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 National Geographic Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2013-10-10 15:26:27 +05:30
parent 7275d89cb5
commit bfe6099a3d
1 changed files with 46 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

87
recipes/national_geographic_mag.recipe
View File

@ -1,46 +1,49 @@
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class NatGeoMag(BasicNewsRecipe): class NGM(BasicNewsRecipe):
title = 'National Geographic Mag'
__author__ = 'Terminal Veracity' title = 'National Geographic Magazine'
description = 'The National Geographic Magazine' __author__ = 'Krittika Goyal'
publisher = 'National Geographic' description = 'National Geographic Magazine'
oldest_article = 31 timefmt = ' [%d %b, %Y]'
max_articles_per_feed = 50
category = 'geography, magazine' no_stylesheets = True
language = 'en' auto_cleanup = True
publication_type = 'magazine' auto_cleanup_keep = '//div[@class="featurepic"]'
cover_url = 'http://www.yourlogoresources.com/wp-content/uploads/2011/09/national-geographic-logo.jpg'
use_embedded_content = False def nejm_get_index(self):
no_stylesheets = True return self.index_to_soup('http://ngm.nationalgeographic.com/2013/10/table-of-contents')
remove_javascript = True
recursions = 1 # To parse artice toc
remove_empty_feeds = True def parse_index(self):
feeds = [('National Geographic Magazine', 'http://feeds.nationalgeographic.com/ng/NGM/NGM_Magazine')] soup = self.nejm_get_index()
remove_tags = [dict(name='div', attrs={'class':['nextpage_continue', 'subscribe']})] tocfull = soup.find('div', attrs={'class':'coltoc'})
keep_only_tags = [dict(attrs={'class':'main_3narrow'})]
extra_css = """ toc = tocfull.find('div', attrs={'class':'more_section'})
h1 {font-size: large; font-weight: bold; margin: .5em 0; }
h2 {font-size: large; font-weight: bold; margin: .5em 0; } articles = []
h3 {font-size: medium; font-weight: bold; margin: 0 0; } feeds = []
.article_credits_author {font-size: small; font-style: italic; } section_title = 'Features'
.article_credits_photographer {font-size: small; font-style: italic; display: inline } 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]))
def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self)
for feed in feeds:
for article in feed.articles[:]:
if 'Flashback' in article.title:
feed.articles.remove(article)
elif 'Desktop Wallpaper' in article.title:
feed.articles.remove(article)
elif 'Visions of Earth' in article.title:
feed.articles.remove(article)
elif 'Your Shot' in article.title:
feed.articles.remove(article)
elif 'MyShot' in article.title:
feed.articles.remove(article)
elif 'Field Test' in article.title:
feed.articles.remove(article)
return feeds return feeds