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

Fix New York Times recipe

Browse Source
This commit is contained in:
Kovid Goyal 2008-11-01 19:57:52 -07:00
parent 114c1e799e
commit b6e55e908d
2 changed files with 23 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/calibre/library/test.py
View File

@ -7,7 +7,7 @@ __docformat__ = 'restructuredtext en'
Unit tests for database layer.
'''
import sys, unittest, os
import sys, unittest, os, cStringIO
from itertools import repeat
from calibre.ptempfile import PersistentTemporaryDirectory
@ -60,6 +60,11 @@ class DBTest(unittest.TestCase):
self.assertEqual(ga(self.m2, p), ga(m2, p))
self.assertEqual(self.db.format(1, 'txt', index_is_id=True), 'test')
self.assertEqual(self.db.formats(1, index_is_id=True), 'TXT')
self.db.add_format(1, 'html', cStringIO.StringIO('<html/>'), index_is_id=True)
self.assertEqual(self.db.formats(1, index_is_id=True), 'HTML,TXT')
self.db.remove_format(1, 'html', index_is_id=True)
self.assertEqual(self.db.formats(1, index_is_id=True), 'TXT')
self.assertNotEqual(self.db.cover(1, index_is_id=True), None)
self.assertEqual(self.db.cover(2, index_is_id=True), None)
@ -76,6 +81,12 @@ class DBTest(unittest.TestCase):
self.assertEqual('new auth', self.db.authors(2))
self.assertEqual(self.db.format(3, 'txt', index_is_id=True), 'test')
def testSorting(self):
self.db.sort('authors', True)
self.assertEqual(self.db.authors(0), 'Test Author 1')
self.db.sort('rating', False)
self.assertEqual(self.db.rating(0), 3)
def suite():
return unittest.TestLoader().loadTestsFromTestCase(DBTest)

17
src/calibre/web/feeds/recipes/nytimes.py
View File

@ -5,9 +5,10 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
nytimes.com
'''
import string
import string, re
from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class NYTimes(BasicNewsRecipe):
@ -57,7 +58,8 @@ class NYTimes(BasicNewsRecipe):
a = div.find('a', href=True)
if not a:
continue
url = self.print_version(a['href'])
url = re.sub(r'\?.*', '', a['href'])
url += '?pagewanted=print'
title = self.tag_to_string(a, use_alt=True).strip()
description = ''
pubdate = strftime('%a, %d %b')
@ -77,7 +79,10 @@ class NYTimes(BasicNewsRecipe):
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans
def print_version(self, url):
if url.endswith('?&pagewanted=print'):
return url
return url + '?&pagewanted=print'
def preprocess_html(self, soup):
refresh = soup.find('meta', {'http-equiv':'refresh'})
if refresh is None:
return soup
content = refresh.get('content').partition('=')[2]
raw = self.browser.open('http://www.nytimes.com'+content).read()
return BeautifulSoup(raw.decode('cp1252', 'replace'))