Added some comics.

This commit is contained in:
Bastian Kleineidam 2013-02-06 22:08:36 +01:00
parent 137e30b3ac
commit c19cb93a14
8 changed files with 143 additions and 4 deletions

View file

@ -2,7 +2,10 @@ Dosage 1.10 (released xx.xx.2013)
Features: Features:
- comics: Added comic strips SequentialArt, VampireCheerleader, - comics: Added comic strips SequentialArt, VampireCheerleader,
GrrlPower, Spinnerette, HijinksEnsue, Nedroid. GrrlPower, Spinnerette, HijinksEnsue, Nedroid, Antics, ChannelAte,
ToonHole, ThisIsIndexed, WastedTalent, ChainsawSuit, ThreePanelSoul,
SpaceTrawler, ScenesFromAMultiverse, BroodHollow, BoxerHockey,
Wonderella, BadMachinery.
Changes: Changes:
- cmdline: Added the --continue option. - cmdline: Added the --continue option.

View file

@ -120,6 +120,14 @@ class Angels2200(_BasicScraper):
help = 'Index format: yyyy/mm/dd/part-<n>-comic-<n>' help = 'Index format: yyyy/mm/dd/part-<n>-comic-<n>'
class Antics(_BasicScraper):
url = 'http://www.anticscomic.com/'
stripUrl = url + '?p=%s'
imageSearch = compile(tagre("img", "src", r'(http://www\.anticscomic\.com/comics/\d+-\d+-\d+[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.anticscomic\.com/\?p=\d+)', after='prev'))
help = 'Index format: number'
class AppleGeeks(_BasicScraper): class AppleGeeks(_BasicScraper):
url = 'http://www.applegeeks.com/' url = 'http://www.applegeeks.com/'
stripUrl = url + 'comics/viewcomic.php?issue=%s' stripUrl = url + 'comics/viewcomic.php?issue=%s'

View file

@ -9,6 +9,14 @@ from ..scraper import _BasicScraper
from ..helpers import indirectStarter from ..helpers import indirectStarter
class BadMachinery(_BasicScraper):
url = 'http://scarygoround.com/'
stripUrl = url + '?date=%s'
imageSearch = compile(tagre("img", "src", r'(strips/\d+[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(\?date=\d+)') + 'Previous')
help = 'Index format: yyyymmdd'
class Bardsworth(_BasicScraper): class Bardsworth(_BasicScraper):
url = 'http://www.bardsworth.com/' url = 'http://www.bardsworth.com/'
stripUrl = url + '?p=%s' stripUrl = url + '?p=%s'
@ -106,6 +114,40 @@ class BoyOnAStickAndSlither(_BasicScraper):
return pageUrl.rsplit('/')[-1] return pageUrl.rsplit('/')[-1]
class BoxerHockey(_BasicScraper):
url = 'http://boxerhockey.fireball20xl.com/'
stripUrl = url + '?id=%s'
imageSearch = compile(tagre("img", "src", r'(img/comic/[^"]+)', after="comicimg"))
prevSearch = compile(tagre("a", "href", r'(http://www\.boxerhockey\.com/\?id=\d+)') +
r'[^>]+Previous')
help = 'Index format: n (unpadded)'
class BroodHollow(_BasicScraper):
url = 'http://broodhollow.chainsawsuit.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://broodhollow\.chainsawsuit\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://broodhollow\.chainsawsuit\.com/\d+/\d+/\d+/[^"]+)', after="prev"))
help = 'Index format: yyyy/mm/dd/stripname'
class ButterSafe(_BasicScraper):
url = 'http://buttersafe.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://buttersafe\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://buttersafe\.com/\d+\d+/\d+/\d+/[^"]+)', after="prev"))
help = 'Index format: yyyy/mm/dd/stripname'
# XXX disallowed by robots.txt
class _ButtercupFestival(_BasicScraper):
url = 'http://www.buttercupfestival.com/'
stripUrl = url + '%s.html'
imageSearch = compile(tagre("img", "src", r'(http://www\.buttercupfestival\.com/\d+-\d+[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(\d+-\d+\.html)', quote="") + "previous")
help = 'Index format: number-number'
class ButternutSquash(_BasicScraper): class ButternutSquash(_BasicScraper):
url = 'http://www.butternutsquash.net/' url = 'http://www.butternutsquash.net/'
stripUrl = url + '%s' stripUrl = url + '%s'

