calibre/recipes/hindustan_times_print.recipe
unkn0w7n b49eed0582 ...
2024-08-04 09:21:30 +05:30

131 lines
5.2 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
import json
from collections import defaultdict
from datetime import date
from calibre.web.feeds.news import BasicNewsRecipe
index = 'https://epaper.hindustantimes.com'
class ht(BasicNewsRecipe):
title = 'Hindustan Times Print Edition'
language = 'en_IN'
__author__ = 'unkn0wn'
masthead_url = 'https://www.htmedia.in/wp-content/uploads/2020/08/HT-dot-com-logo-product.png'
description = 'Articles from the Hindustan Times epaper, digital edition'
encoding = 'utf-8'
delay = 1
ignore_duplicate_articles = {'title'}
extra_css = '''
.cap { text-align:center; font-size:small; }
img { display:block; margin:0 auto; }
'''
recipe_specific_options = {
'location': {
'short': 'The name of the local edition',
'long': ('If The Hindustan Times is available in your local town/city, '
'set 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(
'\n***\nif this recipe fails, report it on: '
'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
day, month, year = (int(x) for x in today.split('/'))
dt = date(year, month, day)
self.timefmt = ' [%s]' % dt.strftime('%b %d, %Y')
today = today.replace('/', '%2F')
get_edition = index + '/Home/GetEditionSupplementHierarchy?EditionDate=' + today
edi_data = json.loads(self.index_to_soup(get_edition, raw=True))
cities = []
for edi in edi_data:
cities.append(edi['EditionName'])
self.log('## For your local_edition, modify this recipe to match your city from the names below\n(', ', '.join(cities), ')\n')
for edi in edi_data:
if edi['EditionName'] == local_edition:
edi_name = edi['EditionName']
edi_id = str(edi['EditionId'])
self.log('Downloading', edi_name, 'Edition', self.timefmt)
url = index + '/Home/GetAllpages?editionid=' + edi_id + '&editiondate=' + today
main_data = json.loads(self.index_to_soup(url, raw=True))
feeds_dict = defaultdict(list)
for page in main_data:
page_no = page['PageNumber']
sec_name = page['NewsProPageTitle']
if sec_name == 'Full Page Ad':
continue
if sec_name.startswith('Front'):
self.cover_url = page['HighResolution']
art = index + '/Home/getingRectangleObject?pageid=' + str(page['PageId'])
self.log(sec_name, ' ', page_no)
art_data = json.loads(self.index_to_soup(art, raw=True))
for snaps in art_data:
section = sec_name
url = str(snaps['OrgId'])
title = ' '.join(snaps['StoryTitle'].split()[:15])
if not title:
continue
desc = page_no
self.log('\t', title, ' ', desc)
feeds_dict[section].append({"title": title, "description": desc, "url": url})
return [(section, articles) for section, articles in feeds_dict.items()]
def preprocess_raw_html(self, raw, *a):
data = json.loads(raw)
body = ''
for x in data['StoryContent']:
if x['Headlines']:
if len(x['Headlines']) > 0:
body += '<h1>' + x['Headlines'][0].replace('\n', ' ') + '</h1>'
for y in x['Headlines'][1:]:
body += '<h4>' + y.replace('\n', ' ') + '</h4>'
if data['LinkPicture']:
for pics in data['LinkPicture']:
if pics['fullpathlinkpic']:
body += '<div><img src="{}"></div>'.format(pics['fullpathlinkpic'])
if pics['caption']:
body += '<div class="cap">' + pics['caption'] + '</div><p>'
for x in data['StoryContent']:
if x['Body']:
body += x['Body']
# if data['filepathstorypic']: # this gives you a snap image of the article from page
# body += '<div><img src="{}"></div>'.format(data['filepathstorypic'].replace('\\', '/'))
return '<html><body><div>' + body + '</div></body></html>'
def print_version(self, url):
return index + '/User/ShowArticleView?OrgId=' + url
def populate_article_metadata(self, article, soup, first):
article.url = '***'