| 1 |
__license__ = 'GPL v3' |
| 2 |
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>' |
| 3 |
''' |
| 4 |
odb.org |
| 5 |
''' |
| 6 |
|
| 7 |
import uuid |
| 8 |
|
| 9 |
from lxml import html |
| 10 |
|
| 11 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 12 |
|
| 13 |
|
| 14 |
class OurDailyBread(BasicNewsRecipe): |
| 15 |
title = 'Our Daily Bread' |
| 16 |
__author__ = 'Kovid Goyal' |
| 17 |
description = "Our Daily Bread is a daily devotional from RBC Ministries which helps readers spend time each day in God's Word." |
| 18 |
oldest_article = 15 |
| 19 |
language = 'en' |
| 20 |
max_articles_per_feed = 100 |
| 21 |
no_stylesheets = True |
| 22 |
use_embedded_content = False |
| 23 |
encoding = 'utf-8' |
| 24 |
|
| 25 |
conversion_options = {'comments': description, 'language': language, 'linearize_tables': True} |
| 26 |
|
| 27 |
keep_only_tags = [dict(attrs={'class': 'calibre-inserted-psalm'}), {'id': 'content'}] |
| 28 |
remove_tags = [ |
| 29 |
dict(attrs={'class': ['listen-box', 'entry-zoom', 'entry-footer']}), |
| 30 |
{'id': 'nav-single'}, |
| 31 |
dict(attrs={'class': lambda x: x and ' sharing ' in x}), |
| 32 |
] |
| 33 |
|
| 34 |
extra_css = ''' |
| 35 |
.text{font-family:Arial,Helvetica,sans-serif;font-size:x-small;} |
| 36 |
.devotionalTitle{font-family:Arial,Helvetica,sans-serif; font-size:large; font-weight: bold;} |
| 37 |
.devotionalDate{font-family:Arial,Helvetica,sans-serif; font-size:xx-small;} |
| 38 |
.devotionalVerse{font-family:Arial,Helvetica,sans-serif; font-size:xx-small; } |
| 39 |
a{color:#000000;font-family:Arial,Helvetica,sans-serif; font-size:x-small;} |
| 40 |
''' |
| 41 |
|
| 42 |
feeds = [('Our Daily Bread', 'http://odb.org/feed/')] |
| 43 |
|
| 44 |
def preprocess_raw_html(self, raw, url): |
| 45 |
# Convert links to referenced Psalms to the actual psalms |
| 46 |
root = html.fromstring(raw) |
| 47 |
for a in root.xpath('//a[starts-with(@href, "http://www.biblegateway.com")]'): |
| 48 |
uid = type('')(uuid.uuid4()) |
| 49 |
raw = self.index_to_soup(a.get('href'), raw=True) |
| 50 |
iroot = html.fromstring(raw) |
| 51 |
matches = iroot.xpath('//div[contains(@class, "result-text-style-normal")]') |
| 52 |
if matches: |
| 53 |
div = matches[0] |
| 54 |
div.getparent().remove(div) |
| 55 |
root.xpath('//body')[0].append(div) |
| 56 |
a.set('href', '#' + uid) |
| 57 |
del a.attrib['target'] |
| 58 |
div.set('id', uid) |
| 59 |
div.set('class', 'calibre-inserted-psalm') |
| 60 |
hr = div.makeelement('hr') |
| 61 |
div.insert(0, hr) |
| 62 |
# print(html.tostring(div)) |
| 63 |
raw = html.tostring(root, encoding='unicode') |
| 64 |
return raw |
| 65 |
|
| 66 |
def preprocess_html(self, soup): |
| 67 |
d = soup.find(id='content') |
| 68 |
d.extract() |
| 69 |
soup.find('body').insert(0, d) |
| 70 |
return soup |