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

Improved recipe for The Atlantic

Browse Source
This commit is contained in:
Kovid Goyal 2009-08-15 10:10:23 -06:00
parent eed245a760
commit 976b3139db
1 changed files with 28 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
src/calibre/web/feeds/recipes/recipe_atlantic.py
View File

@ -9,44 +9,61 @@ import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class TheAtlantic(BasicNewsRecipe): class TheAtlantic(BasicNewsRecipe):
title = 'The Atlantic' title = 'The Atlantic'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal and Sujata Raman'
description = 'Current affairs and politics focussed on the US' description = 'Current affairs and politics focussed on the US'
INDEX = 'http://www.theatlantic.com/doc/current' INDEX = 'http://www.theatlantic.com/doc/current'
language = _('English') language = _('English')
remove_tags_before = dict(name='div', id='storytop') remove_tags_before = dict(name='div', id='storytop')
remove_tags = [dict(name='div', id=['seealso', 'storybottom', 'footer', 'ad_banner_top', 'sidebar'])] remove_tags = [
dict(name='div', id=['seealso','storybottom', 'footer', 'ad_banner_top', 'sidebar','articletoolstop','subcontent',]),
dict(name='p', attrs={'id':["pagination"]}),
dict(name='table',attrs={'class':"tools"}),
dict(name='a', href='/a/newsletters.mhtml')
]
no_stylesheets = True no_stylesheets = True
extra_css = '''
#timestamp{font-family:Arial,Helvetica,sans-serif; color:#666666 ;font-size:x-small}
#storytype{font-family:Arial,Helvetica,sans-serif; color:#D52B1E ;font-weight:bold; font-size:x-small}
h2{font-family:georgia,serif; font-style:italic;font-size:x-small;font-weight:normal;}
h1{font-family:georgia,serif; font-weight:bold; font-size:large}
#byline{font-family:georgia,serif; font-weight:bold; font-size:x-small}
#topgraf{font-family:Arial,Helvetica,sans-serif;font-size:x-small;font-weight:bold;}
.artsans{{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
'''
def parse_index(self): def parse_index(self):
articles = [] articles = []
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
issue = soup.find('span', attrs={'class':'issue'}) issue = soup.find('span', attrs={'class':'issue'})
if issue: if issue:
self.timefmt = ' [%s]'%self.tag_to_string(issue).rpartition('|')[-1].strip().replace('/', '-') self.timefmt = ' [%s]'%self.tag_to_string(issue).rpartition('|')[-1].strip().replace('/', '-')
cover = soup.find('img', alt=re.compile('Cover'), src=True) cover = soup.find('img', alt=re.compile('Cover'), src=True)
if cover is not None: if cover is not None:
self.cover_url = 'http://theatlantic.com'+cover['src'] self.cover_url = 'http://theatlantic.com'+cover['src']
for item in soup.findAll('div', attrs={'class':'item'}): for item in soup.findAll('div', attrs={'class':'item'}):
a = item.find('a') a = item.find('a')
if a and a.has_key('href'): if a and a.has_key('href'):
url = a['href'].replace('/doc', 'doc/print') url = a['href']#.replace('/doc', 'doc/print')
if not url.startswith('http://'): if not url.startswith('http://'):
url = 'http://www.theatlantic.com/'+url url = 'http://www.theatlantic.com/'+url
title = self.tag_to_string(a) title = self.tag_to_string(a)
byline = item.find(attrs={'class':'byline'}) byline = item.find(attrs={'class':'byline'})
date = self.tag_to_string(byline) if byline else '' date = self.tag_to_string(byline) if byline else ''
description = '' description = ''
articles.append({ articles.append({
'title':title, 'title':title,
'date':date, 'date':date,
'url':url, 'url':url,
'description':description 'description':description
}) })
return [('Current Issue', articles)] return [('Current Issue', articles)]