda match: ''))

3
src/calibre/ebooks/docx/container.py
View File

@ -19,7 +19,6 @@ from calibre.utils.localization import canonicalize_lang
from calibre.utils.logging import default_log from calibre.utils.logging import default_log
from calibre.utils.zipfile import ZipFile from calibre.utils.zipfile import ZipFile
from calibre.ebooks.oeb.parse_utils import RECOVER_PARSER from calibre.ebooks.oeb.parse_utils import RECOVER_PARSER
from polyglot.builtins import unicode_type
def fromstring(raw, parser=RECOVER_PARSER): def fromstring(raw, parser=RECOVER_PARSER):
@ -56,7 +55,7 @@ def read_doc_props(raw, mi, XPath):
desc = XPath('//dc:description')(root) desc = XPath('//dc:description')(root)
if desc: if desc:
raw = etree.tostring(desc[0], method='text', encoding=unicode_type) raw = etree.tostring(desc[0], method='text', encoding='unicode')
raw = raw.replace('_x000d_', '') # Word 2007 mangles newlines in the summary raw = raw.replace('_x000d_', '') # Word 2007 mangles newlines in the summary
mi.comments = raw.strip() mi.comments = raw.strip()

4
src/calibre/ebooks/docx/index.py
View File

@ -10,7 +10,7 @@ from operator import itemgetter
from lxml import etree from lxml import etree
from calibre.utils.icu import partition_by_first_letter, sort_key from calibre.utils.icu import partition_by_first_letter, sort_key
from polyglot.builtins import iteritems, unicode_type, filter from polyglot.builtins import iteritems, filter
def get_applicable_xe_fields(index, xe_fields, XPath, expand): def get_applicable_xe_fields(index, xe_fields, XPath, expand):
@ -246,7 +246,7 @@ def polish_index_markup(index, blocks):
a = block.xpath('descendant::a[1]') a = block.xpath('descendant::a[1]')
text = '' text = ''
if a: if a:
text = etree.tostring(a[0], method='text', with_tail=False, encoding=unicode_type).strip() text = etree.tostring(a[0], method='text', with_tail=False, encoding='unicode').strip()
if ':' in text: if ':' in text:
path_map[block] = parts = list(filter(None, (x.strip() for x in text.split(':')))) path_map[block] = parts = list(filter(None, (x.strip() for x in text.split(':'))))
if len(parts) > 1: if len(parts) > 1:

4
src/calibre/ebooks/docx/toc.py
View File

@ -12,7 +12,7 @@ from lxml.etree import tostring
from calibre.ebooks.metadata.toc import TOC from calibre.ebooks.metadata.toc import TOC
from calibre.ebooks.oeb.polish.toc import elem_to_toc_text from calibre.ebooks.oeb.polish.toc import elem_to_toc_text
from polyglot.builtins import iteritems, unicode_type, range from polyglot.builtins import iteritems, range
def from_headings(body, log, namespace): def from_headings(body, log, namespace):
@ -93,7 +93,7 @@ def link_to_txt(a, styles, object_map):
if rs.css.get('display', None) == 'none': if rs.css.get('display', None) == 'none':
a.remove(child) a.remove(child)
return tostring(a, method='text', with_tail=False, encoding=unicode_type).strip() return tostring(a, method='text', with_tail=False, encoding='unicode').strip()
def from_toc(docx, link_map, styles, object_map, log, namespace): def from_toc(docx, link_map, styles, object_map, log, namespace):

4
src/calibre/ebooks/docx/writer/styles.py
View File

@ -14,7 +14,7 @@ from lxml import etree
from calibre.ebooks import parse_css_length from calibre.ebooks import parse_css_length
from calibre.ebooks.docx.writer.utils import convert_color, int_or_zero from calibre.ebooks.docx.writer.utils import convert_color, int_or_zero
from calibre.utils.localization import lang_as_iso639_1 from calibre.utils.localization import lang_as_iso639_1
from polyglot.builtins import iteritems, unicode_type, filter from polyglot.builtins import iteritems, filter
from tinycss.css21 import CSS21Parser from tinycss.css21 import CSS21Parser
css_parser = CSS21Parser() css_parser = CSS21Parser()
@ -46,7 +46,7 @@ def bmap(x):
def is_dropcaps(html_tag, tag_style): def is_dropcaps(html_tag, tag_style):
return len(html_tag) < 2 and len(etree.tostring(html_tag, method='text', encoding=unicode_type, with_tail=False)) < 5 and tag_style['float'] == 'left' return len(html_tag) < 2 and len(etree.tostring(html_tag, method='text', encoding='unicode', with_tail=False)) < 5 and tag_style['float'] == 'left'
class CombinedStyle(object): class CombinedStyle(object):

