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

Updated recipes: Psychology Today, WSJ

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-19 17:04:41 -06:00
parent caa451213e
commit dc97a0c2e1
2 changed files with 99 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
resources/recipes/psych.recipe
View File

@ -1,39 +1,44 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class PsychologyToday(BasicNewsRecipe): from calibre.ptempfile import PersistentTemporaryFile
from calibre.webfeeds.news import BasicNewsRecipe
class AdvancedUserRecipe1275708473(BasicNewsRecipe):
title = u'Psychology Today' title = u'Psychology Today'
_author__ = 'rty'
publisher = u'www.psychologytoday.com'
category = u'Psychology'
max_articles_per_feed = 100
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'en' language = 'en'
__author__ = 'Krittika Goyal' temp_files = []
oldest_article = 1 #days articles_are_obfuscated = True
max_articles_per_feed = 25
#encoding = 'latin1'
remove_stylesheets = True
#remove_tags_before = dict(name='h1', attrs={'class':'heading'})
#remove_tags_after = dict(name='td', attrs={'class':'newptool1'})
remove_tags = [ remove_tags = [
dict(name='iframe'), dict(name='div', attrs={'class':['print-source_url','field-items','print-footer']}),
dict(name='div', attrs={'class':['pt-box-title', 'pt-box-content', 'blog-entry-footer', 'item-list', 'article-sub-meta']}), dict(name='span', attrs={'class':'print-footnote'}),
dict(name='div', attrs={'id':['block-td_search_160', 'block-cam_search_160']}),
#dict(name='ul', attrs={'class':'article-tools'}),
#dict(name='ul', attrs={'class':'articleTools'}),
] ]
remove_tags_before = dict(name='h1', attrs={'class':'print-title'})
remove_tags_after = dict(name='div', attrs={'class':['field-items','print-footer']})
feeds = [ feeds = [(u'Contents', u'http://www.psychologytoday.com/articles/index.rss')]
('PSY TODAY',
'http://www.psychologytoday.com/articles/index.rss'),
]
def preprocess_html(self, soup): def get_article_url(self, article):
story = soup.find(name='div', attrs={'id':'contentColumn'}) return article.get('link', None)
#td = heading.findParent(name='td')
#td.extract() def get_obfuscated_article(self, url):
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>') br = self.get_browser()
body = soup.find(name='body') br.open(url)
body.insert(0, story) response = br.follow_link(url_regex = r'/print/[0-9]+', nr = 0)
for x in soup.findAll(name='p', text=lambda x:x and '--&gt;' in x): html = response.read()
p = x.findParent('p') self.temp_files.append(PersistentTemporaryFile('_fa.html'))
if p is not None: self.temp_files[-1].write(html)
p.extract() self.temp_files[-1].close()
return soup return self.temp_files[-1].name
def get_cover_url(self):
index = 'http://www.psychologytoday.com/magazine/'
soup = self.index_to_soup(index)
for image in soup.findAll('img',{ "class" : "imagefield imagefield-field_magazine_cover" }):
return image['src'] + '.jpg'
return None

