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 Rue89

Browse Source
This commit is contained in:
Kovid Goyal 2012-03-30 16:53:37 +05:30
parent 1079778dd3
commit cdbef8d6b0
1 changed files with 33 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
recipes/rue89.recipe
View File

@ -6,6 +6,7 @@ Rue89
__author__ = '2010-2012, Louis Gesbert <meta at antislash dot info>' __author__ = '2010-2012, Louis Gesbert <meta at antislash dot info>'
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Rue89(BasicNewsRecipe): class Rue89(BasicNewsRecipe):
@ -15,23 +16,24 @@ class Rue89(BasicNewsRecipe):
title = u'Rue89' title = u'Rue89'
language = 'fr' language = 'fr'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 12 max_articles_per_feed = 50
use_embedded_content = False use_embedded_content = False
# From http://www.rue89.com/les-flux-rss-de-rue89 # From http://www.rue89.com/les-flux-rss-de-rue89
feeds = [ feeds = [
(u'La Une', u'http://www.rue89.com/feed'), (u'La Une', u'http://www.rue89.com/feed'),
(u'Rue69', u'http://www.rue89.com/rue69/feed'), # Other feeds disabled, 'La Une' seems to include them all
(u'Eco', u'http://www.rue89.com/rue89-eco/feed'), # (u'Rue69', u'http://www.rue89.com/rue69/feed'),
(u'Planète', u'http://www.rue89.com/rue89-planete/feed'), # (u'Eco', u'http://www.rue89.com/rue89-eco/feed'),
(u'Sport', u'http://www.rue89.com/rue89-sport/feed'), # (u'Planète', u'http://www.rue89.com/rue89-planete/feed'),
(u'Culture', u'http://www.rue89.com/culture/feed'), # (u'Sport', u'http://www.rue89.com/rue89-sport/feed'),
(u'Hi-tech', u'http://www.rue89.com/hi-tech/feed'), # (u'Culture', u'http://www.rue89.com/culture/feed'),
(u'Media', u'http://www.rue89.com/medias/feed'), # (u'Hi-tech', u'http://www.rue89.com/hi-tech/feed'),
(u'Monde', u'http://www.rue89.com/monde/feed'), # (u'Media', u'http://www.rue89.com/medias/feed'),
(u'Politique', u'http://www.rue89.com/politique/feed'), # (u'Monde', u'http://www.rue89.com/monde/feed'),
(u'Societe', u'http://www.rue89.com/societe/feed'), # (u'Politique', u'http://www.rue89.com/politique/feed'),
# (u'Societe', u'http://www.rue89.com/societe/feed'),
] ]
# Follow redirection from feedsportal.com # Follow redirection from feedsportal.com
@ -41,19 +43,36 @@ class Rue89(BasicNewsRecipe):
def print_version(self, url): def print_version(self, url):
return url + '?imprimer=1' return url + '?imprimer=1'
no_stylesheets = True
conversion_options = { 'smarten_punctuation' : True } conversion_options = { 'smarten_punctuation' : True }
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':'article'}), dict(name='div', attrs={'id':'content'}),
] ]
remove_tags_after = [ remove_tags_after = [
dict(name='div', attrs={'id':'plus_loin'}), dict(name='div', attrs={'id':'plus_loin'}),
dict(name='div', attrs={'class':'stats'}),
] ]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'id':'article_tools'}), dict(name='div', attrs={'id':'article_tools'}),
dict(name='div', attrs={'id':'plus_loin'}), dict(name='div', attrs={'id':'plus_loin'}),
dict(name='div', attrs={'class':'stats'}),
dict(name='div', attrs={'class':'tools'}),
] ]
extra_css = "#content { padding: 0 0; }"
# Without this, parsing of video articles returns strange results
preprocess_regexps = [
(re.compile(r'<script.*?</script>', re.IGNORECASE|re.DOTALL), ''),
]
def preprocess_html(self, soup):
# Remove whole article if it's a "zapnet" (video)
if soup.find('h1', {'class':'zapnet_title'}):
return None
# Reduce h2 titles to h3
for title in soup.findAll('h2'):
title.name = 'h3'
return soup