IGN:Updated recipe for Outlook India

This commit is contained in:
Kovid Goyal 2009-08-24 08:33:53 -06:00
parent 6261ba3f72
commit 8dd752d850

View File

@ -3,6 +3,8 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid at kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid at kovidgoyal.net>'
import re import re
from calibre import strftime
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class OutlookIndia(BasicNewsRecipe): class OutlookIndia(BasicNewsRecipe):
@ -13,10 +15,19 @@ class OutlookIndia(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
encoding = 'utf-8' encoding = 'utf-8'
language = _('English') language = _('English')
recursions = 1
extra_css = '''
body{font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
.fspheading{color:#AF0E25 ; font-family:"Times New Roman",Times,serif; font-weight:bold ; font-size:large; }
.fspauthor{color:#AF0E25; font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
.fspintro{color:#666666; font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
.fspchannelhome{font-family:Arial,Helvetica,sans-serif; font-size:x-small;}
.fspphotocredit{color:##999999; font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
'''
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':["ctl00_cphpagemiddle_reparticle_ctl00_divfullstorytext","ctl00_cphpagemiddle_reparticle_ctl00_divartpic","ctl00_cphpagemiddle_reparticle_ctl00_divfspheading", "ctl00_cphpagemiddle_reparticle_ctl00_divartpiccaption", "ctl00_cphpagemiddle_reparticle_ctl00_divartpiccredit","ctl00_cphpagemiddle_reparticle_ctl00_divfspintro", "ctl00_cphpagemiddle_reparticle_ctl00_divartbyline", ]}), dict(name='div', attrs={'id':["ctl00_cphpagemiddle_reparticle_ctl00_divfullstorytext","ctl00_cphpagemiddle_reparticle_ctl00_divartpic","ctl00_cphpagemiddle_reparticle_ctl00_divfspheading", "ctl00_cphpagemiddle_reparticle_ctl00_divartpiccaption", "ctl00_cphpagemiddle_reparticle_ctl00_divartpiccredit","ctl00_cphpagemiddle_reparticle_ctl00_divfspintro", "ctl00_cphpagemiddle_reparticle_ctl00_divartbyline", "ctl00_cphpagemiddle_divglitteratiregulars","ctl00_cphpagemiddle_divcartoon","feedbackslatestfirst","ctl00_cphpagemiddle_divregulars","ctl00_cphpagemiddle_divquotes"]}),
] ]
remove_tags = [dict(name=['script','object'])] remove_tags = [dict(name=['script','object','hr']),]
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
@ -27,12 +38,11 @@ class OutlookIndia(BasicNewsRecipe):
br.set_cookiejar(None) br.set_cookiejar(None)
return br return br
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://www.outlookindia.com/issues.aspx') soup = self.index_to_soup('http://www.outlookindia.com/issues.aspx')
# find cover pic # find cover pic
div = soup.find('div', attrs={'class':re.compile('cententcellpadding')}) div = soup.find('div', attrs={'class':re.compile('cententcellpadding')})
if div is None: return None if div is None: return None
@ -47,8 +57,8 @@ class OutlookIndia(BasicNewsRecipe):
self.cover_url = cover['src'] self.cover_url = cover['src']
# end find cover pic # end find cover pic
#find current issue
div = soup.find('table', attrs={'id':re.compile('ctl00_cphpagemiddle_dlissues')}) div = soup.find('table', attrs={'id':re.compile('ctl00_cphpagemiddle_dlissues')})
if div is None: return None if div is None: return None
@ -58,25 +68,48 @@ class OutlookIndia(BasicNewsRecipe):
href = 'http://www.outlookindia.com/' + a['href'] href = 'http://www.outlookindia.com/' + a['href']
soup = self.index_to_soup(href) soup = self.index_to_soup(href)
#find current issue
#find the articles in the current issue
articles = [] articles = []
for a in soup.findAll('a', attrs={'class':'contentpgsubheadinglink'}): for a in soup.findAll('a', attrs={'class':['contentpgsubheadinglink',"contentpgtext6",]}):
if a and a.has_key('href'): if a and a.has_key('href'):
url = 'http://www.outlookindia.com/' + a['href'] url = 'http://www.outlookindia.com/' + a['href']
else: else:
url ='' url =''
title = self.tag_to_string(a) title = self.tag_to_string(a)
desc = ''
date = '' date = ''
description = ''
articles.append({ articles.append({
'title':title, 'title':title,
'date':date, 'date':date,
'url':url, 'url':url,
'description':description 'description':desc,
}) })
for a in soup.findAll('a', attrs={'id':["ctl00_cphpageleft_hlglitterati","ctl00_cphpageleft_hlposcape",]}):
if a and a.has_key('href'):
url = 'http://www.outlookindia.com/' + a['href']
else:
url =''
title = self.tag_to_string(a)
desc = ''
date = ''
articles.append({
'title':title,
'date':date,
'url':url,
'description':desc,
})
return [('Current Issue', articles)] return [('Current Issue', articles)]
@ -85,11 +118,15 @@ class OutlookIndia(BasicNewsRecipe):
del item['style'] del item['style']
return self.adeify_images(soup) return self.adeify_images(soup)
def postrocess_html(self, soup, first): def postrocess_html(self, soup, first):
for tag in soup.findAll(name=['table', 'tr', 'td','tbody']): for item in soup.findAll(align = "left"):
tag.name = 'div' del item['align']
for tag in soup.findAll(name=['table', 'tr','td','tbody','ul','li','font','span']):
tag.name = 'div'
return soup return soup