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
|
#!/usr/bin/env python3
# SPDX-License-Identifier: MIT
# SPDX-FileCopyrightText: © 2004 Tristan Seligmann and Jonathan Jacobs
# SPDX-FileCopyrightText: © 2012 Bastian Kleineidam
# SPDX-FileCopyrightText: © 2015 Tobias Gruetzmacher
"""
Script to get ComicFury comics and save the info in a JSON file for further
processing.
"""
import sys
from urllib.parse import urlsplit
import scriptutil
class ComicFuryUpdater(scriptutil.ComicListUpdater):
# Absolute minumum number of pages a comic may have (restrict search space)
MIN_COMICS = 90
dup_templates = ('ComicSherpa/%s', 'Creators/%s', 'GoComics/%s',
'KeenSpot/%s', 'Arcamax/%s')
langmap = {
'german': 'de',
'spanish': 'es',
'italian': 'it',
'japanese': 'ja',
'french': 'fr',
'portuguese': 'pt',
}
# names of comics to exclude
excluded_comics = (
# unsuitable navigation
"AlfdisAndGunnora",
"AnAmericanNerdInAnimatedTokyo",
"AngryAlien",
"BoozerAndStoner",
"Bonejangles",
"ConradStory",
"Crossing",
"ChristianHumberReloaded",
"CorkAndBlotto",
"Democomix",
"ErraticBeatComics",
"EnergyWielders",
"EvilBearorg",
"Fiascos",
"FateOfTheBlueStar",
"FPK",
"Fanartgyle",
"FrigginRandom",
"GoodbyeKitty",
"GoodSirICannotDraw",
"HighlyExperiMental",
"IfAndCanBeFlowers",
"JournalismStory",
"JohnsonSuperior",
"Keel",
"JudgeDredBasset",
"LomeathAndHuilii",
"MNPB",
"LucidsDream",
"MadDog",
"Minebreakers",
"MoonlightValley",
"MyImmortalFool",
"NATO",
"NothingFits",
"OptimisticFishermenAndPessimisticFishermen",
"Old2G",
"NothingFitsArtBlog",
"OutToLunchTheStingRayWhoreStory",
"Pandemonium",
"Pewfell",
"ProjectX",
"Ratantia",
"RealLifeTrips",
"Sandgate",
"Secondpuberty",
"Seconds",
"SlightlyEccentricOrigins",
"StardustTheCat",
"StrangerThanFiction",
"TalamakGreatAdventure",
"TheBattalion",
"TheBends",
"TheDailyProblem",
"TheMansionOfE",
"ThePainter",
"TheSeekers",
"TheTrialsOfKlahadOfTheAbyss",
"TheStickmen",
"ThornsInOurSide",
"TopHeavyVeryBustyPinUpsForAdults",
"USBUnlimitedSimulatedBody",
"TylerHumanRecycler",
"UAF",
"WhenPigsFly",
"YeOldeLegotimeTheatre",
# no content
"Angst",
"TheDevonLegacyPrologue",
# images gone
"BaseballCapsAndTiaras",
"BiMorphon",
"CROSSWORLDSNEXUS",
"DevilSpy",
"Fathead",
"GOODBYEREPTILIANS",
"KevinZombie",
"KindergardenCrisIs",
"NoSongsForTheDead",
"RequiemShadowbornPariah",
"SandboxDrama",
"STICKFODDER",
"TezzleAndZeek",
"TheRealmOfKaerwyn",
# broken HTML
"CrossingOver",
# unique html
"IKilledTheHero",
"PowerOfPower",
"Schizmatic",
"WakeTheSleepers",
"WeightOfEternity",
# moved
"OopsComicAdventure",
)
def handle_url(self, url):
"""Parse one search result page."""
data = self.get_url(url)
for comicdiv in self.xpath(data, '//div[d:class("webcomic-result")]'):
comiclink = self.xpath(comicdiv, './div[d:class("webcomic-result-title")]/a')[0]
comicurl = comiclink.attrib['href']
name = comiclink.text
info = self.xpath(comicdiv, './/span[d:class("stat-value")]')
# find out how many images this comic has
count = int(info[0].text.strip())
self.add_comic(name, comicurl, count)
nextlink = self.xpath(data, '//div[d:class("search-next-page")]/a')
if nextlink:
return nextlink[0].attrib['href']
else:
return None
def collect_results(self):
"""Parse all search result pages."""
# Sort by page count, so we can abort when we get under some threshold.
url = ('https://comicfury.com/search.php?query=&lastupdate=0&' +
'completed=1&fn=2&fv=2&fs=2&fl=2&sort=0')
print("Parsing search result pages...", file=sys.stderr)
while url:
url = self.handle_url(url)
def get_entry(self, name, entry):
url = entry
sub = urlsplit(url).hostname.split('.', 1)[0]
return f"cls('{name}', '{sub}'),"
if __name__ == '__main__':
ComicFuryUpdater(__file__).run()
|
