mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-07 10:14:46 -04:00
remove no longer working recipes
This commit is contained in:
parent
aad9e8e705
commit
107545a2cf
@ -1,52 +0,0 @@
|
|||||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
||||||
|
|
||||||
class NGM(BasicNewsRecipe):
|
|
||||||
|
|
||||||
title = 'National Geographic Magazine'
|
|
||||||
__author__ = 'Krittika Goyal'
|
|
||||||
description = 'National Geographic Magazine'
|
|
||||||
timefmt = ' [%d %b, %Y]'
|
|
||||||
language = 'en'
|
|
||||||
|
|
||||||
no_stylesheets = True
|
|
||||||
auto_cleanup = True
|
|
||||||
auto_cleanup_keep = '//div[@class="featurepic"]'
|
|
||||||
|
|
||||||
def nejm_get_index(self):
|
|
||||||
soup = self.index_to_soup('http://ngm.nationalgeographic.com/')
|
|
||||||
a = soup.find('div', id='current_issue').find('a', href=True)
|
|
||||||
return self.index_to_soup('http://ngm.nationalgeographic.com' + a['href'])
|
|
||||||
|
|
||||||
# To parse artice toc
|
|
||||||
def parse_index(self):
|
|
||||||
soup = self.nejm_get_index()
|
|
||||||
tocfull = soup.find('div', attrs={'class':'coltoc'})
|
|
||||||
|
|
||||||
toc = tocfull.find('div', attrs={'class':'more_section'})
|
|
||||||
|
|
||||||
articles = []
|
|
||||||
feeds = []
|
|
||||||
section_title = 'Features'
|
|
||||||
for x in toc.findAll(True):
|
|
||||||
if x.name == 'a':
|
|
||||||
# Article found
|
|
||||||
title = self.tag_to_string(x)
|
|
||||||
url = x.get('href', False)
|
|
||||||
if not url or not title:
|
|
||||||
continue
|
|
||||||
url = 'http://ngm.nationalgeographic.com' + url
|
|
||||||
self.log('\t\tFound article:', title)
|
|
||||||
self.log('\t\t\t', url)
|
|
||||||
articles.append({'title': title, 'url':url,
|
|
||||||
'description':'', 'date':''})
|
|
||||||
feeds.append((section_title, articles))
|
|
||||||
|
|
||||||
art1 = tocfull.findAll('a')[1]
|
|
||||||
art1_title = self.tag_to_string(art1.find('div', attrs={'class': 'toched'}))
|
|
||||||
art1_url = art1.get('href', False)
|
|
||||||
art1_url = 'http://ngm.nationalgeographic.com' + art1_url
|
|
||||||
art1feed = {'title': art1_title, 'url':art1_url,
|
|
||||||
'description':'', 'date':''}
|
|
||||||
feeds.append(('Cover Story', [art1feed]))
|
|
||||||
|
|
||||||
return feeds
|
|
@ -1,33 +0,0 @@
|
|||||||
__license__ = 'GPL v3'
|
|
||||||
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
|
|
||||||
'''
|
|
||||||
nationalgeographic.com
|
|
||||||
'''
|
|
||||||
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
|
||||||
import re
|
|
||||||
|
|
||||||
class NationalGeographicNews(BasicNewsRecipe):
|
|
||||||
title = u'National Geographic News'
|
|
||||||
oldest_article = 7
|
|
||||||
language = 'en'
|
|
||||||
max_articles_per_feed = 100
|
|
||||||
remove_javascript = True
|
|
||||||
no_stylesheets = True
|
|
||||||
use_embedded_content = False
|
|
||||||
auto_cleanup = True
|
|
||||||
|
|
||||||
feeds = [(u'news', u'http://feeds.nationalgeographic.com/ng/News/News_Main')]
|
|
||||||
|
|
||||||
def parse_feeds(self):
|
|
||||||
feeds = BasicNewsRecipe.parse_feeds(self)
|
|
||||||
for curfeed in feeds:
|
|
||||||
delList = []
|
|
||||||
for a,curarticle in enumerate(curfeed.articles):
|
|
||||||
if re.search(r'ads\.pheedo\.com', curarticle.url):
|
|
||||||
delList.append(curarticle)
|
|
||||||
if len(delList)>0:
|
|
||||||
for d in delList:
|
|
||||||
index = curfeed.articles.index(d)
|
|
||||||
curfeed.articles[index:index+1] = []
|
|
||||||
return feeds
|
|
Loading…
x
Reference in New Issue
Block a user