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

News Observer by Krittika Goyal

Browse Source
This commit is contained in:
Kovid Goyal 2010-03-06 22:16:38 -07:00
parent 83cd0f85b6
commit ce6ef6e01a
2 changed files with 46 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
resources/recipes/newsobs.recipe Normal file
View File

@ -0,0 +1,33 @@
from calibre.web.feeds.news import BasicNewsRecipe
class NewsAndObserver(BasicNewsRecipe):
title = u'News And Observer'
language = 'en'
__author__ = 'Krittika Goyal'
oldest_article = 1 #days
max_articles_per_feed = 25
#encoding = 'latin1'
no_stylesheets = True
remove_tags_before = dict(name='div', attrs={'id':'story_header'})
remove_tags_after = dict(name='div', attrs={'id':'shirttail'})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':['contained_round', 'contained']}),
dict(name='div', attrs={'id':['story_tools', 'toolbox', 'shirttail', 'comment_widget', 'stories_widget', 'classifieds_widget', 'most_popular_widget', 'footer']}),
#dict(name='ul', attrs={'class':'article-tools'}),
dict(name='ul', attrs={'id':'story_tabs'}),
]
feeds = [
('Cover', 'http://www.newsobserver.com/100/index.rss'),
('News', 'http://www.newsobserver.com/102/index.rss'),
('Politics', 'http://www.newsobserver.com/105/index.rss'),
('Business', 'http://www.newsobserver.com/104/index.rss'),
('Sports', 'http://www.newsobserver.com/103/index.rss'),
('College Sports', 'http://www.newsobserver.com/119/index.rss'),
('Lifestyles', 'http://www.newsobserver.com/106/index.rss'),
('Editorials', 'http://www.newsobserver.com/158/index.rss')]

33
resources/recipes/sfbg.recipe
View File

@ -1,42 +1,35 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class SanFranciscoBayGuardian(BasicNewsRecipe): class SanFranciscoBayGuardian(BasicNewsRecipe):
title = u'San Francisco Bay Guardian' title = u'San Francisco Bay Guardian'
language = 'en' language = 'en'
__author__ = 'Krittika Goyal' __author__ = 'Krittika Goyal'
oldest_article = 1 #days oldest_article = 31 #days
max_articles_per_feed = 25 max_articles_per_feed = 25
#encoding = 'latin1' #encoding = 'latin1'
no_stylesheets = True no_stylesheets = True
remove_tags_before = dict(name='div', attrs={'id':'story_header'}) #remove_tags_before = dict(name='div', attrs={'id':'story_header'})
remove_tags_after = dict(name='div', attrs={'id':'shirttail'}) #remove_tags_after = dict(name='div', attrs={'id':'shirttail'})
remove_tags = [ remove_tags = [
dict(name='iframe'), dict(name='iframe'),
#dict(name='div', attrs={'class':'related-articles'}), #dict(name='div', attrs={'class':'related-articles'}),
dict(name='div', attrs={'id':['story_tools', 'toolbox', 'shirttail', 'comment_widget']}), #dict(name='div', attrs={'id':['story_tools', 'toolbox', 'shirttail', 'comment_widget']}),
#dict(name='ul', attrs={'class':'article-tools'}), #dict(name='ul', attrs={'class':'article-tools'}),
dict(name='ul', attrs={'id':'story_tabs'}), #dict(name='ul', attrs={'id':'story_tabs'}),
] ]
feeds = [ feeds = [
('Cover', 'http://www.newsobserver.com/100/index.rss'), ('sfbg', 'http://www.sfbg.com/rss.xml'),
('News', 'http://www.newsobserver.com/102/index.rss'), ]
('Politics', 'http://www.newsobserver.com/105/index.rss'),
('Business', 'http://www.newsobserver.com/104/index.rss'),
('Sports', 'http://www.newsobserver.com/103/index.rss'),
('College Sports', 'http://www.newsobserver.com/119/index.rss'),
('Lifestyles', 'http://www.newsobserver.com/106/index.rss'),
('Editorials', 'http://www.newsobserver.com/158/index.rss')]
def preprocess_html(self, soup): #def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'id':'story_body'}) #story = soup.find(name='div', attrs={'id':'story_body'})
#td = heading.findParent(name='td') #td = heading.findParent(name='td')
#td.extract() #td.extract()
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>') #soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body') #body = soup.find(name='body')
body.insert(0, story) #body.insert(0, story)
return soup #return soup