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 India Today

Browse Source
This commit is contained in:
Kovid Goyal 2022-07-23 19:50:45 +05:30
parent 320dff52a6
commit 3e6d7dd057
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 41 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
recipes/india_today.recipe
View File

@ -7,17 +7,27 @@ class IndiaToday(BasicNewsRecipe):
__author__ = 'unkn0wn'
no_stylesheets = True
use_embedded_content = False
remove_attributes = ['style','height','width']
remove_attributes = ['style', 'height', 'width']
ignore_duplicate_articles = {'url'}
extra_css = '[itemprop^="description"] {font-size: small; font-style: italic;}'
description = (
'India’s Most Reputed, Credible and Popular news magazine.'
' Read the most preferred magazine of 9.5 million Indians to access highly researched and unbiased content.')
' Read the most preferred magazine of 9.5 million Indians to access highly researched and unbiased content.'
)
masthead_url = 'https://akm-img-a-in.tosshub.com/sites/all/themes/itg/logo.png'
extra_css = '''
.body_caption{font-size:small;}
.image-alt{font-size:small;}
'''
def get_cover_url(self):
soup = self.index_to_soup('https://www.readwhere.com/magazine/the-india-today-group/India-Today/1154')
for citem in soup.findAll('meta', content=lambda s: s and s.endswith('/magazine/300/new')):
soup = self.index_to_soup(
'https://www.readwhere.com/magazine/the-india-today-group/India-Today/1154'
)
for citem in soup.findAll(
'meta', content=lambda s: s and s.endswith('/magazine/300/new')
):
return citem['content'].replace('300', '600')
keep_only_tags = [
@ -32,32 +42,40 @@ class IndiaToday(BasicNewsRecipe):
section = None
sections = {}
for tag in soup.findAll('div', attrs={'class':['magazin-top-left', 'section-ordering']}):
for tag in soup.findAll(
'div', attrs={'class': ['magazin-top-left', 'section-ordering']}
):
sec = tag.find('span')
section = self.tag_to_string(sec)
self.log(section)
sections[section] = []
for a in tag.findAll('a', href=lambda x: x and x.startswith(("/magazine/cover-story/story/", "https://www.indiatoday.in/magazine/"))):
for a in tag.findAll(
'a',
href=lambda x: x and x.startswith((
"/magazine/cover-story/story/",
"https://www.indiatoday.in/magazine/"
))
):
url = a['href']
if url.startswith('https'):
url = url
else:
url = 'https://www.indiatoday.in' + url
title = self.tag_to_string(a)
empty = " "
if title is empty:
url = ''
title = self.tag_to_string(a).strip()
if not url or not title:
continue
self.log('\t', title)
self.log('\t\t', url)
sections[section].append({
'title': title,
'url': url})
sections[section].append({'title': title, 'url': url})
def sort_key(x):
section = x[0]
try:
return ('EDITOR\'S NOTE', 'Cover Story', 'The Big Story', 'Upfront', 'NATION', 'INTERVIEW').index(section)
return (
'EDITOR\'S NOTE', 'Cover Story', 'The Big Story', 'Upfront',
'NATION', 'INTERVIEW'
).index(section)
except Exception:
return 99999999
@ -66,6 +84,15 @@ class IndiaToday(BasicNewsRecipe):
def preprocess_raw_html(self, raw_html, url):
from calibre.ebooks.BeautifulSoup import BeautifulSoup
soup = BeautifulSoup(raw_html)
for div in soup.findAll('div', attrs={'id': 'premium_content_data'}):
div.extract()
for tv in soup.findAll(
'div',
attrs={
'class': ['live-tv-ico', 'sendros', 'live-tv-ico-st', 'sendros-st']
}
):
tv.extract()
for script in soup.findAll('script'):
script.extract()
for style in soup.findAll('style'):