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

Updated recipes for Harpers Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2009-06-07 17:58:36 -07:00
parent 7dd7ad65dd
commit 79f15cd010
2 changed files with 33 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
src/calibre/web/feeds/recipes/recipe_harpers.py
View File

@ -6,6 +6,7 @@ __copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
harpers.org
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Harpers(BasicNewsRecipe):
title = u"Harper's Magazine"
@ -18,23 +19,30 @@ class Harpers(BasicNewsRecipe):
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_javascript = True
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em} img {margin-top: 0em; margin-bottom: 0.4em}"'
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em} img {margin-top: 0em; margin-bottom: 0.4em}"'
keep_only_tags = [ dict(name='div', attrs={'id':'cached'}) ]
remove_tags = [
dict(name='table', attrs={'class':'rcnt'})
,dict(name='table', attrs={'class':'rcnt topline'})
dict(name='table', attrs={'class':['rcnt','rcnt topline']})
,dict(name=['link','object','embed'])
]
feeds = [(u"Harper's Magazine", u'http://www.harpers.org/rss/frontpage-rss20.xml')]
def preprocess_html(self, soup):
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(1,mcharset)
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(xmlns=True):
del item['xmlns']
return soup

30
src/calibre/web/feeds/recipes/recipe_harpers_full.py
View File

@ -9,40 +9,38 @@ images and pdf's are ignored
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Harpers_full(BasicNewsRecipe):
title = u"Harper's Magazine - articles from printed edition"
__author__ = u'Darko Miletic'
description = u"Harper's Magazine: Founded June 1850."
publisher = "Harpers's"
category = 'news, politics, USA'
category = 'news, politics, USA'
oldest_article = 30
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
simultaneous_downloads = 1
delay = 1
language = _('English')
needs_subscription = True
INDEX = strftime('http://www.harpers.org/archive/%Y/%m')
LOGIN = 'http://www.harpers.org'
cover_url = strftime('http://www.harpers.org/media/pages/%Y/%m/gif/0001.gif')
remove_javascript = True
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em} img {margin-top: 0em; margin-bottom: 0.4em}"'
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em} img {margin-top: 0em; margin-bottom: 0.4em}"'
keep_only_tags = [ dict(name='div', attrs={'id':'cached'}) ]
remove_tags = [
dict(name='table', attrs={'class':'rcnt'})
,dict(name='table', attrs={'class':'rcnt topline'})
dict(name='table', attrs={'class':['rcnt','rcnt topline']})
,dict(name='link')
]
def get_browser(self):
@ -54,13 +52,13 @@ class Harpers_full(BasicNewsRecipe):
br['password'] = self.password
br.submit()
return br
def parse_index(self):
articles = []
print 'Processing ' + self.INDEX
soup = self.index_to_soup(self.INDEX)
for item in soup.findAll('div', attrs={'class':'title'}):
text_link = item.parent.find('img',attrs={'alt':'Text'})
text_link = item.parent.find('img',attrs={'alt':'Text'})
if text_link:
url = self.LOGIN + item.a['href']
title = item.a.contents[0]
@ -72,4 +70,12 @@ class Harpers_full(BasicNewsRecipe):
,'description':''
})
return [(soup.head.title.string, articles)]
def preprocess_html(self, soup):
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(1,mcharset)
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(xmlns=True):
del item['xmlns']
return soup