2
src/calibre/ebooks/fb2/fb2ml.py
View File

@ -65,7 +65,7 @@ class FB2MLizer(object):
output = self.clean_text(u''.join(output)) output = self.clean_text(u''.join(output))
if self.opts.pretty_print: if self.opts.pretty_print:
return u'<?xml version="1.0" encoding="UTF-8"?>\n%s' % etree.tostring(etree.fromstring(output), encoding=unicode_type, pretty_print=True) return u'<?xml version="1.0" encoding="UTF-8"?>\n%s' % etree.tostring(etree.fromstring(output), encoding='unicode', pretty_print=True)
else: else:
return u'<?xml version="1.0" encoding="UTF-8"?>' + output return u'<?xml version="1.0" encoding="UTF-8"?>' + output

4
src/calibre/ebooks/metadata/fb2.py
View File

@ -27,7 +27,7 @@ NAMESPACES = {
'xlink' : 'http://www.w3.org/1999/xlink' 'xlink' : 'http://www.w3.org/1999/xlink'
} }
tostring = partial(etree.tostring, method='text', encoding=unicode_type) tostring = partial(etree.tostring, method='text', encoding='unicode')
def XLINK(tag): def XLINK(tag):
@ -448,7 +448,7 @@ def ensure_namespace(doc):
break break
if bare_tags: if bare_tags:
import re import re
raw = etree.tostring(doc, encoding=unicode_type) raw = etree.tostring(doc, encoding='unicode')
raw = re.sub(r'''<(description|body)\s+xmlns=['"]['"]>''', r'<\1>', raw) raw = re.sub(r'''<(description|body)\s+xmlns=['"]['"]>''', r'<\1>', raw)
doc = etree.fromstring(raw) doc = etree.fromstring(raw)
return doc return doc

8
src/calibre/ebooks/metadata/opf2.py
View File

@ -893,7 +893,7 @@ class OPF(object): # {{{
ans = None ans = None
for match in self.pubdate_path(self.metadata): for match in self.pubdate_path(self.metadata):
try: try:
val = parse_date(etree.tostring(match, encoding=unicode_type, val = parse_date(etree.tostring(match, encoding='unicode',
method='text', with_tail=False).strip()) method='text', with_tail=False).strip())
except: except:
continue continue
@ -906,7 +906,7 @@ class OPF(object): # {{{
least_val = least_elem = None least_val = least_elem = None
for match in self.pubdate_path(self.metadata): for match in self.pubdate_path(self.metadata):
try: try:
cval = parse_date(etree.tostring(match, encoding=unicode_type, cval = parse_date(etree.tostring(match, encoding='unicode',
method='text', with_tail=False).strip()) method='text', with_tail=False).strip())
except: except:
match.getparent().remove(match) match.getparent().remove(match)
@ -964,7 +964,7 @@ class OPF(object): # {{{
for attr, val in iteritems(x.attrib): for attr, val in iteritems(x.attrib):
if attr.endswith('scheme'): if attr.endswith('scheme'):
typ = icu_lower(val) typ = icu_lower(val)
val = etree.tostring(x, with_tail=False, encoding=unicode_type, val = etree.tostring(x, with_tail=False, encoding='unicode',
method='text').strip() method='text').strip()
if val and typ not in ('calibre', 'uuid'): if val and typ not in ('calibre', 'uuid'):
if typ == 'isbn' and val.lower().startswith('urn:isbn:'): if typ == 'isbn' and val.lower().startswith('urn:isbn:'):
@ -973,7 +973,7 @@ class OPF(object): # {{{
found_scheme = True found_scheme = True
break break
if not found_scheme: if not found_scheme:
val = etree.tostring(x, with_tail=False, encoding=unicode_type, val = etree.tostring(x, with_tail=False, encoding='unicode',
method='text').strip() method='text').strip()
if val.lower().startswith('urn:isbn:'): if val.lower().startswith('urn:isbn:'):
val = check_isbn(val.split(':')[-1]) val = check_isbn(val.split(':')[-1])

