calibre/recipes/scientific_american.recipe
2015-05-19 10:13:56 +05:30

101 lines
4.7 KiB
Python

#!/usr/bin/env python2
__license__ = 'GPL v3'
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.utils.date import now
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. Should be downloaded around the middle of each month.'
category = 'science'
__author__ = 'Kovid Goyal'
no_stylesheets = True
language = 'en'
publisher = 'Nature Publishing Group'
remove_empty_feeds = True
remove_javascript = True
timefmt = ' [%B %Y]'
needs_subscription = 'optional'
keep_only_tags = [
dict(attrs={'class':['article-title', 'article-dek', 'article-author article-date', 'article-complementary', 'article-slatwallPayWall']}),
dict(attrs={'class':lambda x: x and 'article-content' in x.split()}),
]
remove_tags = [
dict(attrs={'class':['article-footer']}),
dict(id=['seeAlsoLinks']),
dict(attrs={'class':lambda x: x and 'moreToExplore' in x.split()}),
]
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 root.xpath('''descendant-or-self::*[@class and contains(concat(' ', normalize-space(@class), ' '), ' archiveIssues ')]/descendant-or-self::*/a[@class and contains(concat(' ', normalize-space(@class), ' '), ' cover ') and (@href)]'''): # noqa
url = a.get('href')
month = int(filter(None, url.split('/'))[-1].partition('-')[0])
if month > now().month:
continue
self.cover_url = absurl(a.xpath('descendant-or-self::img[@src]')[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(root.xpath('''descendant-or-self::div[@class and contains(concat(' ', normalize-space(@class), ' '), ' toc-features ')] | descendant-or-self::div[@class and contains(concat(' ', normalize-space(@class), ' '), ' toc-departments ')]''')): # noqa
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 div.xpath('''descendant-or-self::li/descendant-or-self::*/a[@href]/descendant-or-self::*/h4'''):
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 div.xpath('''descendant-or-self::li/descendant-or-self::*/a[@href]/descendant-or-self::*/h3 | descendant-or-self::li/descendant-or-self::*/span[@class and contains(concat(' ', normalize-space(@class), ' '), ' deptTitle ')]/descendant-or-self::*/a[@href]'''): # noqa
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))