| 1 |
import re |
| 2 |
|
| 3 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 4 |
|
| 5 |
|
| 6 |
class argumentRecipe(BasicNewsRecipe): |
| 7 |
__author__ = 'bubak' |
| 8 |
title = '!argument' |
| 9 |
description = 'casopisargument.cz' |
| 10 |
oldest_article = 1 |
| 11 |
max_articles_per_feed = 20 |
| 12 |
|
| 13 |
sections = [('Argument', 'http://casopisargument.cz')] |
| 14 |
|
| 15 |
language = 'cs' |
| 16 |
cover_url = 'http://casopisargument.cz/wp-content/uploads/2016/12/logo-argument.png' |
| 17 |
remove_javascript = True |
| 18 |
no_stylesheets = True |
| 19 |
|
| 20 |
remove_attributes = [] |
| 21 |
remove_tags_before = dict(name='h1', attrs={'class': ['entry-title']}) |
| 22 |
remove_tags_after = dict(name='footer', attrs={'class': ['entry-footer']}) |
| 23 |
remove_tags = [dict(name='img'), dict(name='div', attrs={'id': ['AAAsocial-bookmark']})] |
| 24 |
|
| 25 |
preprocess_regexps = [(re.compile(r'<a\s[^>]*>([^<]*)</a>', re.DOTALL | re.IGNORECASE), lambda match: match.group(1))] |
| 26 |
|
| 27 |
def parse_index(self): |
| 28 |
res = [] |
| 29 |
seen_titles = set() |
| 30 |
for section in self.sections: |
| 31 |
self.log('\tTrying section ' + section[0]) |
| 32 |
articles = [] |
| 33 |
soup = self.index_to_soup(section[1]) |
| 34 |
content = soup.findAll('article') |
| 35 |
if content is None: |
| 36 |
raise ValueError('Could not find category content') |
| 37 |
for c in content: |
| 38 |
article = c.find('a', text=re.compile(r'.')) |
| 39 |
if article and article.get('href'): |
| 40 |
url = article['href'] |
| 41 |
title = re.sub(r'^\s*(\S.*\S)\s*$', r'\1', article.text) |
| 42 |
if url.startswith('/'): |
| 43 |
url = 'http://casopisargument.cz' + url |
| 44 |
if title in seen_titles: |
| 45 |
self.log('\tAlready seen: ', title) |
| 46 |
continue |
| 47 |
seen_titles.add(title) |
| 48 |
self.log('\tFound article:', title, 'at', url) |
| 49 |
articles.append({'title': title, 'url': url, 'description': '', 'date': ''}) |
| 50 |
res.append((section[0], articles)) |
| 51 |
return res |