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

Update The Hindu

Browse Source
This commit is contained in:
Kovid Goyal 2017-06-11 11:02:58 +05:30
parent 1eeb0c7c92
commit 09217dd851
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 26 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
recipes/hindu.recipe
View File

@ -6,6 +6,12 @@ from calibre.web.feeds.news import BasicNewsRecipe
import string import string
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
class TheHindu(BasicNewsRecipe): class TheHindu(BasicNewsRecipe):
title = u'The Hindu' title = u'The Hindu'
language = 'en_IN' language = 'en_IN'
@ -14,11 +20,19 @@ class TheHindu(BasicNewsRecipe):
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
remove_attributes = ['style']
auto_cleanup = True
ignore_duplicate_articles = {'title', 'url'} ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [
dict(name='h1', attrs={'class': 'title'}),
classes('lead-img-cont mobile-author-cont'),
dict(id=lambda x: x and x.startswith('content-body-')),
]
extra_css = '.photo-caption { font-size: smaller }' def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src-template': True}):
img['src'] = img['data-src-template'].replace('BINARY/thumbnail', 'alternates/FREE_660')
return soup
def articles_from_soup(self, soup): def articles_from_soup(self, soup):
ans = [] ans = []
@ -34,8 +48,11 @@ class TheHindu(BasicNewsRecipe):
continue continue
self.log('\t\tFound article:', title) self.log('\t\tFound article:', title)
self.log('\t\t\t', url) self.log('\t\t\t', url)
ans.append({'title': title, 'url': url, ans.append({
'description': '', 'date': ''}) 'title': title,
'url': url,
'description': '',
'date': ''})
return ans return ans
def parse_index(self): def parse_index(self):
@ -64,21 +81,11 @@ class TheHindu(BasicNewsRecipe):
def is_accepted_entry(self, entry): def is_accepted_entry(self, entry):
# Those sections in the top nav bar that we will omit # Those sections in the top nav bar that we will omit
omit_list = ['tp-tamilnadu', omit_list = [
'tp-karnataka', 'tp-tamilnadu', 'tp-karnataka', 'tp-kerala', 'tp-andhrapradesh',
'tp-kerala', 'tp-telangana', 'tp-newdelhi', 'tp-mumbai', 'tp-otherstates',
'tp-andhrapradesh', 'tp-in-school', 'tp-metroplus', 'tp-youngworld', 'tp-fridayreview',
'tp-telangana', 'tp-downtown', 'tp-bookreview', 'tp-others']
'tp-newdelhi',
'tp-mumbai',
'tp-otherstates',
'tp-in-school',
'tp-metroplus',
'tp-youngworld',
'tp-fridayreview',
'tp-downtown',
'tp-bookreview',
'tp-others']
is_accepted = True is_accepted = True
for omit_entry in omit_list: for omit_entry in omit_list: