| 1 |
#!/usr/bin/env python |
| 2 |
|
| 3 |
# ebook-convert.exe c:\billorielly.recipe c:\test -vv |
| 4 |
|
| 5 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 6 |
|
| 7 |
|
| 8 |
class BillOReilly(BasicNewsRecipe): |
| 9 |
cover_url = 'http://images.billoreilly.com/images/headers/borbanner.jpg' |
| 10 |
title = "Bill O'Reilly" |
| 11 |
__author__ = 'Rob Lammert - rob.lammert[at]gmail.com' |
| 12 |
description = "Articles from Bill O'Reilly's website and his Fox New's website" |
| 13 |
language = 'en' |
| 14 |
oldest_article = 7.0 |
| 15 |
max_articles_per_feed = 100 |
| 16 |
recursions = 0 |
| 17 |
encoding = 'utf8' |
| 18 |
no_stylesheets = True |
| 19 |
remove_javascript = True |
| 20 |
|
| 21 |
def parse_index(self): |
| 22 |
feeds = [] |
| 23 |
|
| 24 |
articles_shows = self.bo_parse_shows('http://www.billoreilly.com/show?action=tvShowArchive') |
| 25 |
articles_columns = self.bo_parse_columns('http://www.billoreilly.com/columns') |
| 26 |
|
| 27 |
if articles_shows: |
| 28 |
feeds.append(("O'Reilly Factor", articles_shows)) |
| 29 |
|
| 30 |
if articles_columns: |
| 31 |
feeds.append(('Newspaper Column', articles_columns)) |
| 32 |
|
| 33 |
return feeds |
| 34 |
|
| 35 |
def bo_parse_shows(self, url): |
| 36 |
soup = self.index_to_soup(url) |
| 37 |
links = soup.find(attrs={'class': 'showLinks'}) |
| 38 |
|
| 39 |
current_articles = [] |
| 40 |
counter = 0 |
| 41 |
for lnk in links.findAllNext(attrs={'class': ['showLinks']}): |
| 42 |
if counter <= 5: |
| 43 |
title = self.tag_to_string(lnk) |
| 44 |
url = lnk.get('href', False) |
| 45 |
|
| 46 |
if not url or not title: |
| 47 |
continue |
| 48 |
|
| 49 |
if url.startswith('/'): |
| 50 |
url = 'http://www.billoreilly.com' + url + '&dest=/pg/jsp/community/tvshowprint.jsp' |
| 51 |
|
| 52 |
self.log('\t\tFound article:', title) |
| 53 |
self.log('\t\t\t', url) |
| 54 |
current_articles.append({'title': title, 'url': url, 'description': '', 'date': ''}) |
| 55 |
counter += 1 |
| 56 |
return current_articles |
| 57 |
|
| 58 |
def bo_parse_columns(self, url): |
| 59 |
soup = self.index_to_soup(url) |
| 60 |
links = soup.find(attrs={'id': 'bold'}) |
| 61 |
|
| 62 |
current_articles = [] |
| 63 |
counter = 0 |
| 64 |
for lnk in links.findAllNext(attrs={'id': ['bold']}): |
| 65 |
test = lnk.get('class', False) |
| 66 |
if counter <= 5 and test == 'defaultLinks': |
| 67 |
title = self.tag_to_string(lnk) |
| 68 |
url = lnk.get('href', False) |
| 69 |
|
| 70 |
if not url or not title: |
| 71 |
continue |
| 72 |
|
| 73 |
if url.startswith('/'): |
| 74 |
url = 'http://www.billoreilly.com' + url + '&printerFriendly=true"' |
| 75 |
|
| 76 |
self.log('\t\tFound article:', title) |
| 77 |
self.log('\t\t\t', url) |
| 78 |
current_articles.append({'title': title, 'url': url, 'description': '', 'date': ''}) |
| 79 |
counter += 1 |
| 80 |
return current_articles |