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 Smithsonian Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2013-03-14 23:21:14 +05:30
parent 6e53973981
commit 7c1b735906
1 changed files with 14 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
recipes/smith.recipe
View File

@ -25,7 +25,7 @@ class Smithsonian(BasicNewsRecipe):
soup = self.index_to_soup(current_issue_url) soup = self.index_to_soup(current_issue_url)
#Go to the main body #Go to the main body
div = soup.find ('div', attrs={'id':'content-inset'}) div = soup.find ('div', attrs={'id':'article-body'})
#Find date #Find date
date = re.sub('.*\:\W*', "", self.tag_to_string(div.find('h2')).strip()) date = re.sub('.*\:\W*', "", self.tag_to_string(div.find('h2')).strip())
@ -36,35 +36,26 @@ class Smithsonian(BasicNewsRecipe):
feeds = OrderedDict() feeds = OrderedDict()
section_title = '' section_title = ''
subsection_title = '' articles = []
for post in div.findAll('div', attrs={'class':['plainModule', 'departments plainModule']}): for post in div.findAll('div', attrs={'class':['plainModule', 'departments plainModule']}):
articles = [] h4=post.find('h3')
prefix = '' if h4 is not None:
h3=post.find('h3') if articles:
if h3 is not None: if section_title not in feeds:
section_title = self.tag_to_string(h3) feeds[section_title] = []
feeds[section_title] += articles
section_title = self.tag_to_string(h4)
articles = []
self.log('Found section:', section_title)
else: else:
subsection=post.find('p',attrs={'class':'article-cat'})
link=post.find('a',href=True) link=post.find('a',href=True)
url=link['href']+'?c=y&story=fullstory' url=link['href']+'?c=y&story=fullstory'
if subsection is not None: description=self.tag_to_string(post.find('p')).strip()
subsection_title = self.tag_to_string(subsection).strip()
prefix = (subsection_title+': ')
description=self.tag_to_string(post('p', limit=2)[1]).strip()
else:
if post.find('img') is not None:
subsection_title = self.tag_to_string(post.findPrevious('div', attrs={'class':'departments plainModule'}).find('p', attrs={'class':'article-cat'})).strip()
prefix = (subsection_title+': ')
description=self.tag_to_string(post.find('p')).strip()
desc=re.sub('\sBy\s.*', '', description, re.DOTALL) desc=re.sub('\sBy\s.*', '', description, re.DOTALL)
author=re.sub('.*By\s', '', description, re.DOTALL) author=re.sub('.*By\s', '', description, re.DOTALL)
title=prefix + self.tag_to_string(link).strip()+ u' (%s)'%author title=self.tag_to_string(link).strip()+ u' (%s)'%author
self.log('\tFound article:', title)
articles.append({'title':title, 'url':url, 'description':desc, 'date':''}) articles.append({'title':title, 'url':url, 'description':desc, 'date':''})
if articles:
if section_title not in feeds:
feeds[section_title] = []
feeds[section_title] += articles
ans = [(key, val) for key, val in feeds.iteritems()] ans = [(key, val) for key, val in feeds.iteritems()]
return ans return ans