| 1 |
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai |
| 2 |
|
| 3 |
import re |
| 4 |
|
| 5 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 6 |
|
| 7 |
|
| 8 |
class AdvancedUserRecipe1348146838(BasicNewsRecipe): |
| 9 |
title = 'Portfolio.hu' |
| 10 |
__author__ = 'bubak' |
| 11 |
oldest_article = 1 |
| 12 |
language = 'hu' |
| 13 |
|
| 14 |
author = 'bubak' |
| 15 |
simultaneous_downloads = 1 |
| 16 |
max_articles_per_feed = 50 |
| 17 |
|
| 18 |
feeds = [ |
| 19 |
('Összes hír', 'https://www.portfolio.hu/rss/all.xml'), |
| 20 |
('Globál hírek', 'https://www.portfolio.hu/rss/global.xml'), |
| 21 |
('Uniós források hírek', 'https://www.portfolio.hu/rss/unios-forrasok.xml'), |
| 22 |
('Gazdaság', 'http://www.portfolio.hu/rss/cikkek/gazdasag.xml'), |
| 23 |
('Ingatlan', 'http://www.portfolio.hu/rss/cikkek/ingatlan.xml'), |
| 24 |
('Pénzcentrum', 'http://www.penzcentrum.hu/rss/all.xml'), |
| 25 |
('All news', 'https://www.portfolio.hu/en/rss/all.xml'), |
| 26 |
] |
| 27 |
|
| 28 |
remove_tags = [ |
| 29 |
dict(name='div', attrs={'id': ['prevent-box']}), |
| 30 |
dict(name='div', attrs={'class': re.compile(r'conf-short', re.IGNORECASE)}), |
| 31 |
dict(name='img', attrs={'src': re.compile(r'\.(jpg|svg|gif)', re.IGNORECASE)}), |
| 32 |
dict(name='div', attrs={'class': re.compile(r'event.*linked|hidden|blogger-block|grid-block', re.IGNORECASE)}), |
| 33 |
dict(name='article', attrs={'class': re.compile(r'article-list-item', re.IGNORECASE)}), |
| 34 |
dict(name='section', attrs={'class': re.compile(r'pfblogger-block|recentnews|pfforum-box|newslettersubs|ai-summary', re.IGNORECASE)}), |
| 35 |
dict(name='section', attrs={'id': ['BlockPodcast', 'BlockCimlaprol', 'BlockTrader', 'BlockCalendar', 'BlockIngatlan']}), |
| 36 |
dict(name='ul', attrs={'class': 'tags'}), |
| 37 |
dict(name='div', attrs={'class': ['event-share', 'trc_rbox_container', 'related', 'author-name']}), |
| 38 |
dict(name='span', attrs={'class': 'footer-wrapper'}), |
| 39 |
] |
| 40 |
remove_tags_before = dict(name='h1') |
| 41 |
|
| 42 |
preprocess_regexps = [(re.compile(r'<a\s[^>]*>([^<]*)</a>', re.DOTALL | re.IGNORECASE), lambda match: match.group(1))] |
| 43 |
|
| 44 |
visited_urls = {} |
| 45 |
|
| 46 |
def get_article_url(self, article): |
| 47 |
url = BasicNewsRecipe.get_article_url(self, article) |
| 48 |
if url in self.visited_urls: |
| 49 |
self.log.debug('Ignoring duplicate: ' + url) |
| 50 |
return None |
| 51 |
else: |
| 52 |
self.visited_urls[url] = True |
| 53 |
self.log.debug('Accepting: ' + url) |
| 54 |
return url |