Update: fixes the processing of section titles
I've made sure to use the more recent code from 0.9.26
Code:
__license__ = 'GPL v3'
__copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.ft.com/uk-edition
'''
import datetime
from calibre.ptempfile import PersistentTemporaryFile
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from collections import OrderedDict
class FinancialTimes(BasicNewsRecipe):
title = 'Financial Times (UK)'
__author__ = 'Darko Miletic'
description = "The Financial Times (FT) is one of the world's leading business news and information organisations, recognised internationally for its authority, integrity and accuracy."
publisher = 'The Financial Times Ltd.'
category = 'news, finances, politics, UK, World'
oldest_article = 2
language = 'en_GB'
max_articles_per_feed = 250
no_stylesheets = True
use_embedded_content = False
needs_subscription = True
encoding = 'utf8'
publication_type = 'newspaper'
articles_are_obfuscated = True
temp_files = []
masthead_url = 'http://im.media.ft.com/m/img/masthead_main.jpg'
LOGIN = 'https://registration.ft.com/registration/barrier/login'
LOGIN2 = 'http://media.ft.com/h/subs3.html'
INDEX = 'http://www.ft.com/uk-edition'
PREFIX = 'http://www.ft.com'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
, 'linearize_tables' : True
}
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open(self.INDEX)
if self.username is not None and self.password is not None:
br.open(self.LOGIN2)
br.select_form(name='loginForm')
br['username'] = self.username
br['password'] = self.password
br.submit()
return br
keep_only_tags = [
dict(name='div' , attrs={'class':['fullstory fullstoryHeader', 'ft-story-header']})
,dict(name='div' , attrs={'class':'standfirst'})
,dict(name='div' , attrs={'id' :'storyContent'})
,dict(name='div' , attrs={'class':['ft-story-body','index-detail']})
,dict(name='h2' , attrs={'class':'entry-title'} )
,dict(name='span', attrs={'class':lambda x: x and 'posted-on' in x.split()} )
,dict(name='span', attrs={'class':'author_byline'} )
,dict(name='div' , attrs={'class':'entry-content'} )
]
remove_tags = [
dict(name='div', attrs={'id':'floating-con'})
,dict(name=['meta','iframe','base','object','embed','link'])
,dict(attrs={'class':['storyTools','story-package','screen-copy','story-package separator','expandable-image']})
]
remove_attributes = ['width','height','lang']
extra_css = """
body{font-family: Georgia,Times,"Times New Roman",serif}
h2{font-size:large}
.ft-story-header{font-size: x-small}
.container{font-size:x-small;}
h3{font-size:x-small;color:#003399;}
.copyright{font-size: x-small}
img{margin-top: 0.8em; display: block}
.lastUpdated{font-family: Arial,Helvetica,sans-serif; font-size: x-small}
.byline,.ft-story-body,.ft-story-header{font-family: Arial,Helvetica,sans-serif}
"""
def get_artlinks(self, elem):
articles = []
count = 0
for item in elem.findAll('a',href=True):
count = count + 1
if self.test and count > 2:
return articles
rawlink = item['href']
url = rawlink
if not rawlink.startswith('http://'):
url = self.PREFIX + rawlink
try:
urlverified = self.browser.open_novisit(url).geturl() # resolve redirect.
except:
continue
title = self.tag_to_string(item)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :urlverified
,'description':''
})
return articles
def parse_index(self):
feeds = OrderedDict()
soup = self.index_to_soup(self.INDEX)
#dates= self.tag_to_string(soup.find('div', attrs={'class':'btm-links'}).find('div'))
#self.timefmt = ' [%s]'%dates
for column in soup.findAll('div', attrs = {'class':'feedBoxes clearfix'}):
for section in column. findAll('div', attrs = {'class':'feedBox'}):
sectiontitle=self.tag_to_string(section.find('h4'))
if not '...' in sectiontitle: section_title=sectiontitle
for article in section.ul.findAll('li'):
articles = []
title=self.tag_to_string(article.a)
url=article.a['href']
articles.append({'title':title, 'url':url, 'description':'', 'date':''})
if articles:
if section_title not in feeds:
feeds[section_title] = []
feeds[section_title] += articles
ans = [(key, val) for key, val in feeds.iteritems()]
return ans
def preprocess_html(self, soup):
items = ['promo-box','promo-title',
'promo-headline','promo-image',
'promo-intro','promo-link','subhead']
for item in items:
for it in soup.findAll(item):
it.name = 'div'
it.attrs = []
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
if limg:
item.name = 'div'
item.attrs = []
else:
str = self.tag_to_string(item)
item.replaceWith(str)
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
return soup
def get_cover_url(self):
cdate = datetime.date.today()
if cdate.isoweekday() == 7:
cdate -= datetime.timedelta(days=1)
return cdate.strftime('http://specials.ft.com/vtf_pdf/%d%m%y_FRONT1_LON.pdf')
def get_obfuscated_article(self, url):
count = 0
while (count < 10):
try:
response = self.browser.open(url)
html = response.read()
count = 10
except:
print "Retrying download..."
count += 1
tfile = PersistentTemporaryFile('_fa.html')
tfile.write(html)
tfile.close()
self.temp_files.append(tfile)
return tfile.name