mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
74 lines
3.3 KiB
Python
74 lines
3.3 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
|
|
'''
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
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'
|
|
|
|
keep_only_tags = [
|
|
{'attrs':{'class':['body', 'intro', 'article-magazine', 'byline', 'view-byline', 'sticky-wrap', 'body hack']}},
|
|
]
|
|
remove_tags = [
|
|
{'name': ['meta', 'link', 'noscript', 'clearfix', 'flag']},
|
|
]
|
|
no_stylesheets = True
|
|
preprocess_regexps = [(re.compile(r'<br[ ]*/>', re.IGNORECASE), lambda m: ''),
|
|
(re.compile(r'<br[ ]*clear.*/>', re.IGNORECASE), lambda m: '')]
|
|
|
|
extra_css = 'body { font-family: helvetica, sans-serif; } \
|
|
h2 { text-align: left; font-size: 1em; font-weight: bold; }}'
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup(self.INDEX)
|
|
# find cover
|
|
self.cover_url = soup.find('li', attrs={'class':'cover'}).find('img', src=True)['src']
|
|
# parse articles
|
|
col = soup.find(attrs={'class':'view-content'})
|
|
current_section, current_articles = None, []
|
|
feeds = []
|
|
for tag in col.findAll(name=['section', 'a'], attrs={'class':['content-block in-this-issue no-border', None]}):
|
|
if tag.name == 'section':
|
|
if current_section and current_articles:
|
|
feeds.append((current_section, current_articles))
|
|
current_section = self.tag_to_string(tag.find('h2'))[15:].capitalize()
|
|
current_articles = []
|
|
self.log('Found section:', current_section)
|
|
elif current_section:
|
|
a=tag # since tag itself is a <a> tag use it directly instead of using find
|
|
if a is not None:
|
|
if self.tag_to_string(a.h2) == "":
|
|
title = self.tag_to_string(a.h1)
|
|
else:
|
|
title = self.tag_to_string(a.h2) + ": " + self.tag_to_string(a.h1)
|
|
if "http://www.technologyreview.com" in a['href']:
|
|
url = a['href']
|
|
else:
|
|
url = "http://www.technologyreview.com" + a['href']
|
|
if title and url:
|
|
p = tag.find('p', attrs={'class':'columns-off'})
|
|
desc = self.tag_to_string(p) if p is not None else ''
|
|
current_articles.append({'title':title, 'url':url, 'description':desc})
|
|
self.log('\tArticle:', title, '[%s]' % url)
|
|
self.log('\t\t', desc)
|
|
if current_section and current_articles:
|
|
feeds.append((current_section, current_articles))
|
|
return feeds
|