2
src/calibre/ebooks/metadata/toc.py
View File

@ -210,7 +210,7 @@ class TOC(list):
text = u'' text = u''
for txt in txt_path(nl): for txt in txt_path(nl):
text += etree.tostring(txt, method='text', text += etree.tostring(txt, method='text',
encoding=unicode_type, with_tail=False) encoding='unicode', with_tail=False)
content = content_path(np) content = content_path(np)
if content and text: if content and text:
content = content[0] content = content[0]

2
src/calibre/ebooks/mobi/writer8/main.py
View File

@ -235,7 +235,7 @@ class KF8Writer(object):
root = self.data(item) root = self.data(item)
for svg in XPath('//svg:svg')(root): for svg in XPath('//svg:svg')(root):
raw = etree.tostring(svg, encoding=unicode_type, with_tail=False) raw = etree.tostring(svg, encoding='unicode', with_tail=False)
idx = len(self.flows) idx = len(self.flows)
self.flows.append(raw) self.flows.append(raw)
p = svg.getparent() p = svg.getparent()

2
src/calibre/ebooks/oeb/base.py
View File

@ -400,7 +400,7 @@ def xml2str(root, pretty_print=False, strip_comments=False, with_tail=True):
def xml2text(elem, pretty_print=False): def xml2text(elem, pretty_print=False):
return etree.tostring(elem, method='text', encoding=unicode_type, with_tail=False, pretty_print=pretty_print) return etree.tostring(elem, method='text', encoding='unicode', with_tail=False, pretty_print=pretty_print)
def escape_cdata(root): def escape_cdata(root):

4
src/calibre/ebooks/oeb/parse_utils.py
View File

@ -112,7 +112,7 @@ def _html4_parse(data):
for elem in data.iter(tag=etree.Comment): for elem in data.iter(tag=etree.Comment):
if elem.text: if elem.text:
elem.text = elem.text.strip('-') elem.text = elem.text.strip('-')
data = etree.tostring(data, encoding=unicode_type) data = etree.tostring(data, encoding='unicode')
# Setting huge_tree=True causes crashes in windows with large files # Setting huge_tree=True causes crashes in windows with large files
parser = etree.XMLParser(no_network=True) parser = etree.XMLParser(no_network=True)
@ -273,7 +273,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
if not namespace(data.tag): if not namespace(data.tag):
log.warn('Forcing', filename, 'into XHTML namespace') log.warn('Forcing', filename, 'into XHTML namespace')
data.attrib['xmlns'] = XHTML_NS data.attrib['xmlns'] = XHTML_NS
data = etree.tostring(data, encoding=unicode_type) data = etree.tostring(data, encoding='unicode')
try: try:
data = etree.fromstring(data, parser=parser) data = etree.fromstring(data, parser=parser)

2
src/calibre/ebooks/oeb/polish/stats.py
View File

@ -120,7 +120,7 @@ def get_element_text(elem, resolve_property, resolve_pseudo_property, capitalize
if before: if before:
ans.append(before) ans.append(before)
if for_pseudo is not None: if for_pseudo is not None:
ans.append(tostring(elem, method='text', encoding=unicode_type, with_tail=False)) ans.append(tostring(elem, method='text', encoding='unicode', with_tail=False))
else: else:
if elem.text: if elem.text:
ans.append(elem.text) ans.append(elem.text)

