mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
Support subtitle in Douban metadata plugin
This commit is contained in:
Li Fanxi
parent
dedbc1ddb3
commit
d1a6113a8a
@ -1,5 +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 absolute_import, division, print_function, unicode_literals
|
from __future__ import absolute_import, division, print_function, unicode_literals
|
||||||
|
|
||||||
__license__ = 'GPL v3'
|
__license__ = 'GPL v3'
|
||||||
@ -15,7 +16,7 @@ except ImportError:
|
|||||||
|
|
||||||
|
|
||||||
from calibre.ebooks.metadata import check_isbn
|
from calibre.ebooks.metadata import check_isbn
|
||||||
from calibre.ebooks.metadata.sources.base import Source
|
from calibre.ebooks.metadata.sources.base import Option, Source
|
||||||
from calibre.ebooks.metadata.book.base import Metadata
|
from calibre.ebooks.metadata.book.base import Metadata
|
||||||
from calibre import as_unicode
|
from calibre import as_unicode
|
||||||
|
|
||||||
@ -44,112 +45,6 @@ def get_details(browser, url, timeout): # {{{
|
|||||||
# }}}
|
# }}}
|
||||||
|
|
||||||
|
|
||||||
def to_metadata(browser, log, entry_, timeout): # {{{
|
|
||||||
from lxml import etree
|
|
||||||
from calibre.ebooks.chardet import xml_to_unicode
|
|
||||||
from calibre.utils.date import parse_date, utcnow
|
|
||||||
from calibre.utils.cleantext import clean_ascii_chars
|
|
||||||
|
|
||||||
XPath = partial(etree.XPath, namespaces=NAMESPACES)
|
|
||||||
entry = XPath('//atom:entry')
|
|
||||||
entry_id = XPath('descendant::atom:id')
|
|
||||||
title = XPath('descendant::atom:title')
|
|
||||||
description = XPath('descendant::atom:summary')
|
|
||||||
publisher = XPath("descendant::db:attribute[@name='publisher']")
|
|
||||||
isbn = XPath("descendant::db:attribute[@name='isbn13']")
|
|
||||||
date = XPath("descendant::db:attribute[@name='pubdate']")
|
|
||||||
creator = XPath("descendant::db:attribute[@name='author']")
|
|
||||||
booktag = XPath("descendant::db:tag/attribute::name")
|
|
||||||
rating = XPath("descendant::gd:rating/attribute::average")
|
|
||||||
cover_url = XPath("descendant::atom:link[@rel='image']/attribute::href")
|
|
||||||
|
|
||||||
def get_text(extra, x):
|
|
||||||
try:
|
|
||||||
ans = x(extra)
|
|
||||||
if ans:
|
|
||||||
ans = ans[0].text
|
|
||||||
if ans and ans.strip():
|
|
||||||
return ans.strip()
|
|
||||||
except:
|
|
||||||
log.exception('Programming error:')
|
|
||||||
return None
|
|
||||||
|
|
||||||
id_url = entry_id(entry_)[0].text.replace('http://', 'https://')
|
|
||||||
douban_id = id_url.split('/')[-1]
|
|
||||||
title_ = ': '.join([x.text for x in title(entry_)]).strip()
|
|
||||||
authors = [x.text.strip() for x in creator(entry_) if x.text]
|
|
||||||
if not authors:
|
|
||||||
authors = [_('Unknown')]
|
|
||||||
if not id_url or not title:
|
|
||||||
# Silently discard this entry
|
|
||||||
return None
|
|
||||||
|
|
||||||
mi = Metadata(title_, authors)
|
|
||||||
mi.identifiers = {'douban':douban_id}
|
|
||||||
try:
|
|
||||||
raw = get_details(browser, id_url, timeout)
|
|
||||||
feed = etree.fromstring(xml_to_unicode(clean_ascii_chars(raw),
|
|
||||||
strip_encoding_pats=True)[0])
|
|
||||||
extra = entry(feed)[0]
|
|
||||||
except:
|
|
||||||
log.exception('Failed to get additional details for', mi.title)
|
|
||||||
return mi
|
|
||||||
mi.comments = get_text(extra, description)
|
|
||||||
mi.publisher = get_text(extra, publisher)
|
|
||||||
|
|
||||||
# ISBN
|
|
||||||
isbns = []
|
|
||||||
for x in [t.text for t in isbn(extra)]:
|
|
||||||
if check_isbn(x):
|
|
||||||
isbns.append(x)
|
|
||||||
if isbns:
|
|
||||||
mi.isbn = sorted(isbns, key=len)[-1]
|
|
||||||
mi.all_isbns = isbns
|
|
||||||
|
|
||||||
# Tags
|
|
||||||
try:
|
|
||||||
