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

New recipes for Republika and Monitor Online by Darko Miletic

Browse Source
This commit is contained in:
Kovid Goyal 2009-08-19 09:34:17 -06:00
parent 935b76f6c1
commit cf3582d450
3 changed files with 166 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/calibre/web/feeds/recipes/__init__.py
View File

@ -54,6 +54,7 @@ recipe_modules = ['recipe_' + r for r in (
'fastcompany', 'accountancyage', 'laprensa_hn', 'latribuna',
'eltiempo_hn', 'slate', 'tnxm', 'bbcvietnamese', 'vnexpress',
'volksrant', 'theeconomictimes_india', 'ourdailybread',
'monitor', 'republika',
)]

85
src/calibre/web/feeds/recipes/recipe_monitor.py Normal file
View File

@ -0,0 +1,85 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
monitorcg.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
class MonitorCG(BasicNewsRecipe):
title = 'Monitor online'
__author__ = 'Darko Miletic'
description = 'News from Montenegro'
publisher = 'MONITOR d.o.o. Podgorica'
category = 'news, politics, Montenegro'
oldest_article = 15
max_articles_per_feed = 150
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
language = _('Montenegrin')
lang ='sr-Latn-Me'
INDEX = 'http://www.monitorcg.com'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : lang
, 'pretty_print' : True
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [dict(name='div', attrs={'id':'ja-current-content'})]
remove_tags = [ dict(name=['object','link','embed'])
, dict(attrs={'class':['buttonheading','article-section']})]
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(0,mlang)
soup.head.insert(1,mcharset)
return self.adeify_images(soup)
def parse_index(self):
totalfeeds = []
soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('div',attrs={'class':'ja-catslwi'})
if cover_item:
dt = cover_item['onclick'].partition("location.href=")[2]
curl = self.INDEX + dt.strip("'")
lfeeds = [(u'Svi clanci', curl)]
for feedobj in lfeeds:
feedtitle, feedurl = feedobj
self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
articles = []
soup = self.index_to_soup(feedurl)
contitem = soup.find('div',attrs={'class':'article-content'})
if contitem:
img = contitem.find('img')
if img:
self.cover_url = self.INDEX + img['src']
for item in contitem.findAll('a'):
url = self.INDEX + item['href']
title = self.tag_to_string(item)
articles.append({
'title' :title
,'date' :''
,'url' :url
,'description':''
})
totalfeeds.append((feedtitle, articles))
return totalfeeds

80
src/calibre/web/feeds/recipes/recipe_republika.py Normal file
View File

@ -0,0 +1,80 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
republika.co.yu
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Republika(BasicNewsRecipe):
title = 'Republika'
__author__ = 'Darko Miletic'
description = 'Glasilo gradjanskog samooslobadjanja. Protiv stihije straha, mrznje i nasilja'
publisher = ' Zadruga Res Publica'
category = 'news, politics, Serbia'
language = _('Serbian')
lang = 'sr-Latn-RS'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'cp1250'
use_embedded_content = False
INDEX = u'http://www.republika.co.yu/'
extra_css = ' @font-face {font-family: "serif1"; src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif} .naslov{font-size: x-large; font-weight: bold} .autor{font-size: small; font-weight: bold} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : lang
, 'pretty_print' : True
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [ dict(attrs={'class':'naslov'})
, dict(attrs={'class':'text1'})
]
remove_tags = [dict(name=['object','link','iframe','base','img'])]
feeds = [(u'Svi clanci', INDEX)]
def preprocess_html(self, soup):
attribs = [ 'style','font','valign'
,'colspan','width','height'
,'rowspan','summary','align'
,'cellspacing','cellpadding'
,'frames','rules','border'
]
for item in soup.body.findAll(name=['table','td','tr','th','caption','thead','tfoot','tbody','colgroup','col']):
item.name = 'div'
for attrib in attribs:
if item.has_key(attrib):
del item[attrib]
return soup
def parse_index(self):
totalfeeds = []
lfeeds = self.get_feeds()
for feedobj in lfeeds:
feedtitle, feedurl = feedobj
self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
articles = []
soup = self.index_to_soup(feedurl)
for item in soup.findAll('a', attrs={'class':'naslovLink'}):
url = item['href']
title = self.tag_to_string(item)
articles.append({
'title' :title
,'date' :''
,'url' :url
,'description':''
})
totalfeeds.append((feedtitle, articles))
return totalfeeds