8
src/calibre/ebooks/oeb/polish/toc.py
View File

@ -142,7 +142,7 @@ def add_from_navpoint(container, navpoint, parent, ncx_name):
text = '' text = ''
for txt in child_xpath(nl, 'text'): for txt in child_xpath(nl, 'text'):
text += etree.tostring(txt, method='text', text += etree.tostring(txt, method='text',
encoding=unicode_type, with_tail=False) encoding='unicode', with_tail=False)
content = child_xpath(navpoint, 'content') content = child_xpath(navpoint, 'content')
if content: if content:
content = content[0] content = content[0]
@ -190,7 +190,7 @@ def parse_ncx(container, ncx_name):
def add_from_li(container, li, parent, nav_name): def add_from_li(container, li, parent, nav_name):
dest = frag = text = None dest = frag = text = None
for x in li.iterchildren(XHTML('a'), XHTML('span')): for x in li.iterchildren(XHTML('a'), XHTML('span')):
text = etree.tostring(x, method='text', encoding=unicode_type, with_tail=False).strip() or ' '.join(x.xpath('descendant-or-self::*/@title')).strip() text = etree.tostring(x, method='text', encoding='unicode', with_tail=False).strip() or ' '.join(x.xpath('descendant-or-self::*/@title')).strip()
href = x.get('href') href = x.get('href')
if href: if href:
dest = nav_name if href.startswith('#') else container.href_to_name(href, base=nav_name) dest = nav_name if href.startswith('#') else container.href_to_name(href, base=nav_name)
@ -225,7 +225,7 @@ def parse_nav(container, nav_name):
if ol is not None: if ol is not None:
process_nav_node(container, ol, toc_root, nav_name) process_nav_node(container, ol, toc_root, nav_name)
for h in nav.iterchildren(*map(XHTML, 'h1 h2 h3 h4 h5 h6'.split())): for h in nav.iterchildren(*map(XHTML, 'h1 h2 h3 h4 h5 h6'.split())):
text = etree.tostring(h, method='text', encoding=unicode_type, with_tail=False) or h.get('title') text = etree.tostring(h, method='text', encoding='unicode', with_tail=False) or h.get('title')
if text: if text:
toc_root.toc_title = text toc_root.toc_title = text
break break
@ -323,7 +323,7 @@ def get_nav_landmarks(container):
for a in li.iterdescendants(XHTML('a')): for a in li.iterdescendants(XHTML('a')):
href, rtype = a.get('href'), a.get(et) href, rtype = a.get('href'), a.get(et)
if href: if href:
title = etree.tostring(a, method='text', encoding=unicode_type, with_tail=False).strip() title = etree.tostring(a, method='text', encoding='unicode', with_tail=False).strip()
href, frag = href.partition('#')[::2] href, frag = href.partition('#')[::2]
name = container.href_to_name(href, nav) name = container.href_to_name(href, nav)
if container.has_name(name): if container.has_name(name):

2
src/calibre/ebooks/oeb/reader.py
View File

@ -428,7 +428,7 @@ class OEBReader(object):
'descendant::calibre:meta[@name = "description"]') 'descendant::calibre:meta[@name = "description"]')
if descriptionElement: if descriptionElement:
description = etree.tostring(descriptionElement[0], description = etree.tostring(descriptionElement[0],
method='text', encoding=unicode_type).strip() method='text', encoding='unicode').strip()
if not description: if not description:
description = None description = None
else: else:

4
src/calibre/ebooks/oeb/transforms/metadata.py
View File

@ -9,7 +9,7 @@ __docformat__ = 'restructuredtext en'
import os, re import os, re
from calibre.utils.date import isoformat, now from calibre.utils.date import isoformat, now
from calibre import guess_type from calibre import guess_type
from polyglot.builtins import iteritems, unicode_type, filter from polyglot.builtins import iteritems, filter
filter filter
@ -206,7 +206,7 @@ class MergeMetadata(object):
for item in affected_items: for item in affected_items:
body = XPath('//h:body')(item.data) body = XPath('//h:body')(item.data)
if body: if body:
text = etree.tostring(body[0], method='text', encoding=unicode_type) text = etree.tostring(body[0], method='text', encoding='unicode')
else: else:
text = '' text = ''
text = re.sub(r'\s+', '', text) text = re.sub(r'\s+', '', text)