View file

@ -52,6 +52,22 @@ class Catena(_BasicScraper):
help = 'Index format: yyyy/mm/dd/<name>' help = 'Index format: yyyy/mm/dd/<name>'
class ChainsawSuit(_BasicScraper):
url = 'http://chainsawsuit.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://chainsawsuit\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://chainsawsuit\.com/\d+/\d+/\d+/[^"]+)', after="prev"))
help = 'Index format: yyyy/mm/dd/stripname'
class ChannelAte(_BasicScraper):
url = 'http://www.channelate.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://www\.channelate\.com/comics/\d+-\d+-\d+[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.channelate\.com/\d+/\d+/\d+/[^"]+)', after="prev"))
help = 'Index format: yyyy/mm/dd/name'
class ChasingTheSunset(_BasicScraper): class ChasingTheSunset(_BasicScraper):
url = 'http://www.fantasycomic.com/' url = 'http://www.fantasycomic.com/'
stripUrl = url + 'index.php?p=c%s' stripUrl = url + 'index.php?p=c%s'

View file

@ -166,3 +166,12 @@ class Dilbert(_BasicScraper):
imageSearch = compile(tagre("img", "src", r'(/dyn/str_strip/[^"]+\.strip\.zoom\.gif)')) imageSearch = compile(tagre("img", "src", r'(/dyn/str_strip/[^"]+\.strip\.zoom\.gif)'))
help = 'Index format: yyyy-mm-dd' help = 'Index format: yyyy-mm-dd'
# XXX namer # XXX namer
# XXX disallowed by robots.txt
class _DumbingOfAge(_BasicScraper):
url = 'http://www.dumbingofage.com/'
stripUrl = url + '%s/'
prevSearch = compile(tagre("a", "href", r'(http://www\.dumbingofage\.com/\d+/[^"]+)', after="prev"))
imageSearch = compile(tagre("img", "src", r'(http://www\.dumbingofage\.com/comics/\d+-\d+-\d+[^"]+)'))
help = 'Index format: yyyy/comic/book-num/seriesname/stripname'

View file

@ -41,6 +41,14 @@ class ScaryGoRound(_BasicScraper):
help = 'Index format: n (unpadded)' help = 'Index format: n (unpadded)'
class ScenesFromAMultiverse(_BasicScraper):
url = 'http://amultiverse.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://amultiverse\.com/files/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://amultiverse\.com/\d+\d+/\d+/\d+/[^"]+)', after="prev"))
help = 'Index format: yyyy/mm/dd/stripname'
class SchlockMercenary(_BasicScraper): class SchlockMercenary(_BasicScraper):
url = 'http://www.schlockmercenary.com/' url = 'http://www.schlockmercenary.com/'
stripUrl = url + '%s' stripUrl = url + '%s'
@ -134,6 +142,14 @@ class Sorcery101(_BasicScraper):
help = 'Index format: stripname' help = 'Index format: stripname'
class SpaceTrawler(_BasicScraper):
url = 'http://spacetrawler.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://spacetrawler\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://spacetrawler\.com/\d+/\d+/\d+/[^"]+)', after="navi-prev"))
help = 'Index format: yyyy/mm/dd/stripname'
class SpareParts(_BasicScraper): class SpareParts(_BasicScraper):
baseUrl = 'http://www.sparepartscomics.com/' baseUrl = 'http://www.sparepartscomics.com/'
url = baseUrl + 'comics/?date=20080328' url = baseUrl + 'comics/?date=20080328'

