From 8336bd6e4986effa3a184a410d885f95989c4d29 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sun, 22 May 2011 10:48:45 -0600
Subject: [PATCH] Update Washington Post. Fixes #786609 (Updated recipe for The
 Washington Post)

---
 recipes/icons/wash_post.png | Bin 0 -> 1158 bytes
 recipes/wash_post.recipe    | 119 ++++++++++++++++++++----------------
 2 files changed, 65 insertions(+), 54 deletions(-)
 create mode 100644 recipes/icons/wash_post.png

diff --git a/recipes/icons/wash_post.png b/recipes/icons/wash_post.png
new file mode 100644
index 0000000000000000000000000000000000000000..e392e4c3ff7b37e4106fb51359242e524fd80413
GIT binary patch
literal 1158
zcmV;11bO?3P)<h;3K|Lk000e1NJLTq002M$002M;0ssI2B@5<>000C{Nkl<Zc%1E;
z{WSwY6vbsLpaUup9nb+4paN8Y3Q$3)02QEuqytKz0)EHMnT+|~582H*xqmpx?%Ox_
z&b*oT_Q~k``+H-RF<J}g87nWKO5gtc{9F!?#t5$fyzlSt@9yr#<MHF;<ML^hBOu`R
z_V)Vv8V!@l<mBX}4^}nsM*yUcj*ebmU-^7<b8~)v-W#uCEcO8G4-O8*9t?l(g@pj-
zem0w#ubZ2jeekJ`xqzpqCo}iL@XsG%F5vn3*|~9Xaj|qVO)wYm@$uo@;22#A4RZmU
z_x?T3Q$owRh^oE4y>x)Fm$tUHn1T`pB@Ttt(^HNa$8s*<?CdP~3<<&h3MW*-&v#_A
z*ImZTYA_DbU>_kt_87BKouTIfwzs!0FE4{^j5W{W#bFs^Z;zT_ZyXZCJZLmrU0w0j
zSh7mSkA^Uoi({0u6+Aj+Y7Z9EpgicPifQm2DiQfXt5x!c7O{l@*avq)a4=tkhW8JH
zpoW-3O@SRt2}`BjOf?D~9v*N(j0Nv1d`)P^(jOko)QVFg)7wEy@C0MqXvhn|3xmDC
zzsH7D`0`;ooxZ%h#59<B#bELa>=XGOd)VWU{Xj(=v&;*CH-qsZQJk_qqD~MdGzf=>
zhw?N2MbPH!>x;j*k^zsz+~x%wA0L~~Xb6_52r%9mQi2<Uxo6oOc`>zl0S+j$vo<XY
zL6Xn@{(hlxZ2?OFbF{m=TWCB)0kIP=h<*fcaB;%e3AHgQxg&jyMkD8y;Ge(--Pze8
zxiVb)w~h)IWFkL-{}ULl+bX?M1ENEZX)sgW4p%L0?uB5n)CN`O9!sEpnMt&5P<87r
z3*~IaqB<a3weNjYc!Ygd?y^W!HO){_X4Xm^Es=QZXof$nMY}U+z=S!K2^qt&!2mP!
zRj&t*4P`xrv2!stA{XD@-fW*S<F$abfR+OC#hl-D^fCKI!hntYPtE$g0IIHFU%-Y6
zs#pt1>r?mWB*U^|+4{1moQ9d{{v}EeboxQU>u->~!YsiL0n};OsC12){Sjcl{yI?m
zL>-Yt-e5?3xlBXA0e;f#ZJ3t_rwUX?cmGF*Q@^`rL!6kBL{*GJMh))Tjd-uhK%3ZU
z%Q_$|)oXD>Nbwq*WA>t6>e-RVh=n!mxf^7!=}a&y0aIhbGO!0=Ih{`ZgzxlxV!^$U
z>>#y#{ZQE0Qxo3Ava?C(ibL0ziUC&=Z9{Vgu+->G)I~&rlYjV1<>p+Bo<eE>sxKL2
zZ-!BAY|Ijz)U3yhIMf6s&Q^IgZ74fzY~+6{;Wx>GU|EroHdC|K7Fm*sdCFf6gQDJO
zNdb(2teH-Ty5%$k5{<g0_Jx?p&R_a^{<%%9VlIf47cj)$Xsv$Z-~_N=IjKr&cwtxq
zs89$S@=y693`hXHm9|tb7QR0WWfM34by)u^;MZNX(6a!sFaM92kCp%3=vqMESPSSI
YKbDM<r?pMJIsgCw07*qoM6N<$f+!g;wg3PC

