Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-05 08:40:13 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #1162167 (Updated recipe for Harpers printed edition)

Browse Source
This commit is contained in:
Kovid Goyal 2013-03-30 17:07:01 +05:30
parent 7a90d00dc8
commit 1c315cb263
1 changed files with 23 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
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
@ -14,7 +14,7 @@ from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Harpers_full(BasicNewsRecipe): class Harpers_full(BasicNewsRecipe):
title = "Harper's Magazine - Printed Edition" title = "Harper's Magazine - articles from printed edition"
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = "Harper's Magazine, the oldest general-interest monthly in America, explores the issues that drive our national conversation, through long-form narrative journalism and essays, and such celebrated features as the iconic Harper's Index." description = "Harper's Magazine, the oldest general-interest monthly in America, explores the issues that drive our national conversation, through long-form narrative journalism and essays, and such celebrated features as the iconic Harper's Index."
publisher = "Harpers's" publisher = "Harpers's"
@ -29,7 +29,6 @@ class Harpers_full(BasicNewsRecipe):
needs_subscription = 'optional' needs_subscription = 'optional'
masthead_url = 'http://harpers.org/wp-content/themes/harpers/images/pheader.gif' masthead_url = 'http://harpers.org/wp-content/themes/harpers/images/pheader.gif'
publication_type = 'magazine' publication_type = 'magazine'
INDEX = ''
LOGIN = 'http://harpers.org/wp-content/themes/harpers/ajax_login.php' LOGIN = 'http://harpers.org/wp-content/themes/harpers/ajax_login.php'
extra_css = """ extra_css = """
body{font-family: adobe-caslon-pro,serif} body{font-family: adobe-caslon-pro,serif}
@ -66,37 +65,40 @@ class Harpers_full(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
#find current issue #find current issue
soup = self.index_to_soup('http://harpers.org/') soup = self.index_to_soup('http://harpers.org/')
currentIssue=soup.find('div',attrs={'class':'mainNavi'}).find('li',attrs={'class':'curentIssue'}) currentIssue=soup.find('div',attrs={'class':'mainNavi'}).find('li',attrs={'class':'curentIssue'})
currentIssue_url=self.tag_to_string(currentIssue.a['href']) currentIssue_url=self.tag_to_string(currentIssue.a['href'])
self.log(currentIssue_url)
#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
self.cover_url = soup1.find('div', attrs = {'class':'picture_hp'}).find('img', src=True)['src'] self.cover_url = soup1.find('div', attrs = {'class':'picture_hp'}).find('img', src=True)['src']
self.log(self.cover_url)
articles = [] articles = []
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'