New Honduran recipes by Darko Miletic

This commit is contained in:
Kovid Goyal 2009-07-06 17:16:10 -06:00
parent 4f1c599581
commit 3bb5d82da6
7 changed files with 174 additions and 1 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 3.2 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 306 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 553 B

View File

@ -51,9 +51,11 @@ recipe_modules = ['recipe_' + r for r in (
'theeconomictimes_india', '7dias', 'buenosaireseconomico',
'diagonales', 'miradasalsur', 'newsweek_argentina', 'veintitres',
'gva_be', 'hln', 'tijd', 'degentenaar', 'inquirer_net', 'uncrate',
'fastcompany', 'accountancyage',
'fastcompany', 'accountancyage', 'laprensa_hn', 'latribuna',
'eltiempo_hn',
)]
import re, imp, inspect, time, os
from calibre.web.feeds.news import BasicNewsRecipe, CustomIndexRecipe, AutomaticNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup

View File

@ -0,0 +1,52 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.tiempo.hn
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
class ElTiempoHn(BasicNewsRecipe):
title = 'El Tiempo - Honduras'
__author__ = 'Darko Miletic'
description = 'Noticias de Honduras y mundo'
publisher = 'El Tiempo'
category = 'news, politics, Honduras'
oldest_article = 2
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
remove_javascript = True
encoding = 'utf-8'
language = _('Spanish')
lang = 'es-HN'
direction = 'ltr'
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
, '--ignore-tables'
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True\npretty_print=True\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} img {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em}"'
remove_tags = [dict(name=['form','object','embed','base'])]
keep_only_tags = [dict(name='td' , attrs={'id':'mainbodycont'})]
feeds = [(u'Noticias', u'http://www.tiempo.hn/index.php?format=feed&type=rss')]
def preprocess_html(self, soup):
soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction
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)
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)

View File

@ -0,0 +1,54 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.laprensahn.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
class LaPrensaHn(BasicNewsRecipe):
title = 'La Prensa - Honduras'
__author__ = 'Darko Miletic'
description = 'Noticias de Honduras y mundo'
publisher = 'La Prensa'
category = 'news, politics, Honduras'
oldest_article = 2
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
remove_javascript = True
encoding = 'utf-8'
language = _('Spanish')
lang = 'es-HN'
direction = 'ltr'
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\npretty_print=True\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
remove_tags = [dict(name=['form','object','embed'])]
keep_only_tags = [
dict(name='h1' , attrs={'class':'titulo1'})
,dict(name='div', attrs={'class':['sumario11','hora','texto']})
]
feeds = [(u'Noticias', u'http://feeds.feedburner.com/laprensa_titulares')]
def preprocess_html(self, soup):
soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction
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)
for item in soup.findAll(style=True):
del item['style']
return soup

View File

@ -0,0 +1,65 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.latribuna.hn
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
class LaTribuna(BasicNewsRecipe):
title = 'La Tribuna - Honduras'
__author__ = 'Darko Miletic'
description = 'Noticias de Honduras y mundo'
publisher = 'La Tribuna'
category = 'news, politics, Honduras'
oldest_article = 2
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
remove_javascript = True
encoding = 'utf-8'
language = _('Spanish')
lang = 'es-HN'
direction = 'ltr'
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\npretty_print=True\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
remove_tags = [dict(name=['form','object','embed'])]
keep_only_tags = [
dict(name='p', attrs={'id':['BlogTitle','BlogDate']})
,dict(name='div', attrs={'id':'BlogContent'})
]
feeds = [(u'Noticias', u'http://www.latribuna.hn/web2.0/?feed=rss')]
def print_version(self, url):
return url + '&print=1'
def preprocess_html(self, soup):
soup.html['lang'] = self.lang
soup.html['dir' ] = self.direction
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)
for item in soup.findAll(style=True):
del item['style']
return soup
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup('http://www.latribuna.hn/web2.0/')
cover_item = soup.find('div',attrs={'class':'portada_impresa'})
if cover_item:
cover_url = cover_item.a.img['src']
return cover_url