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

Update Le Monde diplomatique.fr

Browse Source
This commit is contained in:
Kovid Goyal 2015-12-12 10:58:33 +05:30
parent 4d78cc9f1a
commit 30b0783a4e
1 changed files with 31 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
recipes/le_monde_diplomatique_fr.recipe
View File

@ -11,6 +11,11 @@ import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds import feeds_from_index
def absurl(url):
if url.startswith('/'):
url = 'http://www.monde-diplomatique.fr' + url
return url
class LeMondeDiplomatiqueSiteWeb(BasicNewsRecipe):
title = u'Le Monde diplomatique.fr'
__author__ = 'Gaëtan Lehmann'
@ -44,12 +49,11 @@ class LeMondeDiplomatiqueSiteWeb(BasicNewsRecipe):
dict(name='div', attrs={'class':'espace'})]
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
}
'comments' : description,
'tags' : category,
'publisher' : publisher,
'linearize_tables': True
}
remove_empty_feeds = True
@ -60,45 +64,43 @@ class LeMondeDiplomatiqueSiteWeb(BasicNewsRecipe):
def parse_index_valise(self):
articles = []
soup = self.index_to_soup('http://www.monde-diplomatique.fr/carnet/')
cnt = soup.find('ul',attrs={'class':'hermetique liste'})
cnt = soup.find('ul',attrs={'class':'liste double'})
for item in cnt.findAll('li'):
description = ''
feed_link = item.find('a')
feed_link = item.find('a', href=True)
title = self.tag_to_string(item.find('h3'))
desc = item.find('div',attrs={'class':'intro'})
date = item.find('div',attrs={'class':'dates_auteurs'})
if desc:
description = desc.string
if feed_link and feed_link.has_key('href'):
url = 'http://www.monde-diplomatique.fr' + feed_link['href']
title = self.tag_to_string(feed_link)
if feed_link:
articles.append({
'title' :title
,'date' :date.string.strip()
,'url' :url
,'description':description
})
'title' :title,
'date' :self.tag_to_string(date),
'url' :absurl(feed_link['href']),
'description':description
})
return [("La valise diplomatique", articles)]
def parse_index_cartes(self):
articles = []
soup = self.index_to_soup('http://www.monde-diplomatique.fr/cartes/')
cnt = soup.find('div',attrs={'class':'decale hermetique'})
for item in cnt.findAll('div',attrs={'class':re.compile('grid_3 filet hombre_demi')}):
feed_link = item.find('a',attrs={'class':'couve'})
h3 = item.find('h3')
authorAndDate = item.find('div',attrs={'class':'dates_auteurs'})
author_date = authorAndDate.string.strip().split(', ')
cnt = soup.find('ul',attrs={'class':'liste_vignettes hautcartes'})
for li in cnt.findAll('li'):
feed_link = li.find('a', href=True)
h3 = li.find('h3')
authorAndDate = li.find('div',attrs={'class':'dates_auteurs'})
author_date = self.tag_to_string(authorAndDate).split(', ')
author = author_date[0]
date = author_date[-1]
if feed_link and feed_link.has_key('href'):
url = 'http://www.monde-diplomatique.fr' + feed_link['href']
if feed_link:
title = self.tag_to_string(h3)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description': author
})
'title' :title,
'date' :date,
'url' :absurl(feed_link['href']),
'description': author
})
return [("Cartes", articles)]
def parse_feeds(self):