mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
130 lines
4.8 KiB
Python
130 lines
4.8 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
'''
|
|
economist.com
|
|
'''
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Tag, NavigableString
|
|
from collections import OrderedDict
|
|
|
|
import time, re
|
|
|
|
class Economist(BasicNewsRecipe):
|
|
|
|
title = 'The Economist'
|
|
language = 'en'
|
|
|
|
__author__ = "Kovid Goyal"
|
|
INDEX = 'http://www.economist.com/printedition'
|
|
description = ('Global news and current affairs from a European'
|
|
' perspective. Best downloaded on Friday mornings (GMT)')
|
|
extra_css = '.headline {font-size: x-large;} \n h2 { font-size: small; } \n h1 { font-size: medium; }'
|
|
oldest_article = 7.0
|
|
cover_url = 'http://www.economist.com/images/covers/currentcoverus_large.jpg'
|
|
remove_tags = [
|
|
dict(name=['script', 'noscript', 'title', 'iframe', 'cf_floatingcontent']),
|
|
dict(attrs={'class':['dblClkTrk', 'ec-article-info', 'share_inline_header']}),
|
|
{'class': lambda x: x and 'share-links-header' in x},
|
|
]
|
|
keep_only_tags = [dict(id='ec-article-body')]
|
|
needs_subscription = False
|
|
no_stylesheets = True
|
|
preprocess_regexps = [(re.compile('</html>.*', re.DOTALL),
|
|
lambda x:'</html>')]
|
|
|
|
'''
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser()
|
|
br.open('http://www.economist.com')
|
|
req = mechanize.Request(
|
|
'http://www.economist.com/members/members.cfm?act=exec_login',
|
|
headers = {
|
|
'Referer':'http://www.economist.com/',
|
|
},
|
|
data=urllib.urlencode({
|
|
'logging_in' : 'Y',
|
|
'returnURL' : '/',
|
|
'email_address': self.username,
|
|
'fakepword' : 'Password',
|
|
'pword' : self.password,
|
|
'x' : '0',
|
|
'y' : '0',
|
|
}))
|
|
br.open(req).read()
|
|
return br
|
|
'''
|
|
|
|
def parse_index(self):
|
|
try:
|
|
return self.economist_parse_index()
|
|
except:
|
|
raise
|
|
self.log.warn(
|
|
'Initial attempt to parse index failed, retrying in 30 seconds')
|
|
time.sleep(30)
|
|
return self.economist_parse_index()
|
|
|
|
def economist_parse_index(self):
|
|
soup = self.index_to_soup(self.INDEX)
|
|
feeds = OrderedDict()
|
|
for section in soup.findAll(attrs={'class':'section'}):
|
|
h4 = section.find('h4')
|
|
if h4 is None:
|
|
continue
|
|
section_title = self.tag_to_string(h4).strip()
|
|
if not section_title:
|
|
continue
|
|
self.log('Found section: %s'%section_title)
|
|
articles = []
|
|
for h5 in section.findAll('h5'):
|
|
article_title = self.tag_to_string(h5).strip()
|
|
if not article_title:
|
|
continue
|
|
data = h5.findNextSibling(attrs={'class':'article'})
|
|
if data is None: continue
|
|
a = data.find('a', href=True)
|
|
if a is None: continue
|
|
url = a['href']
|
|
if url.startswith('/'): url = 'http://www.economist.com'+url
|
|
url += '/print'
|
|
article_title += ': %s'%self.tag_to_string(a).strip()
|
|
articles.append({'title':article_title, 'url':url,
|
|
'description':'', 'date':''})
|
|
if articles:
|
|
feeds[section_title] = articles
|
|
|
|
ans = [(key, val) for key, val in feeds.iteritems()]
|
|
if not ans:
|
|
raise Exception('Could not find any articles, either the '
|
|
'economist.com server is having trouble and you should '
|
|
'try later or the website format has changed and the '
|
|
'recipe needs to be updated.')
|
|
return ans
|
|
|
|
def eco_find_image_tables(self, soup):
|
|
for x in soup.findAll('table', align=['right', 'center']):
|
|
if len(x.findAll('font')) in (1,2) and len(x.findAll('img')) == 1:
|
|
yield x
|
|
|
|
def postprocess_html(self, soup, first):
|
|
body = soup.find('body')
|
|
for name, val in body.attrs:
|
|
del body[name]
|
|
|
|
for table in list(self.eco_find_image_tables(soup)):
|
|
caption = table.find('font')
|
|
img = table.find('img')
|
|
div = Tag(soup, 'div')
|
|
div['style'] = 'text-align:left;font-size:70%'
|
|
ns = NavigableString(self.tag_to_string(caption))
|
|
div.insert(0, ns)
|
|
div.insert(1, Tag(soup, 'br'))
|
|
del img['width']
|
|
del img['height']
|
|
img.extract()
|
|
div.insert(2, img)
|
|
table.replaceWith(div)
|
|
return soup
|