calibre/recipes/chronicle_higher_ed.recipe

91 lines
3.4 KiB
Plaintext

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', 'blog-mod']}),
]
remove_tags = [dict(name='div', attrs={'class': ['related module1', 'maintitle', 'entry-utility', 'object-meta']}),
dict(name='div', attrs={
'id': ['section-nav', 'icon-row', 'enlarge-popup', 'confirm-popup']}),
dict(name='a', attrs={'class': 'show-enlarge enlarge'})]
no_javascript = True
no_stylesheets = True
needs_subscription = True
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
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': 'side-content'}).find(attrs={'src': re.compile("photos/biz/Current")})
if cover is not None:
if "chronicle.com" in cover['src']:
self.cover_url = cover['src']
else:
self.cover_url = "http://chronicle.com" + cover['src']
# Go to the main body
soup = self.index_to_soup(issueurl)
div = soup.find('div', attrs={'id': 'article-body'})
feeds = OrderedDict()
section_title = ''
for post in div.findAll('li'):
articles = []
a = post.find('a', href=True)
if a is not None:
title = self.tag_to_string(a)
url = "http://chronicle.com" + a['href'].strip()
sectiontitle = post.findPrevious('h3')
if sectiontitle is None:
sectiontitle = post.findPrevious('h4')
section_title = self.tag_to_string(sectiontitle)
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.items()]
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