calibre/recipes/gazeta_pl_krakow.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

99 lines
3.3 KiB
Python

#!/usr/bin/env python2
__license__ = 'GPL v3'
__copyright__ = 'teepel <teepel44@gmail.com> based on GW from fenuks'
'''
krakow.gazeta.pl
'''
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.ebooks.BeautifulSoup import Comment
class gw_krakow(BasicNewsRecipe):
title = u'Gazeta Wyborcza Kraków'
__author__ = 'teepel <teepel44@gmail.com> based on GW from fenuks'
language = 'pl'
description = u'Wiadomości z Krakowa na portalu Gazeta.pl.'
category = 'newspaper'
publication_type = 'newspaper'
# encoding = 'iso-8859-2'
masthead_url = 'http://bi.gazeta.pl/im/5/8528/m8528105.gif'
INDEX = 'http://krakow.gazeta.pl'
cover_url = 'http://bi.gazeta.pl/i/hp/hp2009/logo.gif'
remove_empty_feeds = True
oldest_article = 3
max_articles_per_feed = 100
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
ignore_duplicate_articles = {'title', 'url'}
# rules for gazeta.pl
preprocess_regexps = [
(re.compile(u'<b>Czytaj więcej</b>.*', re.DOTALL), lambda m: '</body>')]
keep_only_tags = [dict(id='gazeta_article')]
remove_tags = [dict(id=['gazeta_article_tools', 'gazeta_article_miniatures']), dict(
attrs={'class': ['mod mod_sociallist', 'c0', 'fb', 'voteNeedLogin']})]
remove_tags_after = dict(id='gazeta_article_body')
feeds = [(u'Wiadomości', u'http://rss.gazeta.pl/pub/rss/krakow.xml')]
def print_version(self, url):
if 'feedsportal.com' in url:
s = url.rpartition('gazeta0Bpl')
u = s[2]
if not s[0]:
u = url.rpartition('wyborcza0Bpl')[2]
u = u.replace('/l/', '/')
u = u.replace('/ia1.htm', '')
u = u.replace('/story01.htm', '')
u = u.replace('0C', '/')
u = u.replace('A', '')
u = u.replace('0E', '-')
u = u.replace('0H', ',')
u = u.replace('0I', '_')
u = u.replace('0B', '.')
u = self.INDEX + u
return u
else:
return url
def preprocess_html(self, soup):
tag = soup.find(id='Str')
if soup.find(attrs={'class': 'piano_btn_1'}):
return None
elif tag and tag.findAll('a'):
self.append_page(soup, soup.body)
return soup
def append_page(self, soup, appendtag):
tag = soup.find('div', attrs={'id': 'Str'})
try:
baseurl = soup.find(name='meta', attrs={
'property': 'og:url'})['content']
except:
return 1
link = tag.findAll('a')[-1]
while link:
soup2 = self.index_to_soup(baseurl + link['href'])
link = soup2.find('div', attrs={'id': 'Str'}).findAll('a')[-1]
if u'następne' not in link.string:
link = ''
pagetext = soup2.find(id='artykul')
comments = pagetext.findAll(
text=lambda text: isinstance(text, Comment))
for comment in comments:
comment.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
tag.extract()
def image_url_processor(self, baseurl, url):
if url.startswith(' '):
return url.strip()
else:
return url