dosage/scripts/gocomics.py

44 lines
1.4 KiB
Python
Raw Normal View History

#!/usr/bin/env python3
# SPDX-License-Identifier: MIT
2016-10-28 22:21:41 +00:00
# Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs
2016-04-12 22:52:16 +00:00
# Copyright (C) 2012-2014 Bastian Kleineidam
2020-04-19 23:03:30 +00:00
# Copyright (C) 2015-2020 Tobias Gruetzmacher
"""
2016-04-12 22:52:16 +00:00
Script to get a list of gocomics and save the info in a JSON file for further
processing.
"""
from scriptutil import ComicListUpdater
class GoComicsUpdater(ComicListUpdater):
# names of comics to exclude
2016-11-01 01:51:00 +00:00
excluded_comics = (
# too short
'LukeyMcGarrysTLDR',
2016-11-01 01:51:00 +00:00
)
2020-04-19 23:03:30 +00:00
def handle_gocomics(self, url, outercss='a.gc-blended-link', lang=None):
"""Parse one GoComics alphabetic page."""
2016-04-14 22:26:14 +00:00
data = self.get_url(url, expand=False)
for comiclink in data.cssselect(outercss):
2020-04-19 23:03:30 +00:00
link = comiclink.attrib['href'].split('/')[1]
name = comiclink.cssselect('h4')[0].text
self.add_comic(name, (link, lang))
def collect_results(self):
"""Parse all listing pages."""
2020-04-19 23:03:30 +00:00
self.handle_gocomics('http://www.gocomics.com/comics/a-to-z')
self.handle_gocomics('http://www.gocomics.com/comics/espanol', lang='es')
self.handle_gocomics('http://www.gocomics.com/comics/espanol?page=2', lang='es')
def get_entry(self, name, data):
url, lang = data
langopt = ", '%s'" % lang if lang else ''
2020-04-19 23:03:30 +00:00
return u"cls('%s', '%s'%s)," % (name, url, langopt)
if __name__ == '__main__':
GoComicsUpdater(__file__).run()