View file

@ -54,14 +54,27 @@ class TheWotch(_BasicScraper):
help = 'Index format: yyyy-mm-dd' help = 'Index format: yyyy-mm-dd'
class ThisIsIndexed(_BasicScraper):
url = 'http://thisisindexed.com/'
stripUrl = url + 'page/%s'
imageSearch = compile(tagre("img", "src", r'(http://thisisindexed\.com/wp-content/uploads/\d+/\d+/card[^"]+)'))
multipleImagesPerStrip = True
prevSearch = compile(tagre("div", "class", "nav-previous") +
tagre("a", "href", r'(http://thisisindexed\.com/page/\d+/)'))
help = 'Index format: number'
class ThunderAndLightning(_BasicScraper): class ThunderAndLightning(_BasicScraper):
baseUrl = 'http://www.talcomic.com/wp/' url = 'http://www.talcomic.com/wp/'
url = baseUrl + '?latestcomic' stripUrl = url + '%s/'
stripUrl = baseUrl + '%s/'
prevSearch = compile(tagre("a", "href", r'(http://www\.talcomic\.com/wp/[^"]+)', after="prev")) prevSearch = compile(tagre("a", "href", r'(http://www\.talcomic\.com/wp/[^"]+)', after="prev"))
imageSearch = compile(tagre("img", "src", r'(http://www\.talcomic\.com/wp/comics/[^"]+)')) imageSearch = compile(tagre("img", "src", r'(http://www\.talcomic\.com/wp/comics/[^"]+)'))
help = 'Index format: yyyy/mm/dd/page-nn' help = 'Index format: yyyy/mm/dd/page-nn'
@classmethod
def starter(cls):
return cls.url + '?latestcomic'
class TinyKittenTeeth(_BasicScraper): class TinyKittenTeeth(_BasicScraper):
url = 'http://www.tinykittenteeth.com/' url = 'http://www.tinykittenteeth.com/'
@ -71,6 +84,14 @@ class TinyKittenTeeth(_BasicScraper):
help = 'Index format: yyyy/mm/dd/stripname (unpadded)' help = 'Index format: yyyy/mm/dd/stripname (unpadded)'
class ToonHole(_BasicScraper):
url = 'http://www.toonhole.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://www\.toonhole\.com/comics/\d+-\d+-\d+[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.toonhole\.com/\d+/\d+/[^"]+)', after="prev"))
help = 'Index format: yyyy/mm/stripname'
# XXX disallowed by robots.txt # XXX disallowed by robots.txt
class _TwoLumps(_BasicScraper): class _TwoLumps(_BasicScraper):
url = 'http://www.twolumps.net/' url = 'http://www.twolumps.net/'
@ -113,6 +134,14 @@ class TheOuterQuarter(_BasicScraper):
help = 'Index format: nnn' help = 'Index format: nnn'
class ThreePanelSoul(_BasicScraper):
url = 'http://threepanelsoul.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://threepanelsoul\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://threepanelsoul\.com/\d+/\d+/\d+/[^"]+)', after="prev"))
help = 'Index format: yyyy/mm/dd/stripname'
class TracyAndTristan(_BasicScraper): class TracyAndTristan(_BasicScraper):
url = 'http://tandt.thecomicseries.com/' url = 'http://tandt.thecomicseries.com/'
stripUrl = url + 'comics/%s' stripUrl = url + 'comics/%s'

View file

@ -16,6 +16,14 @@ class WayfarersMoon(_BasicScraper):
help = 'Index format: nn' help = 'Index format: nn'
class WastedTalent(_BasicScraper):
url = 'http://www.wastedtalent.ca/'
stripUrl = url + 'comic/%s'
imageSearch = compile(tagre("img", "src", r'(http://www\.wastedtalent\.ca/sites/default/files/imagecache/comic_full/comics/\d+/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/comic/[^"]+)', after="comic_prev"))
help = 'Index format: stripname'
class WhiteNinja(_BasicScraper): class WhiteNinja(_BasicScraper):
url = 'http://www.whiteninjacomics.com/comics.shtml' url = 'http://www.whiteninjacomics.com/comics.shtml'
stripUrl = 'http://www.whiteninjacomics.com/comics/%s.shtml' stripUrl = 'http://www.whiteninjacomics.com/comics/%s.shtml'
@ -49,6 +57,14 @@ class Wigu(_BasicScraper):
help = 'Index format: n' help = 'Index format: n'
class Wonderella(_BasicScraper):
url = 'http://nonadventures.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://nonadventures\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://nonadventures\.com/\d+/\d+/\d+/[^"]+)', after="prev"))
help = 'Index format: yyyy/mm/dd/name'
class WotNow(_BasicScraper): class WotNow(_BasicScraper):
url = 'http://shadowburn.binmode.com/wotnow/' url = 'http://shadowburn.binmode.com/wotnow/'
stripUrl = url + 'comic.php?comic_id=%s' stripUrl = url + 'comic.php?comic_id=%s'