From 6a0eb2b6087f47f7c4c482c595ea1b309714ce3a Mon Sep 17 00:00:00 2001 From: Hassan Williamson Date: Sun, 14 Feb 2016 23:54:33 +0000 Subject: [PATCH] Update Al-Ahram Arabic recipe. * Fix broken urls. * Tidy recent website changes. --- recipes/al_ahram.recipe | 64 ++++++++++++++++++++++------------------- 1 file changed, 34 insertions(+), 30 deletions(-) diff --git a/recipes/al_ahram.recipe b/recipes/al_ahram.recipe index 8850e82ebf..a03d877303 100644 --- a/recipes/al_ahram.recipe +++ b/recipes/al_ahram.recipe @@ -1,27 +1,28 @@ # coding=utf-8 __license__ = 'GPL v3' -__copyright__ = '2011, Hassan Williamson ' +__copyright__ = '2011-2016, Hassan Williamson ' ''' ahram.org.eg ''' from calibre.web.feeds.recipes import BasicNewsRecipe class AlAhram(BasicNewsRecipe): - title = 'Al-Ahram' + title = 'Al-Ahram (الأهرام)' __author__ = 'Hassan Williamson' - description = 'News from Egypt in Arabic.' + description = 'The Arabic version of the Al-Ahram newspaper.' + language = 'ar' + encoding = 'utf8' + cover_url = 'http://www.ahram.org.eg/Media/News/2015/3/14/2015-635619650946000713-600.jpg' oldest_article = 7 max_articles_per_feed = 100 no_stylesheets = True #delay = 1 use_embedded_content = False - encoding = 'utf8' publisher = 'Al-Ahram' category = 'News' - language = 'ar' publication_type = 'newsportal' - extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif; direction: rtl; } .txtTitle{ font-weight: bold; } ' + extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif; direction: rtl; } .bbtitle{ font-weight: bold; font-size: 2em; } .bbsubtitle{ font-size: 1.3em; } #WriterImage{ height: 10px; } ' keep_only_tags = [ dict(name='div', attrs={'class':['bbcolright']}) @@ -29,34 +30,37 @@ class AlAhram(BasicNewsRecipe): remove_tags = [ dict(name='div', attrs={'class':['bbnav', 'bbsp']}), - dict(name='div', attrs={'id':['AddThisButton']}) + dict(name='div', attrs={'id':['AddThisButton']}), + dict(name='a', attrs={'class':['twitter-share-button']}), + dict(name='div', attrs={'id':['ReaderCount']}), ] remove_attributes = [ - 'width','height' + 'width','height','style' ] feeds = [ - (u'الأولى', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=25'), - (u'مصر', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=27'), - (u'المحافظات', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=29'), - (u'الوطن العربي', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=31'), - (u'العالم', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=26'), - (u'تقارير المراسلين', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=2'), - (u'تحقيقات', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=3'), - (u'قضايا واراء', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=4'), - (u'اقتصاد', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=5'), - (u'رياضة', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=6'), - (u'حوادث', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=38'), - (u'دنيا الثقافة', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=7'), - (u'المراة والطفل', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=8'), - (u'يوم جديد', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=9'), - (u'الكتاب', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=10'), - (u'الاعمدة', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=11'), - (u'أراء حرة', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=59'), - (u'ملفات الاهرام', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=12'), - (u'بريد الاهرام', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=15'), - (u'الاخيرة', 'http://www.ahram.org.eg/RssXml.aspx?CategoryID=16'), + (u'الأولى', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=25'), + (u'الصفحة الثانية', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=74'), + (u'مصر', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=27'), + (u'المشهد السياسي', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=60'), + (u'المحافظات', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=29'), + (u'الوطن العربي', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=31'), + (u'العالم', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=26'), + (u'تقارير المراسلين', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=2'), + (u'تحقيقات', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=3'), + (u'قضايا واراء', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=4'), + (u'اقتصاد', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=5'), + (u'رياضة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=6'), + (u'حوادث', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=38'), + (u'دنيا الثقافة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=7'), + (u'المراة والطفل', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=8'), + (u'يوم جديد', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=9'), + (u'الكتاب', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=10'), + (u'الاعمدة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=11'), + (u'أراء حرة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=59'), + (u'ملفات الاهرام', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=12'), + (u'بريد الاهرام', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=15'), + (u'برلمان الثورة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=61'), + (u'الاخيرة', 'http://www.ahram.org.eg/archive/RssXml.aspx?CategoryID=16'), ] - -