mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
111 lines
4.2 KiB
Plaintext
111 lines
4.2 KiB
Plaintext
from calibre import strftime
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
|
|
MANIFESTO_BASEURL = 'http://www.ilmanifesto.it/'
|
|
|
|
|
|
class IlManifesto(BasicNewsRecipe):
|
|
title = 'Il Manifesto'
|
|
__author__ = 'Giacomo Lacava'
|
|
description = 'quotidiano comunista - ultima edizione html disponibile'
|
|
publication_type = 'newspaper'
|
|
publisher = 'il manifesto coop. editrice a r.l.'
|
|
language = 'it'
|
|
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
delay = 1
|
|
no_stylesheets = True
|
|
simultaneous_downloads = 5
|
|
timeout = 30
|
|
auto_cleanup = True
|
|
remove_tags = [dict(name='div', attrs={'class': 'column_1 float_left'})]
|
|
remove_tags_before = dict(
|
|
name='div', attrs={'class': 'column_2 float_right'})
|
|
remove_tags_after = dict(id='myPrintArea')
|
|
|
|
manifesto_index = None
|
|
manifesto_datestr = None
|
|
|
|
def _set_manifesto_index(self):
|
|
if self.manifesto_index is None:
|
|
startUrl = MANIFESTO_BASEURL + 'area-abbonati/in-edicola/'
|
|
startSoup = self.index_to_soup(startUrl)
|
|
lastEdition = startSoup.findAll('div', id='accordion_inedicola')[
|
|
1].find('a')['href']
|
|
del(startSoup)
|
|
self.manifesto_index = MANIFESTO_BASEURL + lastEdition
|
|
urlsplit = lastEdition.split('/')
|
|
self.manifesto_datestr = urlsplit[-1]
|
|
if urlsplit[-1] == '':
|
|
self.manifesto_datestr = urlsplit[-2]
|
|
|
|
def get_cover_url(self):
|
|
self._set_manifesto_index()
|
|
url = MANIFESTO_BASEURL + \
|
|
'fileadmin/archivi/in_edicola/%sprimapagina.gif' % self.manifesto_datestr
|
|
return url
|
|
|
|
def parse_index(self):
|
|
self._set_manifesto_index()
|
|
soup = self.index_to_soup(self.manifesto_index)
|
|
feedLinks = soup.find('div', id='accordion_inedicola').findAll('a')
|
|
result = []
|
|
for feed in feedLinks:
|
|
articles = []
|
|
feedName = feed.find('h2').string
|
|
feedUrl = MANIFESTO_BASEURL + feed['href']
|
|
feedSoup = self.index_to_soup(feedUrl)
|
|
indexRoot = feedSoup.find('div', attrs={'class': 'column1'})
|
|
for div in indexRoot.findAll('div', attrs={'class': 'strumenti1_inedicola'}):
|
|
artLink = div.find('a')
|
|
if artLink is None:
|
|
continue # empty div
|
|
title = artLink.string
|
|
url = MANIFESTO_BASEURL + artLink['href']
|
|
|
|
description = ''
|
|
descNode = div.find('div', attrs={'class': 'text_12'})
|
|
if descNode is not None:
|
|
description = descNode.string
|
|
|
|
author = ''
|
|
authNode = div.find('div', attrs={'class': 'firma'})
|
|
if authNode is not None:
|
|
author = authNode.string
|
|
|
|
articleText = ''
|
|
article = {
|
|
'title': title,
|
|
'url': url,
|
|
'date': strftime('%d %B %Y'),
|
|
'description': description,
|
|
'content': articleText,
|
|
'author': author
|
|
}
|
|
articles.append(article)
|
|
result.append((feedName, articles))
|
|
return result
|
|
|
|
def extract_readable_article(self, html, url):
|
|
|
|
bs = BeautifulSoup(html)
|
|
col1 = bs.find('div', attrs={'class': 'column1'})
|
|
|
|
content = col1.find('div', attrs={'class': 'bodytext'})
|
|
title = bs.find(id='titolo_articolo').string
|
|
author = col1.find('span', attrs={'class': 'firma'})
|
|
subtitle = ''
|
|
subNode = col1.findPrevious('div', attrs={'class': 'occhiello_rosso'})
|
|
if subNode is not None:
|
|
subtitle = subNode
|
|
summary = ''
|
|
sommNode = bs.find('div', attrs={'class': 'sommario'})
|
|
if sommNode is not None:
|
|
summary = sommNode
|
|
|
|
template = "<html><head><title>%(title)s</title></head><body><h1>%(title)s</h1><h2>%(subtitle)s</h2><h3>%(author)s</h3><div style='font-size: x-large;'>%(summary)s</div><div>%(content)s</div></body></html>" # noqa
|
|
del(bs)
|
|
return template % dict(title=title, subtitle=subtitle, author=author, summary=summary, content=content)
|