calibre/recipes/newsweek_polska.recipe

92 lines
2.9 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010, matek09, matek09@gmail.com'
from calibre.web.feeds.news import BasicNewsRecipe
class Newsweek(BasicNewsRecipe):
FIND_LAST_FULL_ISSUE = True
EDITION = '0'
EXCLUDE_LOCKED = True
LOCKED_ICO = 'http://www.newsweek.pl/bins/media/static/newsweek/img/ico_locked.gif'
title = u'Newsweek Polska'
__author__ = 'matek09'
description = 'Weekly magazine'
encoding = 'utf-8'
no_stylesheets = True
language = 'pl'
remove_javascript = True
keep_only_tags =[]
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'article'}))
remove_tags =[]
remove_tags.append(dict(name = 'div', attrs = {'class' : 'copy'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 'url'}))
extra_css = '''
.body {font-size: small}
.author {font-size: x-small}
.lead {font-size: x-small}
.title{font-size: x-large; font-weight: bold}
'''
def print_version(self, url):
return url.replace("http://www.newsweek.pl/artykuly/wydanie/" + str(self.EDITION), "http://www.newsweek.pl/artykuly") + '/print'
def is_locked(self, a):
if a.findNext('img')['src'] == 'http://www.newsweek.pl/bins/media/static/newsweek/img/ico_locked.gif':
return True
else:
return False
def is_full(self, issue_soup):
if len(issue_soup.findAll('img', attrs={'src' : 'http://www.newsweek.pl/bins/media/static/newsweek/img/ico_locked.gif'})) > 1:
return False
else:
return True
def find_last_full_issue(self):
frame_url = 'http://www.newsweek.pl/Frames/IssueCover.aspx'
while True:
frame_soup = self.index_to_soup(frame_url)
self.EDITION = frame_soup.find('a', attrs={'target' : '_parent'})['href'].replace('/wydania/','')
issue_soup = self.index_to_soup('http://www.newsweek.pl/wydania/' + self.EDITION)
if self.is_full(issue_soup):
break
frame_url = 'http://www.newsweek.pl/Frames/' + frame_soup.find(lambda tag: tag.name == 'span' and not tag.attrs).a['href']
def parse_index(self):
if self.FIND_LAST_FULL_ISSUE:
self.find_last_full_issue()
soup = self.index_to_soup('http://www.newsweek.pl/wydania/' + self.EDITION)
img = soup.find('img', id="ctl00_C1_PaperIsssueView_IssueImage", src=True)
self.cover_url = img['src']
feeds = []
parent = soup.find(id='content-left-big')
for txt in parent.findAll(attrs={'class':'txt_normal_red strong'}):
articles = list(self.find_articles(txt))
if len(articles) > 0:
section = self.tag_to_string(txt).capitalize()
feeds.append((section, articles))
return feeds
def find_articles(self, txt):
for a in txt.findAllNext( attrs={'class':['strong','hr']}):
if a.name in "div":
break
if (not self.FIND_LAST_FULL_ISSUE) & self.EXCLUDE_LOCKED & self.is_locked(a):
continue
yield {
'title' : self.tag_to_string(a),
'url' : 'http://www.newsweek.pl' + a['href'],
'date' : '',
'description' : ''
}