| 1 |
from datetime import date |
| 2 |
|
| 3 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 4 |
|
| 5 |
# default edition is Delhi i.e., 'cap' |
| 6 |
# Hyderabad - 'toih'; Delhi - 'cap'; Mumbai - 'toim'; Banglore - 'toibgc'; |
| 7 |
# Chennai - 'toich'; Chandigarh - 'toicgct'; Jaipur - 'toijc'; Kolkata - 'toikc'; |
| 8 |
# There are others too, try to figure it out, visit toi epaper link. |
| 9 |
|
| 10 |
le = 'cap' # local edition; |
| 11 |
|
| 12 |
date0 = date.today().strftime('%Y/%m/%d') |
| 13 |
|
| 14 |
# for older edition change date0 below. |
| 15 |
# date0 = '2023/09/15' |
| 16 |
|
| 17 |
year, month, day = (int(x) for x in date0.split('/')) |
| 18 |
dt = date(year, month, day) |
| 19 |
date_ = dt.strftime('%d_%m_%Y') |
| 20 |
|
| 21 |
img_index = 'https://cmsimages.timesgroup.com/image-resizer?epaper_s3_path=PublicationData/TOI/' + le + '/' + date0 |
| 22 |
|
| 23 |
|
| 24 |
class TOIPring(BasicNewsRecipe): |
| 25 |
title = 'TOI Print Edition' |
| 26 |
language = 'en_IN' |
| 27 |
__author__ = 'Kovid Goyal' |
| 28 |
masthead_url = 'https://static.toiimg.com/photo/98333929.cms' |
| 29 |
timefmt = ' [' + dt.strftime('%b %d, %Y') + ']' |
| 30 |
description = 'Articles from the Times of India epaper, digital edition' |
| 31 |
encoding = 'utf-8' |
| 32 |
remove_empty_feeds = True |
| 33 |
|
| 34 |
keep_only_tags = [classes('printeditioncontentwrapper')] |
| 35 |
remove_tags = [ |
| 36 |
classes('header-container popupWrapper footer_wrapper icon_share_wrap'), |
| 37 |
{'id': 'blocker'}, |
| 38 |
{'name': 'style'}, |
| 39 |
] |
| 40 |
|
| 41 |
extra_css = ''' |
| 42 |
.sub { color:#202020; } |
| 43 |
.auth { font-size:small; font-weight:bold; color:#202020; } |
| 44 |
.cap { text-align:center; font-size:small; } |
| 45 |
img { display:block; margin:0 auto; } |
| 46 |
.info { font-size:small; color:#404040; } |
| 47 |
.lead { color:#404040; } |
| 48 |
''' |
| 49 |
|
| 50 |
def parse_index(self): |
| 51 |
url = 'https://epaper.indiatimes.com/english-news-paper-today-toi-print-edition/' |
| 52 |
# url = 'file:///t/raw.html' |
| 53 |
soup = self.index_to_soup(url) |
| 54 |
ans = [] |
| 55 |
for sec in soup.find_all('section', attrs={'data-content': True}): |
| 56 |
h1 = sec.find('h1') |
| 57 |
section = self.tag_to_string(h1) |
| 58 |
self.log(section) |
| 59 |
articles = [] |
| 60 |
listing = sec.find_next_sibling(type='listing') |
| 61 |
for a in listing.find_all('a', href=True): |
| 62 |
url = a['href'] |
| 63 |
title = self.tag_to_string(a.find('h2')) |
| 64 |
self.log(' ', title) |
| 65 |
articles.append({'title': title, 'url': url}) |
| 66 |
if articles: |
| 67 |
ans.append((section, articles)) |
| 68 |
return ans |