Ynet by marbs

resources/recipes/ynet.recipe

@@ -0,0 +1,72 @@
+import re
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import mechanize
+
+class AdvancedUserRecipe1283848012(BasicNewsRecipe):
+    description   = 'This is a recipe of Ynet.co.il. The recipe opens the article page and clicks on an advertisement to not hurt the sites advertising income.'
+    cover_url      = 'http://www.bneiakiva.net/uploads/images/ynet%282%29.jpg'
+    title          = u'Ynet'
+    __author__ = 'marbs'
+    language              = 'he'
+    extra_css='img {max-width:100%;direction: rtl;} #article{direction: rtl;} div{direction: rtl;} title{direction: rtl; } article_description{direction: rtl; } a.article{direction: rtl; } calibre_feed_description{direction: rtl; } body{direction: ltr;}'
+    remove_attributes = ['width']
+    simultaneous_downloads = 5
+    keep_only_tags =dict(name='div', attrs={'id':'articleContainer'})
+    remove_javascript     = True
+    timefmt        = '[%a, %d %b, %Y]'
+    oldest_article = 1
+    remove_tags = [dict(name='p', attrs={'text':[' ']})]
+    max_articles_per_feed = 100
+    preprocess_regexps = [
+        (re.compile(r'<p>&nbsp;</p>', re.DOTALL|re.IGNORECASE), lambda match: '')
+        ]
+
+    def preprocess_html(self, soup):
+        soup.html['dir'] = 'rtl'
+        soup.body['dir'] = 'rtl'
+        return soup
+
+    feeds =[(u'\u05d7\u05d3\u05e9\u05d5\u05ea',
+  u'http://www.ynet.co.il/Integration/StoryRss2.xml'),
+ (u'\u05db\u05dc\u05db\u05dc\u05d4',
+  u'http://www.ynet.co.il/Integration/StoryRss6.xml'),
+ (u'\u05e6\u05e8\u05db\u05e0\u05d5\u05ea',
+  u'http://www.ynet.co.il/Integration/StoryRss437.xml'),
+ (u'\u05e1\u05e4\u05d5\u05e8\u05d8',
+  u'http://www.ynet.co.il/Integration/StoryRss3.xml'),
+ (u'\u05ea\u05e8\u05d1\u05d5\u05ea',
+  u'http://www.ynet.co.il/Integration/StoryRss538.xml'),
+ (u'\u05de\u05e2\u05d5\u05e8\u05d1\u05d5\u05ea \u05d5\u05d7\u05d1\u05e8\u05d4',
+  u'http://www.ynet.co.il/Integration/StoryRss3262.xml'),
+ (u'\u05d1\u05e8\u05d9\u05d0\u05d5\u05ea',
+  u'http://www.ynet.co.il/Integration/StoryRss1208.xml'),
+ (u'\u05d9\u05e8\u05d5\u05e7',
+  u'http://www.ynet.co.il/Integration/StoryRss4872.xml'),
+ (u'\u05de\u05d7\u05e9\u05d1\u05d9\u05dd',
+  u'http://www.ynet.co.il/Integration/StoryRss544.xml'),
+ (u'\u05e8\u05db\u05d1', u'http://www.ynet.co.il/Integration/StoryRss550.xml'),
+ (u'\u05ea\u05d9\u05d9\u05e8\u05d5\u05ea',
+  u'http://www.ynet.co.il/Integration/StoryRss598.xml'),
+ (u'\u05d4\u05d5\u05e8\u05d9\u05dd',
+  u'http://www.ynet.co.il/Integration/StoryRss3052.xml'),
+ (u'\u05d0\u05d5\u05db\u05dc',
+  u'http://www.ynet.co.il/Integration/StoryRss975.xml'),
+ (u'\u05d9\u05d4\u05d3\u05d5\u05ea',
+  u'http://www.ynet.co.il/Integration/StoryRss4403.xml'),
+ (u'\u05de\u05d3\u05e2 \u05d5\u05d8\u05d1\u05e2',
+  u'http://www.ynet.co.il/Integration/StoryRss2142.xml'),
+ (u'\u05d9\u05d7\u05e1\u05d9\u05dd',
+  u'http://www.ynet.co.il/Integration/StoryRss3925.xml'),
+ (u'\u05d3\u05e2\u05d5\u05ea',
+  u'http://www.ynet.co.il/Integration/StoryRss194.xml')]
+
+    def print_version(self, url):
+#remove from here
+        br = BasicNewsRecipe.get_browser()
+        br.open(url)
+        br.follow_link(mechanize.Link(base_url = '', url =url, text = '', tag = 'a', attrs = [{'id':'buzzerATop'}]))
+#to here to stop supporting ynet...
+        split1 = url.split("-")
+        print_url = 'http://www.ynet.co.il/Ext/Comp/ArticleLayout/CdaArticlePrintPreview/1,2506,L-' + split1[1]
+        return print_url