4
src/calibre/ebooks/oeb/transforms/split.py
View File

@ -20,7 +20,7 @@ from calibre.ebooks.epub import rules
from calibre.ebooks.oeb.base import (OEB_STYLES, XPNSMAP as NAMESPACES, from calibre.ebooks.oeb.base import (OEB_STYLES, XPNSMAP as NAMESPACES,
urldefrag, rewrite_links, urlunquote, XHTML, urlnormalize) urldefrag, rewrite_links, urlunquote, XHTML, urlnormalize)
from calibre.ebooks.oeb.polish.split import do_split from calibre.ebooks.oeb.polish.split import do_split
from polyglot.builtins import iteritems, unicode_type, range, map from polyglot.builtins import iteritems, range, map
from css_selectors import Select, SelectorError from css_selectors import Select, SelectorError
XPath = functools.partial(_XPath, namespaces=NAMESPACES) XPath = functools.partial(_XPath, namespaces=NAMESPACES)
@ -295,7 +295,7 @@ class FlowSplitter(object):
if body is None: if body is None:
return False return False
txt = re.sub(u'\\s+|\\xa0', '', txt = re.sub(u'\\s+|\\xa0', '',
etree.tostring(body, method='text', encoding=unicode_type)) etree.tostring(body, method='text', encoding='unicode'))
if len(txt) > 1: if len(txt) > 1:
return False return False
for img in root.xpath('//h:img', namespaces=NAMESPACES): for img in root.xpath('//h:img', namespaces=NAMESPACES):

6
src/calibre/ebooks/pdf/reflow.py
View File

@ -11,7 +11,7 @@ from itertools import count
from lxml import etree from lxml import etree
from polyglot.builtins import unicode_type, range, map from polyglot.builtins import range, map
class Font(object): class Font(object):
@ -76,10 +76,10 @@ class Text(Element):
text.tail = '' text.tail = ''
self.text_as_string = etree.tostring(text, method='text', self.text_as_string = etree.tostring(text, method='text',
encoding=unicode_type) encoding='unicode')
self.raw = text.text if text.text else u'' self.raw = text.text if text.text else u''
for x in text.iterchildren(): for x in text.iterchildren():
self.raw += etree.tostring(x, method='xml', encoding=unicode_type) self.raw += etree.tostring(x, method='xml', encoding='unicode')
self.average_character_width = self.width/len(self.text_as_string) self.average_character_width = self.width/len(self.text_as_string)
def coalesce(self, other, page_number): def coalesce(self, other, page_number):

2
src/calibre/ebooks/pml/pmlml.py
View File

@ -135,7 +135,7 @@ class PMLMLizer(object):
text = [u''] text = [u'']
for item in self.oeb_book.spine: for item in self.oeb_book.spine:
self.log.debug('Converting %s to PML markup...' % item.href) self.log.debug('Converting %s to PML markup...' % item.href)
content = unicode_type(etree.tostring(item.data, encoding=unicode_type)) content = etree.tostring(item.data, encoding='unicode')
content = self.prepare_text(content) content = self.prepare_text(content)
content = etree.fromstring(content) content = etree.fromstring(content)
stylizer = Stylizer(content, item.href, self.oeb_book, self.opts, self.opts.output_profile) stylizer = Stylizer(content, item.href, self.oeb_book, self.opts, self.opts.output_profile)

2
src/calibre/ebooks/rtf/rtfml.py
View File

@ -120,7 +120,7 @@ class RTFMLizer(object):
self.log.debug('Converting %s to RTF markup...' % item.href) self.log.debug('Converting %s to RTF markup...' % item.href)
# Removing comments is needed as comments with -- inside them can # Removing comments is needed as comments with -- inside them can
# cause fromstring() to fail # cause fromstring() to fail
content = re.sub(u'<!--.*?-->', u'', etree.tostring(item.data, encoding=unicode_type), flags=re.DOTALL) content = re.sub(u'<!--.*?-->', u'', etree.tostring(item.data, encoding='unicode'), flags=re.DOTALL)
content = self.remove_newlines(content) content = self.remove_newlines(content)
content = self.remove_tabs(content) content = self.remove_tabs(content)
content = etree.fromstring(content) content = etree.fromstring(content)

