Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Psychology Today

Browse Source
This commit is contained in:
Kovid Goyal 2013-04-13 14:55:37 +05:30
parent 09befeb459
commit c95ca53d59
1 changed files with 19 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
recipes/psych.recipe
View File

@ -11,7 +11,8 @@ class PsychologyToday(BasicNewsRecipe):
language = 'en' language = 'en'
category = 'news' category = 'news'
encoding = 'UTF-8' encoding = 'UTF-8'
keep_only_tags = [dict(attrs={'class':['print-title', 'print-submitted', 'print-content', 'print-footer', 'print-source_url', 'print-links']})] 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
@ -31,50 +32,32 @@ class PsychologyToday(BasicNewsRecipe):
self.timefmt = u' [%s]'%date self.timefmt = u' [%s]'%date
articles = [] articles = []
for post in div.findAll('div', attrs={'class':'collections-node-feature-info'}): for post in div.findAll('div', attrs={'class':'collections-node-feature collection-node-even'}):
title = self.tag_to_string(post.find('h2')) title = self.tag_to_string(post.find('h2'))
author_item=post.find('div', attrs={'class':'collection-node-byline'}) author_item=post.find('div', attrs={'class':'collection-node-byline'})
author = re.sub(r'.*by\s',"",self.tag_to_string(author_item).strip()) author = re.sub(r'.*by\s',"",self.tag_to_string(author_item).strip())
title = title + u' (%s)'%author title = title + u' (%s)'%author
article_page= self.index_to_soup('http://www.psychologytoday.com'+post.find('a', href=True)['href']) url= 'http://www.psychologytoday.com'+post.find('a', href=True)['href']
print_page=article_page.find('li', attrs={'class':'print_html first'}) #print_page=article_page.find('li', attrs={'class':'print_html first'})
url='http://www.psychologytoday.com'+print_page.find('a',href=True)['href'] #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})
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() desc = self.tag_to_string(post.find('div', attrs={'class':'collection-node-description'})).strip()
self.log('Found article:', title) self.log('Found article:', title)
self.log('\t', url) self.log('\t', url)
self.log('\t', desc) self.log('\t', desc)
articles.append({'title':title, 'url':url, 'date':'','description':desc}) articles.append({'title':title, 'url':url, 'date':'','description':desc})
for post in div.findAll('div', attrs={'class':'collections-node-thumbnail-info'}):
title = self.tag_to_string(post.find('h2'))
author_item=post.find('div', attrs={'class':'collection-node-byline'})
article_page= self.index_to_soup('http://www.psychologytoday.com'+post.find('a', href=True)['href'])
print_page=article_page.find('li', attrs={'class':'print_html first'})
description = post.find('div', attrs={'class':'collection-node-description'})
author = re.sub(r'.*by\s',"",self.tag_to_string(description.nextSibling).strip())
desc = self.tag_to_string(description).strip()
url='http://www.psychologytoday.com'+print_page.find('a',href=True)['href']
title = title + u' (%s)'%author
self.log('Found article:', title)
self.log('\t', url)
self.log('\t', desc)
articles.append({'title':title, 'url':url, 'date':'','description':desc})
for post in div.findAll('li', attrs={'class':['collection-item-list-odd','collection-item-list-even']}):
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
article_page= self.index_to_soup('http://www.psychologytoday.com'+post.find('a', href=True)['href'])
print_page=article_page.find('li', attrs={'class':'print_html first'})
if print_page is not None:
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)]