83
resources/recipes/wsj.recipe
View File

@ -4,13 +4,14 @@ __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import copy
# http://online.wsj.com/page/us_in_todays_paper.html # http://online.wsj.com/page/us_in_todays_paper.html
class WallStreetJournal(BasicNewsRecipe): class WallStreetJournal(BasicNewsRecipe):
title = 'The Wall Street Journal (US)' title = 'The Wall Street Journal'
__author__ = 'Kovid Goyal and Sujata Raman' __author__ = 'Kovid Goyal, Sujata Raman, and Joshua Oster-Morris'
description = 'News and current affairs' description = 'News and current affairs'
needs_subscription = True needs_subscription = True
language = 'en' language = 'en'
@ -67,6 +68,16 @@ class WallStreetJournal(BasicNewsRecipe):
def wsj_get_index(self): def wsj_get_index(self):
return self.index_to_soup('http://online.wsj.com/itp') return self.index_to_soup('http://online.wsj.com/itp')
def wsj_add_feed(self,feeds,title,url):
self.log('Found section:', title)
if url.endswith('whatsnews'):
articles = self.wsj_find_wn_articles(url)
else:
articles = self.wsj_find_articles(url)
if articles:
feeds.append((title, articles))
return feeds
def parse_index(self): def parse_index(self):
soup = self.wsj_get_index() soup = self.wsj_get_index()
@ -82,25 +93,62 @@ class WallStreetJournal(BasicNewsRecipe):
div = soup.find('div', attrs={'class':'itpHeader'}) div = soup.find('div', attrs={'class':'itpHeader'})
div = div.find('ul', attrs={'class':'tab'}) div = div.find('ul', attrs={'class':'tab'})
for a in div.findAll('a', href=lambda x: x and '/itp/' in x): for a in div.findAll('a', href=lambda x: x and '/itp/' in x):
pageone = a['href'].endswith('pageone')
if pageone:
title = 'Front Section'
url = 'http://online.wsj.com' + a['href']
feeds = self.wsj_add_feed(feeds,title,url)
title = 'What''s News'
url = url.replace('pageone','whatsnews')
feeds = self.wsj_add_feed(feeds,title,url)
else:
title = self.tag_to_string(a) title = self.tag_to_string(a)
url = 'http://online.wsj.com' + a['href'] url = 'http://online.wsj.com' + a['href']
self.log('Found section:', title) feeds = self.wsj_add_feed(feeds,title,url)
articles = self.wsj_find_articles(url)
if articles:
feeds.append((title, articles))
return feeds return feeds
def wsj_find_wn_articles(self, url):
soup = self.index_to_soup(url)
articles = []
whats_news = soup.find('div', attrs={'class':lambda x: x and 'whatsNews-simple' in x})
if whats_news is not None:
for a in whats_news.findAll('a', href=lambda x: x and '/article/' in x):
container = a.findParent(['p'])
meta = a.find(attrs={'class':'meta_sectionName'})
if meta is not None:
meta.extract()
title = self.tag_to_string(a).strip()
url = a['href']
desc = ''
if container is not None:
desc = self.tag_to_string(container)
articles.append({'title':title, 'url':url,
'description':desc, 'date':''})
self.log('\tFound WN article:', title)
return articles
def wsj_find_articles(self, url): def wsj_find_articles(self, url):
soup = self.index_to_soup(url) soup = self.index_to_soup(url)
whats_news = soup.find('div', attrs={'class':lambda x: x and whats_news = soup.find('div', attrs={'class':lambda x: x and 'whatsNews-simple' in x})
'whatsNews-simple' in x})
if whats_news is not None: if whats_news is not None:
whats_news.extract() whats_news.extract()
articles = [] articles = []
flavorarea = soup.find('div', attrs={'class':lambda x: x and 'ahed' in x})
if flavorarea is not None:
flavorstory = flavorarea.find('a', href=lambda x: x and x.startswith('/article'))
if flavorstory is not None:
flavorstory['class'] = 'mjLinkItem'
metapage = soup.find('span', attrs={'class':lambda x: x and 'meta_sectionName' in x})
if metapage is not None:
flavorstory.append( copy.copy(metapage) ) #metapage should always be A1 because that should be first on the page
for a in soup.findAll('a', attrs={'class':'mjLinkItem'}, href=True): for a in soup.findAll('a', attrs={'class':'mjLinkItem'}, href=True):
container = a.findParent(['li', 'div']) container = a.findParent(['li', 'div'])
meta = a.find(attrs={'class':'meta_sectionName'}) meta = a.find(attrs={'class':'meta_sectionName'})
@ -118,26 +166,9 @@ class WallStreetJournal(BasicNewsRecipe):
self.log('\tFound article:', title) self.log('\tFound article:', title)
'''
# Find related articles
a.extract()
for a in container.findAll('a', href=lambda x: x and '/article/'
in x and 'articleTabs' not in x):
url = a['href']
if not url.startswith('http:'):
url = 'http://online.wsj.com'+url
title = self.tag_to_string(a).strip()
if not title or title.startswith('['): continue
if title:
articles.append({'title':self.tag_to_string(a),
'url':url, 'description':'', 'date':''})
self.log('\t\tFound related:', title)
'''
return articles return articles
def cleanup(self): def cleanup(self):
self.browser.open('http://online.wsj.com/logout?url=http://online.wsj.com') self.browser.open('http://online.wsj.com/logout?url=http://online.wsj.com')