calibre/recipes/frontlineonnet.recipe
2014-04-05 09:45:07 +05:30

90 lines
3.9 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
'''
frontlineonnet.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Frontlineonnet(BasicNewsRecipe):
title = 'Frontline'
__author__ = 'Darko Miletic'
description = "India's national magazine"
publisher = 'Frontline'
category = 'news, politics, India'
no_stylesheets = True
delay = 1
INDEX = 'http://frontlineonnet.com/'
use_embedded_content = False
encoding = 'utf-8'
language = 'en_IN'
publication_type = 'magazine'
masthead_url = 'http://frontlineonnet.com/images/newfline.jpg'
extra_css = """
body{font-family: Verdana,Arial,Helvetica,sans-serif}
img{margin-top:0.5em; margin-bottom: 0.7em; display: block}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
, 'linearize_tables' : True
}
preprocess_regexps = [
(re.compile(r'.*?<base', re.DOTALL|re.IGNORECASE),lambda match: '<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"><html dir="ltr" xml:lang="en-IN"><head><title>title</title><base') # noqa
,(re.compile(r'<base .*?>', re.DOTALL|re.IGNORECASE),lambda match: '</head><body>')
,(re.compile(r'<byline>', re.DOTALL|re.IGNORECASE),lambda match: '<div class="byline">')
,(re.compile(r'</byline>', re.DOTALL|re.IGNORECASE),lambda match: '</div>')
,(re.compile(r'<center>', re.DOTALL|re.IGNORECASE),lambda match: '<div class="ctr">')
,(re.compile(r'</center>', re.DOTALL|re.IGNORECASE),lambda match: '</div>')
]
keep_only_tags= [
dict(name='div', attrs={'id':'content'})
]
remove_attributes=['size','noshade','border']
use_javascript_to_login = True
needs_subscription = True
def javascript_login(self, browser, username, password):
browser.visit('http://www.frontline.in/profile/login.do')
browser.wait_for_element('form#loginForm', timeout=180)
form = browser.select_form('#loginForm') # Select the first form on the page
form['userName'] = username
form['password'] = password
browser.submit(timeout=120)
def parse_index(self):
articles = []
current_section = None
feeds = []
soup = self.index_to_soup(self.INDEX)
for h3 in soup.findAll('h3'):
if h3.get('class', None) == 'artListSec':
if articles:
feeds.append((current_section, articles))
articles = []
current_section = self.tag_to_string(h3).strip()
self.log(current_section)
elif h3.get('id', None) in {'headseccol', 'headsec'}:
a = h3.find('a', href=True)
if a is not None:
title = self.tag_to_string(a)
url = a['href']
articles.append({
'title' :title
,'date' :''
,'url' :url
,'description':''
})
self.log('\t', title, url)
if articles:
feeds.append((current_section, articles))
return feeds