BBC Chinese and Singtao Daily by rty. Fix #6075 (Error while accessing Cybook Gen3)

This commit is contained in:
Kovid Goyal 2010-07-03 08:28:40 -06:00
parent c4022017e9
commit 3bcfa5d0d7
3 changed files with 115 additions and 2 deletions

View File

@ -0,0 +1,39 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1277443634(BasicNewsRecipe):
title = u'BBC Chinese'
oldest_article = 7
max_articles_per_feed = 100
feeds = [
(u'\u4e3b\u9875', u'http://www.bbc.co.uk/zhongwen/simp/index.xml'),
(u'\u56fd\u9645\u65b0\u95fb', u'http://www.bbc.co.uk/zhongwen/simp/world/index.xml'),
(u'\u4e24\u5cb8\u4e09\u5730', u'http://www.bbc.co.uk/zhongwen/simp/china/index.xml'),
(u'\u91d1\u878d\u8d22\u7ecf', u'http://www.bbc.co.uk/zhongwen/simp/business/index.xml'),
(u'\u7f51\u4e0a\u4e92\u52a8', u'http://www.bbc.co.uk/zhongwen/simp/interactive/index.xml'),
(u'\u97f3\u89c6\u56fe\u7247', u'http://www.bbc.co.uk/zhongwen/simp/multimedia/index.xml'),
(u'\u5206\u6790\u8bc4\u8bba', u'http://www.bbc.co.uk/zhongwen/simp/indepth/index.xml')
]
extra_css = '''
@font-face {font-family: "DroidFont", serif, sans-serif; src: url(res:///system/fonts/DroidSansFallback.ttf); }\n
body {margin-right: 8pt; font-family: 'DroidFont', serif;}\n
h1 {font-family: 'DroidFont', serif;}\n
.articledescription {font-family: 'DroidFont', serif;}
'''
__author__ = 'rty'
__version__ = '1.0'
language = 'zh'
pubisher = 'British Broadcasting Corporation'
description = 'BBC news in Chinese'
category = 'News, Chinese'
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
encoding = 'UTF-8'
conversion_options = {'linearize_tables':True}
masthead_url = 'http://wscdn.bbc.co.uk/zhongwen/simp/images/1024/brand.jpg'
keep_only_tags = [
dict(name='h1'),
dict(name='p', attrs={'class':['primary-topic','summary']}),
dict(name='div', attrs={'class':['bodytext','datestamp']}),
]

View File

@ -0,0 +1,73 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1278063072(BasicNewsRecipe):
title = u'Singtao Daily - Canada'
oldest_article = 7
max_articles_per_feed = 100
__author__ = 'rty'
description = 'Toronto Canada Chinese Newspaper'
publisher = 'news.singtao.ca'
category = 'Chinese, News, Canada'
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'zh'
conversion_options = {'linearize_tables':True}
masthead_url = 'http://news.singtao.ca/i/site_2009/logo.jpg'
extra_css = '''
@font-face {font-family: "DroidFont", serif, sans-serif; src: url(res:///system/fonts/DroidSansFallback.ttf); }\
body {text-align: justify; margin-right: 8pt; font-family: 'DroidFont', serif;}\
h1 {font-family: 'DroidFont', serif;}\
.articledescription {font-family: 'DroidFont', serif;}
'''
keep_only_tags = [
dict(name='div', attrs={'id':['title','storybody']}),
dict(name='div', attrs={'class':'content'})
]
def parse_index(self):
feeds = []
for title, url in [
('Editorial', 'http://news.singtao.ca/toronto/editorial.html'),
('Toronto \xe5\x9f\x8e\xe5\xb8\x82/\xe7\xa4\xbe\xe5\x8d\x80', 'http://news.singtao.ca/toronto/city.html'),
('Canada \xe5\x8a\xa0\xe5\x9c\x8b', 'http://news.singtao.ca/toronto/canada.html'),
('Entertainment', 'http://news.singtao.ca/toronto/entertainment.html'),
('World', 'http://news.singtao.ca/toronto/world.html'),
('Finance \xe5\x9c\x8b\xe9\x9a\x9b\xe8\xb2\xa1\xe7\xb6\x93', 'http://news.singtao.ca/toronto/finance.html'),
('Sports', 'http://news.singtao.ca/toronto/sports.html'),
]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
return feeds
def parse_section(self, url):
soup = self.index_to_soup(url)
div = soup.find(attrs={'class': ['newslist paddingL10T10','newslist3 paddingL10T10']})
#date = div.find(attrs={'class': 'underlineBLK'})
current_articles = []
for li in div.findAll('li'):
a = li.find('a', href = True)
if a is None:
continue
title = self.tag_to_string(a)
url = a.get('href', False)
if not url or not title:
continue
if url.startswith('/'):
url = 'http://news.singtao.ca'+url
# self.log('\ \ Found article:', title)
# self.log('\ \ \ ', url)
current_articles.append({'title': title, 'url': url, 'description':''})
return current_articles
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(width=True):
del item['width']
return soup

View File

@ -501,8 +501,9 @@ class DeviceBooksView(BooksView): # {{{
def contextMenuEvent(self, event): def contextMenuEvent(self, event):
self.edit_collections_menu.setVisible( self.edit_collections_menu.setVisible(
self._model.db.supports_collections() and \ callable(getattr(self._model.db, 'supports_collections', None)) and \
prefs['preserve_user_collections']) self._model.db.supports_collections() and \
prefs['preserve_user_collections'])
self.context_menu.popup(event.globalPos()) self.context_menu.popup(event.globalPos())
event.accept() event.accept()