| 1 |
import re |
| 2 |
|
| 3 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 4 |
|
| 5 |
|
| 6 |
class syrzdarmaRecipe(BasicNewsRecipe): |
| 7 |
__author__ = 'bubak' |
| 8 |
title = 'Sýr zdarma' |
| 9 |
description = 'syrzdarma.cz' |
| 10 |
oldest_article = 1 |
| 11 |
max_articles_per_feed = 20 |
| 12 |
|
| 13 |
sections = [('Sýr zdarma', 'https://www.syrzdarma.cz')] |
| 14 |
|
| 15 |
language = 'cs' |
| 16 |
cover_url = 'https://www.syrzdarma.cz/assets/logo-text-optimized.svg' |
| 17 |
remove_javascript = False |
| 18 |
no_stylesheets = True |
| 19 |
use_embedded_content = False |
| 20 |
recursions = 0 |
| 21 |
articles_are_obfuscated = True |
| 22 |
|
| 23 |
ignore_duplicate_articles = {'title', 'url'} |
| 24 |
|
| 25 |
remove_attributes = [] |
| 26 |
remove_tags_before = dict(name='h1', attrs={'class': ['AAAtitulek-clanku']}) |
| 27 |
remove_tags = [dict(name='img'), dict(name='div', attrs={'AAAclass': re.compile(r'sidebar-column|post-share|no-login-icon', re.IGNORECASE)})] |
| 28 |
|
| 29 |
visited_urls = {} |
| 30 |
|
| 31 |
def get_article_url(self, article): |
| 32 |
url = BasicNewsRecipe.get_article_url(self, article) |
| 33 |
if url in self.visited_urls: |
| 34 |
self.log.debug('Ignoring duplicate: ' + url) |
| 35 |
return None |
| 36 |
else: |
| 37 |
self.visited_urls[url] = True |
| 38 |
self.log.debug('Accepting: ' + url) |
| 39 |
return url |
| 40 |
|
| 41 |
def get_obfuscated_article(self, url): |
| 42 |
result = None |
| 43 |
response = self.browser.open(url) |
| 44 |
html = response.read().decode('utf-8') |
| 45 |
|
| 46 |
s1 = re.sub(r'^.*cdk-overlay-container', '', html, flags=re.DOTALL) |
| 47 |
s2 = re.sub(r'^.*articleComponent_article', '', s1, flags=re.DOTALL) |
| 48 |
s2a = re.sub(r'\n.*', '', s2) |
| 49 |
s3 = re.sub(r'\\&q;', '', s2a) |
| 50 |
s4 = re.sub(r',*{insert:([^}]*)},*', r'\1', s3) |
| 51 |
s5 = re.sub(r',*{attributes:{([^:]*)[^}]*},insert:([^}]*)}', r'<\1>\2</\1>', s4) |
| 52 |
s5a = re.sub(r',*{attributes:{nbsp:{}},insert:([^}]*)}', ' ', s5) |
| 53 |
s6 = re.sub(r'\\\\n', '<br>', s5a) |
| 54 |
s6a = re.sub(r'\\n', '<br>', s6) |
| 55 |
s7 = s6a.replace(r'bold>', 'b>') |
| 56 |
s8 = s7.replace(r'italic>', 'i>') |
| 57 |
s9 = re.sub(r'].*', '', s8) |
| 58 |
s9a = s9.replace('&s;', "'") |
| 59 |
s10 = re.sub(r'^.*title&q;:&q;([^&]*)&.*perex&q;:&q;([^&]*)&q.*\[', r'<h1>\1</h1><i>\2</i>', s9a) |
| 60 |
|
| 61 |
result = s10 |
| 62 |
return {'data': result, 'url': url} |
| 63 |
|
| 64 |
def parse_index(self): |
| 65 |
res = [] |
| 66 |
for section in self.sections: |
| 67 |
self.log('\tTrying section ' + section[0]) |
| 68 |
soup = self.index_to_soup(section[1]) |
| 69 |
content = soup.find_all('h1') |
| 70 |
if content is None: |
| 71 |
raise ValueError('Could not find category content') |
| 72 |
seen_urls = set() |
| 73 |
articles = [] |
| 74 |
for article in content: |
| 75 |
a = article.find('a') |
| 76 |
if a.get('href'): |
| 77 |
url = a['href'] |
| 78 |
if url.startswith('/'): |
| 79 |
url = 'https://syrzdarma.cz' + url |
| 80 |
if url in seen_urls: |
| 81 |
continue |
| 82 |
seen_urls.add(url) |
| 83 |
title = a.contents[0] |
| 84 |
self.log('\tFound article:', title, url) |
| 85 |
articles.append({'title': title, 'url': url, 'description': '', 'date': ''}) |
| 86 |
res.append((section[0], articles)) |
| 87 |
return res |
| 88 |
|
| 89 |
def image_url_processor(b, u): |
| 90 |
None |