calibre/recipes/billorielly.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

86 lines
2.8 KiB
Python

#!/usr/bin/env python
# ebook-convert.exe c:\billorielly.recipe c:\test -vv
from calibre.web.feeds.recipes import BasicNewsRecipe
class BillOReilly(BasicNewsRecipe):
cover_url = 'http://images.billoreilly.com/images/headers/borbanner.jpg'
title = u"Bill O'Reilly"
__author__ = 'Rob Lammert - rob.lammert[at]gmail.com'
description = u"Articles from Bill O'Reilly's website and his Fox New's website"
language = 'en'
oldest_article = 7.0
max_articles_per_feed = 100
recursions = 0
encoding = 'utf8'
no_stylesheets = True
remove_javascript = True
def parse_index(self):
feeds = []
articles_shows = self.bo_parse_shows(
'http://www.billoreilly.com/show?action=tvShowArchive')
articles_columns = self.bo_parse_columns(
'http://www.billoreilly.com/columns')
if articles_shows:
feeds.append(("O'Reilly Factor", articles_shows))
if articles_columns:
feeds.append(("Newspaper Column", articles_columns))
return feeds
def bo_parse_shows(self, url):
soup = self.index_to_soup(url)
links = soup.find(attrs={'class': 'showLinks'})
current_articles = []
counter = 0
for lnk in links.findAllNext(attrs={'class': ['showLinks']}):
if counter <= 5:
title = self.tag_to_string(lnk)
url = lnk.get('href', False)
if not url or not title:
continue
if url.startswith('/'):
url = 'http://www.billoreilly.com' + url + \
'&dest=/pg/jsp/community/tvshowprint.jsp'
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
current_articles.append(
{'title': title, 'url': url, 'description': '', 'date': ''})
counter += 1
return current_articles
def bo_parse_columns(self, url):
soup = self.index_to_soup(url)
links = soup.find(attrs={'id': 'bold'})
current_articles = []
counter = 0
for lnk in links.findAllNext(attrs={'id': ['bold']}):
test = lnk.get('class', False)
if counter <= 5 and test == 'defaultLinks':
title = self.tag_to_string(lnk)
url = lnk.get('href', False)
if not url or not title:
continue
if url.startswith('/'):
url = 'http://www.billoreilly.com' + url + '&printerFriendly=true"'
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
current_articles.append(
{'title': title, 'url': url, 'description': '', 'date': ''})
counter += 1
return current_articles