Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update India Today

Browse Source
This commit is contained in:
Kovid Goyal 2022-05-24 06:52:53 +05:30
parent bf43041b19
commit 99cecfb737
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 33 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
recipes/india_today.recipe
View File

@ -10,8 +10,9 @@ class IndiaToday(BasicNewsRecipe):
remove_attributes = ['style','height','width'] remove_attributes = ['style','height','width']
ignore_duplicate_articles = {'url'} ignore_duplicate_articles = {'url'}
extra_css = '[itemprop^="description"] {font-size: small; font-style: italic;}' extra_css = '[itemprop^="description"] {font-size: small; font-style: italic;}'
description = ('India’s Most Reputed, Credible and Popular news magazine.' description = (
' Read the most preferred magazine of 9.5 million Indians to access highly researched and unbiased content.') 'India’s Most Reputed, Credible and Popular news magazine.'
' Read the most preferred magazine of 9.5 million Indians to access highly researched and unbiased content.')
masthead_url = 'https://akm-img-a-in.tosshub.com/sites/all/themes/itg/logo.png' masthead_url = 'https://akm-img-a-in.tosshub.com/sites/all/themes/itg/logo.png'
def get_cover_url(self): def get_cover_url(self):
@ -27,17 +28,17 @@ class IndiaToday(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('https://www.indiatoday.in/magazine') soup = self.index_to_soup('https://www.indiatoday.in/magazine')
ans = self.it_parse_index(soup)
return ans
def it_parse_index(self, soup): section = None
feeds = [] sections = {}
for section in soup.findAll('div', attrs={'class':['magazin-top-left', 'section-ordering']}):
sec = section.find('span') for tag in soup.findAll('div', attrs={'class':['magazin-top-left', 'section-ordering']}):
secname = self.tag_to_string(sec) sec = tag.find('span')
self.log(secname) section = self.tag_to_string(sec)
articles = [] self.log(section)
for a in section.findAll('a', href=lambda x: x and x.startswith(("/magazine/cover-story/story/", "https://www.indiatoday.in/magazine/"))): sections[section] = []
for a in tag.findAll('a', href=lambda x: x and x.startswith(("/magazine/cover-story/story/", "https://www.indiatoday.in/magazine/"))):
url = a['href'] url = a['href']
if url.startswith('https'): if url.startswith('https'):
url = url url = url
@ -49,11 +50,28 @@ class IndiaToday(BasicNewsRecipe):
url = '' url = ''
self.log('\t', title) self.log('\t', title)
self.log('\t\t', url) self.log('\t\t', url)
articles.append({ sections[section].append({
'title': title, 'title': title,
'url': url}) 'url': url})
if articles:
feeds.append((secname, articles)) feeds = []
# Insert feeds in specified order, if available
feedSort = ['EDITOR\'S NOTE', 'Cover Story', 'The Big Story', 'Upfront', 'NATION', 'INTERVIEW']
for i in feedSort:
if i in sections:
feeds.append((i, sections[i]))
# Done with the sorted feeds
for i in feedSort:
del sections[i]
# Append what is left over...
for i in sections:
feeds.append((i, sections[i]))
return feeds return feeds
def preprocess_raw_html(self, raw_html, url): def preprocess_raw_html(self, raw_html, url):