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 psych.recipe

Browse Source
This commit is contained in:
unkn0w7n 2024-07-19 11:06:13 +05:30
parent d64c7ad715
commit c7dc4bab2b
1 changed files with 23 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
recipes/psych.recipe
View File

@ -31,6 +31,19 @@ class PsychologyToday(BasicNewsRecipe):
encoding = 'UTF-8' encoding = 'UTF-8'
no_stylesheets = True no_stylesheets = True
publication_type = 'magazine' publication_type = 'magazine'
remove_attributes = ['style', 'height', 'width']
extra_css = '''
.image-article_inline_full, .image-article-inline-half { text-align:center; font-size:small; }
em, blockquote { color:#202020; }
.blog-entry__date--full { font-size:small; }
'''
recipe_specific_options = {
'date': {
'short': 'The date of the Past Edition to download (YYYY/MM format)',
'long': 'For example, 2024/07'
}
}
keep_only_tags = [dict(attrs={'id': 'block-pt-content'})] keep_only_tags = [dict(attrs={'id': 'block-pt-content'})]
remove_tags = [classes('pt-social-media')] remove_tags = [classes('pt-social-media')]
@ -38,9 +51,15 @@ class PsychologyToday(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('https://www.psychologytoday.com/us/magazine/archive') soup = self.index_to_soup('https://www.psychologytoday.com/us/magazine/archive')
a = soup.find(**classes('magazine-thumbnail')).a a = soup.find(**classes('magazine-thumbnail')).a
self.timefmt = ' [%s]' % a['title'] url = a['href']
self.cover_url = absurl(a.img['src']) past_edition = self.recipe_specific_options.get('date')
soup = self.index_to_soup(absurl(a['href'])) if past_edition:
url = '/us/magazine/archive/' + past_edition
soup = self.index_to_soup(absurl(url))
cov = soup.find(**classes('content-header--cover-image'))
if cov:
self.cover_url = cov.img['src']
self.timefmt = ' [%s]' % cov.img['alt'].replace(' magazine cover', '')
articles = [] articles = []
for article in soup.findAll('div', attrs={'class':'article-text'}): for article in soup.findAll('div', attrs={'class':'article-text'}):
title = self.tag_to_string(article.find(attrs={'class':['h2','h3']})).strip() title = self.tag_to_string(article.find(attrs={'class':['h2','h3']})).strip()
@ -53,4 +72,4 @@ class PsychologyToday(BasicNewsRecipe):
else: else:
desc = '' desc = ''
articles.append({'title': title, 'url': url, 'description': desc, 'author': author}) articles.append({'title': title, 'url': url, 'description': desc, 'author': author})
return [('Current Issue', articles)] return [('Articles', articles)]