1# -*- coding: utf-8 -*-
2# Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs
3# Copyright (C) 2012-2014 Bastian Kleineidam
4# Copyright (C) 2015-2020 Tobias Gruetzmacher
5# Copyright (C) 2019-2020 Daniel Ring
6
7from __future__ import absolute_import, division, print_function
8
9from ..scraper import _ParserScraper
10from ..helpers import indirectStarter, xpath_class
11
12# Common base classes for comics with the same structure (same hosting
13# software, for example) go here. Since those are shared by many modules,
14# please don't use lists of expression, as that makes it hard to track which
15# expression is for which comics.
16
17
18class _WordPressScraper(_ParserScraper):
19    imageSearch = '//div[@id="comic"]//img'
20    prevSearch = '//a[%s]' % xpath_class('comic-nav-previous')
21    nextSearch = '//a[%s]' % xpath_class('comic-nav-next')
22    latestSearch = '//a[%s]' % xpath_class('comic-nav-last')
23
24
25class _WPNavi(_WordPressScraper):
26    prevSearch = '//a[%s]' % xpath_class('navi-prev')
27
28
29class _WPNaviIn(_WordPressScraper):
30    prevSearch = '//a[%s]' % xpath_class('navi-prev-in')
31
32
33class _WPWebcomic(_WordPressScraper):
34    imageSearch = '//div[{}]//img'.format(xpath_class('webcomic-image'))
35    prevSearch = '//a[{}]'.format(xpath_class('previous-webcomic-link'))
36    nextSearch = '///a[{}]'.format(xpath_class('next-webcomic-link'))
37    latestSearch = '//a[{}]'.format(xpath_class('last-webcomic-link'))
38
39
40class _ComicControlScraper(_ParserScraper):
41    imageSearch = '//img[@id="cc-comic"]'
42    prevSearch = '//a[@rel="prev"]'
43    nextSearch = '//a[@rel="next"]'
44    latestSearch = '//a[@rel="last"]'
45
46
47class _TumblrScraper(_ParserScraper):
48    starter = indirectStarter
49
50    def namer(self, image_url, page_url):
51        # tumblr URLs: http://host/post/num/name
52        #              0    1 2    3    4   5
53        parts = page_url.split('/')
54        if len(parts) > 5:
55            return '%s_%s' % (parts[4], parts[5])
56        else:
57            return parts[4]
58
59    def shouldSkipUrl(self, url, data):
60        """Reblogged stuff is iframed"""
61        return data.xpath('//div[@id="post"]//iframe')
62