fixed 16 comics

This commit is contained in:
Damjan Košir 2015-05-25 21:57:06 +12:00
parent 3edaa97fb9
commit 5569439c43
11 changed files with 21 additions and 179 deletions

View file

@ -220,16 +220,6 @@ class AmazingSuperPowers(_BasicScraper):
)
class Amya(_BasicScraper):
url = 'http://www.amyachronicles.com/'
rurl = escape(url)
stripUrl = url + 'archives/%s'
firstStripUrl = stripUrl % '117'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%sarchives/\d+)' % rurl, after="Previous"))
help = 'Index format: n'
class Angband(_BasicScraper):
url = 'http://angband.calamarain.net/'
stripUrl = url + 'view.php?date=%s'
@ -331,19 +321,3 @@ class ASkeweredParadise(_BasicScraper):
imageSearch = compile(tagre("img", "src", r'(http://aspcomics\.net/sites/default/files[^"]*/asp\d+\.jpg)[^"]+'))
prevSearch = compile(tagre("a", "href", "(/comic/\d+)")+r"[^>]+Previous")
help = 'Index format: nnn'
class AxeCop(_BasicScraper):
url = 'http://axecop.com/'
rurl = escape(url)
starter = bounceStarter(url,
(
compile(tagre("a", "href", r'(%scomic/page-\d+-[^"]+/)' % rurl, after="navi-next")),
compile(tagre("a", "href", r'(%scomic/[^"]+/)' % rurl, after="navi-next")),
)
)
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % '0'
imageSearch = compile(tagre("img", "src", r'(http://mainsite\.axecop\.wpengine\.com/wp-content/uploads/sites/\d+/\d+/\d+/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+/)' % rurl, after="navi-prev"))
help = 'Index format: usually stripname'

View file

@ -249,15 +249,6 @@ class BoyOnAStickAndSlither(_BasicScraper):
return pageUrl.rsplit('/')[-1]
class BratHalla(_BasicScraper):
url = 'http://brat-halla.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % '1-balder-dash'
imageSearch = compile(r"(/comics/.+?)' target='_blank")
prevSearch = compile(r'headernav2".+?"(http.+?)"')
help = 'Index format: number-stripname'
class BrentalFloss(_BasicScraper):
url = 'http://brentalflossthecomic.com/'
stripUrl = url + '?id=%s'

View file

@ -99,16 +99,6 @@ class CatAndGirl(_BasicScraper):
)
class Catena(_BasicScraper):
url = 'http://catenamanor.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2003/06/17/the-start-of-it-all'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'([^"]+)', after='rel="prev"'))
help = 'Index format: yyyy/mm/dd/<name>'
class CatsAndCameras(_BasicScraper):
url = 'http://catsncameras.com/cnc/'
rurl = escape(url)

View file

@ -17,11 +17,26 @@ def add(name, url, firstUrl=None, lang=None):
attrs['firstUrl'] = url + firstUrl
globals()[name] = make_scraper(name, _ParserScraper, **attrs)
add('1997', 'http://1977thecomic.com/')
add('Amya', 'http://www.amyachronicles.com/')
add('AxeCop', 'http://axecop.com/comic/season-two/')
add('BloodBound', 'http://bloodboundcomic.com/', 'comic/06112006/')
add('BratHalla', 'http://brat-halla.com/')
add('BroodHollow', 'http://broodhollow.chainsawsuit.com/', 'page/2012/10/06/book-1-curious-little-thing')
add('Catena', 'http://catenamanor.com/')
add('CourtingDisaster', 'http://www.courting-disaster.com/', 'comic/courting-disaster-17/')
add('Hipsters', 'http://www.hipsters-comic.com/', 'comic/hip01/')
add('IDreamOfAJeanieBottle', 'http://jeaniebottle.com/')
add('ItsWalky', 'http://www.itswalky.com/')
add('KatzenfutterGeleespritzer', 'http://www.katzenfuttergeleespritzer.de/', 'comics/gert-grendil/', 'de')
add('Meiosis', 'http://meiosiswebcomic.com/')
add('Melonpool', 'http://www.melonpool.com/')
add('Nedroid', 'http://nedroid.com/')
add('Nicky510', 'http://www.nickyitis.com/')
add('OnTheEdge', 'http://ontheedgecomics.com/', 'comic/ote0001/')
add('PandyLand', 'http://pandyland.net/', '1/')
add('Hipsters', 'http://www.hipsters-comic.com/', 'comic/hip01/')
add('SailorsunOrg', 'http://sailorsun.org/')
add('SlightlyDamned', 'http://www.sdamned.com/')
add('SPQRBlues', 'http://spqrblues.com/IV/')
add('TheDreamlandChronicles', 'http://www.thedreamlandchronicles.com/')
add('YAFGC', 'http://yafgc.net/')

