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

New recipe for Courrier International and updated Le Monde by Mathieu Godlewski

Browse Source
This commit is contained in:
Kovid Goyal 2009-02-25 11:08:44 -08:00
parent 0a493da7e8
commit 18c39c6e20
3 changed files with 88 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/calibre/web/feeds/recipes/__init__.py
View File

@ -31,7 +31,7 @@ recipe_modules = ['recipe_' + r for r in (
'pobjeda', 'chicago_breaking_news', 'glasgow_herald', 'linuxdevices',
'hindu', 'cincinnati_enquirer', 'physics_world', 'pressonline',
'la_republica', 'physics_today', 'chicago_tribune', 'e_novine',
'al_jazeera', 'winsupersite', 'borba',
'al_jazeera', 'winsupersite', 'borba', 'courrierinternational',
)]
import re, imp, inspect, time, os

41
src/calibre/web/feeds/recipes/recipe_courrierinternational.py Normal file
View File

@ -0,0 +1,41 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>'
'''
Courrier International
'''
import re
from datetime import date
from calibre.web.feeds.news import BasicNewsRecipe
class CourrierInternational(BasicNewsRecipe):
title = 'Courrier International'
__author__ = 'Mathieu Godlewski <mathieu at godlewski.fr>'
description = 'Global news in french from international newspapers'
oldest_article = 7
language = _('French')
max_articles_per_feed = 50
no_stylesheets = True
html2lrf_options = ['--base-font-size', '10']
feeds = [
# Some articles requiring subscription fails on download.
('A la Une', 'http://www.courrierinternational.com/rss/rss_a_la_une.xml'),
]
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
[
#Handle Depeches
(r'.*<td [^>]*>([0-9][0-9]/.*</p>)</td>.*', lambda match : '<html><body><table><tr><td>'+match.group(1)+'</td></tr></table></body></html>'),
#Handle Articles
(r'.*<td [^>]*>(Courrier international.*?) <td width="10"><img src="/img/espaceur.gif"></td>.*', lambda match : '<html><body><table><tr><td>'+match.group(1)+'</body></html>'),
]
]
def print_version(self, url):
return re.sub('/[a-zA-Z]+\.asp','/imprimer.asp' ,url)

56
src/calibre/web/feeds/recipes/recipe_le_monde.py
View File

@ -7,7 +7,7 @@ lemonde.fr
'''
import re
from datetime import date
from calibre.web.feeds.news import BasicNewsRecipe
@ -15,11 +15,15 @@ class LeMonde(BasicNewsRecipe):
title = 'LeMonde.fr'
__author__ = 'Mathieu Godlewski <mathieu at godlewski.fr>'
description = 'Global news in french'
oldest_article = 7
oldest_article = 3
language = _('French')
max_articles_per_feed = 20
max_articles_per_feed = 30
no_stylesheets = True
cover_url='http://abonnes.lemonde.fr/titresdumonde/'+date.today().strftime("%y%m%d")+'/1.jpg'
html2lrf_options = ['--base-font-size', '10']
feeds = [
('A la Une', 'http://www.lemonde.fr/rss/une.xml'),
('International', 'http://www.lemonde.fr/rss/sequence/0,2-3210,1-0,0.xml'),
@ -38,25 +42,57 @@ class LeMonde(BasicNewsRecipe):
('Examens', 'http://www.lemonde.fr/rss/sequence/0,2-3404,1-0,0.xml'),
('Opinions', 'http://www.lemonde.fr/rss/sequence/0,2-3232,1-0,0.xml')
]
remove_tags = [dict(name='img', attrs={'src':'http://medias.lemonde.fr/mmpub/img/lgo/lemondefr_pet.gif'}),
dict(name='div', attrs={'id':'xiti-logo-noscript'}),
dict(name='br', attrs={}),
dict(name='iframe', attrs={}),
]
extra_css = '.ar-tit {font-size: x-large;} \n .dt {font-size: x-small;}'
filter_regexps = [r'xiti\.com']
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
[
(r'<html.*(<div class="post".*?>.*?</div>.*?<div class="entry">.*?</div>).*You can start editing here.*</html>', lambda match : '<html><body>'+match.group(1)+'</body></html>'),
(r'<p>&nbsp;</p>', lambda match : ''),
(r'<img src="http://medias\.lemonde\.fr/mmpub/img/let/(.)\.gif"[^>]*><div class=ar-txt>', lambda match : '<div class=ar-txt>'+match.group(1).upper()),
(r'<img src="http://medias\.lemonde\.fr/mmpub/img/let/q(.)\.gif"[^>]*><div class=ar-txt>', lambda match : '<div class=ar-txt>"'+match.group(1).upper()),
(r'(<div class=desc><b>.*</b></div>).*</body>', lambda match : match.group(1)),
]
]
article_match_regexps = [ (re.compile(i)) for i in
[
(r'http://www\.lemonde\.fr/\S+/article/.*'),
(r'http://www\.lemonde\.fr/\S+/portfolio/.*'),
(r'http://www\.lemonde\.fr/\S+/article_interactif/.*'),
(r'http://\S+\.blog\.lemonde\.fr/.*'),
]
]
def print_version(self, url):
return re.sub('http:.*_([0-9]+)_[0-9]+\.html.*','http://www.lemonde.fr/web/imprimer_element/0,40-0,50-\\1,0.html' ,url)
return re.sub('http://www\.lemonde\.fr/.*_([0-9]+)_[0-9]+\.html.*','http://www.lemonde.fr/web/imprimer_element/0,40-0,50-\\1,0.html' ,url)
# Used to filter duplicated articles
articles_list = []
def get_article_url(self, article):
url=article.get('link', None)
url=url[0:url.find("#")]
if url in self.articles_list:
self.log_debug(_('Skipping duplicated article: %s')%url)
return False
if self.is_article_wanted(url):
self.articles_list.append(url)
return url
self.log_debug(_('Skipping filtered article: %s')%url)
return False
def is_article_wanted(self, url):
if self.article_match_regexps:
for m in self.article_match_regexps:
if m.search(url):
return True
return False
return False