Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update .tyzden

Browse Source 
Merge branch 'master' of https://github.com/rakyi/calibre
This commit is contained in:
Kovid Goyal 2015-08-27 09:02:12 +05:30
commit 730c7387fd
1 changed files with 35 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
recipes/tyzden.recipe
View File

@ -18,66 +18,61 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
__license__ = 'GPL v3'
__copyright__ = '2014 - 2015 Martin Račák <martin.racak@riseup.net>, 2011 Miroslav Vasko <zemiak@gmail.com>'
__copyright__ = ('2014 - 2015 Martin Račák <martin.racak@riseup.net>,'
'2011 Miroslav Vasko <zemiak@gmail.com>')
'''
.týždeň - iný pohľad na spoločnosť
'''
import re
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Tyzden(BasicNewsRecipe):
title = u'týždeň'
title = u'.týždeň'
__author__ = u'Martin Račák, zemiak'
description = 'A conservative weekly magazine.'
description = u'Politicko-spoločenský týždenník.'
publisher = 'www.tyzden.sk'
publication_type = 'magazine'
language = 'sk'
needs_subscription = 'optional'
use_embedded_content = False
no_stylesheets = True
base_url = 'http://www.tyzden.sk'
piano_param = '?piano_d=1'
issue_url = base_url + '/casopis/'
keep_only_tags = [
dict(name='div', attrs={'class': 'detail__title article__title'}),
dict(name='div', attrs={'class': 'article'}),
]
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open(self.base_url + '/' + self.piano_param)
br.set_cookie('pianovisitkey=""')
if self.username is not None and self.password is not None:
br.open('http://www.tyzden.sk/prihlasenie.html')
br.select_form(nr=1)
br['user'] = self.username
br['pass'] = self.password
br.select_form(nr=2)
br['username'] = self.username
br['password'] = self.password
br.submit()
return br
base_url = 'http://www.tyzden.sk/'
issue_url = base_url + 'casopis.html'
keep_only_tags = []
keep_only_tags.append(dict(name='div', attrs={'class': 'text_area top_nofoto'}))
keep_only_tags.append(dict(name='div', attrs={'class': 'text_block'}))
def find_sections(self):
soup = self.index_to_soup(self.issue_url)
# Use only the impotant part of page
content = soup.find('div', 'top')
content.extract()
img_wrapper = soup.find('div', 'mag__title-img-wrapper')
if img_wrapper is not None:
self.cover_url = img_wrapper.img['src']
# Find cover pic
img = content.find('div', 'foto').img
if img is not None:
self.cover_url = self.base_url + img['src']
for section in content.findAll('a', {'href': re.compile(r'rubrika/.*')}):
yield (self.tag_to_string(section), section)
for section in soup.findAll('div', 'mag__section'):
section_title = section.find('span', 'mag__section-title')
yield (self.tag_to_string(section_title), section)
def find_articles(self, soup):
for article in soup.findAllNext('a'):
if (not article['href'].startswith('casopis/')):
break
for title in soup.findAll('h1', 'teaser__title'):
yield {
'title': self.tag_to_string(article),
'url': self.base_url + article['href'],
'title': self.tag_to_string(title.a),
'url': title.a['href'],
'date': strftime(' %a, %d %b'),
}
@ -85,6 +80,5 @@ class Tyzden(BasicNewsRecipe):
feeds = []
for title, section in self.find_sections():
feeds.append((title, list(self.find_articles(section))))
return feeds