Update Focus (PL)

This commit is contained in:
Kovid Goyal 2013-10-04 15:43:09 +05:30
parent 002886b0ba
commit 9a9daa7908

View File

@ -1,85 +1,51 @@
#!/usr/bin/env python from calibre.web.feeds.recipes import BasicNewsRecipe
__license__ = 'GPL v3'
import re
from calibre.web.feeds.news import BasicNewsRecipe
class FocusRecipe(BasicNewsRecipe): class NYTimes(BasicNewsRecipe):
__author__ = u'Artur Stachecki <artur.stachecki@gmail.com>' title = 'Focus'
__author__ = 'Krittika Goyal'
language = 'pl' language = 'pl'
version = 1 description = 'Polish scientific monthly magazine'
timefmt = ' [%d %b, %Y]'
title = u'Focus' needs_subscription = False
publisher = u'Gruner + Jahr Polska'
category = u'News'
description = u'Focus.pl - pierwszy w Polsce portal społecznościowy dla miłośników nauki. Tematyka: nauka, historia, cywilizacja, technika, przyroda, sport, gadżety'
category = 'magazine'
cover_url = ''
remove_empty_feeds = True
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100000
recursions = 0
no_stylesheets = True no_stylesheets = True
remove_javascript = True keep_only_tags = dict(name='article', attrs={'class': 'content'})
encoding = 'utf-8' remove_tags_after = dict(name='div', attrs={'class': 'inner_article'})
# Seems to work best, but YMMV remove_tags = [
simultaneous_downloads = 5 dict(name='div', attrs={'class': ['social_btns']}),
r = re.compile('.*(?P<url>http:\/\/(www.focus.pl)|(rss.feedsportal.com\/c)\/.*\.html?).*')
keep_only_tags = []
keep_only_tags.append(dict(name='div', attrs={'id': 'cll'}))
remove_tags = []
remove_tags.append(dict(name='div', attrs={'class': 'ulm noprint'}))
remove_tags.append(dict(name='div', attrs={'class': 'txb'}))
remove_tags.append(dict(name='div', attrs={'class': 'h2'}))
remove_tags.append(dict(name='ul', attrs={'class': 'txu'}))
remove_tags.append(dict(name='div', attrs={'class': 'ulc'}))
extra_css = '''
body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
h1{text-align: left;}
h2{font-size: medium; font-weight: bold;}
p.lead {font-weight: bold; text-align: left;}
.authordate {font-size: small; color: #696969;}
.fot{font-size: x-small; color: #666666;}
'''
feeds = [
('Nauka', 'http://www.focus.pl/nauka/rss/'),
('Historia', 'http://www.focus.pl/historia/rss/'),
('Cywilizacja', 'http://www.focus.pl/cywilizacja/rss/'),
('Sport', 'http://www.focus.pl/sport/rss/'),
('Technika', 'http://www.focus.pl/technika/rss/'),
('Przyroda', 'http://www.focus.pl/przyroda/rss/'),
('Technologie', 'http://www.focus.pl/gadzety/rss/')
] ]
def skip_ad_pages(self, soup): # TO GET ARTICLE TOC
if ('advertisement' in soup.find('title').string.lower()): def nejm_get_index(self):
href = soup.find('a').get('href') return self.index_to_soup('http://www.focus.pl/')
return self.index_to_soup(href, raw=True)
else:
return None
def get_cover_url(self): # To parse artice toc
soup = self.index_to_soup('http://www.focus.pl/magazyn/') def parse_index(self):
tag = soup.find(name='div', attrs={'class': 'clr fl'}) soup = self.nejm_get_index()
if tag:
self.cover_url = 'http://www.focus.pl/' + tag.a['href']
return getattr(self, 'cover_url', self.cover_url)
def print_version(self, url): toc = soup.find('div', id='wrapper')
if url.count('focus.pl.feedsportal.com'):
u = url.find('focus0Bpl') articles = []
u = 'http://www.focus.pl/' + url[u + 11:] feeds = []
u = u.replace('0C', '/') section_title = 'Focus Articles'
u = u.replace('A', '') for x in toc.findAll(True):
u = u.replace('0E', '-') if x.name == 'h1':
u = u.replace('/nc/1//story01.htm', '/do-druku/1') # Article found
else: a = x.find('a')
u = url.replace('/nc/1', '/do-druku/1') if a is None:
return u continue
title = self.tag_to_string(a)
url = a.get('href', False)
if not url or not title:
continue
# if url.startswith('story'):
url = 'http://www.focus.pl' + url
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
articles.append({'title': title, 'url': url,
'description': '', 'date': ''})
feeds.append((section_title, articles))
return feeds