Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Setting EPUB metadata: Fix date format. Fix language being overwritten by und when unspecified. Fix empty ISBN identifier being created

Browse Source
This commit is contained in:
Kovid Goyal 2010-10-18 21:25:58 -06:00
parent 1ebee86c83
commit 199d870b19
2 changed files with 20 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
resources/recipes/theeconomictimes_india.recipe
View File

@ -19,18 +19,18 @@ class TheEconomicTimes(BasicNewsRecipe):
simultaneous_downloads = 1 simultaneous_downloads = 1
encoding = 'utf-8' encoding = 'utf-8'
language = 'en_IN' language = 'en_IN'
publication_type = 'newspaper' publication_type = 'newspaper'
masthead_url = 'http://economictimes.indiatimes.com/photo/2676871.cms' masthead_url = 'http://economictimes.indiatimes.com/photo/2676871.cms'
extra_css = """ body{font-family: Arial,Helvetica,sans-serif} extra_css = """ body{font-family: Arial,Helvetica,sans-serif}
.heading1{font-size: xx-large; font-weight: bold} """ .heading1{font-size: xx-large; font-weight: bold} """
conversion_options = { conversion_options = {
'comment' : description 'comment' : description
, 'tags' : category , 'tags' : category
, 'publisher' : publisher , 'publisher' : publisher
, 'language' : language , 'language' : language
} }
keep_only_tags = [dict(attrs={'class':['heading1','headingnext','Normal']})] keep_only_tags = [dict(attrs={'class':['heading1','headingnext','Normal']})]
remove_tags = [dict(name=['object','link','embed','iframe','base','table','meta'])] remove_tags = [dict(name=['object','link','embed','iframe','base','table','meta'])]
@ -48,5 +48,5 @@ class TheEconomicTimes(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
return self.adeify_images(soup) return self.adeify_images(soup)

25
src/calibre/ebooks/metadata/opf2.py
View File

@ -382,11 +382,13 @@ class Guide(ResourceCollection): # {{{
class MetadataField(object): class MetadataField(object):
def __init__(self, name, is_dc=True, formatter=None, none_is=None): def __init__(self, name, is_dc=True, formatter=None, none_is=None,
renderer=lambda x: unicode(x)):
self.name = name self.name = name
self.is_dc = is_dc self.is_dc = is_dc
self.formatter = formatter self.formatter = formatter
self.none_is = none_is self.none_is = none_is
self.renderer = renderer
def __real_get__(self, obj, type=None): def __real_get__(self, obj, type=None):
ans = obj.get_metadata_element(self.name) ans = obj.get_metadata_element(self.name)
@ -418,7 +420,7 @@ class MetadataField(object):
return return
if elem is None: if elem is None:
elem = obj.create_metadata_element(self.name, is_dc=self.is_dc) elem = obj.create_metadata_element(self.name, is_dc=self.is_dc)
obj.set_text(elem, unicode(val)) obj.set_text(elem, self.renderer(val))
def serialize_user_metadata(metadata_elem, all_user_metadata, tail='\n'+(' '*8)): def serialize_user_metadata(metadata_elem, all_user_metadata, tail='\n'+(' '*8)):
@ -489,10 +491,11 @@ class OPF(object): # {{{
series = MetadataField('series', is_dc=False) series = MetadataField('series', is_dc=False)
series_index = MetadataField('series_index', is_dc=False, formatter=float, none_is=1) series_index = MetadataField('series_index', is_dc=False, formatter=float, none_is=1)
rating = MetadataField('rating', is_dc=False, formatter=int) rating = MetadataField('rating', is_dc=False, formatter=int)
pubdate = MetadataField('date', formatter=parse_date) pubdate = MetadataField('date', formatter=parse_date,
renderer=isoformat)
publication_type = MetadataField('publication_type', is_dc=False) publication_type = MetadataField('publication_type', is_dc=False)
timestamp = MetadataField('timestamp', is_dc=False, timestamp = MetadataField('timestamp', is_dc=False,
formatter=parse_date) formatter=parse_date, renderer=isoformat)
def __init__(self, stream, basedir=os.getcwdu(), unquote_urls=True, def __init__(self, stream, basedir=os.getcwdu(), unquote_urls=True,
@ -826,11 +829,10 @@ class OPF(object): # {{{
def fset(self, val): def fset(self, val):
matches = self.isbn_path(self.metadata) matches = self.isbn_path(self.metadata)
if val is None: if not val:
if matches: for x in matches:
for x in matches: x.getparent().remove(x)
x.getparent().remove(x) return
return
if not matches: if not matches:
attrib = {'{%s}scheme'%self.NAMESPACES['opf']: 'ISBN'} attrib = {'{%s}scheme'%self.NAMESPACES['opf']: 'ISBN'}
matches = [self.create_metadata_element('identifier', matches = [self.create_metadata_element('identifier',
@ -987,11 +989,14 @@ class OPF(object): # {{{
def smart_update(self, mi, replace_metadata=False): def smart_update(self, mi, replace_metadata=False):
for attr in ('title', 'authors', 'author_sort', 'title_sort', for attr in ('title', 'authors', 'author_sort', 'title_sort',
'publisher', 'series', 'series_index', 'rating', 'publisher', 'series', 'series_index', 'rating',
'isbn', 'language', 'tags', 'category', 'comments', 'isbn', 'tags', 'category', 'comments',
'pubdate'): 'pubdate'):
val = getattr(mi, attr, None) val = getattr(mi, attr, None)
if val is not None and val != [] and val != (None, None): if val is not None and val != [] and val != (None, None):
setattr(self, attr, val) setattr(self, attr, val)
lang = getattr(mi, 'language', None)
if lang and lang != 'und':
self.language = lang
temp = self.to_book_metadata() temp = self.to_book_metadata()
temp.smart_update(mi, replace_metadata=replace_metadata) temp.smart_update(mi, replace_metadata=replace_metadata)
self._user_metadata_ = temp.get_all_user_metadata(True) self._user_metadata_ = temp.get_all_user_metadata(True)