2
src/calibre/ebooks/snb/snbml.py
View File

@ -85,7 +85,7 @@ class SNBMLizer(object):
from calibre.ebooks.oeb.stylizer import Stylizer from calibre.ebooks.oeb.stylizer import Stylizer
output = [u''] output = [u'']
stylizer = Stylizer(self.item.data, self.item.href, self.oeb_book, self.opts, self.opts.output_profile) stylizer = Stylizer(self.item.data, self.item.href, self.oeb_book, self.opts, self.opts.output_profile)
content = unicode_type(etree.tostring(self.item.data.find(XHTML('body')), encoding=unicode_type)) content = etree.tostring(self.item.data.find(XHTML('body')), encoding='unicode')
# content = self.remove_newlines(content) # content = self.remove_newlines(content)
trees = {} trees = {}
for subitem, subtitle in self.subitems: for subitem, subtitle in self.subitems:

4
src/calibre/ebooks/txt/txtml.py
View File

@ -12,7 +12,7 @@ Transform OEB content into plain text
import re import re
from lxml import etree from lxml import etree
from polyglot.builtins import unicode_type, string_or_bytes from polyglot.builtins import string_or_bytes
BLOCK_TAGS = [ BLOCK_TAGS = [
@ -74,7 +74,7 @@ class TXTMLizer(object):
for x in item.data.iterdescendants(etree.Comment): for x in item.data.iterdescendants(etree.Comment):
if x.text and '--' in x.text: if x.text and '--' in x.text:
x.text = x.text.replace('--', '__') x.text = x.text.replace('--', '__')
content = unicode_type(etree.tostring(item.data, encoding=unicode_type)) content = etree.tostring(item.data, encoding='unicode')
content = self.remove_newlines(content) content = self.remove_newlines(content)
content = etree.fromstring(content) content = etree.fromstring(content)
stylizer = Stylizer(content, item.href, self.oeb_book, self.opts, self.opts.output_profile) stylizer = Stylizer(content, item.href, self.oeb_book, self.opts, self.opts.output_profile)

2
src/calibre/gui2/comments_editor.py
View File

@ -360,7 +360,7 @@ class EditorWidget(QWebView, LineEditECM): # {{{
for body in root.xpath('//body'): for body in root.xpath('//body'):
if body.text: if body.text:
elems.append(body.text) elems.append(body.text)
elems += [html.tostring(x, encoding=unicode_type) for x in body if elems += [html.tostring(x, encoding='unicode') for x in body if
x.tag not in ('script', 'style')] x.tag not in ('script', 'style')]
if len(elems) > 1: if len(elems) > 1:

2
src/calibre/gui2/dialogs/plugin_updater.py
View File

@ -840,7 +840,7 @@ class PluginUpdaterDialog(SizePersistedDialog):
continue continue
if heading_node.text_content().lower().find('version history') != -1: if heading_node.text_content().lower().find('version history') != -1:
div_node = spoiler_node.xpath('div')[0] div_node = spoiler_node.xpath('div')[0]
text = html.tostring(div_node, method='html', encoding=unicode_type) text = html.tostring(div_node, method='html', encoding='unicode')
return re.sub(r'<div\s.*?>', '<div>', text) return re.sub(r'<div\s.*?>', '<div>', text)
except: except:
if DEBUG: if DEBUG:

2
src/calibre/gui2/tweak_book/diff/view.py
View File

@ -65,7 +65,7 @@ def beautify_text(raw, syntax):
else: else:
root = parse(raw, line_numbers=False) root = parse(raw, line_numbers=False)
pretty_html_tree(None, root) pretty_html_tree(None, root)
return etree.tostring(root, encoding=unicode_type) return etree.tostring(root, encoding='unicode')
class LineNumberMap(dict): # {{{ class LineNumberMap(dict): # {{{

