Merge from trunk

This commit is contained in:
Charles Haley 2011-05-08 09:30:15 +01:00
commit f997a54203
2 changed files with 38 additions and 3 deletions

View File

@ -0,0 +1,36 @@
__license__ = 'GPL v3'
__copyright__ = '2011, Seongkyoun Yoo <Seongkyoun.yoo at gmail.com>'
'''
Profile to download KoreaHerald
'''
from calibre.web.feeds.news import BasicNewsRecipe
class KoreaHerald(BasicNewsRecipe):
title = u'KoreaHerald'
language = 'en'
description = u'Korea Herald News articles'
__author__ = 'Seongkyoun Yoo'
oldest_article = 10
recursions = 3
max_articles_per_feed = 10
no_stylesheets = True
keep_only_tags = [
dict(id=['contentLeft', '_article'])
]
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':['left','htit2', 'navigation','banner_txt','banner_img']}),
dict(name='ul', attrs={'class':['link_icon', 'flow_icon','detailTextAD110113']}),
]
feeds = [
('All News','http://www.koreaherald.com/rss/020000000000.xml'),
('National','http://www.koreaherald.com/rss/020100000000.xml'),
('Business','http://www.koreaherald.com/rss/020200000000.xml'),
('Life&Style','http://www.koreaherald.com/rss/020300000000.xml'),
('Entertainment','http://www.koreaherald.com/rss/020400000000.xml'),
('Sports','http://www.koreaherald.com/rss/020500000000.xml'),
('Opinion','http://www.koreaherald.com/rss/020600000000.xml'),
('English Cafe','http://www.koreaherald.com/rss/021000000000.xml'),
]

View File

@ -16,7 +16,6 @@ from calibre.customize import CatalogPlugin
from calibre.customize.conversion import OptionRecommendation, DummyReporter from calibre.customize.conversion import OptionRecommendation, DummyReporter
from calibre.ebooks.BeautifulSoup import BeautifulSoup, BeautifulStoneSoup, Tag, NavigableString from calibre.ebooks.BeautifulSoup import BeautifulSoup, BeautifulStoneSoup, Tag, NavigableString
from calibre.ebooks.chardet import substitute_entites from calibre.ebooks.chardet import substitute_entites
from calibre.ebooks.metadata import title_sort as _title_sort
from calibre.library.save_to_disk import preprocess_template from calibre.library.save_to_disk import preprocess_template
from calibre.ptempfile import PersistentTemporaryDirectory from calibre.ptempfile import PersistentTemporaryDirectory
from calibre.utils.bibtex import BibTeX from calibre.utils.bibtex import BibTeX
@ -128,7 +127,7 @@ class CSV_XML(CatalogPlugin): # {{{
if field.startswith('#'): if field.startswith('#'):
item = db.get_field(entry['id'],field,index_is_id=True) item = db.get_field(entry['id'],field,index_is_id=True)
elif field == 'title_sort': elif field == 'title_sort':
item = _title_sort(unicode(entry['title'])) item = entry['sort']
else: else:
item = entry[field] item = entry[field]
@ -183,7 +182,7 @@ class CSV_XML(CatalogPlugin): # {{{
record.append(item) record.append(item)
if 'title' in fields: if 'title' in fields:
title = E.title(r['title'], sort=_title_sort(unicode(r['title']))) title = E.title(r['title'], sort=r['sort'])
record.append(title) record.append(title)
if 'authors' in fields: if 'authors' in fields: