A small script to generate RSS 2.0 feeds from archiveofourown.org works.

rss_archiveofourown

#!/usr/bin/python3

# MIT License

# Copyright (c) 2018 Daniel Nunes

# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:

# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.

# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.


# USAGE
# rss_archiveofourown <id>
#
# id - The number found in the work's url after 'archiveofourown.org/works/'
#
# The built feed will be printed to stdout.
#
# There is no code to account for improper usage, you're on your own.


import requests
import sys
import xml.etree.ElementTree as etree

from bs4 import BeautifulSoup
from urllib.parse import urljoin


MAX_CHAPS = 10


work_id = sys.argv[1]
index_url = 'https://archiveofourown.org/works/{}/navigate'.format(work_id)

response = requests.get(index_url)
response.raise_for_status()
chap_soup = BeautifulSoup(response.content, features="html5lib")

new_feed = etree.Element('rss', version="2.0")
channel = etree.SubElement(new_feed, 'channel')
title = etree.SubElement(channel, 'title')
title.text = chap_soup.find('a', href='/works/{}'.format(work_id)).string
link = etree.SubElement(new_feed, 'link')
link.text = 'https://archiveofourown.org/works/{}'.format(work_id)

chap_list = chap_soup.find('ol', {'class': 'chapter index group'})
for chap in reversed(chap_list.contents):
    if not str(chap).strip():
        continue
    item = etree.SubElement(channel, 'item')
    chap_url = urljoin(index_url, chap.a['href'])
    response = requests.get(chap_url)
    response.raise_for_status()
    item_soup = BeautifulSoup(response.content, features='html5lib')

    title_div = item_soup.find('div', attrs={'class': 'chapter preface group'})
    title = etree.SubElement(item, 'title')
    title.text = "".join(title_div.h3.strings).strip()

    link = etree.SubElement(item, 'link')
    link.text = chap_url

    guid = etree.SubElement(item, 'guid', isPermaLink='false')
    guid.text = chap_url

    desc = etree.SubElement(item, 'description')
    desc_div = item_soup.find('div', attrs={'class': 'userstuff module'})
    children = desc_div.children
    desc_txt = "".join(str(child) for child in children if str(child).strip())
    desc.text = desc_txt

    MAX_CHAPS -= 1
    if MAX_CHAPS == 0:
        break

print(etree.tostring(new_feed, encoding='unicode'))