1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
|
# SPDX-License-Identifier: MIT
# SPDX-FileCopyrightText: © 2004 Tristan Seligmann and Jonathan Jacobs
# SPDX-FileCopyrightText: © 2012 Bastian Kleineidam
# SPDX-FileCopyrightText: © 2015 Tobias Gruetzmacher
# SPDX-FileCopyrightText: © 2019 Daniel Ring
from re import compile, escape
from .. import util
from ..helpers import bounceStarter, indirectStarter, joinPathPartsNamer
from ..scraper import BasicScraper, ParserScraper
from ..util import tagre
from .common import ComicControlScraper, WordPressNaviIn, WordPressScraper
class Hackles(ParserScraper):
url = ('https://web.archive.org/web/20220128022158/'
'http://hackles.org/')
stripUrl = url + 'cgi-bin/archives.pl?request=%s'
firstStripUrl = stripUrl % '1'
imageSearch = '//img[contains(@src, "strips/")]'
prevSearch = '//a[text()="< previous"]'
endOfLife = True
class HagarTheHorrible(BasicScraper):
url = 'http://www.hagarthehorrible.net/'
stripUrl = 'http://www.hagardunor.net/comicstrips_us.php?serietype=9&colortype=1&serieno=%s'
firstStripUrl = stripUrl % '1'
multipleImagesPerStrip = True
imageSearch = compile(tagre("img", "src", r'(stripus\d+/(?:Hagar_The_Horrible_?|h)\d+[^ >]+)', quote=""))
prevUrl = r'(comicstrips_us\.php\?serietype\=9\&colortype\=1\&serieno\=\d+)'
prevSearch = compile(tagre("a", "href", prevUrl, after="Previous"))
help = 'Index format: number'
def starter(self):
"""Return last gallery link."""
url = 'http://www.hagardunor.net/comics.php'
data = self.getPage(url)
pattern = compile(tagre("a", "href", self.prevUrl))
return self.fetchUrls(url, data, pattern)[-1]
class HarkAVagrant(BasicScraper):
url = 'http://www.harkavagrant.com/'
rurl = escape(url)
starter = bounceStarter
stripUrl = url + 'index.php?id=%s'
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'(%s[^"]+)' % rurl,
after='BORDER'))
prevSearch = compile(tagre("a", "href", r'(%sindex\.php\?id=\d+)' % rurl) +
tagre("img", "src", "buttonprevious.png"))
nextSearch = compile(tagre("a", "href", r'(%sindex\.php\?id=\d+)' % rurl) +
tagre("img", "src", "buttonnext.png"))
help = 'Index format: number'
def namer(self, image_url, page_url):
filename = util.urlpathsplit(image_url)[-1]
num = page_url.rsplit('=', 1)[1]
return f'{num}-{filename}'
class HavocInc(WordPressScraper):
url = 'http://www.radiocomix.com/havoc-inc/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'havoc-cover'
class HeadlessBliss(ComicControlScraper):
url = 'http://headlessbliss.com/'
class Hellkats(ParserScraper):
url = 'https://poecatcomix.com/hellkatscomic/'
stripUrl = url + '%s/'
firstStripUrl = stripUrl % 'hellkats-issue-1-cover'
imageSearch = '//img[@class="scale-with-grid wp-post-image"]'
prevSearch = '//a[d:class("fixed-nav-prev")]'
latestSearch = '//div[@class="post-title"]//a'
starter = indirectStarter
adult = True
namer = joinPathPartsNamer(pageparts=(-2,))
class HeyFox(WordPressScraper):
url = 'http://www.steamclaw.com/heyfox/'
stripUrl = url + 'archives/comic/%s'
firstStripUrl = stripUrl % '11092004'
adult = True
class HeyKitty(WordPressScraper):
url = 'http://heykittycomic.com/'
stripUrl = url + '?comic=%s'
firstStripUrl = stripUrl % 'it-begins'
class Hipsters(WordPressScraper):
url = 'http://www.hipsters-comic.com/'
firstStripUrl = 'http://www.hipsters-comic.com/comic/hip01/'
class HijinksEnsue(WordPressNaviIn):
url = 'http://hijinksensue.com/'
latestSearch = '//a[text()="Latest HijiNKS ENSUE"]'
firstStripUrl = 'http://hijinksensue.com/comic/who-is-your-daddy-and-what-does-he-do/'
starter = indirectStarter
class HijinksEnsueClassic(WordPressNaviIn):
url = 'http://hijinksensue.com/comic/open-your-eyes/'
firstStripUrl = 'http://hijinksensue.com/comic/a-soul-as-black-as-eyeliner/'
endOfLife = True
class HijinksEnsueConvention(WordPressNaviIn):
url = 'http://hijinksensue.com/comic/emerald-city-comicon-2015-fancy-sketches-part-4/'
firstStripUrl = 'http://hijinksensue.com/comic/whatever-dad-im-outta-here/'
endOfLife = True
class HijinksEnsuePhoto(WordPressNaviIn):
url = 'http://hijinksensue.com/comic/emerald-city-comicon-2015-fancy-photo-comic-part-2/'
firstStripUrl = 'http://hijinksensue.com/comic/san-diego-comic-con-fancy-picto-comic-pt-1/'
endOfLife = True
class HowToBeAWerewolf(ComicControlScraper):
url = 'https://www.howtobeawerewolf.com/'
stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % 'coming-february-3rd'
def namer(self, image_url, page_url):
filename = util.urlpathsplit(image_url)[-1]
if filename[0].isdigit():
filename = filename.split('-', 1)[1]
return filename
|