4
src/calibre/gui2/tweak_book/text_search.py
View File

@ -16,7 +16,7 @@ from calibre.gui2.tweak_book import tprefs, editors, current_container
from calibre.gui2.tweak_book.search import get_search_regex, InvalidRegex, initialize_search_request from calibre.gui2.tweak_book.search import get_search_regex, InvalidRegex, initialize_search_request
from calibre.gui2.tweak_book.widgets import BusyCursor from calibre.gui2.tweak_book.widgets import BusyCursor
from calibre.gui2.widgets2 import HistoryComboBox from calibre.gui2.widgets2 import HistoryComboBox
from polyglot.builtins import iteritems, unicode_type, error_message from polyglot.builtins import iteritems, error_message
# UI {{{ # UI {{{
@ -179,7 +179,7 @@ def run_text_search(search, current_editor, current_editor_name, searchable_name
else: else:
root = current_container().parsed(fname) root = current_container().parsed(fname)
if hasattr(root, 'xpath'): if hasattr(root, 'xpath'):
raw = tostring(root, method='text', encoding=unicode_type, with_tail=True) raw = tostring(root, method='text', encoding='unicode', with_tail=True)
else: else:
raw = current_container().raw_data(fname) raw = current_container().raw_data(fname)
if pat.search(raw) is not None: if pat.search(raw) is not None:

6
src/calibre/utils/open_with/osx.py
View File

@ -10,7 +10,7 @@ from collections import defaultdict
from calibre.ptempfile import TemporaryDirectory from calibre.ptempfile import TemporaryDirectory
from calibre.utils.icu import numeric_sort_key from calibre.utils.icu import numeric_sort_key
from polyglot.builtins import iteritems, unicode_type, string_or_bytes from polyglot.builtins import iteritems, string_or_bytes
from polyglot.plistlib import loads from polyglot.plistlib import loads
application_locations = ('/Applications', '~/Applications', '~/Desktop') application_locations = ('/Applications', '~/Applications', '~/Desktop')
@ -30,8 +30,8 @@ def generate_public_uti_map():
for table in tables: for table in tables:
for tr in table.xpath('descendant::tr')[1:]: for tr in table.xpath('descendant::tr')[1:]:
td = tr.xpath('descendant::td') td = tr.xpath('descendant::td')
identifier = etree.tostring(td[0], method='text', encoding=unicode_type).strip() identifier = etree.tostring(td[0], method='text', encoding='unicode').strip()
tags = etree.tostring(td[2], method='text', encoding=unicode_type).strip() tags = etree.tostring(td[2], method='text', encoding='unicode').strip()
identifier = identifier.split()[0].replace('\u200b', '') identifier = identifier.split()[0].replace('\u200b', '')
exts = [x.strip()[1:].lower() for x in tags.split(',') if x.strip().startswith('.')] exts = [x.strip()[1:].lower() for x in tags.split(',') if x.strip().startswith('.')]
for ext in exts: for ext in exts:

2
src/calibre/web/feeds/__init__.py
View File

@ -43,7 +43,7 @@ class Article(object):
if summary and '<' in summary: if summary and '<' in summary:
try: try:
s = html.fragment_fromstring(summary, create_parent=True) s = html.fragment_fromstring(summary, create_parent=True)
summary = html.tostring(s, method='text', encoding=unicode_type) summary = html.tostring(s, method='text', encoding='unicode')
except: except:
print('Failed to process article summary, deleting:') print('Failed to process article summary, deleting:')
print(summary.encode('utf-8')) print(summary.encode('utf-8'))

4
src/calibre/web/feeds/news.py
View File

@ -743,7 +743,7 @@ class BasicNewsRecipe(Recipe):
heading.text = extracted_title heading.text = extracted_title
body.insert(0, heading) body.insert(0, heading)
raw_html = tostring(root, encoding=unicode_type) raw_html = tostring(root, encoding='unicode')
return raw_html return raw_html
@ -1667,7 +1667,7 @@ class BasicNewsRecipe(Recipe):
return tag return tag
if callable(getattr(tag, 'xpath', None)) and not hasattr(tag, 'contents'): # a lxml tag if callable(getattr(tag, 'xpath', None)) and not hasattr(tag, 'contents'): # a lxml tag
from lxml.etree import tostring from lxml.etree import tostring
ans = tostring(tag, method='text', encoding=unicode_type, with_tail=False) ans = tostring(tag, method='text', encoding='unicode', with_tail=False)
else: else:
strings = [] strings = []
for item in tag.contents: for item in tag.contents: