27d28b8eef
The default encoding for source files is UTF-8 since Python 3, so we can drop all encoding headers. While we are at it, just replace them with SPDX headers.
45 lines
1.2 KiB
Python
Executable file
45 lines
1.2 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
# SPDX-License-Identifier: MIT
|
|
# Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs
|
|
# Copyright (C) 2012-2014 Bastian Kleineidam
|
|
# Copyright (C) 2015-2017 Tobias Gruetzmacher
|
|
"""
|
|
Script to get a list of ComicSherpa and save the info in a JSON file for
|
|
further processing.
|
|
"""
|
|
|
|
from scriptutil import ComicListUpdater
|
|
|
|
|
|
class ComicSherpaUpdater(ComicListUpdater):
|
|
# names of comics to exclude
|
|
excluded_comics = (
|
|
# missing images
|
|
'Pi',
|
|
'Rufus',
|
|
|
|
# too short
|
|
'BeneathTheFerns',
|
|
'BillyAndCo',
|
|
'BuffaloChips',
|
|
'Crawdiddy',
|
|
'Gravy',
|
|
'NewFeature',
|
|
)
|
|
|
|
def collect_results(self):
|
|
"""Parse all listing pages."""
|
|
data = self.get_url('http://www.comicssherpa.com/site/home.html', expand=False)
|
|
|
|
for comiclink in data.xpath('//a[contains(@href, "site/feature")]'):
|
|
link = comiclink.attrib['href'].split('=')[1]
|
|
name = comiclink.text
|
|
self.add_comic(name, link)
|
|
|
|
def get_entry(self, name, url):
|
|
return u"cls('%s', '%s')," % (name, url)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
ComicSherpaUpdater(__file__).run()
|