dosage/scripts/creators.py

45 lines
1.3 KiB
Python
Raw Normal View History

#!/usr/bin/env python
2016-04-06 22:20:03 +00:00
# -*- coding: utf-8 -*-
2014-01-05 15:50:57 +00:00
# Copyright (C) 2012-2014 Bastian Kleineidam
2016-04-06 22:20:03 +00:00
# Copyright (C) 2015-2016 Tobias Gruetzmacher
"""
2016-04-06 22:20:03 +00:00
Script to get a list of creators.com comics and save the info in a JSON file
for further processing.
"""
2016-04-06 22:20:03 +00:00
from __future__ import absolute_import, division, print_function
from scriptutil import ComicListUpdater
2016-04-06 22:20:03 +00:00
class CreatorsUpdater(ComicListUpdater):
dup_templates = ('GoComics/%s',)
# names of comics to exclude
excluded_comics = (
# no images
'Doodles',
)
def handle_url(self, url):
"""Parse one listing page."""
data = self.get_url(url)
for comicdiv in data.cssselect('ul.all-test li'):
comiclink = comicdiv.cssselect('a')[0]
comicurl = comiclink.attrib['href']
name = comicdiv.cssselect('p strong')[0].text
2016-04-06 22:20:03 +00:00
self.add_comic(name, comicurl.rsplit('/', 1)[1])
2016-04-06 22:20:03 +00:00
def collect_results(self):
"""Parse all search result pages."""
self.handle_url('https://www.creators.com/categories/comics/all')
self.handle_url('https://www.creators.com/categories/cartoons/all')
def get_entry(self, name, path):
langopt = ", 'es'" if name.lower().endswith('spanish') else ''
return u"cls('%s', '%s'%s)," % (name, path, langopt)
if __name__ == '__main__':
CreatorsUpdater(__file__).run()