literal 0
HcmV?d00001

diff --git a/recipes/wash_post.recipe b/recipes/wash_post.recipe
index 0ca6410b4e..61a469b47d 100644
--- a/recipes/wash_post.recipe
+++ b/recipes/wash_post.recipe
@@ -1,64 +1,75 @@
+__license__   = 'GPL v3'
+__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.washingtonpost.com
+'''
+
+from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 
+class TheWashingtonPost(BasicNewsRecipe):
+    title                 = 'The Washington Post'
+    __author__            = 'Darko Miletic'
+    description           = 'Leading source for news, video and opinion on politics, business, world and national news, science, travel, entertainment and more. Our local coverage includes reporting on education, crime, weather, traffic, real estate, jobs and cars for DC, Maryland and Virginia. Offering award-winning opinion writing, entertainment information and restaurant reviews.'
+    publisher             = 'The Washington Post Company'
+    category              = 'news, politics, USA'
+    oldest_article        = 2
+    max_articles_per_feed = 200
+    no_stylesheets        = True
+    encoding              = 'utf8'
+    delay                 = 1
+    use_embedded_content  = False
+    language              = 'en'
+    remove_empty_feeds    = True
+    publication_type      = 'newspaper'
+    masthead_url          = 'http://www.washingtonpost.com/rw/sites/twpweb/img/logos/twp_logo_300.gif'
+    cover_url             = strftime('http://www.washingtonpost.com/rw/WashingtonPost/Content/Epaper/%Y-%m-%d/Ax1.pdf')
+    extra_css             = """
+                               body{font-family: Georgia,serif }
+                            """
 
-class WashingtonPost(BasicNewsRecipe):
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
 
-    title = 'Washington Post'
-    description = 'US political news'
-    __author__ = 'Kovid Goyal'
-    use_embedded_content   = False
-    max_articles_per_feed = 20
-    language = 'en'
-    encoding = 'utf-8'
+    keep_only_tags   = [dict(attrs={'id':['content','entryhead','entrytext']})]
+    remove_tags      = [
+                          dict(name=['meta','link','iframe','base'])
+                         ,dict(attrs={'id':'multimedia-leaf-page'})
+                       ]
+    remove_attributes= ['lang','property','epochtime','datetitle','pagetype','contenttype','comparetime']
 
 
-    remove_javascript = True
-    no_stylesheets = True
-
     feeds = [
-            ('Politics', 'http://www.washingtonpost.com/rss/politics'),
-            ('Nation', 'http://www.washingtonpost.com/rss/national'),
-            ('World', 'http://www.washingtonpost.com/rss/world'),
-            ('Business', 'http://www.washingtonpost.com/rss/business'),
-            ('Lifestyle', 'http://www.washingtonpost.com/rss/lifestyle'),
-            ('Sports', 'http://www.washingtonpost.com/rss/sports'),
-            ('Redskins', 'http://www.washingtonpost.com/rss/sports/redskins'),
-            ('Opinions', 'http://www.washingtonpost.com/rss/opinions'),
-            ('Entertainment', 'http://www.washingtonpost.com/rss/entertainment'),
-            ('Local', 'http://www.washingtonpost.com/rss/local'),
-            ('Investigations',
-                'http://www.washingtonpost.com/rss/investigations'),
-    ]
-
-    remove_tags = [
-            {'class':lambda x: x and 'article-toolbar' in x},
-            {'class':lambda x: x and 'quick-comments' in x},
-            {'class':lambda x: x and 'tweet' in x},
-            {'class':lambda x: x and 'article-related' in x},
-            {'class':lambda x: x and 'hidden' in x.split()},
-            {'class':lambda x: x and 'also-read' in x.split()},
-            {'class':lambda x: x and 'partners-content' in x.split()},
-            {'class':['module share', 'module ads', 'comment-vars', 'hidden',
-                'share-icons-wrap', 'comments', 'flipper']},
-            {'id':['right-rail', 'save-and-share']},
-            {'width':'1', 'height':'1'},
-
-    ]
-
-    keep_only_tags = dict(id=['content', 'article'])
-
-    def get_article_url(self, *args):
-        ans = BasicNewsRecipe.get_article_url(self, *args)
-        ans = ans.rpartition('?')[0]
-        if ans.endswith('_video.html'):
-            return None
-        if 'ads.pheedo.com' in ans:
-            return None
-        #if not ans.endswith('_blog.html'):
-        #    return None
-        return ans
-
+              (u'World'          , u'http://feeds.washingtonpost.com/rss/world'                   )
+             ,(u'National'       , u'http://feeds.washingtonpost.com/rss/national'                )
+             ,(u'White House'    , u'http://feeds.washingtonpost.com/rss/politics/whitehouse'     )
+             ,(u'Business'       , u'http://feeds.washingtonpost.com/rss/business'                )
+             ,(u'Opinions'       , u'http://feeds.washingtonpost.com/rss/opinions'                )
+             ,(u'Investigations' , u'http://feeds.washingtonpost.com/rss/investigations'          )
+             ,(u'Local'          , u'http://feeds.washingtonpost.com/rss/local'                   )
+             ,(u'Entertainment'  , u'http://feeds.washingtonpost.com/rss/entertainment'           )
+             ,(u'Sports'         , u'http://feeds.washingtonpost.com/rss/sports'                  )
+             ,(u'Redskins'       , u'http://feeds.washingtonpost.com/rss/sports/redskins'         )
+             ,(u'Special Reports', u'http://feeds.washingtonpost.com/rss/national/special-reports')
+            ]
 
     def print_version(self, url):
-        return url.replace('_story.html', '_singlePage.html')
+        if '_story.html' in url:
+           return url.replace('_story.html','_print.html')
+        return url
+
+    def get_article_url(self, article):
+        link = BasicNewsRecipe.get_article_url(self,article)
+        if not 'washingtonpost.com' in link:
+           self.log('Skipping adds:', link)
+           return None
+        for it in ['_video.html','_gallery.html','_links.html']:
+            if it in link:
+               self.log('Skipping non-article:', link)
+               return None
+        return link