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

Update .týždeň recipe

Browse Source
This commit is contained in:
Martin Racak 2017-03-10 00:18:13 +01:00
parent db6243dfff
commit 25cfde2945
1 changed files with 62 additions and 76 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

138
recipes/tyzden.recipe
View File

@ -1,7 +1,7 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=utf-8 # vim:fileencoding=utf-8
# #
# Copyright 2014 - 2016 Martin Račák <rakyi@riseup.net> # Copyright 2014 - 2017 Martin Račák <rakyi@riseup.net>
# Copyright 2011 Miroslav Vasko <zemiak@gmail.com> # Copyright 2011 Miroslav Vasko <zemiak@gmail.com>
# #
# This program is free software: you can redistribute it and/or modify # This program is free software: you can redistribute it and/or modify
@ -18,12 +18,10 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>. # along with this program. If not, see <http://www.gnu.org/licenses/>.
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = ('2014 - 2015 Martin Račák <martin.racak@riseup.net>,' __copyright__ = ('2014 - 2017 Martin Račák <martin.racak@riseup.net>,'
'2011 Miroslav Vasko <zemiak@gmail.com>') '2011 Miroslav Vasko <zemiak@gmail.com>')
''' import re
.týždeň - iný pohľad na spoločnosť
'''
from calibre import strftime from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
@ -39,102 +37,90 @@ class Tyzden(BasicNewsRecipe):
needs_subscription = 'optional' needs_subscription = 'optional'
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
base_url = 'http://www.tyzden.sk' issue_url = 'http://www.tyzden.sk/casopis/'
piano_param = '?piano_d=1'
issue_url = base_url + '/casopis/'
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'class': 'detail__title article__title'}), dict(name='div', attrs={'class': 'section__content section__content--archive'}),
dict(name='div', attrs={'class': 'article'}), dict(name='article', attrs={'class': re.compile(r'\barticle\b')}),
] ]
extra_css = """*, *::before, *::after {
-moz-box-sizing: border-box; extra_css = """.theme-highlight {
-webkit-box-sizing: border-box; color: #999;
box-sizing: border-box; text-decoration: none;
} }
.detail__content h2::before { .author-highlight {
color: #000; color: #bf1f10;
content: "."; text-decoration: none;
}
.article__content h2::before {
content: '.';
display: inline; display: inline;
} }
.highlight { .article__image-credit {
color: #bf1f10; font: 12px "TheSerifSemiLight",arial;
}
.content-photo__image-credit,
.photo__image-credit {
font-size: 11px;
font-family: 'Helvetica Neue', 'Helvetica', 'Arial', sans-serif;
text-transform: uppercase; text-transform: uppercase;
} }
.image-title { .article__image-title {
border-bottom: 3px solid #bf1f10; padding-top: 2px;
display: block; padding-bottom: 2px;
padding-bottom: 3px; margin: 0;
line-height: 22px; font: 15px "TheSerifBold",arial;
font-size: 16px; border-bottom: 2px solid #bf1f10;
font-family: 'TheMix_Bold', 'Georgia', 'Times', 'Times New Roman', serif;
font-weight: 500;
}
.teaser--mag-feature {
margin-top: 25px;
padding: 10px 0 10px;
width: 100%;
box-sizing: content-box;
border-top: 2px dotted #555;
border-bottom: 2px dotted #555;
font-size: 20px;
}
.teaser__wrapper {
display: block; display: block;
} }
.teaser a { .teaser__title {
outline: none; font: 18px "TheSerifBold",arial;
text-decoration: none; color: #bf1f10;
color: inherit;
} }
.teaser__title { .teaser__title .highlight {
font-size: 26px; color: #000;
}""" }
"""
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
br.open(self.base_url + '/' + self.piano_param)
br.set_cookie('_t', '9bcb7dc397cf9516cbc504b700cf14e', '.tyzden.sk')
br.set_cookie('pianovisitkey', '', '.tyzden.sk')
if self.username is not None and self.password is not None: if self.username is not None and self.password is not None:
br.select_form(nr=2) br.open('https://crm.tyzden.sk/sign/in/')
br['email'] = self.username br.select_form(nr=0)
br['username'] = self.username
br['password'] = self.password br['password'] = self.password
br.submit() br.submit()
return br return br
def find_sections(self): def parse_index(self):
soup = self.index_to_soup(self.issue_url) soup = self.index_to_soup(self.issue_url)
img_wrapper = soup.find('div', 'mag__title-img-wrapper') cover_img = soup.findAll('img', 'teaser__image')[-1]
if img_wrapper is not None: if cover_img is not None:
self.cover_url = img_wrapper.img['src'] self.cover_url = cover_img['src']
for section in soup.findAll('div', 'mag__section'): feeds = []
section_title = section.find('span', 'mag__section-title') teasers = soup.findAll('div', {'class': re.compile(r'\bteaser--list\b')})
yield (self.tag_to_string(section_title), section) for teaser in teasers:
section = self.tag_to_string(teaser.find('a', 'theme-heading__wrapper'))
def find_articles(self, soup): article_title = self.tag_to_string(
for title in soup.findAll('h1', 'teaser__title'): teaser.find('h1', {'class': re.compile(r'\bteaser__title\b')}))
yield { article_link = teaser.find('a', 'teaser__link--main')
'title': self.tag_to_string(title.a), article = {
'url': title.a['href'], 'title': article_title,
'date': strftime(' %a, %d %b'), 'url': article_link['href'],
'date': strftime(' %a, %d %b')
} }
def parse_index(self): if not feeds:
feeds = [] # First cycle iteration.
for title, section in self.find_sections(): feeds.append((section, [article]))
feeds.append((title, list(self.find_articles(section)))) continue
last_section, last_articles = feeds[-1]
if section == last_section:
last_articles.append(article)
else:
feeds.append((section, [article]))
return feeds return feeds