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

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2023-09-05 20:10:21 +05:30
commit e01740cf8a
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
recipes/natgeomag.recipe
View File

@ -3,6 +3,7 @@
from __future__ import absolute_import, division, print_function, unicode_literals from __future__ import absolute_import, division, print_function, unicode_literals
import json, re import json, re
from datetime import date
from pprint import pformat from pprint import pformat
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
@ -108,6 +109,7 @@ class NatGeo(BasicNewsRecipe):
remove_attributes = ['style'] remove_attributes = ['style']
remove_javascript = False remove_javascript = False
masthead_url = 'https://i.natgeofe.com/n/e76f5368-6797-4794-b7f6-8d757c79ea5c/ng-logo-2fl.png?w=600&h=600' masthead_url = 'https://i.natgeofe.com/n/e76f5368-6797-4794-b7f6-8d757c79ea5c/ng-logo-2fl.png?w=600&h=600'
remove_empty_feeds = True
extra_css = ''' extra_css = '''
.sub { color:#404040; } .sub { color:#404040; }
@ -118,12 +120,10 @@ class NatGeo(BasicNewsRecipe):
''' '''
def parse_index(self): def parse_index(self):
issues = self.index_to_soup('https://www.nationalgeographic.com/magazine') url = 'https://www.nationalgeographic.com/magazine/issue/' + date.today().strftime('%B-%Y'). lower()
mag = issues.find('a', attrs={'href':lambda x: x and x.startswith( self.log('Downloading ', url)
'https://www.nationalgeographic.com/magazine/issue/' self.timefmt = ' [' + date.today().strftime('%B %Y') + ']'
)}) soup = self.index_to_soup(url)
self.timefmt = ' [' + self.tag_to_string(mag).replace(' Issue', '') + ']'
soup = self.index_to_soup(mag['href'])
png = re.findall('https://i\.natgeofe\.com\S+?national-geographic-magazine-\S+?\.jpg', soup.decode('utf-8')) png = re.findall('https://i\.natgeofe\.com\S+?national-geographic-magazine-\S+?\.jpg', soup.decode('utf-8'))
self.cover_url = png[0] + '?w=1000&h=1000' self.cover_url = png[0] + '?w=1000&h=1000'
@ -140,6 +140,8 @@ class NatGeo(BasicNewsRecipe):
for article in soup.findAll('article'): for article in soup.findAll('article'):
a = article.find('a') a = article.find('a')
url = a['href'] url = a['href']
if '/graphics/' in url:
continue
section = self.tag_to_string(article.find(**classes('SectionLabel'))) section = self.tag_to_string(article.find(**classes('SectionLabel')))
title = self.tag_to_string(article.find(**classes('PromoTile__Title--truncated'))) title = self.tag_to_string(article.find(**classes('PromoTile__Title--truncated')))
articles = ans.setdefault(section, []) articles = ans.setdefault(section, [])