mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
101 lines
3.9 KiB
Python
101 lines
3.9 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
|
|
'''
|
|
http://freeway.com.uy
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class General(BasicNewsRecipe):
|
|
title = 'freeway.com.uy'
|
|
__author__ = 'Gustavo Azambuja'
|
|
description = 'Revista Freeway, Montevideo, Uruguay'
|
|
language = 'es_UY'
|
|
timefmt = '[%a, %d %b, %Y]'
|
|
use_embedded_content = False
|
|
recursion = 1
|
|
encoding = 'utf8'
|
|
remove_javascript = True
|
|
no_stylesheets = True
|
|
conversion_options = {'linearize_tables': True}
|
|
|
|
oldest_article = 180
|
|
max_articles_per_feed = 100
|
|
keep_only_tags = [
|
|
dict(id=['contenido']),
|
|
dict(name='a', attrs={'class':'titulo_art_ppal'}),
|
|
dict(name='img', attrs={'class':'recuadro'}),
|
|
dict(name='td', attrs={'class':'txt_art_ppal'})
|
|
]
|
|
remove_tags = [
|
|
dict(name=['object','link'])
|
|
]
|
|
remove_attributes = ['width','height', 'style', 'font', 'color']
|
|
|
|
extra_css = '''
|
|
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
|
|
h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
|
|
h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
|
|
img {float:left; clear:both; margin:10px}
|
|
p {font-family:Arial,Helvetica,sans-serif;}
|
|
'''
|
|
|
|
def parse_index(self):
|
|
feeds = []
|
|
for title, url in [('Articulos', 'http://freeway.com.uy/revista/')]:
|
|
articles = self.art_parse_section(url)
|
|
if articles:
|
|
feeds.append((title, articles))
|
|
return feeds
|
|
|
|
def art_parse_section(self, url):
|
|
soup = self.index_to_soup(url)
|
|
div = soup.find(attrs={'id': 'tbl_1'})
|
|
|
|
current_articles = []
|
|
for tag in div.findAllNext(attrs = {'class': 'ancho_articulos'}):
|
|
if tag.get('class') == 'link-list-heading':
|
|
break
|
|
for td in tag.findAll('td'):
|
|
a = td.find('a', attrs= {'class': 'titulo_articulos'})
|
|
if a is None:
|
|
continue
|
|
title = self.tag_to_string(a)
|
|
url = a.get('href', False)
|
|
if not url or not title:
|
|
continue
|
|
if url.startswith('/'):
|
|
url = 'http://freeway.com.uy'+url
|
|
p = td.find('p', attrs= {'class': 'txt_articulos'})
|
|
description = self.tag_to_string(p)
|
|
self.log('\t\tFound article:', title)
|
|
self.log('\t\t\t', url)
|
|
self.log('\t\t\t', description)
|
|
current_articles.append({'title': title, 'url': url, 'description':description, 'date':''})
|
|
|
|
return current_articles
|
|
|
|
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 get_cover_url(self):
|
|
#index = 'http://www.cosmohispano.com/revista'
|
|
#soup = self.index_to_soup(index)
|
|
#link_item = soup.find('img',attrs={'class':'img_portada'})
|
|
#if link_item:
|
|
# cover_url = "http://www.cosmohispano.com"+link_item['src']
|
|
return 'http://freeway.com.uy/_upload/_n_foto_grande/noticia_1792_tapanoviembre2010.jpg'
|