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 Wired Magazine Monthly Edition

Browse Source
This commit is contained in:
Kovid Goyal 2022-04-08 07:54:39 +05:30
parent 71f6d8b162
commit b27ac9936f
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
recipes/wired.recipe
View File

@ -16,7 +16,7 @@ def classes(classes):
class WiredDailyNews(BasicNewsRecipe): class WiredDailyNews(BasicNewsRecipe):
title = 'Wired Magazine, Monthly Edition' title = 'Wired Magazine, Monthly Edition'
__author__ = 'Darko Miletic, update by Zach Lapidus, Michael Marotta' __author__ = 'Darko Miletic, update by Howard Cornett, Zach Lapidus, Michael Marotta'
description = ('Wired is a full-color monthly American magazine, ' description = ('Wired is a full-color monthly American magazine, '
'published in both print and online editions, that ' 'published in both print and online editions, that '
'reports on how emerging technologies affect culture, ' 'reports on how emerging technologies affect culture, '
@ -57,10 +57,10 @@ class WiredDailyNews(BasicNewsRecipe):
self.log('Parsing index page', currenturl) self.log('Parsing index page', currenturl)
soup = self.index_to_soup(currenturl) soup = self.index_to_soup(currenturl)
baseurl = 'https://www.wired.com' baseurl = 'https://www.wired.com'
for a in soup.find("ul", {"class" : 'archive-list-component__items'}).findAll('a', href=True): for a in soup.find("div", {"class" : 'multi-packages'}).findAll('a', href=True):
url = a['href'] url = a['href']
if url.startswith('/story') and url.endswith('/'): if url.startswith('/story') and url.endswith('/'):
title = self.tag_to_string(a.parent.find('h2')) title = self.tag_to_string(a.parent.find('h3'))
dateloc = a.parent.find('time') dateloc = a.parent.find('time')
date = self.tag_to_string(dateloc) date = self.tag_to_string(dateloc)
if title.lower() != 'read more' and title and url not in seen: if title.lower() != 'read more' and title and url not in seen:
@ -73,7 +73,7 @@ class WiredDailyNews(BasicNewsRecipe):
} }
def parse_index(self): def parse_index(self):
baseurl = 'https://www.wired.com/magazine/page/{}/' baseurl = 'https://www.wired.com/magazine/?page={}/'
pagenum = 1 pagenum = 1
articles = [] articles = []
seen = set() seen = set()