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 #5969 (Hindu newspaper download problem)

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-27 11:29:29 -06:00
parent 10b18f15d9
commit 1c278e59c0
1 changed files with 31 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
resources/recipes/hindu.recipe
View File

@ -2,7 +2,7 @@ from __future__ import with_statement
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
import re import time
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class TheHindu(BasicNewsRecipe): class TheHindu(BasicNewsRecipe):
@ -10,45 +10,41 @@ class TheHindu(BasicNewsRecipe):
language = 'en_IN' language = 'en_IN'
oldest_article = 7 oldest_article = 7
__author__ = 'Kovid Goyal and Sujata Raman' __author__ = 'Kovid Goyal'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
remove_tags_before = {'name':'font', 'class':'storyhead'} keep_only_tags = [dict(id='content')]
preprocess_regexps = [ remove_tags = [dict(attrs={'class':['article-links', 'breadcr']}),
(re.compile(r'<!-- story ends -->.*', re.DOTALL), dict(id=['email-section', 'right-column', 'printfooter'])]
lambda match: '</body></html>'),
] extra_css = '.photo-caption { font-size: smaller }'
extra_css = '''
.storyhead{font-family:Arial,Helvetica,sans-serif; font-size:large; color:#000099;}
body{font-family:Verdana,Arial,Helvetica,sans-serif; font-size:x-small; text-align:left;}
'''
feeds = [
(u'Main - Front Page', u'http://www.hindu.com/rss/01hdline.xml'),
(u'Main - National', u'http://www.hindu.com/rss/02hdline.xml'),
(u'Main - International', u'http://www.hindu.com/rss/03hdline.xml'),
(u'Main - Opinion', u'http://www.hindu.com/rss/05hdline.xml'),
(u'Main - Business', u'http://www.hindu.com/rss/06hdline.xml'),
(u'Main - Sport', u'http://www.hindu.com/rss/07hdline.xml'),
(u'Main - Weather / Religion / Crossword / Cartoon',
u'http://www.hindu.com/rss/10hdline.xml'),
(u'Main - Engagements', u'http://www.hindu.com/rss/26hdline.xml'),
(u'Supplement - Literary Review',
u'http://www.hindu.com/rss/lrhdline.xml'),
(u'Supplement - Sunday Magazine',
u'http://www.hindu.com/rss/maghdline.xml'),
(u'Supplement - Open Page', u'http://www.hindu.com/rss/ophdline.xml'),
(u'Supplement - Business Review',
u'http://www.hindu.com/rss/bizhdline.xml'),
(u'Supplement - Book Review',
u'http://www.hindu.com/rss/brhdline.xml'),
(u'Supplement - Science & Technology',
u'http://www.hindu.com/rss/setahdline.xml')
]
def postprocess_html(self, soup, first_fetch): def postprocess_html(self, soup, first_fetch):
for t in soup.findAll(['table', 'tr', 'td','center']): for t in soup.findAll(['table', 'tr', 'td','center']):
t.name = 'div' t.name = 'div'
return soup return soup
def parse_index(self):
today = time.strftime('%Y-%m-%d')
soup = self.index_to_soup(
'http://www.thehindu.com/todays-paper/tp-index/?date=' + today)
div = soup.find(id='left-column')
feeds = []
current_section = None
current_articles = []
for x in div.findAll(['h3', 'div']):
if current_section and x.get('class', '') == 'tpaper':
a = x.find('a', href=True)
if a is not None:
current_articles.append({'url':a['href']+'?css=print',
'title':self.tag_to_string(a), 'date': '',
'description':''})
if x.name == 'h3':
if current_section and current_articles:
feeds.append((current_section, current_articles))
current_section = self.tag_to_string(x)
current_articles = []
return feeds