calibre/recipes/scientific_american.recipe
2015-01-23 19:08:21 +05:30

97 lines
3.7 KiB
Python

#!/usr/bin/env python2
__license__ = 'GPL v3'
from calibre.web.feeds.news import BasicNewsRecipe
try:
from calibre.web.feeds.jsnews import CSSSelect
except ImportError:
def CSSSelect(expr):
from cssselect import HTMLTranslator
from lxml.etree import XPath
return XPath(HTMLTranslator().css_to_xpath(expr))
def absurl(url):
if url.startswith('/'):
url = 'http://www.scientificamerican.com' + url
return url
class ScientificAmerican(BasicNewsRecipe):
title = u'Scientific American'
description = u'Popular Science. Monthly magazine.'
category = 'science'
__author__ = 'Kovid Goyal'
no_stylesheets = True
language = 'en'
publisher = 'Nature Publishing Group'
remove_empty_feeds = True
remove_javascript = True
needs_subscription = 'optional'
keep_only_tags = [
dict(attrs={'class':['article-title', 'article-dek', 'article-author article-date', 'article-content', 'article-slatwallPayWall']}),
]
def get_browser(self, *args):
br = BasicNewsRecipe.get_browser(self)
if self.username and self.password:
br.open('https://www.scientificamerican.com/my-account/login/')
br.select_form(predicate=lambda f:f.attrs.get('id') == 'login')
br['emailAddress'] = self.username
br['password'] = self.password
br.submit()
return br
def parse_index(self):
# Get the cover, date and issue URL
root = self.index_to_soup('http://www.scientificamerican.com/sciammag/', as_tree=True)
for a in CSSSelect('.archiveIssues a.cover[href]')(root):
self.cover_url = absurl(CSSSelect('img[src]')(a)[0].get('src'))
root = self.index_to_soup(absurl(a.get('href')), as_tree=True)
for a in a.xpath('following-sibling::a[@href]'):
self.timefmt = self.tag_to_string(a).strip()
break
break
else:
raise ValueError('The Scientific American website has changed, this recipe needs to be updated')
# Now parse the actual issue to get the list of articles
feeds = []
for i, div in enumerate(CSSSelect('div.toc-features, div.toc-departments')(root)):
if i == 0:
feeds.append(('Features', list(self.parse_sciam_features(div))))
else:
feeds.extend(self.parse_sciam_departments(div))
return feeds
def parse_sciam_features(self, div):
for h4 in CSSSelect('li a[href] h4')(div):
title = self.tag_to_string(h4)
a = h4.getparent()
url = absurl(a.get('href'))
desc = ''
for span in a.xpath('following-sibling::span'):
desc = self.tag_to_string(span)
break
self.log('Found feature article: %s at %s' % (title, url))
self.log('\t' + desc)
yield {'title':title, 'url':url, 'description':desc}
def parse_sciam_departments(self, div):
section_title, articles = 'Unknown', []
for x in CSSSelect('li a[href] h3, li span.deptTitle a[href]')(div):
if x.tag == 'a':
if articles:
yield section_title, list(articles)
section_title = self.tag_to_string(x)
del articles[:]
self.log('\nFound section: %s' % section_title)
else:
title = self.tag_to_string(x)
a = x.getparent()
url = absurl(a.get('href'))
articles.append({'title':title, 'url':url, 'description':''})
self.log('\tFound article: %s at %s' % (title, url))