View file

@ -27,15 +27,6 @@ class ICanBarelyDraw(_BasicScraper):
help = 'Index format: number'
class IDreamOfAJeanieBottle(_BasicScraper):
url = 'http://jeaniebottle.com/'
stripUrl = url + '?p=%s'
firstStripUrl = stripUrl % '15'
imageSearch = compile(r'(/comics/.+?)"')
prevSearch = compile(tagre("a", "href", r'(http://jeaniebottle\.com/\?p=\d+)', after="prev"))
help = 'Index format: n (unpadded)'
class InternetWebcomic(_BasicScraper):
url = 'http://www.internet-webcomic.com/'
rurl = escape(url)
@ -53,12 +44,3 @@ class IrregularWebcomic(_BasicScraper):
imageSearch = compile(r'<img .*src="(.*comics/.*(png|jpg|gif))".*>')
prevSearch = compile(r'<a href="(/\d+\.html|/cgi-bin/comic\.pl\?comic=\d+)">Previous ')
help = 'Index format: nnn'
class ItsWalky(_BasicScraper):
url = 'http://www.itswalky.com/'
stripUrl = url + 'd/%s.html'
firstStripUrl = stripUrl % '19970908'
imageSearch = compile(tagre("img", "src", r'(/comic[s|/][^"]+)'))
prevSearch = compile(tagre("a", "href", r'[^"]*(/d/\d+\.s?html)')+r"[^>]+/images/(?:nav_02|previous_day)\.gif")
help = 'Index format: yyyymmdd'

View file

@ -111,16 +111,6 @@ class MegaTokyo(_BasicScraper):
help = 'Index format: nnnn'
class Meiosis(_BasicScraper):
url = 'http://meiosiswebcomic.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2006/10/10142006'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="navi-prev"))
help = 'Index format: yyyy/mm/ddmmyyyy'
class MenageA3(_BasicScraper):
adult = True
url = 'http://www.ma3comic.com/'
@ -130,16 +120,6 @@ class MenageA3(_BasicScraper):
help = 'Index format: name'
class Melonpool(_BasicScraper):
url = 'http://www.melonpool.com/'
rurl = escape(url)
stripUrl = url + '?p=%s'
firstStripUrl = stripUrl % '41'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
help = 'Index format: n'
class Misfile(_BasicScraper):
url = 'http://www.misfile.com/'
stripUrl = url + '?date=%s'

View file

@ -47,16 +47,6 @@ class NatalieDee(_BasicScraper):
return '%s-%s' % (date, filename)
class Nedroid(_BasicScraper):
url = 'http://nedroid.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2005/09/2210-whee'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/[^"]+)' % rurl, after="prev"))
help = 'Index format: yyyy/mm/dd/name'
class NeoEarth(_BasicScraper):
url = 'http://www.neo-earth.com/NE/'
stripUrl = url + 'index.php?date=%s'
@ -82,16 +72,6 @@ class NewWorld(_BasicScraper):
help = 'Index format: yyyy/mm/dd/stripn'
class Nicky510(_BasicScraper):
url = 'http://www.nickyitis.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % 'close-enough'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl, after="Previous"))
help = 'Index format: stripname'
class NekkoAndJoruba(_BasicScraper):
url = 'http://www.nekkoandjoruba.com/'
stripUrl = url + '?p=%s'

View file

@ -6,14 +6,3 @@ from re import compile, escape
from ..util import tagre
from ..scraper import _BasicScraper
class NineteenNinetySeven(_BasicScraper):
name = '1997'
url = 'http://1977thecomic.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '1977-comics/from-the-beginning-part-1'
imageSearch = compile(tagre("img", "src", r'(%scomics-1977/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'([^"]+)')+"Previous")
help = 'Index format: yyyy/mm/dd/strip-name'

