Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

The Hindu update

Browse Source
This commit is contained in:
unkn0w7n 2023-08-13 11:43:42 +05:30
parent 56cad44079
commit d4900b902b
2 changed files with 25 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
recipes/business_standard.recipe
View File

@ -95,11 +95,12 @@ class BusinessStandard(BasicNewsRecipe):
if 'multiple_authors_name' in data: if 'multiple_authors_name' in data:
auth = '<div><p class="auth">' + data['multiple_authors_name'] + ' | ' + data['placeName'] + ' | ' + date + '</p></div>' auth = '<div><p class="auth">' + data['multiple_authors_name'] + ' | ' + data['placeName'] + ' | ' + date + '</p></div>'
if data['featuredImageObj'] and 'url' in data['featuredImageObj']: if 'featuredImageObj' in data:
if img_url is not None: if 'url' in data['featuredImageObj']:
lede = '<p class="cap"><img src="{}">'.format(img_url) if img_url is not None:
else: lede = '<p class="cap"><img src="{}">'.format(img_url)
lede = '<p class="cap"><img src="{}">'.format(data['featuredImageObj']['url']) else:
lede = '<p class="cap"><img src="{}">'.format(data['featuredImageObj']['url'])
if 'alt_text' in data['featuredImageObj']: if 'alt_text' in data['featuredImageObj']:
caption = '<span>' + data['featuredImageObj']['alt_text'] + '</span></p>' caption = '<span>' + data['featuredImageObj']['alt_text'] + '</span></p>'

23
recipes/hindu.recipe
View File

@ -4,7 +4,6 @@ from collections import defaultdict
from datetime import date from datetime import date
from calibre.web.feeds.news import BasicNewsRecipe, classes from calibre.web.feeds.news import BasicNewsRecipe, classes
def absurl(url): def absurl(url):
if url.startswith('/'): if url.startswith('/'):
url = 'https://www.thehindu.com' + url url = 'https://www.thehindu.com' + url
@ -16,11 +15,16 @@ local_edition = None
# For past editions, set date to, for example, '2023-01-28' # For past editions, set date to, for example, '2023-01-28'
past_edition = None past_edition = None
is_monday = date.today().weekday() == 0
is_friday = date.today().weekday() == 4
is_saturday = date.today().weekday() == 5
is_sunday = date.today().weekday() == 6 is_sunday = date.today().weekday() == 6
if past_edition: if past_edition:
year, month, day = (int(x) for x in past_edition.split('-')) year, month, day = (int(x) for x in past_edition.split('-'))
dt = date(year, month, day) dt = date(year, month, day)
is_monday = dt.weekday() == 0
is_saturday = dt.weekday() == 5
is_sunday = dt.weekday() == 6 is_sunday = dt.weekday() == 6
class TheHindu(BasicNewsRecipe): class TheHindu(BasicNewsRecipe):
@ -75,13 +79,23 @@ class TheHindu(BasicNewsRecipe):
today = past_edition today = past_edition
self.log('Downloading past edition of', local_edition + ' from ' + today) self.log('Downloading past edition of', local_edition + ' from ' + today)
url = absurl('/todays-paper/' + today + '/' + local_edition + '/') url = absurl('/todays-paper/' + today + '/' + local_edition + '/')
if is_monday:
mag_url = url + '?supplement=' + local_edition + '-epbs'
if is_saturday:
mag_url = url + '?supplement=' + local_edition + '-mp'
if is_sunday: if is_sunday:
mag_url = url + '?supplement=' + local_edition + '-sm' mag_url = url + '?supplement=' + local_edition + '-sm'
else: else:
url = 'https://www.thehindu.com/todays-paper/' url = 'https://www.thehindu.com/todays-paper/'
if is_monday:
mag_url = url + '?supplement=th_chennai-epbs'
if is_friday:
mag_url = url + '?supplement=th_chennai-fr'
if is_saturday:
mag_url = url + '?supplement=th_chennai-mp'
if is_sunday: if is_sunday:
mag_url = url + '?supplement=th_chennai-sm' mag_url = url + '?supplement=th_chennai-sm'
raw = self.index_to_soup(url, raw=True) raw = self.index_to_soup(url, raw=True)
soup = self.index_to_soup(raw) soup = self.index_to_soup(raw)
ans = self.hindu_parse_index(soup) ans = self.hindu_parse_index(soup)
@ -93,17 +107,18 @@ class TheHindu(BasicNewsRecipe):
'The Hindu Newspaper is not published Today.' 'The Hindu Newspaper is not published Today.'
) )
if mag_url: if mag_url:
self.log('\nFetching Sunday Magazine') self.log('\nFetching Magazine')
soup = self.index_to_soup(mag_url) soup = self.index_to_soup(mag_url)
ans2 = self.hindu_parse_index(soup) ans2 = self.hindu_parse_index(soup)
if ans2: if ans2:
return ans + ans2 return ans + ans2
self.log('\tMagazine not Found')
return ans return ans
return ans return ans
def hindu_parse_index(self, soup): def hindu_parse_index(self, soup):
for script in soup.findAll('script'): for script in soup.findAll('script'):
if not self.tag_to_string(script).strip().startswith('let grouped_articles = {}'): if not self.tag_to_string(script).__contains__('grouped_articles = {"'):
continue continue
if script is not None: if script is not None:
art = re.search(r'grouped_articles = ({\".*)', self.tag_to_string(script)) art = re.search(r'grouped_articles = ({\".*)', self.tag_to_string(script))