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 Harpers Full. Fixes #1153203 (Updated recipe for harpers full)

Browse Source
This commit is contained in:
Kovid Goyal 2013-03-10 19:20:36 +05:30
parent db2e6bcb97
commit 22c8c3c5b6
1 changed files with 18 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
recipes/harpers_full.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2013, Darko Miletic <darko.miletic at gmail.com>'
''' '''
harpers.org - paid subscription/ printed issue articles harpers.org - paid subscription/ printed issue articles
This recipe only get's article's published in text format This recipe only get's article's published in text format
@ -72,7 +72,8 @@ class Harpers_full(BasicNewsRecipe):
#go to the current issue #go to the current issue
soup1 = self.index_to_soup(currentIssue_url) soup1 = self.index_to_soup(currentIssue_url)
date = re.split('\s\|\s',self.tag_to_string(soup1.head.title.string))[0] currentIssue_title = self.tag_to_string(soup1.head.title.string)
date = re.split('\s\|\s',currentIssue_title)[0]
self.timefmt = u' [%s]'%date self.timefmt = u' [%s]'%date
#get cover #get cover
@ -84,27 +85,23 @@ class Harpers_full(BasicNewsRecipe):
count = 0 count = 0
for item in soup1.findAll('div', attrs={'class':'articleData'}): for item in soup1.findAll('div', attrs={'class':'articleData'}):
text_links = item.findAll('h2') text_links = item.findAll('h2')
for text_link in text_links: if text_links:
if count == 0: for text_link in text_links:
count = 1 if count == 0:
else: count = 1
url = text_link.a['href'] else:
title = text_link.a.contents[0] url = text_link.a['href']
date = strftime(' %B %Y') title = self.tag_to_string(text_link.a)
articles.append({ date = strftime(' %B %Y')
'title' :title articles.append({
,'date' :date 'title' :title
,'url' :url ,'date' :date
,'description':'' ,'url' :url
}) ,'description':''
return [(soup1.head.title.string, articles)] })
return [(currentIssue_title, articles)]
def print_version(self, url): def print_version(self, url):
return url + '?single=1' return url + '?single=1'
def cleanup(self):
soup = self.index_to_soup('http://harpers.org/')
signouturl=self.tag_to_string(soup.find('li', attrs={'class':'subLogOut'}).findNext('li').a['href'])
self.log(signouturl)
self.browser.open(signouturl)