Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix purepc.pl recipe

Browse Source
This commit is contained in:
Tomasz Długosz 2018-10-13 23:11:36 +02:00
parent bd09779cd8
commit cbef5c2c9a
1 changed files with 3 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
recipes/pure_pc.recipe
View File

@ -11,35 +11,10 @@ class PurePC(BasicNewsRecipe):
description = u'Artykuły, aktualności, sprzęt, forum, chłodzenie, modding, urządzenia mobilne - wszystko w jednym miejscu.' description = u'Artykuły, aktualności, sprzęt, forum, chłodzenie, modding, urządzenia mobilne - wszystko w jednym miejscu.'
category = 'IT' category = 'IT'
language = 'pl' language = 'pl'
masthead_url = 'http://www.purepc.pl/themes/new/images/purepc.jpg'
cover_url = 'http://www.purepc.pl/themes/new/images/purepc.jpg' cover_url = 'http://www.purepc.pl/themes/new/images/purepc.jpg'
extra_css = '.wykres_logo {float: left; margin-right: 5px;}' extra_css = '.wykres_logo {float: left; margin-right: 5px;}'
no_stylesheets = True no_stylesheets = True
keep_only_tags = [dict(id='content')]
remove_tags_after = dict(attrs={'class': 'fivestar-widget'}) keep_only_tags = [dict(name='div', attrs={'class':'node page0'})]
remove_tags = [dict(id='navigator'), dict( remove_tags = [dict(name='div', attrs={'class':'article-options'})]
attrs={'class': ['box-tools', 'fivestar-widget', 'PageMenuList']})]
feeds = [(u'Wiadomo\u015bci', u'http://www.purepc.pl/node/feed')] feeds = [(u'Wiadomo\u015bci', u'http://www.purepc.pl/node/feed')]
def append_page(self, soup, appendtag):
lasturl = appendtag.find(attrs={'class': 'pager-last'})
if lasturl:
regex = re.search('(.+?2C)(\d+)', lasturl.a['href'])
baseurl = regex.group(1).replace('?page=0%2C', '?page=1%2C')
baseurl = 'http://www.purepc.pl' + baseurl
nr = int(regex.group(2))
for page_nr in range(1, nr + 1):
soup2 = self.index_to_soup(baseurl + str(page_nr))
pagetext = soup2.find(attrs={'class': 'article'})
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class': ['PageMenuList', 'pager', 'fivestar-widget']}):
r.extract()
comments = appendtag.findAll(
text=lambda text: isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
return soup