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 Harper's Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2012-12-29 10:13:46 +05:30
parent 1a3c9e4d8b
commit 7012bb1af2
1 changed files with 26 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
recipes/harpers_full.recipe
View File

@ -8,7 +8,7 @@ If you have institutional subscription based on access IP you do not need to ent
anything in username/password fields
'''
import time
import time, re
import urllib
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
@ -29,7 +29,6 @@ class Harpers_full(BasicNewsRecipe):
needs_subscription = 'optional'
masthead_url = 'http://harpers.org/wp-content/themes/harpers/images/pheader.gif'
publication_type = 'magazine'
INDEX = strftime('http://harpers.org/archive/%Y/%m')
LOGIN = 'http://harpers.org/wp-content/themes/harpers/ajax_login.php'
extra_css = """
body{font-family: adobe-caslon-pro,serif}
@ -65,17 +64,28 @@ class Harpers_full(BasicNewsRecipe):
return br
def parse_index(self):
#find current issue
soup = self.index_to_soup('http://harpers.org/')
currentIssue=soup.find('div',attrs={'class':'mainNavi'}).find('li',attrs={'class':'curentIssue'})
currentIssue_url=self.tag_to_string(currentIssue.a['href'])
self.log(currentIssue_url)
#go to the current issue
soup1 = self.index_to_soup(currentIssue_url)
date = re.split('\s\|\s',self.tag_to_string(soup1.head.title.string))[0]
self.timefmt = u' [%s]'%date
#get cover
coverurl='http://harpers.org/wp-content/themes/harpers/ajax_microfiche.php?img=harpers-'+re.split('harpers.org/',currentIssue_url)[1]+'gif/0001.gif'
soup2 = self.index_to_soup(coverurl)
self.cover_url = self.tag_to_string(soup2.find('img')['src'])
self.log(self.cover_url)
articles = []
print 'Processing ' + self.INDEX
soup = self.index_to_soup(self.INDEX)
count = 0
for item in soup.findAll('div', attrs={'class':'articleData'}):
for item in soup1.findAll('div', attrs={'class':'articleData'}):
text_links = item.findAll('h2')
for text_link in text_links:
if count == 0:
lcover_url = item.find(attrs={'class':'dwpdf'})
if lcover_url:
self.cover_url = lcover_url.a['href']
count = 1
else:
url = text_link.a['href']
@ -87,7 +97,14 @@ class Harpers_full(BasicNewsRecipe):
,'url' :url
,'description':''
})
return [(soup.head.title.string, articles)]
return [(soup1.head.title.string, articles)]
def print_version(self, url):
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)