mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
99 lines
4.6 KiB
Plaintext
99 lines
4.6 KiB
Plaintext
import time
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Comment
|
|
|
|
class GryOnlinePl(BasicNewsRecipe):
|
|
title = u'Gry-Online.pl'
|
|
__author__ = 'fenuks'
|
|
description = u'Wiadomości o grach, recenzje, zapowiedzi. Encyklopedia Gier zawiera opisy gier na PC, konsole Xbox360, PS3 i inne platformy.'
|
|
category = 'games'
|
|
language = 'pl'
|
|
oldest_article = 13
|
|
INDEX = 'http://www.gry-online.pl/'
|
|
masthead_url = 'http://www.gry-online.pl/im/gry-online-logo.png'
|
|
cover_url = 'http://www.gry-online.pl/im/gry-online-logo.png'
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
keep_only_tags = [dict(name='div', attrs={'class':['gc660', 'gc660 S013', 'news_endpage_tit', 'news_container', 'news']})]
|
|
remove_tags = [dict({'class':['nav-social', 'add-info', 'smlb', 'lista lista3 lista-gry', 'S013po', 'S013-npb', 'zm_gfx_cnt_bottom', 'ocen-txt', 'wiecej-txt', 'wiecej-txt2',
|
|
'twitter-share-button']})]
|
|
feeds = [
|
|
(u'Newsy', 'http://www.gry-online.pl/rss/news.xml'),
|
|
('Teksty', u'http://www.gry-online.pl/rss/teksty.xml')]
|
|
|
|
|
|
def append_page(self, soup, appendtag):
|
|
tag = appendtag.find('div', attrs={'class':'n5p'})
|
|
if tag:
|
|
nexturls=tag.findAll('a')
|
|
url_part = soup.find('link', attrs={'rel':'canonical'})['href']
|
|
url_part = url_part[25:].rpartition('?')[0]
|
|
for nexturl in nexturls[1:-1]:
|
|
finalurl = 'http://www.gry-online.pl/' + url_part + nexturl['href']
|
|
for i in range(10):
|
|
try:
|
|
soup2 = self.index_to_soup(finalurl)
|
|
break
|
|
except:
|
|
print 'retrying in 0.5s'
|
|
time.sleep(0.5)
|
|
pagetext = soup2.find(attrs={'class':'gc660'})
|
|
for r in pagetext.findAll(name='header'):
|
|
r.extract()
|
|
for r in pagetext.findAll(attrs={'itemprop':'description'}):
|
|
r.extract()
|
|
|
|
pos = len(appendtag.contents)
|
|
appendtag.insert(pos, pagetext)
|
|
for r in appendtag.findAll(attrs={'class':['n5p', 'add-info', 'twitter-share-button', 'lista lista3 lista-gry', 'imh10b']}):
|
|
r.extract()
|
|
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
|
|
for comment in comments:
|
|
comment.extract()
|
|
else:
|
|
tag = appendtag.find('div', attrs={'class':'S018stronyr'})
|
|
if tag:
|
|
nexturl = tag.a
|
|
url_part = soup.find('link', attrs={'rel':'canonical'})['href']
|
|
url_part = url_part[25:].rpartition('?')[0]
|
|
while tag:
|
|
end = tag.find(attrs={'class':'right left-dead'})
|
|
if end:
|
|
break
|
|
else:
|
|
nexturl = tag.a
|
|
finalurl = 'http://www.gry-online.pl/' + url_part + nexturl['href']
|
|
for i in range(10):
|
|
try:
|
|
soup2 = self.index_to_soup(finalurl)
|
|
break
|
|
except:
|
|
print 'retrying in 0.5s'
|
|
time.sleep(0.5)
|
|
tag = soup2.find('div', attrs={'class':'S018stronyr'})
|
|
pagetext = soup2.find(attrs={'class':'gc660'})
|
|
for r in pagetext.findAll(name='header'):
|
|
r.extract()
|
|
for r in pagetext.findAll(attrs={'itemprop':'description'}):
|
|
r.extract()
|
|
|
|
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
|
|
[comment.extract() for comment in comments]
|
|
pos = len(appendtag.contents)
|
|
appendtag.insert(pos, pagetext)
|
|
for r in appendtag.findAll(attrs={'class':['n5p', 'add-info', 'twitter-share-button', 'lista lista3 lista-gry', 'S018strony', 'imh10b']}):
|
|
r.extract()
|
|
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
|
|
for comment in comments:
|
|
comment.extract()
|
|
|
|
def image_url_processor(self, baseurl, url):
|
|
if url.startswith('..'):
|
|
return url[2:]
|
|
else:
|
|
return url
|
|
|
|
def preprocess_html(self, soup):
|
|
self.append_page(soup, soup.body)
|
|
return soup
|