mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
a80d6302ec
Fixes #1635338 [MIT Technology Review magazine doesn't download main article](https://bugs.launchpad.net/calibre/+bug/1635338)
70 lines
2.3 KiB
Python
70 lines
2.3 KiB
Python
#!/usr/bin/env python2
|
|
from __future__ import unicode_literals
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2015 Michael Marotta <mikefm at gmail.net>'
|
|
# Written April 2015
|
|
# Last edited 4/18/15
|
|
'''
|
|
technologyreview.com
|
|
'''
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
def absurl(x):
|
|
if x.startswith('//'):
|
|
x = 'http:' + x
|
|
elif not x.startswith('http'):
|
|
x = "http://www.technologyreview.com" + x
|
|
return x
|
|
|
|
|
|
def classes(classes):
|
|
q = frozenset(classes.split(' '))
|
|
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
|
|
|
|
|
class MitTechnologyReview(BasicNewsRecipe):
|
|
|
|
title = 'MIT Technology Review Magazine'
|
|
__author__ = 'Michael Marotta'
|
|
description = ('Bi-monthly magazine version of MIT Technology Review.'
|
|
' This is different than the recipe named simply "Technology Review"'
|
|
' which downloads the rss feed with daily articles from the website.')
|
|
INDEX = 'http://www.technologyreview.com/magazine/'
|
|
language = 'en'
|
|
encoding = 'utf-8'
|
|
simultaneous_downloads = 20
|
|
tags = 'news, technology, science'
|
|
no_stylesheets = True
|
|
|
|
keep_only_tags = [
|
|
classes(
|
|
'article-topper__topic article-topper__title article-topper__media-wrap article-body__content'),
|
|
]
|
|
remove_tags = [
|
|
classes('l-article-list'),
|
|
]
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup(self.INDEX)
|
|
# find cover
|
|
self.cover_url = absurl(soup.find(
|
|
'a', attrs={'class': 'magazine-topper__cover'}).find('img', src=True)['src'])
|
|
# parse articles
|
|
current_articles = []
|
|
for div in soup.findAll(attrs={'class': lambda x: x in
|
|
'magazine-topper__title magazine-features-item__top-title magazine-features-item-title author-tz__title feed-tz__title'.split()}):
|
|
a = div.find('a', href=True)
|
|
title = self.tag_to_string(a).strip()
|
|
href = absurl(a['href'])
|
|
if href and title:
|
|
current_articles.append({'title': title, 'url': href})
|
|
self.log(title, '[%s]' % href)
|
|
return [('Articles', current_articles)]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll(srcset=True):
|
|
img['src'] = absurl(img['srcset'].split()[0])
|
|
del img['srcset']
|
|
return soup
|