| 1 |
#!/usr/bin/env python |
| 2 |
from __future__ import absolute_import, division, print_function, unicode_literals |
| 3 |
|
| 4 |
__license__ = 'GPL v3' |
| 5 |
__copyright__ = '2018, PJ Paul' |
| 6 |
''' |
| 7 |
Recipe for Arts and Letters Daily website |
| 8 |
''' |
| 9 |
|
| 10 |
import re |
| 11 |
from datetime import date as dt |
| 12 |
from datetime import timedelta |
| 13 |
from itertools import compress |
| 14 |
|
| 15 |
from calibre.utils.date import parse_date |
| 16 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 17 |
|
| 18 |
|
| 19 |
class ALD(BasicNewsRecipe): |
| 20 |
title = 'Arts and Letters Daily' |
| 21 |
oldest_article = 7 |
| 22 |
max_articles_per_feed = 100 |
| 23 |
auto_cleanup = True |
| 24 |
recursions = 0 |
| 25 |
ignore_duplicate_articles = {'url'} |
| 26 |
index = 'https://www.aldaily.com/alt/' |
| 27 |
cover_url = 'https://www.aldaily.com/static/images/header.gif' |
| 28 |
__author__ = 'https://github.com/pjpaulpj' |
| 29 |
language = 'en' |
| 30 |
encoding = 'utf-8' |
| 31 |
browser_type = 'qt' |
| 32 |
|
| 33 |
def parse_index(self): |
| 34 |
articles_note = [] |
| 35 |
new_books = [] |
| 36 |
essays = [] |
| 37 |
feeds = [] |
| 38 |
soup = self.index_to_soup(self.index) |
| 39 |
delta = timedelta(days=self.oldest_article) |
| 40 |
now = dt.today() |
| 41 |
oldest_date = now - delta |
| 42 |
|
| 43 |
# Extract a list of dates from the page. |
| 44 |
# Subset this out to the list of target dates for extraction. |
| 45 |
date_list = [] |
| 46 |
for div in soup.findAll('div', attrs={'id': 'dayheader'}): |
| 47 |
date_list.append(self.tag_to_string(div)) |
| 48 |
date_list_clean = [re.sub(r'[^\w]', ' ', date) for date in date_list] |
| 49 |
date_list_bool = [parse_date(date).date() >= oldest_date for date in date_list_clean] |
| 50 |
compress_date = list(compress(date_list, date_list_bool)) |
| 51 |
|
| 52 |
# Process each paragraph one by one. |
| 53 |
# Stop when the text of the previous div is not in the target date list. |
| 54 |
for div in soup.findAll('div', attrs={'class': 'mobile-front'}): |
| 55 |
for p in div.findAll('p'): |
| 56 |
if self.tag_to_string(p.findPreviousSibling('div')) in compress_date: |
| 57 |
if p.find('a'): |
| 58 |
title = self.tag_to_string(p) |
| 59 |
link = p.find('a')['href'] |
| 60 |
if self.tag_to_string(p.findPreviousSibling('h3')) == 'Articles of Note': |
| 61 |
articles_note.append({'title': title, 'url': link, 'description': '', 'date': ''}) |
| 62 |
elif self.tag_to_string(p.findPreviousSibling('h3')) == 'New Books': |
| 63 |
new_books.append({'title': title, 'url': link, 'description': '', 'date': ''}) |
| 64 |
else: |
| 65 |
essays.append({'title': title, 'url': link, 'description': '', 'date': ''}) |
| 66 |
else: |
| 67 |
break |
| 68 |
feeds.append(('Articles of Note', articles_note)) |
| 69 |
feeds.append(('New Books', new_books)) |
| 70 |
feeds.append(('Essays and Opinions', essays)) |
| 71 |
return feeds |