Quote:
Originally Posted by macpablus
|
Hi macpablus, i found time to have a look at your recipe.
First of all i saw that the daily comic is located at
http://www.pagina12.com.ar/diario/principal/index.html.
All i had to do was to add this page as a single feed 'Humor' with a single article. Then i modified the postprocess_html. I tried to find a div with id='rudy_paz'. When this div is present, i extracted the div from the soup, removed all content from the soups body, added the image again and returned the soup.
Then the remove_tags_before seems not to work as i expected so i removed it.
The complete recipe is here:
Spoiler:
Code:
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2011, Pablo Marfill'
'''
Calibre recipe to convert the news site pagina12.com.ar to an ebook
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag, NavigableString
class Pagina12(BasicNewsRecipe):
title = 'Pagina/12 - Edicion Impresa'
__author__ = 'Pablo Marfil, a.peter'
description = 'Diario argentino'
INDEX = 'http://www.pagina12.com.ar/diario/secciones/index.html'
language = 'es'
encoding = 'cp1252'
#remove_tags_before = [dict(id='fecha')] # Is a list of dictionaries. But did not work. Why? I don't know.
remove_tags_after = [dict(id='fin')] # Is a list of dictionaries
remove_tags = [dict(id=['volver', 'logo', 'fecha', 'fin', 'pageControls', 'logo_suple', 'fecha_suple'])]
masthead_url = 'http://www.pagina12.com.ar/commons/imgs/logo-home.gif'
no_stylesheets = True
preprocess_regexps= [(re.compile(r'<!DOCTYPE[^>]+>', re.I), lambda m:'')]
def get_cover_url(self):
soup = self.index_to_soup('http://www.pagina12.com.ar/diario/principal/diario/index.html')
for image in soup.findAll('img',alt=True):
if image['alt'].startswith('Tapa de la fecha'):
return image['src']
print image
return None
def parse_index(self):
articles = []
numero = 1
raw = self.index_to_soup('http://www.pagina12.com.ar/diario/secciones/index.html', raw=True)
raw = re.sub(r'(?i)<!DOCTYPE[^>]+>', '', raw)
soup = self.index_to_soup(raw)
feeds = []
feeds.append(('Humor', [{'title':'Rudy y Daniel Paz', 'url':'http://www.pagina12.com.ar/diario/principal/index.html', 'description':'Daily comic', 'date':''}]))
seen_titles = set([])
for section in soup.findAll('div','seccionx'):
numero+=1
print (numero)
section_title = self.tag_to_string(section.find('div','desplegable_titulo on_principal right'))
self.log('Found section:', section_title)
articles = []
for post in section.findAll('h2'):
h = post.find('a', href=True)
title = self.tag_to_string(h)
if title in seen_titles:
continue
seen_titles.add(title)
a = post.find('a', href=True)
url = a['href']
if url.startswith('/'):
url = 'http://pagina12.com.ar/imprimir'+url
p = post.find('div', attrs={'h2'})
desc = None
self.log('\tFound article:', title, 'at', url)
if p is not None:
desc = self.tag_to_string(p)
self.log('\t\t', desc)
articles.append({'title':title, 'url':url, 'description':desc,
'date':''})
if articles:
feeds.append((section_title, articles))
return feeds
def postprocess_html(self, soup, first):
# Added by a.peter:
# Try to find the div containing the image
image = soup.find('div', attrs={'id':'rudy_paz'})
if image:
# if found, extract the div, clear the body and add the image again. Finished.
image.extract()
while len(soup.body) > 0:
soup.body.next.extract()
soup.body.insert(0, image)
return soup
for table in soup.findAll('table', align='right'):
img = table.find('img')
if img is not None:
img.extract()
caption = self.tag_to_string(table).strip()
div = Tag(soup, 'div')
div['style'] = 'text-align:center'
div.insert(0, img)
div.insert(1, Tag(soup, 'br'))
if caption:
div.insert(2, NavigableString(caption))
table.replaceWith(div)
return soup
In the debug mode (only two feeds with each two articles) produced the following output:
Pagina12.epub
I put your name into the copyright and added myself as a co-author