From d18bef33e11c20be510339e9ffe7bca665ff6dde Mon Sep 17 00:00:00 2001 From: Hiroshi Miura Date: Sun, 12 Dec 2010 22:28:55 +0900 Subject: [PATCH] recipe: add national geographic news - national geographic Japan - national geographic News --- resources/recipes/nationalgeographic.recipe | 38 +++++++++++++++++++ resources/recipes/nationalgeographicjp.recipe | 20 ++++++++++ 2 files changed, 58 insertions(+) create mode 100644 resources/recipes/nationalgeographic.recipe create mode 100644 resources/recipes/nationalgeographicjp.recipe diff --git a/resources/recipes/nationalgeographic.recipe b/resources/recipes/nationalgeographic.recipe new file mode 100644 index 0000000000..b540f9b044 --- /dev/null +++ b/resources/recipes/nationalgeographic.recipe @@ -0,0 +1,38 @@ +__license__ = 'GPL v3' +__copyright__ = '2010, Hiroshi Miura ' +''' +nationalgeographic.com +''' + +from calibre.web.feeds.news import BasicNewsRecipe +import re + +class NationalGeographicNews(BasicNewsRecipe): + title = u'National Geographic News' + oldest_article = 7 + max_articles_per_feed = 100 + remove_javascript = True + no_stylesheets = True + use_embedded_content = False + + feeds = [(u'news', u'http://feeds.nationalgeographic.com/ng/News/News_Main')] + + remove_tags_before = dict(id='page_head') + remove_tags_after = [dict(id='social_buttons'),{'class':'aside'}] + remove_tags = [ + {'class':'hidden'} + + ] + + 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 diff --git a/resources/recipes/nationalgeographicjp.recipe b/resources/recipes/nationalgeographicjp.recipe new file mode 100644 index 0000000000..5798acb102 --- /dev/null +++ b/resources/recipes/nationalgeographicjp.recipe @@ -0,0 +1,20 @@ +__license__ = 'GPL v3' +__copyright__ = '2010, Hiroshi Miura ' +''' +nationalgeographic.co.jp +''' + +from calibre.web.feeds.news import BasicNewsRecipe +import re + +class NationalGeoJp(BasicNewsRecipe): + title = u'\u30ca\u30b7\u30e7\u30ca\u30eb\u30fb\u30b8\u30aa\u30b0\u30e9\u30d5\u30a3\u30c3\u30af\u30cb\u30e5\u30fc\u30b9' + oldest_article = 7 + max_articles_per_feed = 100 + no_stylesheets = True + + feeds = [(u'news', u'http://www.nationalgeographic.co.jp/news/rss.php')] + + def print_version(self, url): + return re.sub(r'news_article.php','news_printer_friendly.php', url) +