Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add recipe for xkcd thanks to Martin Pitt. Also make Time magazine recipe a little more efficient.

Browse Source
This commit is contained in:
Kovid Goyal 2009-01-03 20:19:47 -08:00
parent bca2a86168
commit 8f2dd9cf84
3 changed files with 58 additions and 13 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

@ -20,7 +20,7 @@ recipe_modules = ['recipe_' + r for r in (
'science_news', 'the_nation', 'lrb', 'harpers_full', 'liberation',
'linux_magazine', 'telegraph_uk', 'utne', 'sciencedaily', 'forbes',
'time_magazine', 'endgadget', 'fudzilla', 'nspm_int', 'nspm', 'pescanik',
'spiegel_int', 'themarketticker', 'tomshardware',
'spiegel_int', 'themarketticker', 'tomshardware', 'xkcd',
)]
import re, imp, inspect, time, os

33
src/calibre/web/feeds/recipes/recipe_time_magazine.py
View File

@ -6,22 +6,28 @@ __copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
time.com
'''
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.news import BasicNewsRecipe
class Time(BasicNewsRecipe):
title = u'Time'
__author__ = 'Darko Miletic'
__author__ = 'Kovid Goyal'
description = 'Weekly magazine'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
#cover_url = 'http://img.timeinc.net/time/rd/trunk/www/web/feds/i/logo_time_home.gif'
keep_only_tags = [dict(name='div', attrs={'class':'tout1'})]
remove_tags = [dict(name='ul', attrs={'class':['button', 'find']})]
remove_tags_after = [dict(id='connectStory')]
remove_tags = [
dict(name='ul', attrs={'class':['button', 'find']}),
dict(name='div', attrs={'class':['nav', 'header', 'sectheader',
'searchWrap', 'subNav',
'artTools', 'connect',
'similarrecs']}),
dict(name='div', id=['articleSideBar', 'connectStory']),
dict(name='dl', id=['links']),
]
feeds = [
(u'Top Stories', u'http://feedproxy.google.com/time/topstories')
@ -34,17 +40,20 @@ class Time(BasicNewsRecipe):
,(u'Travel', u'http://feedproxy.google.com/time/travel')
]
def get_article_url(self, article):
return article.get('guid', article['link'])
def get_cover_url(self):
soup = self.index_to_soup('http://www.time.com/time/')
img = soup.find('img', alt='Current Time.com Cover', width='107')
if img is not None:
return img.get('src', None)
def print_version(self, url):
raw = self.browser.open(url).read()
soup = BeautifulSoup(raw.decode('utf8', 'replace'))
print_link = soup.find('a', {'id':'prt'})
if print_link is None:
return ''
return 'http://www.time.com' + print_link['href']
try:
soup = self.index_to_soup(url)
print_link = soup.find('a', {'id':'prt'})
return 'http://www.time.com' + print_link['href']
except:
self.log_exception('Failed to find print version for '+url)
return ''

36
src/calibre/web/feeds/recipes/recipe_xkcd.py Normal file
View File

@ -0,0 +1,36 @@
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
Fetch xkcd.
'''
import time
from calibre.web.feeds.news import BasicNewsRecipe
class XkcdCom(BasicNewsRecipe):
title = 'xkcd'
description = 'A webcomic of romance and math humor.'
__author__ = 'Martin Pitt'
use_embedded_content = False
oldest_article = 60
keep_only_tags = [dict(id='middleContent')]
remove_tags = [dict(name='ul'), dict(name='h3'), dict(name='br')]
no_stylesheets = True
def parse_index(self):
INDEX = 'http://xkcd.com/archive/'
soup = self.index_to_soup(INDEX)
articles = []
for item in soup.findAll('a', title=True):
articles.append({
'date': item['title'],
'timestamp': time.mktime(time.strptime(item['title'], '%Y-%m-%d'))+1,
'url': 'http://xkcd.com' + item['href'],
'title': self.tag_to_string(item).encode('UTF-8'),
'description': '',
'content': '',
})
return [('xkcd', articles)]