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 Magazne (printed edition)

Browse Source
This commit is contained in:
Kovid Goyal 2013-03-26 10:01:42 +05:30
parent 189159b67f
commit 9d26d37382
1 changed files with 26 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
recipes/harpers_full.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2013, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2012, 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 - articles from printed edition" title = "Harper's Magazine - 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"
@ -29,6 +29,7 @@ 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}
@ -65,33 +66,29 @@ 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)
currentIssue_title = self.tag_to_string(soup1.head.title.string) date = re.split('\s\|\s',self.tag_to_string(soup1.head.title.string))[0]
date = re.split('\s\|\s',currentIssue_title)[0]
self.timefmt = u' [%s]'%date self.timefmt = u' [%s]'%date
#get cover #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' self.cover_url = soup1.find('div', attrs = {'class':'picture_hp'}).find('img', src=True)['src']
soup2 = self.index_to_soup(coverurl)
self.cover_url = self.tag_to_string(soup2.find('img')['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')
if text_links:
for text_link in text_links: for text_link in text_links:
if count == 0: if count == 0:
count = 1 count = 1
else: else:
url = text_link.a['href'] url = text_link.a['href']
title = self.tag_to_string(text_link.a) title = text_link.a.contents[0]
date = strftime(' %B %Y') date = strftime(' %B %Y')
articles.append({ articles.append({
'title' :title 'title' :title
@ -99,9 +96,13 @@ class Harpers_full(BasicNewsRecipe):
,'url' :url ,'url' :url
,'description':'' ,'description':''
}) })
return [(currentIssue_title, articles)] return [(soup1.head.title.string, 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)