Update Frontline

Fixes #1647313 [Replace Frontline recipe](https://bugs.launchpad.net/calibre/+bug/1647313)
This commit is contained in:
Kovid Goyal 2016-12-05 16:48:26 +05:30
parent 6f99bc3cea
commit 9a60dd0da1
2 changed files with 55 additions and 60 deletions

View File

@ -1,79 +1,74 @@
# -*- mode: python -*-
# -*- coding: utf-8 -*-
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2011 - 2016, Darko Miletic <darko.miletic at gmail.com>'
''' '''
frontlineonnet.com www.frontline.in
''' '''
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Frontlineonnet(BasicNewsRecipe): class Frontlineonnet(BasicNewsRecipe):
title = 'Frontline' title = 'Frontline'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = "India's national magazine" description = """
publisher = 'Frontline' India's National Magazine
category = 'news, politics, India' Frontline, the fortnightly English magazine from the stable of The Hindu, has been a distinguished presence in the media world for the past 27 years.
no_stylesheets = True As per the Indian Readership Survey (IRS) Q4, its average issue readership is 152,000.
delay = 1
INDEX = 'http://frontlineonnet.com/' Frontline's journalism is characterised by in-depth, insightful reporting and analysis of issues and events at the regional, national and international levels.
It excels in long-form journalism.
The topics Frontline covers range from politics, economics and social issues to the environment, nature, culture and cinema.
Its cover stories are comprehensive.
"""
publisher = 'Frontline'
category = 'news, politics, India'
no_stylesheets = True
oldest_article = 15
INDEX = 'http://www.frontline.in/'
use_embedded_content = False use_embedded_content = False
encoding = 'utf-8' encoding = 'utf-8'
language = 'en_IN' language = 'en_IN'
publication_type = 'magazine' publication_type = 'magazine'
masthead_url = 'http://frontlineonnet.com/images/newfline.jpg' auto_cleanup = True
masthead_url = 'http://www.frontline.in/template/1-0-1/gfx/fl_logo.jpg'
extra_css = """ extra_css = """
body{font-family: Verdana,Arial,Helvetica,sans-serif} body{font-family: Georgia,"Times New Roman",serif}
img{margin-top:0.5em; margin-bottom: 0.7em; display: block} img{margin-top:0.5em; margin-bottom: 0.7em; display: block}
""" """
conversion_options = { conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True 'comment' : description,
'tags' : category ,
'publisher': publisher ,
'language' : language
} }
preprocess_regexps = [ feeds = [
(re.compile(r'.*?<base', re.DOTALL | re.IGNORECASE), lambda match: '<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"><html dir="ltr" xml:lang="en-IN"><head><title>title</title><base') # noqa (u'Cover story' , u'http://www.frontline.in/cover-story/?service=rss'),
, (re.compile(r'<base .*?>', re.DOTALL | re.IGNORECASE), lambda match: '</head><body>'), (re.compile(r'<byline>', re.DOTALL | re.IGNORECASE), lambda match: '<div class="byline">'), (re.compile(r'</byline>', re.DOTALL | re.IGNORECASE), lambda match: '</div>'), (re.compile(r'<center>', re.DOTALL | re.IGNORECASE), lambda match: '<div class="ctr">'), (re.compile(r'</center>', re.DOTALL | re.IGNORECASE), lambda match: '</div>') # noqa (u'The Nation' , u'http://www.frontline.in/the-nation/?service=rss'),
] (u'Politics' , u'http://www.frontline.in/politics/?service=rss'),
(u'Columns' , u'http://www.frontline.in/columns/?service=rss'),
keep_only_tags = [ (u'Social Issues' , u'http://www.frontline.in/social-issues/?service=rss'),
dict(name='div', attrs={'id': 'content'}) (u'General issues' , u'http://www.frontline.in/social-issues/general-issues/?service=rss'),
(u'Social justice' , u'http://www.frontline.in/social-issues/social-justice/?service=rss'),
(u'Arts&Culture' , u'http://www.frontline.in/arts-and-culture/?service=rss'),
(u'Economy' , u'http://www.frontline.in/economy/?service=rss'),
(u'World Affairs' , u'http://www.frontline.in/world-affairs/?service=rss'),
(u'Science&Technology', u'http://www.frontline.in/science-and-technology/?service=rss'),
(u'Books' , u'http://www.frontline.in/books/?service=rss'),
(u'Sport' , u'http://www.frontline.in/other/sport/?service=rss')
] ]
remove_attributes = ['size', 'noshade', 'border']
use_javascript_to_login = True def get_cover_url(self):
needs_subscription = True
def javascript_login(self, browser, username, password):
browser.visit('http://www.frontline.in/profile/login.do')
browser.wait_for_element('form#loginForm', timeout=180)
# Select the first form on the page
form = browser.select_form('#loginForm')
form['userName'] = username
form['password'] = password
browser.submit(timeout=120)
def parse_index(self):
articles = []
current_section = None
feeds = []
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
for h3 in soup.findAll('h3'): divtag = soup.find('div', 'smallMagCont')
if h3.get('class', None) == 'artListSec': if divtag:
if articles: return divtag.img['src']
feeds.append((current_section, articles)) return None
articles = []
current_section = self.tag_to_string(h3).strip() def print_version(self, url):
self.log(current_section) return url.replace('?','?css=print&')
elif h3.get('id', None) in {'headseccol', 'headsec'}:
a = h3.find('a', href=True)
if a is not None:
title = self.tag_to_string(a)
url = a['href']
articles.append({
'title': title, 'date': '', 'url': url, 'description': ''
})
self.log('\t', title, url)
if articles:
feeds.append((current_section, articles))
return feeds

Binary file not shown.

After

Width:  |  Height:  |  Size: 527 B