| 1 |
""" |
| 2 |
Fetch Blikk |
| 3 |
""" |
| 4 |
|
| 5 |
import re |
| 6 |
|
| 7 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 8 |
|
| 9 |
|
| 10 |
class blikk(BasicNewsRecipe): |
| 11 |
title = 'Blikk' |
| 12 |
description = '' |
| 13 |
__author__ = 'bubak' |
| 14 |
use_embedded_content = False |
| 15 |
oldest_article = 2 |
| 16 |
max_articles_per_feed = 40 |
| 17 |
no_stylesheets = True |
| 18 |
language = 'hu' |
| 19 |
simultaneous_downloads = 5 |
| 20 |
|
| 21 |
remove_javascript = True |
| 22 |
cover_url = 'http://imagestore1.btl.hu/57_10_2465_576f066aec514d35e7fee2081dde5ffe_07ce26_701.jpg' |
| 23 |
|
| 24 |
feeds = [('Blikk.hu hírek', 'http://blikk.hu/rss')] |
| 25 |
|
| 26 |
extra_css = ''' |
| 27 |
''' |
| 28 |
|
| 29 |
preprocess_regexps = [(re.compile(r'href="[^"]*["]', re.DOTALL | re.IGNORECASE), lambda match: '')] |
| 30 |
|
| 31 |
remove_tags = [ |
| 32 |
dict(name='span', attrs={'class': ['hirdetes']}), |
| 33 |
dict(name='div', attrs={'class': ['cikkFejlec']}), |
| 34 |
dict(name='div', attrs={'id': re.compile(r'div-gpt-ad|adoceanindex', re.IGNORECASE)}), |
| 35 |
dict(name='a', attrs={'class': re.compile(r'gap-2', re.IGNORECASE)}), |
| 36 |
dict(name='p', attrs={'class': re.compile(r'py-2', re.IGNORECASE)}), |
| 37 |
dict(name='div', attrs={'id': ['subscription-box-container', 'articleOfferFlag']}), |
| 38 |
dict(name='div', attrs={'data-tagrecommendation': '/next-topmodel-hungary'}), |
| 39 |
dict(name='div', attrs={'data-blockIndex'}), |
| 40 |
dict(name='header', attrs={'id': ['header']}), |
| 41 |
dict(name='section', attrs={'class': re.compile(r'rightside|google-news|breadcrumb|pb-3', re.IGNORECASE)}), |
| 42 |
dict(name='section', attrs={'class': lambda x: x and 'rightSide' in x.split()}), |
| 43 |
dict(name='section', attrs={'id': 'articleEnd'}), |
| 44 |
dict(name='img', attrs={'alt': 'Szólj hozzá!'}), |
| 45 |
] |
| 46 |
|
| 47 |
remove_tags_after = dict(name='section', attrs={'id': 'articleEnd'}) |
| 48 |
|
| 49 |
def skip_ad_pages(self, soup): |
| 50 |
# ads have fewer links |
| 51 |
self.log.debug('Number of links: ', len(soup.findAll('a'))) |
| 52 |
self.log.debug('Links: ', soup.findAll('a')) |
| 53 |
if len(soup.findAll('a')) < 20: |
| 54 |
a = soup.find('a', text=re.compile(r'^click here')).findParents('a') |
| 55 |
href = a[0]['href'] |
| 56 |
self.log.debug('Skipping to: ' + href) |
| 57 |
new = self.browser.open(href).read().decode('utf-8', 'ignore') |
| 58 |
self.log.debug('Finished: ' + href) |
| 59 |
return new |
| 60 |
return None |