Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Eenadu

Browse Source
This commit is contained in:
Kovid Goyal 2022-06-08 07:25:42 +05:30
parent 946ae082e1
commit 336d6f55f9
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 21 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
recipes/eenadu.recipe
View File

@ -1,5 +1,4 @@
from calibre.web.feeds.news import BasicNewsRecipe, classes
import string
from datetime import date
@ -13,9 +12,9 @@ class eenadu(BasicNewsRecipe):
remove_javascript = True
no_stylesheets = True
remove_attributes = ['height', 'width', 'style']
ignore_duplicate_articles = {'url', 'title'}
ignore_duplicate_articles = {"title", "url"}
masthead_url = 'https://dxxd96tbpm203.cloudfront.net//img/logo.png'
cover_url = 'https://www.ads2publish.com/assets/images/epaper/eenadu-newspaper-epaper.jpg'
cover_url = 'https://d66zsp32hue2v.cloudfront.net/Eenadu/2022/06/07/TEL/5_01/9de49f18_01_mr.jpg'
encoding = 'utf-8'
keep_only_tags = [
@ -24,54 +23,40 @@ class eenadu(BasicNewsRecipe):
dict(name='span', attrs={'id': 'PDSAIApbreak'}),
]
remove_tags = [
classes('sshare-c'),
]
remove_tags = [classes('sshare-c')]
def articles_from_soup(self, soup):
ans = []
for link in soup.findAll(attrs={'class': 'telugu_uni_body'}):
for link in soup.findAll(attrs={'class': ['telugu_uni_body', 'thumb-content-more', 'owl-carousel']}):
for a in link.findAll('a', attrs={'href': True}):
ul = a['href']
if ul.startswith('https') is False:
url = 'https://www.eenadu.net/' + ul
url = a['href']
if url.startswith('https') is False:
url = 'https://www.eenadu.net/' + url
else:
url = ul
if url.__contains__("videos"):
url = 0
url = url
for h3 in a.findAll('h3'):
title = self.tag_to_string(h3)
if not url or not title:
continue
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
self.log('\t', title)
self.log('\t\t', url)
ans.append({
'title': title,
'url': url,
'description': '',
'date': ''
})
'url': url})
return ans
def parse_index(self):
soup = self.index_to_soup('https://www.eenadu.net/')
nav_div = soup.find(id='navbar')
section_list = [
# add links for your district edition here
('సంపాదకీయం', 'https://www.eenadu.net/telangana/editorial'),
(
'హైదరాబాద్',
'https://www.eenadu.net/telangana/districts/hyderabad'
),
# ('నిజామాబాద్', 'https://www.eenadu.net/telangana/districts/nizamabad'),
# ('నల్గొండ', 'https://www.eenadu.net/telangana/districts/nalgonda'),
]
# Finding all the section titles that are acceptable
for x in nav_div.findAll(['a']):
if self.is_accepted_entry(x):
section_list.append(
(string.capwords(self.tag_to_string(x)), x['href'])
(self.tag_to_string(x), x['href'])
)
feeds = []
@ -79,12 +64,11 @@ class eenadu(BasicNewsRecipe):
for section in section_list:
section_title = section[0]
section_url = section[1]
self.log('Found section:', section_title, section_url)
self.log(section_title, section_url)
soup = self.index_to_soup(section_url)
articles = self.articles_from_soup(soup)
if articles:
feeds.append((section_title, articles))
return feeds
def is_accepted_entry(self, entry):
@ -94,12 +78,15 @@ class eenadu(BasicNewsRecipe):
if is_sunday:
omit_list = [
'net/',
'javascript:void(0)',
'#',
'sports',
'movies',
'women',
'technology',
'business',
'stories.eenadu.net',
'calendar',
'devotional',
'youth',
'recipes',
@ -107,7 +94,7 @@ class eenadu(BasicNewsRecipe):
'temples',
'kathalu',
'viral-videos',
'nri',
'Nri',
'videos',
'explained',
'agriculture',
@ -121,12 +108,15 @@ class eenadu(BasicNewsRecipe):
else:
omit_list = [
'net/',
'javascript:void(0)',
'#',
'sports',
'movies',
'women',
'technology',
'business',
'stories.eenadu.net',
'calendar',
'devotional',
'youth',
'recipes',
@ -134,7 +124,7 @@ class eenadu(BasicNewsRecipe):
'temples',
'kathalu',
'viral-videos',
'nri',
'Nri',
'videos',
'explained',
'agriculture',