dosage/dosagelib/plugins/common.py

54 lines
1.7 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
2016-10-28 22:21:41 +00:00
# Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs
# Copyright (C) 2012-2014 Bastian Kleineidam
2017-02-13 21:41:17 +00:00
# Copyright (C) 2015-2017 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function
from ..scraper import _ParserScraper
2017-02-13 21:41:17 +00:00
from ..helpers import indirectStarter, xpath_class
# Common base classes for comics with the same structure (same hosting
# software, for example) go here. Since those are shared by many modules,
# please don't use lists of expression, as that makes it hard to track which
# expression is for which comics.
class _WordPressScraper(_ParserScraper):
imageSearch = '//div[@id="comic"]//img'
2017-05-21 23:17:05 +00:00
prevSearch = '//a[%s]' % xpath_class('comic-nav-previous')
nextSearch = '//a[%s]' % xpath_class('comic-nav-next')
latestSearch = '//a[%s]' % xpath_class('comic-nav-last')
2017-05-21 23:17:05 +00:00
class _WPNavi(_WordPressScraper):
prevSearch = '//a[%s]' % xpath_class('navi-prev')
class _WPNaviIn(_WordPressScraper):
prevSearch = '//a[%s]' % xpath_class('navi-prev-in')
class _ComicControlScraper(_ParserScraper):
imageSearch = '//img[@id="cc-comic"]'
prevSearch = '//a[@rel="prev"]'
2019-06-21 07:54:45 +00:00
nextSearch = '//a[@rel="next"]'
latestSearch = '//a[@rel="last"]'
2016-05-06 23:50:10 +00:00
class _TumblrScraper(_ParserScraper):
starter = indirectStarter
def namer(self, image_url, page_url):
# tumblr URLs: http://host/post/num/name
# 0 1 2 3 4 5
parts = page_url.split('/')
if len(parts) > 5:
return '%s_%s' % (parts[4], parts[5])
else:
return parts[4]
def shouldSkipUrl(self, url, data):
"""Reblogged stuff is iframed"""
return data.xpath('//div[@id="post"]//iframe')