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

...

Browse Source
This commit is contained in:
Kovid Goyal 2011-09-12 21:21:21 -06:00
parent 2bf6e7bed0
commit be7114ba3a
1 changed files with 12 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/businessworldin.recipe
View File

@ -4,6 +4,7 @@ __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
www.businessworld.in www.businessworld.in
''' '''
import re
from calibre import strftime from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
@ -15,7 +16,7 @@ class BusinessWorldMagazine(BasicNewsRecipe):
category = 'news, politics, finances, India, Asia' category = 'news, politics, finances, India, Asia'
delay = 1 delay = 1
no_stylesheets = True no_stylesheets = True
INDEX = 'http://www.businessworld.in/bw/Magazine_Current_Issue' INDEX = 'http://www.businessworld.in/businessworld/magazine_latest_issue.php'
ROOT = 'http://www.businessworld.in' ROOT = 'http://www.businessworld.in'
use_embedded_content = False use_embedded_content = False
encoding = 'utf-8' encoding = 'utf-8'
@ -38,13 +39,17 @@ class BusinessWorldMagazine(BasicNewsRecipe):
if litem == url: if litem == url:
return True return True
return False return False
def parse_index(self): def parse_index(self):
articles = [] articles = []
linklist = [] linklist = []
soup = self.index_to_soup(self.INDEX) br = self.browser
br.open(self.ROOT)
raw = br.open(br.click_link(text_regex=re.compile('Current.*Issue',
re.I))).read()
soup = self.index_to_soup(raw)
tough = soup.find('div', attrs={'id':'tough'}) tough = soup.find('div', attrs={'id':'tough'})
if tough: if tough:
for item in tough.findAll('h1'): for item in tough.findAll('h1'):
@ -63,7 +68,7 @@ class BusinessWorldMagazine(BasicNewsRecipe):
,'description':description ,'description':description
}) })
linklist.append(url) linklist.append(url)
for item in soup.findAll('div', attrs={'class':'nametitle'}): for item in soup.findAll('div', attrs={'class':'nametitle'}):
description = '' description = ''
title_prefix = '' title_prefix = ''
@ -82,7 +87,7 @@ class BusinessWorldMagazine(BasicNewsRecipe):
linklist.append(url) linklist.append(url)
return [(soup.head.title.string, articles)] return [(soup.head.title.string, articles)]
keep_only_tags = [dict(name='div', attrs={'id':'printwrapper'})] keep_only_tags = [dict(name='div', attrs={'id':'printwrapper'})]
remove_tags = [dict(name=['object','link','meta','base','iframe','link','table'])] remove_tags = [dict(name=['object','link','meta','base','iframe','link','table'])]