From 2682d46cf7fa5d25c1567a0f9bc755b7cf4b68bb Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Wed, 23 Dec 2009 09:20:07 -0700
Subject: [PATCH] New recipe for The Houston Chronicle by Kovid Goyal

---
 resources/images/news/houston_chronicle-2.png | Bin 0 -> 406 bytes
 resources/recipes/houston_chronicle.recipe    |  66 ++++++++++++++++++
 2 files changed, 66 insertions(+)
 create mode 100644 resources/images/news/houston_chronicle-2.png
 create mode 100644 resources/recipes/houston_chronicle.recipe

diff --git a/resources/images/news/houston_chronicle-2.png b/resources/images/news/houston_chronicle-2.png
new file mode 100644
index 0000000000000000000000000000000000000000..750a1204ff0f382a598c0c0d47149b384e157d81
GIT binary patch
literal 406
zcmeAS@N?(olHy`uVBq!ia0vp^0wB!61|;P_|4#%`Y)RhkE)4%caKYZ?lYt_f1s;*b
zK-vS0-A-oPfdtD69Mgd`SU*F|v9*VRoc*3Ijv*GOrv{xCJ*>bZTzi+>%sD5`|C!th
zVJ9Bn(ud2{PaB;)!^6Eoi$US}o<$FOd0n0?cerKg;8lA!Ag+QT|EWIv+O4N|UX$YP
z@X(mx-B`tT*iPic(m7L4dWVME9%5;*+OwJ?A%21h^Dirg!*e@keD(N!?~K7DWx+{o
z3%Ffba}EWn3OFbT^j$2Tq0Y#lqW^vS{1=T|uLXE+aah2!@P5>X2{tR<&*%@^CRy>{
zxbw-(Utjt}3t7vzlzm`W+{`~`^O||j5<7i>UQsP^jVMV;EJ?LWE=mPb3`Pb9mb!*U
zx<<w!29{Qa7FMR_x(4P}1_lPs6HcRO$jwj5OsmAL!BI}59H@c8)78&qol`;+06~0;
A#{d8T

literal 0
HcmV?d00001

diff --git a/resources/recipes/houston_chronicle.recipe b/resources/recipes/houston_chronicle.recipe
new file mode 100644
index 0000000000..2b0e653c25
--- /dev/null
+++ b/resources/recipes/houston_chronicle.recipe
@@ -0,0 +1,66 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class HoustonChronicle(BasicNewsRecipe):
+
+    title          = u'The Houston Chronicle'
+    description    = 'News from Houston, Texas'
+    __author__	   = 'Kovid Goyal'
+    language       = 'US'
+    timefmt        = ' [%a, %d %b, %Y]'
+    no_stylesheets = True
+
+    keep_only_tags = [dict(id=['story-head', 'story'])]
+    remove_tags = [dict(id=['share-module', 'resource-box',
+        'resource-box-header'])]
+
+    def parse_index(self):
+        soup = self.index_to_soup('http://www.chron.com/news/')
+        container = soup.find('table', attrs={'class':'body-columns'})
+
+        feeds = []
+        current_section = 'Top Stories'
+        current_articles = []
+
+        self.log('\tFound section:', current_section)
+
+        for div in container.findAll('div'):
+            if div.get('class', None) == 'module-mast':
+                t = self.tag_to_string(div).replace(u'\xbb', '').strip()
+                if t and 'interactives' not in t:
+                    if current_section and current_articles:
+                        feeds.append((current_section, current_articles))
+                    current_section = t
+                    current_articles = []
+                    self.log('\tFound section:', current_section)
+            elif div.get('storyid', False):
+                a = div.find('a', href=True)
+                if a:
+                    title = self.tag_to_string(a)
+                    url = a.get('href')
+                    if title and url:
+                        if url.startswith('/'):
+                            url = 'http://www.chron.com'+url
+                        self.log('\t\tFound article:', title)
+                        self.log('\t\t\t', url)
+                        current_articles.append({'title':title, 'url':url,
+                            'date':'', 'description':''})
+            elif div.get('class', None) == 'columnbox' and \
+                    'special' in current_section.lower():
+                a = div.find('a')
+                if a:
+                    title = self.tag_to_string(a)
+                    url = a.get('href')
+                    if title and url:
+                        if not url.startswith('/'): continue
+                        url = 'http://www.chron.com'+url
+                        self.log('\t\tFound article:', title)
+                        self.log('\t\t\t', url)
+                        a.extract()
+                        desc = self.tag_to_string(div)
+                        current_articles.append({'title':title, 'url':url,
+                            'date':'', 'description':desc})
+
+        if current_section and current_articles:
+            feeds.append((current_section, current_articles))
+        return feeds
+