Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Today Online - Singapore

Browse Source
This commit is contained in:
Kovid Goyal 2016-02-23 09:02:55 +05:30
parent a02c47502a
commit 37eacf65b0
1 changed files with 19 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
recipes/today_online.recipe
View File

@ -14,7 +14,7 @@ class AdvancedUserRecipe1276486274(BasicNewsRecipe):
language = 'en_SG' language = 'en_SG'
temp_files = [] temp_files = []
articles_are_obfuscated = True articles_are_obfuscated = True
masthead_url = 'http://www.todayonline.com/App_Themes/Default/images/icons/TodayOnlineLogo.gif' masthead_url = 'http://www.todayonline.com/sites/all/themes/today/logo.png'
conversion_options = {'linearize_tables':True} conversion_options = {'linearize_tables':True}
extra_css = ''' extra_css = '''
.author{font-style: italic; font-size: small} .author{font-style: italic; font-size: small}
@ -23,30 +23,31 @@ class AdvancedUserRecipe1276486274(BasicNewsRecipe):
.headerStrap{font-weight: bold; font-size: x-large; font-syle: italic} .headerStrap{font-weight: bold; font-size: x-large; font-syle: italic}
.bodyText{font-size: 4px;font-family: Times New Roman;} .bodyText{font-size: 4px;font-family: Times New Roman;}
''' '''
keep_only_tags = [ feeds = [
dict(name='div', attrs={'id':['fullPrintBodyHolder']}) (u'Hot News', u'http://www.todayonline.com/hot-news/feed'),
(u'Singapore', u'http://www.todayonline.com/feed/singapore'),
(u'World', u'http://www.todayonline.com/feed/world'),
(u'Business', u'http://www.todayonline.com/feed/business'),
(u'Tech', u'http://www.todayonline.com/feed/tech'),
(u'Voices', u'http://www.todayonline.com/feed/voices'),
(u'Commentary', u'http://www.todayonline.com/feed/Commentary'),
(u'Daily Focus', u'http://www.todayonline.com/feed/daily-focus'),
(u'Lifestyle', u'http://www.todayonline.com/feed/lifestyle'),
]
keep_only_tags = [
dict(name='div', attrs='print-content')
] ]
remove_tags_after = [ dict(name='div', attrs={'class':'button'})]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':['url','button']}) dict(name='div', attrs={'class':['url','button']}),
] dict(name='div', attrs={'class':'node-type-print-edition'}),
feeds = [ dict(name='div', attrs={'class':['field field-name-field-article-section field-type-taxonomy-term-reference field-label-hidden','field field-name-field-article-abstract field-type-text-long field-label-hidden','authoring']})
(u'Singapore', u'http://www.todayonline.com/RSS/Singapore'),
(u'Hot News', u'http://www.todayonline.com/RSS/Hotnews'),
(u'Today Online', u'http://www.todayonline.com/RSS/Todayonline'),
(u'Voices', u'http://www.todayonline.com/RSS/Voices'),
(u'Commentary', u'http://www.todayonline.com/RSS/Commentary'),
(u'World', u'http://www.todayonline.com/RSS/World'),
(u'Business', u'http://www.todayonline.com/RSS/Business'),
(u'Column', u'http://www.todayonline.com/RSS/Columns'),
]
]
def get_obfuscated_article(self, url): def get_obfuscated_article(self, url):
br = self.get_browser() br = self.get_browser()
br.open(url) br.open(url)
response = br.follow_link(url_regex = r'/Print/', nr = 0) response = br.follow_link(url_regex = r'/print/', nr = 0)
html = response.read() html = response.read()
self.temp_files.append(PersistentTemporaryFile('_fa.html')) self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html) self.temp_files[-1].write(html)