2020-10-01 12:11:11 +00:00
|
|
|
#!/usr/bin/env python3
|
2020-04-18 11:45:44 +00:00
|
|
|
# SPDX-License-Identifier: MIT
|
2019-06-12 07:42:06 +00:00
|
|
|
# Copyright (C) 2019-2020 Tobias Gruetzmacher
|
|
|
|
|
# Copyright (C) 2019-2020 Daniel Ring
|
|
|
|
|
"""
|
|
|
|
|
Script to get a list of WebToons comics and save the info in a
|
|
|
|
|
JSON file for further processing.
|
|
|
|
|
"""
|
2020-02-03 00:03:31 +00:00
|
|
|
from urllib.parse import urlsplit, parse_qs
|
2019-06-12 07:42:06 +00:00
|
|
|
|
|
|
|
|
from scriptutil import ComicListUpdater
|
|
|
|
|
from dosagelib.util import check_robotstxt
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class WebToonsUpdater(ComicListUpdater):
|
|
|
|
|
def collect_results(self):
|
|
|
|
|
# Parse the comic list page
|
|
|
|
|
data = self.get_url('https://www.webtoons.com/en/dailySchedule')
|
|
|
|
|
|
|
|
|
|
for comiclink in data.xpath('//a[contains(@class, "daily_card_item")]'):
|
|
|
|
|
comicurl = comiclink.attrib['href']
|
|
|
|
|
name = comiclink.xpath('.//div[@class="info"]/p[@class="subj"]')[0].text
|
|
|
|
|
try:
|
|
|
|
|
check_robotstxt(comicurl, self.session)
|
|
|
|
|
except IOError as e:
|
|
|
|
|
print('[%s] INFO: robots.txt denied: %s' % (name, e))
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
self.add_comic(name, comicurl)
|
|
|
|
|
|
|
|
|
|
def get_entry(self, name, url):
|
|
|
|
|
shortName = name.replace(' ', '')
|
|
|
|
|
titleNum = int(parse_qs(urlsplit(url).query)['title_no'][0])
|
|
|
|
|
url = url.rsplit('/', 1)[0].replace('https://www.webtoons.com/en/', '')
|
|
|
|
|
return u"cls('%s', '%s', %d)," % (shortName, url, titleNum)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
|
WebToonsUpdater(__file__).run()
|
