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 New York Times Book Review

Browse Source
This commit is contained in:
Kovid Goyal 2012-10-27 22:15:10 +05:30
parent 56bc2dd619
commit e9ff5e2599
1 changed files with 8 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
recipes/nytimesbook.recipe
View File

@ -1,5 +1,4 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class NewYorkTimesBookReview(BasicNewsRecipe):
title = u'New York Times Book Review'
@ -7,50 +6,16 @@ class NewYorkTimesBookReview(BasicNewsRecipe):
__author__ = 'Krittika Goyal'
oldest_article = 8 #days
max_articles_per_feed = 1000
recursions = 2
#recursions = 2
#encoding = 'latin1'
use_embedded_content = False
no_stylesheets = True
auto_cleanup = True
remove_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
remove_tags_after = dict(name='div', attrs={'id':'authorId'})
remove_tags = [
dict(name='iframe'),
dict(name=['div', 'a'], attrs={'class':['enlargeThis', 'jumpLink']}),
dict(name='div', attrs={'id':['sidebarArticles', 'toolsRight']}),
#dict(name='ul', attrs={'class':'article-tools'}),
#dict(name='ul', attrs={'class':'articleTools'}),
]
match_regexps = [
r'http://www.nytimes.com/.+pagewanted=[2-9]+'
]
feeds = [
('New York Times Sunday Book Review',
'http://feeds.nytimes.com/nyt/rss/SundayBookReview'),
]
('New York Times Sunday Book Review',
'http://feeds.nytimes.com/nyt/rss/SundayBookReview'),
]
def preprocess_html(self, soup):
story = soup.find(name='div', attrs={'id':'article'})
#td = heading.findParent(name='td')
#td.extract()
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body')
body.insert(0, story)
#for x in soup.findAll(name='p', text=lambda x:x and '--&gt;' in x):
#p = x.findParent('p')
#if p is not None:
#p.extract()
return soup
def postprocess_html(self, soup, first):
for div in soup.findAll(id='pageLinks'):
div.extract()
if not first:
h1 = soup.find('h1')
if h1 is not None:
h1.extract()
t = soup.find(attrs={'class':'timestamp'})
if t is not None:
t.extract()
return soup