Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #5972 (Houston Chronicle Recipe Fails)

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-27 15:54:47 -06:00
parent 951df0948b
commit f66a9077c6
1 changed files with 20 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
resources/recipes/houston_chronicle.recipe
View File

@ -1,12 +1,15 @@
#!/usr/bin/env python #!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
import string, pprint
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class HoustonChronicle(BasicNewsRecipe): class HoustonChronicle(BasicNewsRecipe):
title = u'The Houston Chronicle' title = u'The Houston Chronicle'
description = 'News from Houston, Texas' description = 'News from Houston, Texas'
__author__ = 'Kovid Goyal and Sujata Raman' __author__ = 'Kovid Goyal'
language = 'en' language = 'en'
timefmt = ' [%a, %d %b, %Y]' timefmt = ' [%a, %d %b, %Y]'
no_stylesheets = True no_stylesheets = True
@ -38,54 +41,23 @@ class HoustonChronicle(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://www.chron.com/news/') categories = ['news', 'sports', 'business', 'entertainment', 'life',
container = soup.find('table', attrs={'class':'body-columns'}) 'travel']
feeds = [] feeds = []
current_section = 'Top Stories' for cat in categories:
current_articles = [] articles = []
soup = self.index_to_soup('http://www.chron.com/%s/'%cat)
self.log('\tFound section:', current_section) for elem in soup.findAll(comptype='story', storyid=True):
a = elem.find('a', href=True)
for div in container.findAll('div'): if a is None: continue
if div.get('class', None) == 'module-mast': url = a['href']
t = self.tag_to_string(div).replace(u'\xbb', '').strip() if not url.startswith('http://'):
if t and 'interactives' not in t: url = 'http://www.chron.com'+url
if current_section and current_articles: articles.append({'title':self.tag_to_string(a), 'url':url,
feeds.append((current_section, current_articles)) 'description':'', 'date':''})
current_section = t pprint.pprint(articles[-1])
current_articles = [] if articles:
self.log('\tFound section:', current_section) feeds.append((string.capwords(cat), articles))
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 return feeds