btags = [x for x in booktag(extra) if x]
|
|
||||||
tags = []
|
|
||||||
for t in btags:
|
|
||||||
atags = [y.strip() for y in t.split('/')]
|
|
||||||
for tag in atags:
|
|
||||||
if tag not in tags:
|
|
||||||
tags.append(tag)
|
|
||||||
except:
|
|
||||||
log.exception('Failed to parse tags:')
|
|
||||||
tags = []
|
|
||||||
if tags:
|
|
||||||
mi.tags = [x.replace(',', ';') for x in tags]
|
|
||||||
|
|
||||||
# pubdate
|
|
||||||
pubdate = get_text(extra, date)
|
|
||||||
if pubdate:
|
|
||||||
try:
|
|
||||||
default = utcnow().replace(day=15)
|
|
||||||
mi.pubdate = parse_date(pubdate, assume_utc=True, default=default)
|
|
||||||
except:
|
|
||||||
log.error('Failed to parse pubdate %r'%pubdate)
|
|
||||||
|
|
||||||
# Ratings
|
|
||||||
if rating(extra):
|
|
||||||
try:
|
|
||||||
mi.rating = float(rating(extra)[0]) / 2.0
|
|
||||||
except:
|
|
||||||
log.exception('Failed to parse rating')
|
|
||||||
mi.rating = 0
|
|
||||||
|
|
||||||
# Cover
|
|
||||||
mi.has_douban_cover = None
|
|
||||||
u = cover_url(extra)
|
|
||||||
if u:
|
|
||||||
u = u[0].replace('/spic/', '/lpic/')
|
|
||||||
# If URL contains "book-default", the book doesn't have a cover
|
|
||||||
if u.find('book-default') == -1:
|
|
||||||
mi.has_douban_cover = u
|
|
||||||
return mi
|
|
||||||
# }}}
|
|
||||||
|
|
||||||
|
|
||||||
class Douban(Source):
|
class Douban(Source):
|
||||||
|
|
||||||
name = 'Douban Books'
|
name = 'Douban Books'
|
||||||
@ -170,6 +65,121 @@ class Douban(Source):
|
|||||||
DOUBAN_API_KEY = '0bd1672394eb1ebf2374356abec15c3d'
|
DOUBAN_API_KEY = '0bd1672394eb1ebf2374356abec15c3d'
|
||||||
DOUBAN_BOOK_URL = 'https://book.douban.com/subject/%s/'
|
DOUBAN_BOOK_URL = 'https://book.douban.com/subject/%s/'
|
||||||
|
|
||||||
|
options = (
|
||||||
|
Option('include_subtitle_in_title', 'bool', True, _('Include subtitle in book title:'),
|
||||||
|
_('Whether to append subtitle in the book title.')),
|
||||||
|
)
|
||||||
|
|
||||||
|
def to_metadata(self, browser, log, entry_, timeout): # {{{
|
||||||
|
from lxml import etree
|
||||||
|
from calibre.ebooks.chardet import xml_to_unicode
|
||||||
|
from calibre.utils.date import parse_date, utcnow
|
||||||
|
from calibre.utils.cleantext import clean_ascii_chars
|
||||||
|
|
||||||
|
XPath = partial(etree.XPath, namespaces=NAMESPACES)
|
||||||
|
entry = XPath('//atom:entry')
|
||||||
|
entry_id = XPath('descendant::atom:id')
|
||||||
|
title = XPath('descendant::atom:title')
|
||||||
|
description = XPath('descendant::atom:summary')
|
||||||
|
subtitle = XPath("descendant::db:attribute[@name='subtitle']")
|
||||||
|
publisher = XPath("descendant::db:attribute[@name='publisher']")
|
||||||
|
isbn = XPath("descendant::db:attribute[@name='isbn13']")
|
||||||
|
date = XPath("descendant::db:attribute[@name='pubdate']")
|
||||||
|
creator = XPath("descendant::db:attribute[@name='author']")
|
||||||
|
booktag = XPath("descendant::db:tag/attribute::name")
|
||||||
|
rating = XPath("descendant::gd:rating/attribute::average")
|
||||||
|
cover_url = XPath("descendant::atom:link[@rel='image']/attribute::href")
|
||||||
|
|
||||||
|
def get_text(extra, x):
|
||||||
|
try:
|
||||||
|
ans = x(extra)
|
||||||
|
if ans:
|
||||||
|
ans = ans[0].text
|
||||||
|
if ans and ans.strip():
|
||||||
|
return ans.strip()
|
||||||
|
except:
|
||||||
|
log.exception('Programming error:')
|
||||||
|
return None
|
||||||
|
|
||||||
|
id_url = entry_id(entry_)[0].text.replace('http://', 'https://')
|
||||||
|
douban_id = id_url.split('/')[-1]
|
||||||
|
title_ = ': '.join([x.text for x in title(entry_)]).strip()
|
||||||
|
subtitle = ': '.join([x.text for x in subtitle(entry_)]).strip()
|
||||||
|
if self.prefs['include_subtitle_in_title'] and len(subtitle) > 0:
