mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
Update Entrepreneur Magazine
Fixes #1464886 [Unable to fetch news from the entrepeneur magazine](https://bugs.launchpad.net/calibre/+bug/1464886)
This commit is contained in:
Kovid Goyal
parent
f2469eefdc
commit
a848440da8
@ -1,11 +1,16 @@
|
||||
#!/usr/bin/env python2
|
||||
# vim:fileencoding=utf-8
|
||||
from __future__ import (unicode_literals, division, absolute_import,
|
||||
print_function)
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
class EntrepeneurMagRecipe(BasicNewsRecipe):
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'kwetal'
|
||||
__author__ = 'Kovid Goyal'
|
||||
language = 'en'
|
||||
version = 1
|
||||
|
||||
title = u'Entrepeneur Magazine'
|
||||
publisher = u'Entrepreneur Media, Inc'
|
||||
@ -17,78 +22,52 @@ class EntrepeneurMagRecipe(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
|
||||
keep_only_tags = []
|
||||
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'printbody'}))
|
||||
|
||||
remove_tags = []
|
||||
remove_tags.append(dict(name = 'base'))
|
||||
remove_tags.append(dict(name = 'a', attrs = {'id': 'ctl00_privacyPolicyLink'}))
|
||||
|
||||
keep_only_tags = [
|
||||
dict(attrs={'class':['headline']}),
|
||||
dict(itemprop='articlebody'),
|
||||
]
|
||||
remove_tags = [
|
||||
dict(attrs={'class':['related-content']}),
|
||||
]
|
||||
remove_attributes = ['style']
|
||||
|
||||
INDEX = 'http://www.entrepeneur.com'
|
||||
|
||||
extra_css = '''
|
||||
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
|
||||
img {float: left; margin-right: 0.5em;}
|
||||
a, a[href] {text-decoration: none; color: blue;}
|
||||
div#ctl00_bodyContentPlaceHolder_articleHeader_divHeaderText {font-weight: bold;
|
||||
font-size: medium;}
|
||||
h1 {font-size: xx-large; font-weight: bold;}
|
||||
div.byline {font-size: small; color: #696969; font-weight: normal;}
|
||||
a.h2 {font-size: medium; font-weight: bold; color: #666666; text-decoration: none;
|
||||
margin-bottom: 0em;}
|
||||
'''
|
||||
|
||||
conversion_options = {'comments': description, 'language': 'en',
|
||||
'publisher': publisher}
|
||||
INDEX = 'http://www.entrepreneur.com'
|
||||
|
||||
def parse_index(self):
|
||||
soup = self.index_to_soup('http://www.entrepreneur.com/magazine/entrepreneur/index.html')
|
||||
answer = []
|
||||
root = self.index_to_soup(self.INDEX + '/magazine/index.html', as_tree=True)
|
||||
for href in root.xpath('//div[@class="Ddeck title"]/a/@href'):
|
||||
return self.parse_ent_index(self.INDEX + href)
|
||||
|
||||
div = soup.find('div', attrs = {'id': 'magfeature'})
|
||||
if div:
|
||||
a = div.find('a', attrs = {'class': 'headline'})
|
||||
if a:
|
||||
title = self.tag_to_string(a)
|
||||
url = self.INDEX + a['href']
|
||||
description = a.findNextSibling(text = True)
|
||||
def parse_ent_index(self, url):
|
||||
root = self.index_to_soup(url, as_tree=True)
|
||||
img = root.xpath('//div[@class="magcoverissue"]/img')[0]
|
||||
self.cover_url = img.get('src')
|
||||
self.timefmt = ' [%s]' % img.get('alt').rpartition('-')[-1].strip()
|
||||
body = root.xpath('//div[@class="cbody"]')[0]
|
||||
current_section = 'Unknown'
|
||||
current_articles = []
|
||||
ans = []
|
||||
for x in body.xpath('descendant::*[name() = "h2" or name() = "h3"]'):
|
||||
if x.tag == 'h2':
|
||||
if current_articles:
|
||||
ans.append((current_section, current_articles))
|
||||
current_section = self.tag_to_string(x)
|
||||
current_articles = []
|
||||
self.log('Found section:', current_section)
|
||||
else:
|
||||
title = self.tag_to_string(x)
|
||||
try:
|
||||
a = x.xpath('./a')[0]
|
||||
except IndexError:
|
||||
continue
|
||||
url = self.INDEX + a.get('href')
|
||||
d = x.getnext()
|
||||
desc = self.tag_to_string(d) if d is not None else ''
|
||||
self.log('\t', title, 'at:', url)
|
||||
self.log('\t\t', desc)
|
||||
current_articles.append({'title':title, 'url':url, 'description':desc})
|
||||
|
||||
articles = [{'title': title, 'date': None, 'url': url, 'description': description}]
|
||||
answer.append(('Cover Story', articles))
|
||||
|
||||
for div in soup.findAll('div', attrs = {'class': 'subhead-special'}):
|
||||
articles = []
|
||||
for tag in div.findNextSiblings(['a', 'div'], attrs = {'class': ['h2', 'subhead-special']}):
|
||||
if tag.name == 'div' and tag['class'] == 'subhead-special':
|
||||
break
|
||||
if tag.name == 'a' and tag['class'] == 'h2':
|
||||
title = self.tag_to_string(tag)
|
||||
url = tag['href']
|
||||
description = tag.findNextSibling(text = True)
|
||||
articles.append({'title': title, 'date': None, 'url': url, 'description': description})
|
||||
answer.append((self.tag_to_string(div), articles))
|
||||
|
||||
return answer
|
||||
|
||||
|
||||
def print_version(self, url):
|
||||
id = url.rpartition('/')[2]
|
||||
|
||||
return 'http://www.entrepreneur.com/article/printthis/' + id
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
div = soup.find('div', attrs = {'id': 'printbody'})
|
||||
if div:
|
||||
a = div.find(lambda tag: tag.name == 'a' and len(tag.attrs) == 1)
|
||||
if a:
|
||||
txt = a.findPreviousSibling(text = re.compile('URL:.*'))
|
||||
if txt:
|
||||
txt.extract()
|
||||
for br in a.findNextSiblings('br'):
|
||||
br.extract()
|
||||
a.extract()
|
||||
|
||||
return soup
|
||||
if current_articles:
|
||||
ans.append((current_section, current_articles))
|
||||
|
||||
return ans
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user