View file

@ -27,6 +27,7 @@ class SabrinaOnline(_BasicScraper):
archivepages = search.findall(data)
return cls.url + archivepages[-1]
class SafelyEndangered(_BasicScraper):
url = 'http://www.safelyendangered.com/'
stripUrl = url + 'comic/%s'
@ -36,15 +37,6 @@ class SafelyEndangered(_BasicScraper):
textSearch = compile(tagre("img", "title", r'([^"]+)', before=r'http://www\.safelyendangered\.com/wp-content/uploads'))
help = 'Index format: yyyy/mm/stripname'
class SailorsunOrg(_BasicScraper):
url = 'http://sailorsun.org/'
rurl = escape(url)
stripUrl = url + '?p=%s'
firstStripUrl = stripUrl % '21'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
help = 'Index format: n (unpadded)'
class SamAndFuzzy(_BasicScraper):
url = 'http://www.samandfuzzy.com/'
@ -54,6 +46,7 @@ class SamAndFuzzy(_BasicScraper):
prevSearch = compile(r'"><a href="(.+?)"><img src="imgint/nav_prev.gif"')
help = 'Index format: nnnn'
class SandraOnTheRocks(_BasicScraper):
url = 'http://www.sandraontherocks.com/'
stripUrl = url + 'strips-sotr/%s'
@ -62,6 +55,7 @@ class SandraOnTheRocks(_BasicScraper):
prevSearch = compile(tagre("a", "href", r'([^"]*/strips-sotr/[^"]+)', before="cn[id]prev"))
help = 'Index format: name'
class ScandinaviaAndTheWorld(_BasicScraper):
url = 'http://satwcomic.com/'
rurl = escape(url)
@ -71,6 +65,7 @@ class ScandinaviaAndTheWorld(_BasicScraper):
prevSearch = compile(tagre("a", "href", r'(%s[^"/]+)' % rurl)+"\s*"+tagre('span', 'class', 'spritePrevious'))
help = 'Index format: stripname'
class ScaryGoRound(_BasicScraper):
url = 'http://www.scarygoround.com/'
stripUrl = url + '?date=%s'
@ -260,16 +255,6 @@ class SkinDeep(_BasicScraper):
help = 'Index format: custom'
class SlightlyDamned(_BasicScraper):
url = 'http://www.sdamned.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2004/03/03142004'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
help = 'Index format: yyyy/mm/number'
class SluggyFreelance(_BasicScraper):
url = 'http://www.sluggy.com/'
stripUrl = url + 'comics/archives/daily/%s'
@ -432,16 +417,6 @@ class Spinnerette(_BasicScraper):
help = 'Index format: number'
class SPQRBlues(_BasicScraper):
url = 'http://spqrblues.com/IV/'
rurl = escape(url)
stripUrl = url + '?p=%s'
firstStripUrl = stripUrl % '1467'
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+\.png)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
help = 'Index format: number'
class StandStillStaySilent(_ParserScraper):
url = 'http://www.sssscomic.com/comic.php'
rurl = escape(url)

View file

@ -27,25 +27,6 @@ class TheDevilsPanties(_BasicScraper):
help = 'Index format: number'
class TheDreamlandChronicles(_BasicScraper):
url = 'http://www.thedreamlandchronicles.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'page-1'
rurl = escape(url)
imageSearch = compile(tagre("img", "src", r'(http://www\.thedreamlandchronicles\.com/wp-content/uploads/\d+/\d+/\d+-\d+-\d+[^"]*)'))
prevSearch = compile(tagre("a", "href", r'(%s[^"]*)' % rurl, after='navi-prev"'))
help = 'Index format: page-n or chapter-n'
@classmethod
def namer(cls, imageUrl, pageUrl):
"""Remove trailing digit from day number."""
name = imageUrl.split('/')[-1]
base, ext = name.split('.', 1)
bp = base.split('-')
if len(bp[2]) == 3:
bp[2] = bp[2][:-1]
return "%s-%s-%s.%s" % (bp[0], bp[1], bp[2], ext)
class TheGamerCat(_ParserScraper):
url = "http://www.thegamercat.com/"
stripUrl = url + "comic/%s/"

View file

@ -5,18 +5,3 @@
from re import compile
from ..scraper import _BasicScraper
from ..util import tagre
class YAFGC(_BasicScraper):
url = 'http://yafgc.net/'
stripUrl = url + '?id=%s'
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'(http://(?:www\.)?yafgc\.net/img/comic/\d+\.jpg)'))
prevSearch = compile(tagre("a", "href", r'(http://(?:www\.)?yafgc\.net/\?id=\d+)') +
tagre("img", "src", r'/img/navbar/go_to_previous\.gif'))
help = 'Index format: number'
@classmethod
def prevUrlModifier(cls, prevUrl):
if prevUrl:
return prevUrl.replace("www.yafgc.net", "yafgc.net")