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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
# 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 .. import util
from ..helpers import bounceStarter, indirectStarter
from ..scraper import ParserScraper, _ParserScraper
from .common import ComicControlScraper, WordPressScraper
class Lancer(WordPressScraper):
url = 'https://lancercomic.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'chapter-1-cover'
class LastResort(WordPressScraper):
url = 'http://www.lastres0rt.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'that-sound-you-hear-is-a-shattered-stereotype'
class LazJonesAndTheMayfieldRegulators(_ParserScraper):
baseUrl = 'https://www.lazjones.com/'
url = baseUrl + 'regulators'
stripUrl = baseUrl + 'comic/%s'
firstStripUrl = stripUrl % 'chapter1_00'
imageSearch = '//img[contains(@src, "comic/pages/")]'
prevSearch = '//a[contains(text(), "Previous")]'
class LazJonesAndTheMayfieldRegulatorsSideStories(LazJonesAndTheMayfieldRegulators):
name = 'LazJonesAndTheMayfieldRegulators/SideStories'
baseUrl = 'https://www.lazjones.com/'
url = baseUrl + 'comics'
stripUrl = baseUrl + 'comic/%s'
firstStripUrl = stripUrl % 'journal01'
def getPrevUrl(self, url, data):
# Fix broken navigation links
if url == self.url and self.match(data, self.prevSearch + '/@href')[0] == self.stripUrl % 'summer00':
return self.stripUrl % 'summer21'
return super(LazJonesAndTheMayfieldRegulators, self).getPrevUrl(url, data)
class LeastICouldDo(ParserScraper):
url = 'https://leasticoulddo.com/'
stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % '20030210'
imageSearch = '//div[d:class("single-post-comic")]//img'
prevSearch = '//a[@rel="prev"]'
latestSearch = '//a[contains(@href, "/comic/")]'
starter = indirectStarter
help = 'Index format: yyyymmdd'
class LetsSpeakEnglish(ComicControlScraper):
url = 'http://www.marycagle.com'
class LifeAintNoPonyFarm(WordPressScraper):
url = ('https://web.archive.org/web/20181221154155/'
'http://sarahburrini.com/en/')
firstStripUrl = url + 'comic/my-first-webcomic/'
multipleImagesPerStrip = True
endOfLife = True
class LifeAsRendered(ParserScraper):
# Reverse navigation doesn't work properly, so search forward instead
stripUrl = 'https://kittyredden.com/LAR/%s/'
url = stripUrl % '0100'
firstStripUrl = stripUrl % '05extra'
imageSearch = '//figure[@class="wp-block-image"]//img'
prevSearch = '//a[img[@alt="Next"]]'
textSearch = '//div[@class="entry-content"]//text()'
adult = True
endOfLife = True
nav = {
'0140': '0200',
'0272': '02ss00',
'02SS14': '0300',
'0367': '03ss00',
'03ss10': '0400',
'0408': '0409',
'0409': '0410',
'0421': '0422',
'0449': '0450',
'0458': '0460',
'0460': '04ss00',
'04ss00': '04ss01',
'04ss10': '0500',
'0500': '0501',
'0508': '0509',
'0558': '0559',
'0577': '05extra',
}
def namer(self, image_url, page_url):
# Fix inconsistent filenames
filename = util.urlpathsplit(image_url)[-1]
return filename.replace('ReN', 'N').replace('N01P', 'A02S')
def extract_image_urls(self, url, data):
# Fix missing image link
if 'LAR/0403' in url:
return [self.stripUrl.rstrip('/') % 'A04/A04P03.png']
return super().extract_image_urls(url, data)
def getPrevUrl(self, url, data):
# Fix broken navigation links
page = util.urlpathsplit(url)[-1]
if page in self.nav:
return self.stripUrl % self.nav[page]
return super().getPrevUrl(url, data)
def fetchText(self, url, data, textSearch, optional):
# Save final summary text
if url == self.firstStripUrl:
url = self.stripUrl % 'the-end'
data = self.getPage(url)
return super().fetchText(url, data, textSearch, optional)
return None
class LilithsWord(ComicControlScraper):
url = 'https://www.lilithword.com/'
stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % 'prologue-page-00'
def namer(self, image_url, page_url):
return util.urlpathsplit(image_url)[-1].split('-', 1)[1]
class LittleGamers(ParserScraper):
url = 'https://www.little-gamers.com/'
firstStripUrl = url + '2000/12/01/99'
imageSearch = '//div[d:class("comic")]//img'
prevSearch = ('//a[@id="previous"]',
'//div[d:class("comic-navigation")]//a[text()="previous"]')
class LittleTales(_ParserScraper):
url = 'http://www.little-tales.com/'
stripUrl = url + 'index.php?Strip=%s'
firstStripUrl = stripUrl % '1'
url = stripUrl % '450'
imageSearch = '//img[contains(@src, "strips/")]'
prevSearch = '//a[./img[@alt="BACK"]]'
nextSearch = '//a[./img[@alt="FORWARD"]]'
starter = bounceStarter
nav = {
'517': '515',
'449': '447',
}
def namer(self, imageUrl, pageUrl):
page = pageUrl.rsplit('=', 1)[-1]
ext = imageUrl.rsplit('.', 1)[-1]
return page + '.' + ext
def getPrevUrl(self, url, data):
# Skip missing pages with broken navigation links
page = url.rsplit('=', 1)[1]
if page in self.nav:
return self.stripUrl % self.nav[page]
return super(LittleTales, self).getPrevUrl(url, data)
class LoadingArtist(_ParserScraper):
url = 'https://loadingartist.com/'
firstStripUrl = url + 'comic/born/'
imageSearch = '//div[d:class("main-image-container")]//img'
prevSearch = '//div[d:class("left-nav")]//a'
latestSearch = '//nav//a[text()="Comic"]'
starter = indirectStarter
class LoFiJinks(WordPressScraper):
baseUrl = 'https://hijinksensue.com/comic/'
url = baseUrl + 'learning-to-love-again/'
firstStripUrl = baseUrl + 'lo-fijinks-everything-i-know-anout-james-camerons-avatar-movie/'
endOfLife = True
class LookingForGroup(ParserScraper):
url = 'https://www.lfg.co/'
stripUrl = url + 'page/%s/'
firstStripUrl = stripUrl % '1'
imageSearch = '//div[@id="comic-img"]//img'
prevSearch = '//a[d:class("comic-nav-prev")]'
latestSearch = '//div[@id="feature-lfg-footer"]/a[contains(@href, "page/")]'
starter = indirectStarter
help = 'Index format: nnn'
def namer(self, imageUrl, pageUrl):
page = util.urlpathsplit(pageUrl)[-1]
return page.replace('2967', '647')
|
