Backup_Repos/calibre
1
0
Fork 0
mirror of git://github.com/kovidgoyal/calibre.git synced 2026-01-03 12:15:42 +01:00
Code Issues Projects Releases Wiki Activity

pep8

Browse source
This commit is contained in:
Kovid Goyal 2014-03-07 09:05:58 +05:30
parent 6f30914a52
commit d410d11e55
1 changed files with 18 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

37
recipes/financial_times_uk.recipe
View file

@ -4,7 +4,6 @@
www.ft.com/intl/uk-edition
'''
import datetime
from calibre.ptempfile import PersistentTemporaryFile
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
@ -13,7 +12,7 @@
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."
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." # noqa
publisher = 'The Financial Times Ltd.'
category = 'news, finances, politics, UK, World'
oldest_article = 2
@ -58,7 +57,7 @@ def get_browser(self):
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','promobox']})
,dict(name='div', attrs={'class':lambda x: x and 'insideArticleRelatedTopics' in x.split()} )
,dict(name='div', attrs={'class':lambda x: x and 'insideArticleRelatedTopics' in x.split()})
]
remove_attributes = ['width','height','lang']
@ -80,13 +79,13 @@ def get_artlinks(self, elem):
for item in elem.findAll('a',href=True):
count = count + 1
if self.test and count > 2:
return articles
return articles
rawlink = item['href']
url = rawlink
if not rawlink.startswith('http://'):
url = self.PREFIX + rawlink
url = self.PREFIX + rawlink
try:
urlverified = self.browser.open_novisit(url).geturl() # resolve redirect.
urlverified = self.browser.open_novisit(url).geturl() # resolve redirect.
except:
continue
title = self.tag_to_string(item)
@ -106,10 +105,11 @@ def parse_index(self):
#self.timefmt = ' [%s]'%dates
section_title = 'Untitled'
for column in soup.findAll('div', attrs = {'class':'feedBoxes clearfix'}):
for section in column. findAll('div', attrs = {'class':'feedBox'}):
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
if '...' not in sectiontitle:
section_title=sectiontitle
for article in section.ul.findAll('li'):
articles = []
title=self.tag_to_string(article.a)
@ -121,7 +121,6 @@ def parse_index(self):
feeds[section_title] = []
feeds[section_title] += articles
ans = [(key, val) for key, val in feeds.iteritems()]
return ans
@ -138,18 +137,18 @@ def preprocess_html(self, soup):
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
str = item.string
item.replaceWith(str)
else:
if limg:
item.name = 'div'
item.attrs = []
else:
str = self.tag_to_string(item)
item.replaceWith(str)
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'
item['alt'] = 'image'
return soup
def get_obfuscated_article(self, url):