| 1 |
import re |
| 2 |
|
| 3 |
from calibre.ebooks.BeautifulSoup import Comment |
| 4 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 5 |
|
| 6 |
|
| 7 |
class in4(BasicNewsRecipe): |
| 8 |
title = 'IN4.pl' |
| 9 |
oldest_article = 7 |
| 10 |
max_articles_per_feed = 100 |
| 11 |
__author__ = 'fenuks' |
| 12 |
description = 'Serwis Informacyjny - Aktualnosci, recenzje' |
| 13 |
category = 'IT' |
| 14 |
language = 'pl' |
| 15 |
index = 'http://www.in4.pl/' |
| 16 |
no_stylesheets = True |
| 17 |
remove_empty_feeds = True |
| 18 |
preprocess_regexps = [(re.compile(r'<a title="translate into.*?</a>', re.DOTALL), lambda match: '')] |
| 19 |
keep_only_tags = [dict(name='div', attrs={'class': 'left_alone'})] |
| 20 |
remove_tags_after = dict(name='img', attrs={'title': 'komentarze'}) |
| 21 |
remove_tags = [dict(name='img', attrs={'title': 'komentarze'})] |
| 22 |
feeds = [ |
| 23 |
('Wiadomo\u015bci', 'http://www.in4.pl/rss.php'), |
| 24 |
('Recenzje', 'http://www.in4.pl/rss_recenzje.php'), |
| 25 |
('Mini recenzje', 'http://www.in4.pl/rss_mini.php'), |
| 26 |
] |
| 27 |
|
| 28 |
def append_page(self, soup, appendtag): |
| 29 |
a = soup.findAll('a') |
| 30 |
nexturl = None |
| 31 |
for i in a: |
| 32 |
if i.string and 'następna str' in i.string: |
| 33 |
nexturl = 'http://www.in4.pl/' + i['href'] |
| 34 |
i.extract() |
| 35 |
while nexturl: |
| 36 |
soup2 = self.index_to_soup(nexturl) |
| 37 |
pagetext = soup2.find(id='news') |
| 38 |
comments = pagetext.findAll(text=lambda text: isinstance(text, Comment)) |
| 39 |
for comment in comments: |
| 40 |
comment.extract() |
| 41 |
pos = len(appendtag.contents) |
| 42 |
appendtag.insert(pos, pagetext) |
| 43 |
nexturl = None |
| 44 |
tag = soup2.findAll('a') |
| 45 |
for z in tag: |
| 46 |
if z.string and 'następna str' in z.string: |
| 47 |
nexturl = 'http://www.in4.pl/' + z['href'] |
| 48 |
break |
| 49 |
|
| 50 |
def preprocess_html(self, soup): |
| 51 |
self.append_page(soup, soup.body) |
| 52 |
for a in soup.findAll('a', href=True): |
| 53 |
if 'http://' not in a['href'] and 'https://' not in a['href']: |
| 54 |
a['href'] = self.index + a['href'] |
| 55 |
return soup |