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

India Today by Krittika Goyal

Browse Source
This commit is contained in:
Kovid Goyal 2011-09-11 15:53:10 -06:00
parent d76c312c89
commit 7a3babf49e
2 changed files with 17 additions and 68 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

83
recipes/india_today.recipe
View File

@ -1,76 +1,25 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class IndiaToday(BasicNewsRecipe): class IndiaToday(BasicNewsRecipe):
title = u'India Today'
title = 'India Today' language = 'en_IN'
__author__ = 'Kovid Goyal' __author__ = 'Krittika Goyal'
language = 'en_IN' oldest_article = 15 #days
timefmt = ' [%d %m, %Y]' max_articles_per_feed = 25
oldest_article = 700
max_articles_per_feed = 10
no_stylesheets = True no_stylesheets = True
auto_cleanup = True
remove_tags_before = dict(id='content_story_title') feeds = [
remove_tags_after = dict(id='rightblockdiv') ('Latest News', 'http://indiatoday.intoday.in/rss/article.jsp?sid=4'),
remove_tags = [dict(id=['rightblockdiv', 'share_links'])] ('Cover Story', 'http://indiatoday.intoday.in/rss/article.jsp?sid=30'),
('Nation', 'http://indiatoday.intoday.in/rss/article.jsp?sid=36'),
extra_css = '#content_story_title { font-size: 170%; font-weight: bold;}' ('States', 'http://indiatoday.intoday.in/rss/article.jsp?sid=21'),
conversion_options = { 'linearize_tables': True } ('Economy', 'http://indiatoday.intoday.in/rss/article.jsp?sid=34'),
('World', 'http://indiatoday.intoday.in/rss/article.jsp?sid=61'),
def it_get_index(self): ('Sport', 'http://indiatoday.intoday.in/rss/article.jsp?sid=41'),
soup = self.index_to_soup('http://indiatoday.intoday.in/site/archive')
a = soup.find('a', href=lambda x: x and 'issueId=' in x)
url = 'http://indiatoday.intoday.in/site/'+a.get('href')
img = a.find('img')
self.cover_url = img.get('src')
return self.index_to_soup(url)
def parse_index(self):
soup = self.it_get_index()
feeds, current_section, current_articles = [], None, []
for x in soup.findAll(name=['h1', 'a']):
if x.name == 'h1':
if current_section and current_articles:
feeds.append((current_section, current_articles))
current_section = self.tag_to_string(x)
current_articles = []
self.log('\tFound section:', current_section)
elif x.name == 'a' and 'Story' in x.get('href', ''):
title = self.tag_to_string(x)
url = x.get('href')
url = url.replace(' ', '%20')
if not url.startswith('/'):
url = 'http://indiatoday.intoday.in/site/' + url
if title and url:
url += '?complete=1'
self.log('\tFound article:', title)
self.log('\t\t', url)
desc = ''
h3 = x.parent.findNextSibling('h3')
if h3 is not None:
desc = 'By ' + self.tag_to_string(h3)
h4 = h3.findNextSibling('h4')
if h4 is not None:
desc = self.tag_to_string(h4) + ' ' + desc
if desc:
self.log('\t\t', desc)
current_articles.append({'title':title, 'description':desc,
'url':url, 'date':''})
if current_section and current_articles:
feeds.append((current_section, current_articles))
return feeds
def postprocess_html(self, soup, first):
a = soup.find(text='Print')
if a is not None:
tr = a.findParent('tr')
if tr is not None:
tr.extract()
return soup
]

2
src/calibre/web/feeds/recipes/collection.py
View File

@ -22,7 +22,7 @@ E = ElementMaker(namespace=NS, nsmap={None:NS})
def iterate_over_builtin_recipe_files(): def iterate_over_builtin_recipe_files():
exclude = ['craigslist', 'iht', 'toronto_sun', exclude = ['craigslist', 'iht', 'toronto_sun',
'india_today', 'livemint'] 'livemint']
d = os.path.dirname d = os.path.dirname
base = os.path.join(d(d(d(d(d(d(os.path.abspath(__file__))))))), 'recipes') base = os.path.join(d(d(d(d(d(d(os.path.abspath(__file__))))))), 'recipes')
for f in os.listdir(base): for f in os.listdir(base):