mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
65 lines
2.8 KiB
Plaintext
65 lines
2.8 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class FIELDSTREAM(BasicNewsRecipe):
|
|
title = 'Field and Stream'
|
|
__author__ = 'Starson17 and Tonythebookworm'
|
|
description = 'Hunting and Fishing and Gun Talk'
|
|
language = 'en'
|
|
no_stylesheets = True
|
|
publisher = 'Starson17 and Tonythebookworm'
|
|
category = 'food recipes, hunting, fishing, guns'
|
|
use_embedded_content= False
|
|
no_stylesheets = True
|
|
oldest_article = 24
|
|
remove_javascript = True
|
|
remove_empty_feeds = True
|
|
masthead_url = 'http://www.fieldandstream.com/sites/all/themes/fs/logo.png'
|
|
cover_url = 'http://www.arrowheadflyangler.com/Portals/1/Articles/FieldStream/Field%20and%20Stream%20March%20Fishing%20Edition%20Article%20Cover.jpg'
|
|
# recursions = 0
|
|
max_articles_per_feed = 10
|
|
INDEX = 'http://www.fieldandstream.com'
|
|
|
|
keep_only_tags = [dict(name='div', attrs={'class':['interior-main']})
|
|
]
|
|
remove_tags = [dict(name='div', attrs={'id':['comments']})]
|
|
|
|
def parse_index(self):
|
|
feeds = []
|
|
for title, url in [
|
|
(u"Wild Chef", u"http://www.fieldandstream.com/blogs/wild-chef"),
|
|
(u"The Gun Nut", u"http://www.fieldandstream.com/blogs/gun-nut"),
|
|
(u"Whitetail 365", u"http://www.fieldandstream.com/blogs/whitetail-365"),
|
|
(u"Fly Talk", u"http://www.fieldandstream.com/blogs/flytalk"),
|
|
(u"Generation Wild", u"http://www.fieldandstream.com/blogs/generation-wild"),
|
|
(u"Conservationist", u"http://www.fieldandstream.com/blogs/conservationist"),
|
|
(u"Honest Angler", u"http://www.fieldandstream.com/blogs/honest-angler"),
|
|
(u"Mans Best Friend", u"http://www.fieldandstream.com/blogs/mans-best-friend"),
|
|
|
|
]:
|
|
articles = self.make_links(url)
|
|
if articles:
|
|
feeds.append((title, articles))
|
|
return feeds
|
|
|
|
def make_links(self, url):
|
|
title = 'Temp'
|
|
current_articles = []
|
|
soup = self.index_to_soup(url)
|
|
print 'The soup is: ', soup
|
|
for item in soup.findAll('h2'):
|
|
print 'item is: ', item
|
|
link = item.find('a')
|
|
print 'the link is: ', link
|
|
if link:
|
|
url = self.INDEX + link['href']
|
|
title = self.tag_to_string(link)
|
|
print 'the title is: ', title
|
|
print 'the url is: ', url
|
|
print 'the title is: ', title
|
|
current_articles.append({'title': title, 'url': url, 'description':'', 'date':''}) # append all this
|
|
return current_articles
|
|
|
|
|
|
|
|
|