| 1 |
import re |
| 2 |
|
| 3 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 4 |
|
| 5 |
|
| 6 |
class telexRecipe(BasicNewsRecipe): |
| 7 |
__author__ = 'bubak' |
| 8 |
title = 'telex' |
| 9 |
description = 'telex.hu' |
| 10 |
oldest_article = 1 |
| 11 |
max_articles_per_feed = 20 |
| 12 |
|
| 13 |
sections = [ |
| 14 |
('BELFÖLD', 'https://telex.hu/rovat/belfold'), |
| 15 |
('KÜLFÖLD', 'https://telex.hu/rovat/kulfold'), |
| 16 |
('GAZDASÁG', 'https://telex.hu/rovat/gazdasag'), |
| 17 |
('ÉLET', 'https://telex.hu/rovat/eletmod'), |
| 18 |
('TECHTUD', 'https://telex.hu/rovat/techtud'), |
| 19 |
('ENGLISH', 'https://telex.hu/english'), |
| 20 |
] |
| 21 |
|
| 22 |
language = 'hu' |
| 23 |
no_stylesheets = True |
| 24 |
use_embedded_content = False |
| 25 |
|
| 26 |
preprocess_regexps = [(re.compile(r'<a\s[^>]*>([^<]*)</a>', re.DOTALL | re.IGNORECASE), lambda match: match.group(1))] |
| 27 |
|
| 28 |
remove_attributes = [] |
| 29 |
remove_tags = [ |
| 30 |
dict(name='div', attrs={'class': ['navigation-container', 'content-wrapper', 'hint_box', 'journalist']}), |
| 31 |
dict(name='div', attrs={'class': re.compile(r'navigation--ov26', re.IGNORECASE)}), |
| 32 |
] |
| 33 |
remove_tags_after = dict(name='div', attrs={'class': 'support-box'}) |
| 34 |
|
| 35 |
visited_urls = {} |
| 36 |
|
| 37 |
def get_browser(self, *a, **kw): |
| 38 |
kw['verify_ssl_certificates'] = False |
| 39 |
return super().get_browser(*a, **kw) |
| 40 |
|
| 41 |
def parse_index(self): |
| 42 |
res = [] |
| 43 |
for section in self.sections: |
| 44 |
self.log('\tTrying section ' + section[0]) |
| 45 |
soup = self.index_to_soup(section[1]) |
| 46 |
content = soup.findAll('div', attrs={'class': re.compile(r'list__highlight__item__title', re.IGNORECASE)}) |
| 47 |
content += soup.findAll('a', attrs={'class': re.compile(r'list__item__title', re.IGNORECASE)}) |
| 48 |
|
| 49 |
if content is None: |
| 50 |
raise ValueError('Could not find section content') |
| 51 |
seen_urls = set() |
| 52 |
articles = [] |
| 53 |
for a in content: |
| 54 |
if a.a: |
| 55 |
url = a.a['href'] |
| 56 |
if url.startswith('/'): |
| 57 |
url = 'https://telex.hu' + url |
| 58 |
if url in seen_urls: |
| 59 |
continue |
| 60 |
seen_urls.add(url) |
| 61 |
self.log('\tFound ' + url) |
| 62 |
title = a.a.contents[0] |
| 63 |
self.log('\tFound article:', title, url) |
| 64 |
articles.append({'title': title, 'url': url, 'description': '', 'date': ''}) |
| 65 |
else: |
| 66 |
url = a['href'] |
| 67 |
if url.startswith('/'): |
| 68 |
url = 'https://telex.hu' + url |
| 69 |
if url in seen_urls: |
| 70 |
continue |
| 71 |
seen_urls.add(url) |
| 72 |
self.log('\tFound ' + url) |
| 73 |
title = a.find('div').find('div').find('div').contents[0] |
| 74 |
self.log('\tFound article:', title, url) |
| 75 |
articles.append({'title': title, 'url': url, 'description': '', 'date': ''}) |
| 76 |
res.append((section[0], articles)) |
| 77 |
return res |
| 78 |
|
| 79 |
def populate_article_metadata(self, article, soup, first): |
| 80 |
self.log('Article date ', article.date) |