From da9d8e996c6013815c40e3b0713d3afee6008588 Mon Sep 17 00:00:00 2001
From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com>
Date: Thu, 28 Dec 2023 13:57:11 +0530
Subject: [PATCH] Hindustan Times Print Edition recipe
---
recipes/hindustan_times_print.recipe | 113 ++++++++++++++++++++++++
recipes/icons/hindustan_times_print.png | Bin 0 -> 1592 bytes
2 files changed, 113 insertions(+)
create mode 100644 recipes/hindustan_times_print.recipe
create mode 100644 recipes/icons/hindustan_times_print.png
diff --git a/recipes/hindustan_times_print.recipe b/recipes/hindustan_times_print.recipe
new file mode 100644
index 0000000000..295aaf8660
--- /dev/null
+++ b/recipes/hindustan_times_print.recipe
@@ -0,0 +1,113 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import json
+from datetime import date
+from collections import defaultdict
+
+# 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'
+
+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'
+ timefmt = ' [' + dt.strftime('%b %d, %Y') + ']'
+ description = 'Articles from the Hindustan Times epaper, digital edition'
+ encoding = 'utf-8'
+ delay = 1
+ 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 = '''
+ .cap { text-align:center; font-size:small; }
+ img { display:block; margin:0 auto; }
+ '''
+
+ 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'
+ )
+
+ 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')
+
+ 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 += '' + x['Headlines'][0].replace('\n', ' ') + '
'
+ for y in x['Headlines'][1:]:
+ body += '' + y.replace('\n', ' ') + '
'
+ if data['LinkPicture']:
+ for pics in data['LinkPicture']:
+ if pics['fullpathlinkpic']:
+ body += ''.format(pics['fullpathlinkpic'])
+ if pics['caption']:
+ body += '' + pics['caption'] + '
'
+ 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 += '
'.format(data['filepathstorypic'].replace('\\', '/'))
+ return '' + body + '
'
+
+ def print_version(self, url):
+ return index + '/User/ShowArticleView?OrgId=' + url
+
+ def populate_article_metadata(self, article, soup, first):
+ article.url = '***'
diff --git a/recipes/icons/hindustan_times_print.png b/recipes/icons/hindustan_times_print.png
new file mode 100644
index 0000000000000000000000000000000000000000..01ab8981a575302fe28a2a6a8fd3d506052c5378
GIT binary patch
literal 1592
zcmV-82FLk{P)hK~#9!rB(%O<46~NB1@4h<^PYFnVFfHnVFfHZ<(1H%T2NklsOCz
zr;u%$GV^VkdhfHx+uSmZM%H*{-uvD>racdpig>lM#^Q-r=-0WlLQmON%CgXMz4ZI|
z%f$1kJ0Lm0k-B>I&Gf}zv?zx*S5UT%aviCOUu-VSrqBPND{o2>9w_%quc3*{Nav>f
zFzJ1yb&0;9_YknkO1bJNqc#RikG=hqx{IerQY{zpfQNZ815$fD9XJv&@6j?n)#-D-|YoH&||7Kjt|YXv;Faf!KR5q>=R4vb7i4>i~J83`c{SF
zw^r2AgykGD=J;NH6Xm$p*S2ooF%o0qOBLa)t?d`+J&@}Rt!u8Yad0&Gg{=-q*BFIh
z&(QYWMp6{mr5@H=A2><{R0C;{?Yab{<
z4H;>ZSsUxbZ`*JJFqo0vAqd1UdbW+eToI;pGhY~?uO^T*jyMVdsW$ka5b&an)%o#m
zT!o@G*0liu$_@4mj)~%6B6+n*fYKvv7ZGECB&JDzG&i5@0#<>hDuQ<2tb-&LiT4jP4!ZC0#ONdpp
z_A-FSOM`~SuC)5LRpI9Lk%SB|c8#o}56m_Aog%~_khM)R4*;&u_bv#=DO~|j=JGrO
z4z{>VTW&)KGZX`Opg3S_2XShQB**XqcnJIiCb^}+$E8`!`v!oPIOH`sj=pz9zckmv
zdLUp%*2Ox1bVlE+2*aw_8BUI!vBiC7ksoWg?4<^Q()R#xgmz~DT4_*zGHkTI3gI(u
zyx6c+`Xz(;NHOKicMZs8=l~4K!)d_
zeVAA0p(}168qcT`mht()=gR_5mxZ1x3&N66H@uLge$c>ZNZ{C^90$ppSi|MvOAi(Y
zZp!!K0=o}v)K2sajCrcy-~jlnbYOzuzagVUyEe7M){F{YwgW0Tty$^fE0uzis%@`+
zf@%l#p){)CQM*;$J?`M9JlT$1meDi3^ucbWpF#a_*hL?<{dNjtxRx(^`~EMoK)BNty{63o000062
literal 0
HcmV?d00001