| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
|
| 4 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 5 |
|
| 6 |
|
| 7 |
def absurl(url): |
| 8 |
if url.startswith('//'): |
| 9 |
return 'https:' + url |
| 10 |
if url.startswith('/'): |
| 11 |
return 'https://www.psychologytoday.com' + url |
| 12 |
return url |
| 13 |
|
| 14 |
|
| 15 |
def classes(classes): |
| 16 |
q = frozenset(classes.split(' ')) |
| 17 |
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) |
| 18 |
|
| 19 |
|
| 20 |
class PsychologyToday(BasicNewsRecipe): |
| 21 |
title = 'Psychology Today' |
| 22 |
__author__ = 'Kovid Goyal' |
| 23 |
|
| 24 |
description = ( |
| 25 |
'This magazine takes information from the latest research' |
| 26 |
' in the field of psychology and makes it useful to people in their everyday' |
| 27 |
' lives. Its coverage encompasses self-improvement, relationships, the mind-body' |
| 28 |
' connection, health, family, the workplace and culture.' |
| 29 |
) |
| 30 |
language = 'en' |
| 31 |
encoding = 'UTF-8' |
| 32 |
no_stylesheets = True |
| 33 |
publication_type = 'magazine' |
| 34 |
remove_attributes = ['style', 'height', 'width'] |
| 35 |
extra_css = ''' |
| 36 |
.image-article_inline_full, .image-article-inline-half { text-align:center; font-size:small; } |
| 37 |
em, blockquote { color:#202020; } |
| 38 |
.blog-entry__date--full { font-size:small; } |
| 39 |
''' |
| 40 |
|
| 41 |
recipe_specific_options = {'date': {'short': 'The date of the Past Edition to download (YYYY/MM format)', 'long': 'For example, 2024/07'}} |
| 42 |
|
| 43 |
keep_only_tags = [dict(attrs={'id': 'block-pt-content'})] |
| 44 |
remove_tags = [classes('pt-social-media')] |
| 45 |
|
| 46 |
def parse_index(self): |
| 47 |
soup = self.index_to_soup('https://www.psychologytoday.com/us/magazine/archive') |
| 48 |
a = soup.find(**classes('magazine-thumbnail')).a |
| 49 |
url = a['href'] |
| 50 |
past_edition = self.recipe_specific_options.get('date') |
| 51 |
if past_edition and isinstance(past_edition, str): |
| 52 |
url = '/us/magazine/archive/' + past_edition |
| 53 |
soup = self.index_to_soup(absurl(url)) |
| 54 |
cov = soup.find(**classes('content-header--cover-image')) |
| 55 |
if cov: |
| 56 |
self.cover_url = cov.img['src'] |
| 57 |
self.timefmt = ' [%s]' % cov.img['alt'].replace(' magazine cover', '') |
| 58 |
articles = [] |
| 59 |
for article in soup.findAll('div', attrs={'class': 'article-text'}): |
| 60 |
title = self.tag_to_string(article.find(attrs={'class': ['h2', 'h3']})).strip() |
| 61 |
url = absurl(article.find(attrs={'class': ['h2', 'h3']}).a['href']) |
| 62 |
self.log('\n', title, 'at', url) |
| 63 |
desc = self.tag_to_string(article.find('p', **classes('description'))).strip() |
| 64 |
author = self.tag_to_string(article.find('p', **classes('byline')).a).strip() |
| 65 |
if desc: |
| 66 |
self.log(desc) |
| 67 |
else: |
| 68 |
desc = '' |
| 69 |
articles.append({'title': title, 'url': url, 'description': desc, 'author': author}) |
| 70 |
return [('Articles', articles)] |