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 Psychology Today

Browse Source 
Fixes #1475142 [Cannot download "Psychology Today" from "Fetch News".](https://bugs.launchpad.net/calibre/+bug/1475142)
This commit is contained in:
Kovid Goyal 2015-07-16 15:55:05 +05:30
parent 6daf4d61b9
commit 31fb52fcd2
1 changed files with 28 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

74
recipes/psych.recipe
View File

@ -1,63 +1,45 @@
import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class PsychologyToday(BasicNewsRecipe): class PsychologyToday(BasicNewsRecipe):
title = 'Psychology Today' title = 'Psychology Today'
__author__ = 'Rick Shang' __author__ = 'Kovid Goyal'
description = 'This magazine takes information from the latest research in the field of psychology and makes it useful to people in their everyday lives. Its coverage encompasses self-improvement, relationships, the mind-body connection, health, family, the workplace and culture.' description = ('This magazine takes information from the latest research'
' in the field of psychology and makes it useful to people in their everyday'
' lives. Its coverage encompasses self-improvement, relationships, the mind-body'
' connection, health, family, the workplace and culture.')
language = 'en' language = 'en'
category = 'news'
encoding = 'UTF-8' encoding = 'UTF-8'
auto_cleanup = True
#keep_only_tags = [dict(attrs={'class':['print-title', 'print-submitted', 'print-content', 'print-footer', 'print-source_url', 'print-links']})]
no_javascript = True no_javascript = True
no_stylesheets = True no_stylesheets = True
keep_only_tags = [
dict(role='main'),
]
remove_tags = [
dict(attrs={'class':['pt-social-media', 'fb-like-button']}),
]
def parse_index(self): def parse_index(self):
articles = []
soup = self.index_to_soup('http://www.psychologytoday.com/magazine') soup = self.index_to_soup('http://www.psychologytoday.com/magazine')
div = soup.find(id='block-views-magazine-issues-block')
a = div.findAll('h3', attrs={'class':'magazine-published-date'})[1].find('a')
#Go to the main body self.timefmt = ' [%s]' % self.tag_to_string(a).capitalize()
div = soup.find('div',attrs={'id':'content-content'}) soup = self.index_to_soup('http://www.psychologytoday.com' + a['href'])
#Find cover & date self.cover_url = soup.find(role='main').find('img', src=lambda x:x and '/field_magazine_cover/' in x)['src'].partition('?')[0]
cover_item = div.find('div', attrs={'class':'collections-header-image'}) div = soup.find(id='block-system-main')
cover = cover_item.find('img',src=True)
self.cover_url = cover['src']
date = self.tag_to_string(cover['title'])
self.timefmt = u' [%s]'%date
articles = [] articles = []
for post in div.findAll('div', attrs={'class':'collections-node-feature collection-node-even'}): for x in div.findAll(attrs={'class':'field__item'}):
title = self.tag_to_string(post.find('h2')) h2 = x.find('h2')
author_item=post.find('div', attrs={'class':'collection-node-byline'}) title = self.tag_to_string(h2)
author = re.sub(r'.*by\s',"",self.tag_to_string(author_item).strip()) url = 'http://www.psychologytoday.com' + h2.find('a')['href']
title = title + u' (%s)'%author self.log('\n', title, 'at', url)
url= 'http://www.psychologytoday.com'+post.find('a', href=True)['href'] desc = ''
#print_page=article_page.find('li', attrs={'class':'print_html first'}) for y in x.findAll(attrs={'class':['subtext', 'collection__subtitle']}):
#url='http://www.psychologytoday.com'+print_page.find('a',href=True)['href'] desc += self.tag_to_string(y) + ' '
desc = self.tag_to_string(post.find('div', attrs={'class':'collection-node-description'})).strip() if desc:
self.log('Found article:', title) self.log(desc)
self.log('\t', url) articles.append({'title':title, 'url':url, 'description':desc})
self.log('\t', desc)
articles.append({'title':title, 'url':url, 'date':'','description':desc})
for post in div.findAll('div', attrs={'class':'collections-node-feature collection-node-odd'}):
title = self.tag_to_string(post.find('h2'))
author_item=post.find('div', attrs={'class':'collection-node-byline'})
author = re.sub(r'.*by\s',"",self.tag_to_string(author_item).strip())
title = title + u' (%s)'%author
url= 'http://www.psychologytoday.com'+post.find('a', href=True)['href']
#print_page=article_page.find('li', attrs={'class':'print_html first'})
#url='http://www.psychologytoday.com'+print_page.find('a',href=True)['href']
desc = self.tag_to_string(post.find('div', attrs={'class':'collection-node-description'})).strip()
self.log('Found article:', title)
self.log('\t', url)
self.log('\t', desc)
articles.append({'title':title, 'url':url, 'date':'','description':desc})
return [('Current Issue', articles)] return [('Current Issue', articles)]