Updated with a (terrible) cover (but the best I can get)
Code:
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
from collections import OrderedDict
class Chronicle(BasicNewsRecipe):
title = 'The Chronicle of Higher Education'
__author__ = 'Rick Shang'
description = 'Weekly news and job-information source for college and university faculty members, administrators, and students.'
language = 'en'
category = 'news'
encoding = 'UTF-8'
keep_only_tags = [
dict(name='div', attrs={'class':'article'}),
]
remove_tags = [dict(name='div',attrs={'class':'related module1'})]
no_javascript = True
no_stylesheets = True
needs_subscription = True
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open('http://chronicle.com/myaccount/login')
br.select_form(nr=1)
br['username'] = self.username
br['password'] = self.password
br.submit()
return br
def parse_index(self):
#Go to the issue
soup0 = self.index_to_soup('http://chronicle.com/section/Archives/39/')
issue = soup0.find('ul',attrs={'class':'feature-promo-list'}).li
issueurl = "http://chronicle.com"+issue.a['href']
#Find date
dates = self.tag_to_string(issue.a).split(': ')[-1]
self.timefmt = u' [%s]'%dates
#Find cover
cover=soup0.find('div',attrs={'class':'promo'}).findNext('div')
self.cover_url="http://chronicle.com"+cover.find('img')['src']
#Go to the main body
soup = self.index_to_soup(issueurl)
div0 = soup.find ('div', attrs={'id':'article-body'})
feeds = OrderedDict()
for div in div0.findAll('div',attrs={'class':'module1'}):
section_title = self.tag_to_string(div.find('h3'))
for post in div.findAll('li',attrs={'class':'sub-promo'}):
articles = []
a=post.find('a', href=True)
title=self.tag_to_string(a)
url="http://chronicle.com"+a['href'].strip()
author=""
desc=self.tag_to_string(post.find('p'))
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()]
return ans
def preprocess_html(self,soup):
#process all the images
for div in soup.findAll('div', attrs={'class':'tableauPlaceholder'}):
noscripts=div.find('noscript').a
div.replaceWith(noscripts)
for div0 in soup.findAll('div',text='Powered by Tableau'):
div0.extract()
return soup