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
# 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>
#
# 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/>.
__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>')
'''
.týždeň - iný pohľad na spoločnosť
'''
import re
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
@ -39,102 +37,90 @@ class Tyzden(BasicNewsRecipe):
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/'
issue_url = 'http://www.tyzden.sk/casopis/'
keep_only_tags = [
dict(name='div', attrs={'class': 'detail__title article__title'}),
dict(name='div', attrs={'class': 'article'}),
dict(name='div', attrs={'class': 'section__content section__content--archive'}),
dict(name='article', attrs={'class': re.compile(r'\barticle\b')}),
]
extra_css = """*, *::before, *::after {
-moz-box-sizing: border-box;
-webkit-box-sizing: border-box;
box-sizing: border-box;
extra_css = """.theme-highlight {
color: #999;
text-decoration: none;
}
.detail__content h2::before {
color: #000;
content: ".";
.author-highlight {
color: #bf1f10;
text-decoration: none;
}
.article__content h2::before {
content: '.';
display: inline;
}
.highlight {
color: #bf1f10;
}
.content-photo__image-credit,
.photo__image-credit {
font-size: 11px;
font-family: 'Helvetica Neue', 'Helvetica', 'Arial', sans-serif;
.article__image-credit {
font: 12px "TheSerifSemiLight",arial;
text-transform: uppercase;
}
.image-title {
border-bottom: 3px solid #bf1f10;
display: block;
padding-bottom: 3px;
line-height: 22px;
font-size: 16px;
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 {
.article__image-title {
padding-top: 2px;
padding-bottom: 2px;
margin: 0;
font: 15px "TheSerifBold",arial;
border-bottom: 2px solid #bf1f10;
display: block;
}
.teaser a {
outline: none;
text-decoration: none;
color: inherit;
.teaser__title {
font: 18px "TheSerifBold",arial;
color: #bf1f10;
}
.teaser__title {
font-size: 26px;
}"""
.teaser__title .highlight {
color: #000;
}
"""
def 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:
br.select_form(nr=2)
br['email'] = self.username
br.open('https://crm.tyzden.sk/sign/in/')
br.select_form(nr=0)
br['username'] = self.username
br['password'] = self.password
br.submit()
return br
def find_sections(self):
def parse_index(self):
soup = self.index_to_soup(self.issue_url)
img_wrapper = soup.find('div', 'mag__title-img-wrapper')
if img_wrapper is not None:
self.cover_url = img_wrapper.img['src']
cover_img = soup.findAll('img', 'teaser__image')[-1]
if cover_img is not None:
self.cover_url = cover_img['src']
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 title in soup.findAll('h1', 'teaser__title'):
yield {
'title': self.tag_to_string(title.a),
'url': title.a['href'],
'date': strftime(' %a, %d %b'),
feeds = []
teasers = soup.findAll('div', {'class': re.compile(r'\bteaser--list\b')})
for teaser in teasers:
section = self.tag_to_string(teaser.find('a', 'theme-heading__wrapper'))
article_title = self.tag_to_string(
teaser.find('h1', {'class': re.compile(r'\bteaser__title\b')}))
article_link = teaser.find('a', 'teaser__link--main')
article = {
'title': article_title,
'url': article_link['href'],
'date': strftime(' %a, %d %b')
}
def parse_index(self):
feeds = []
for title, section in self.find_sections():
feeds.append((title, list(self.find_articles(section))))
if not feeds:
# First cycle iteration.
feeds.append((section, [article]))
continue
last_section, last_articles = feeds[-1]
if section == last_section:
last_articles.append(article)
else:
feeds.append((section, [article]))
return feeds