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 Globe and Mail

Browse Source
This commit is contained in:
Kovid Goyal 2019-08-14 06:50:51 +05:30
commit 4353f2ab9d
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
recipes/globe_and_mail.recipe
View File

@ -18,7 +18,7 @@ def classes(classes):
class GlobeMail(BasicNewsRecipe): class GlobeMail(BasicNewsRecipe):
title = u'Globe & Mail' title = u'The Globe and Mail'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
encoding = 'utf-8' encoding = 'utf-8'
publisher = 'Globe & Mail' publisher = 'Globe & Mail'
@ -32,12 +32,12 @@ class GlobeMail(BasicNewsRecipe):
dict(name='main', attrs={'class': lambda x: x and 'article-primary-content-chain' in x.split()}), dict(name='main', attrs={'class': lambda x: x and 'article-primary-content-chain' in x.split()}),
] ]
remove_tags = [ remove_tags = [
classes('c-ad pb-f-commercial-dfp-ads pb-f-article-actions'), classes('c-ad pb-f-commercial-dfp-ads pb-f-article-actions pb-f-article-meta'),
] ]
def parse_index(self): def parse_index(self):
ans = [] ans = []
for section in 'canada opinion politics sports life arts world'.split(): for section in 'canada opinion politics sports life arts world real-estate'.split():
if self.test and len(ans) >= self.test[0]: if self.test and len(ans) >= self.test[0]:
break break
soup = self.index_to_soup('https://www.theglobeandmail.com/{}/'.format(section)) soup = self.index_to_soup('https://www.theglobeandmail.com/{}/'.format(section))
@ -49,7 +49,8 @@ class GlobeMail(BasicNewsRecipe):
def parse_gm_section(self, soup): def parse_gm_section(self, soup):
for a in soup.findAll('a', href=True, attrs={'data-lt-lid': lambda x: x and x.startswith('Headline.')}): for a in soup.findAll('a', href=True, attrs={'data-lt-lid': lambda x: x and x.startswith('Headline.')}):
title = self.tag_to_string(a) headline = a.find('div', 'c-card__hed-text')
title = self.tag_to_string(headline)
url = absolutize(a['href']) url = absolutize(a['href'])
self.log(' ', title, 'at', url) self.log(' ', title, 'at', url)
yield {'title': title, 'url': url} yield {'title': title, 'url': url}