|
||||||
|
title_ = title_ + ' - ' + subtitle
|
||||||
|
authors = [x.text.strip() for x in creator(entry_) if x.text]
|
||||||
|
if not authors:
|
||||||
|
authors = [_('Unknown')]
|
||||||
|
if not id_url or not title:
|
||||||
|
# Silently discard this entry
|
||||||
|
return None
|
||||||
|
|
||||||
|
mi = Metadata(title_, authors)
|
||||||
|
mi.identifiers = {'douban':douban_id}
|
||||||
|
try:
|
||||||
|
log.info(id_url)
|
||||||
|
raw = get_details(browser, id_url, timeout)
|
||||||
|
feed = etree.fromstring(xml_to_unicode(clean_ascii_chars(raw),
|
||||||
|
strip_encoding_pats=True)[0])
|
||||||
|
extra = entry(feed)[0]
|
||||||
|
except:
|
||||||
|
log.exception('Failed to get additional details for', mi.title)
|
||||||
|
return mi
|
||||||
|
mi.comments = get_text(extra, description)
|
||||||
|
mi.publisher = get_text(extra, publisher)
|
||||||
|
|
||||||
|
# ISBN
|
||||||
|
isbns = []
|
||||||
|
for x in [t.text for t in isbn(extra)]:
|
||||||
|
if check_isbn(x):
|
||||||
|
isbns.append(x)
|
||||||
|
if isbns:
|
||||||
|
mi.isbn = sorted(isbns, key=len)[-1]
|
||||||
|
mi.all_isbns = isbns
|
||||||
|
|
||||||
|
# Tags
|
||||||
|
try:
|
||||||
|
btags = [x for x in booktag(extra) if x]
|
||||||
|
tags = []
|
||||||
|
for t in btags:
|
||||||
|
atags = [y.strip() for y in t.split('/')]
|
||||||
|
for tag in atags:
|
||||||
|
if tag not in tags:
|
||||||
|
tags.append(tag)
|
||||||
|
except:
|
||||||
|
log.exception('Failed to parse tags:')
|
||||||
|
tags = []
|
||||||
|
if tags:
|
||||||
|
mi.tags = [x.replace(',', ';') for x in tags]
|
||||||
|
|
||||||
|
# pubdate
|
||||||
|
pubdate = get_text(extra, date)
|
||||||
|
if pubdate:
|
||||||
|
try:
|
||||||
|
default = utcnow().replace(day=15)
|
||||||
|
mi.pubdate = parse_date(pubdate, assume_utc=True, default=default)
|
||||||
|
except:
|
||||||
|
log.error('Failed to parse pubdate %r'%pubdate)
|
||||||
|
|
||||||
|
# Ratings
|
||||||
|
if rating(extra):
|
||||||
|
try:
|
||||||
|
mi.rating = float(rating(extra)[0]) / 2.0
|
||||||
|
except:
|
||||||
|
log.exception('Failed to parse rating')
|
||||||
|
mi.rating = 0
|
||||||
|
|
||||||
|
# Cover
|
||||||
|
mi.has_douban_cover = None
|
||||||
|
u = cover_url(extra)
|
||||||
|
if u:
|
||||||
|
u = u[0].replace('/spic/', '/lpic/')
|
||||||
|
# If URL contains "book-default", the book doesn't have a cover
|
||||||
|
if u.find('book-default') == -1:
|
||||||
|
mi.has_douban_cover = u
|
||||||
|
return mi
|
||||||
|
# }}}
|
||||||
|
|
||||||
def get_book_url(self, identifiers): # {{{
|
def get_book_url(self, identifiers): # {{{
|
||||||
db = identifiers.get('douban', None)
|
db = identifiers.get('douban', None)
|
||||||
if db is not None:
|
if db is not None:
|
||||||
@ -286,7 +296,7 @@ class Douban(Source):
|
|||||||
from lxml import etree
|
from lxml import etree
|
||||||
for relevance, i in enumerate(entries):
|
for relevance, i in enumerate(entries):
|
||||||
try:
|
try:
|
||||||
ans = to_metadata(br, log, i, timeout)
|
ans = self.to_metadata(br, log, i, timeout)
|
||||||
if isinstance(ans, Metadata):
|
if isinstance(ans, Metadata):
|
||||||
ans.source_relevance = relevance
|
ans.source_relevance = relevance
|
||||||
db = ans.identifiers['douban']
|
db = ans.identifiers['douban']
|
||||||
@ -352,8 +362,6 @@ if __name__ == '__main__': # tests {{{
|
|||||||
title_test, authors_test)
|
title_test, authors_test)
|
||||||
test_identify_plugin(Douban.name,
|
test_identify_plugin(Douban.name,
|
||||||
[
|
[
|
||||||
|
|
||||||
|
|
||||||
(
|
(
|
||||||
{'identifiers':{'isbn': '9787536692930'}, 'title':'三体',
|
{'identifiers':{'isbn': '9787536692930'}, 'title':'三体',
|
||||||
'authors':['刘慈欣']},
|
'authors':['刘慈欣']},
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user