Update hindustan_times_print.recipe

This commit is contained in:
unkn0w7n 2024-07-22 15:38:14 +05:30
parent b71e3ef705
commit 7e394d9c15

View File

@ -1,20 +1,11 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
import json import json
from collections import defaultdict from collections import defaultdict
from datetime import date from datetime import date
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
# figure out your local_edition from the fetch news log of this recipe
local_edition = 'Delhi'
today = date.today().strftime('%d/%m/%Y')
# for older edition, change today
# today = '22/12/2023'
day, month, year = (int(x) for x in today.split('/'))
dt = date(year, month, day)
today = today.replace('/', '%2F')
index = 'https://epaper.hindustantimes.com' index = 'https://epaper.hindustantimes.com'
@ -23,28 +14,49 @@ class ht(BasicNewsRecipe):
language = 'en_IN' language = 'en_IN'
__author__ = 'unkn0wn' __author__ = 'unkn0wn'
masthead_url = 'https://www.htmedia.in/wp-content/uploads/2020/08/HT-dot-com-logo-product.png' masthead_url = 'https://www.htmedia.in/wp-content/uploads/2020/08/HT-dot-com-logo-product.png'
timefmt = ' [' + dt.strftime('%b %d, %Y') + ']'
description = 'Articles from the Hindustan Times epaper, digital edition' description = 'Articles from the Hindustan Times epaper, digital edition'
encoding = 'utf-8' encoding = 'utf-8'
delay = 1 delay = 1
ignore_duplicate_articles = {'title'} ignore_duplicate_articles = {'title'}
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
if self.output_profile.short_name.startswith('kindle'):
self.title = 'HT Print Edition ' + dt.strftime('%b %d, %Y')
extra_css = ''' extra_css = '''
.cap { text-align:center; font-size:small; } .cap { text-align:center; font-size:small; }
img { display:block; margin:0 auto; } img { display:block; margin:0 auto; }
''' '''
def parse_index(self): recipe_specific_options = {
'location': {
'short': 'The name of the local edition',
'long': 'If The Hindustan Times is available in your local town/city,\nset this to your location, for example, Delhi\nAvailable Editions: Delhi, Mumbai, Chandigarh, Lucknow, Patna, Bengaluru, Pune, Gurgaon, Ludhiana, Rajasthan, Amritsar,\nEast UP, Haryana, Jammu, Navi Mumbai, Noida, Punjab, Ranchi, Thane, Uttarakhand, West UP',
'default': 'Delhi'
},
'date': {
'short': 'The date of the edition to download (DD/MM/YYYY format)',
'long': 'For example, 22/12/2023'
}
}
def parse_index(self):
self.log( self.log(
'\n***\nif this recipe fails, report it on: ' '\n***\nif this recipe fails, report it on: '
'https://www.mobileread.com/forums/forumdisplay.php?f=228\n***\n' 'https://www.mobileread.com/forums/forumdisplay.php?f=228\n***\n'
) )
local_edition = 'Delhi'
d = self.recipe_specific_options.get('location')
if d and isinstance(d, str):
local_edition = d
today = date.today().strftime('%d/%m/%Y')
p = self.recipe_specific_options.get('date')
if p and isinstance(p, str):
today = p
self.timefmt = ' [%s]' % today
day, month, year = (int(x) for x in today.split('/'))
dt = date(year, month, day)
today = today.replace('/', '%2F')
get_edition = index + '/Home/GetEditionSupplementHierarchy?EditionDate=' + today get_edition = index + '/Home/GetEditionSupplementHierarchy?EditionDate=' + today
edi_data = json.loads(self.index_to_soup(get_edition, raw=True)) edi_data = json.loads(self.index_to_soup(get_edition, raw=True))
@ -56,7 +68,7 @@ class ht(BasicNewsRecipe):
if edi['EditionName'] == local_edition: if edi['EditionName'] == local_edition:
edi_name = edi['EditionName'] edi_name = edi['EditionName']
edi_id = str(edi['EditionId']) edi_id = str(edi['EditionId'])
self.log('Downloading', edi_name, 'Edition') self.log('Downloading', edi_name, 'Edition', self.timefmt)
url = index + '/Home/GetAllpages?editionid=' + edi_id + '&editiondate=' + today url = index + '/Home/GetAllpages?editionid=' + edi_id + '&editiondate=' + today
main_data = json.loads(self.index_to_soup(url, raw=True)) main_data = json.loads(self.index_to_soup(url, raw=True))