calibre/recipes/forbes_india.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

56 lines
1.9 KiB
Plaintext

from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1276934715(BasicNewsRecipe):
title = u'Forbes India'
__author__ = 'rty'
description = 'India Edition Forbes'
publisher = 'Forbes India'
category = 'Business News, Economy, India'
oldest_article = 7
max_articles_per_feed = 100
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'en_IN'
temp_files = []
articles_are_obfuscated = True
conversion_options = {'linearize_tables': True}
feeds = [
(u'Contents', u'http://business.in.com/rssfeed/rss_all.xml'),
]
extra_css = '''
.t-10-gy-l{font-style: italic; font-size: small}
.t-30-b-d{font-weight: bold; font-size: xx-large}
.t-16-gy-l{font-weight: bold; font-size: x-large; font-syle: italic}
.storycontent{font-size: 4px;font-family: Times New Roman;}
'''
remove_tags_before = dict(name='div', attrs={'class': 'pdl10 pdr15'})
def get_obfuscated_article(self, url):
br = self.get_browser()
br.open(url)
response = br.follow_link(url_regex=r'/printcontent/[0-9]+', nr=0)
html = response.read()
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html)
self.temp_files[-1].close()
return self.temp_files[-1].name
def get_cover_url(self):
index = 'http://business.in.com/magazine/'
soup = self.index_to_soup(index)
for image in soup.findAll('a', {"class": "lbOn a-9-b-d"}):
return image['href']
# return image['href'] + '.jpg'
return None
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(width=True):
del item['width']
return soup