Enable some comics based on current policy.
This commit is contained in:
parent
6b0046f9b3
commit
6a70bf4671
6 changed files with 26 additions and 56 deletions
|
@ -256,17 +256,6 @@ class BrentalFlossGuest(BrentalFloss):
|
|||
firstStripUrl = stripUrl % '1'
|
||||
|
||||
|
||||
# XXX disallowed by robots.txt
|
||||
class _BringBackRoomies(_BasicScraper):
|
||||
url = "http://www.bringbackroomies.com/"
|
||||
rurl = escape(url)
|
||||
stripUrl = url + "comic/%s"
|
||||
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/\d+-\d+-\d+[^"]+)' % rurl))
|
||||
prevSearch = compile(tagre("span", "class", "mininav-prev") +
|
||||
tagre("a", "href", r'(%scomic/[^"]+)' % rurl))
|
||||
help = 'Index format: stripname'
|
||||
|
||||
|
||||
class Brink(_BasicScraper):
|
||||
url = 'http://paperfangs.com/brink/'
|
||||
rurl = escape(url)
|
||||
|
@ -287,13 +276,13 @@ class BrightlyWound(_BasicScraper):
|
|||
help = 'Index format: nnn'
|
||||
|
||||
|
||||
# XXX disallowed by robots.txt
|
||||
class _ButtercupFestival(_BasicScraper):
|
||||
class ButtercupFestival(_ParserScraper):
|
||||
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'
|
||||
stripUrl = url + '%s.htm'
|
||||
firstStripUrl = stripUrl % '2-1'
|
||||
imageSearch = '//center/img'
|
||||
prevSearch = '//a[text()="previous"]'
|
||||
help = 'Index format: 2-number'
|
||||
|
||||
|
||||
class ButterSafe(_BasicScraper):
|
||||
|
|
|
@ -286,15 +286,14 @@ class Drive(_BasicScraper):
|
|||
help = 'Index format: yymmdd'
|
||||
|
||||
|
||||
# XXX navigation works only with JavaScript
|
||||
class _DrMcNinja(_BasicScraper):
|
||||
class DrMcNinja(_ParserScraper):
|
||||
url = 'http://drmcninja.com/'
|
||||
rurl = escape(url)
|
||||
stripUrl = url + 'archives/comic/%s/'
|
||||
firstStripUrl = stripUrl % '0p1'
|
||||
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl))
|
||||
prevSearch = compile(tagre("a", "href", r'(%sarchives/comic/[^"]+)' % rurl, after="prev"))
|
||||
help = 'Index format: episode number and page'
|
||||
css = True
|
||||
imageSearch = 'div#comic img'
|
||||
prevSearch = 'a.prev'
|
||||
help = 'Index format: {episode}p{page}'
|
||||
|
||||
|
||||
class Drowtales(_BasicScraper):
|
||||
|
@ -311,8 +310,7 @@ class Drowtales(_BasicScraper):
|
|||
help = 'Index format: number'
|
||||
|
||||
|
||||
# XXX disallowed by robots.txt
|
||||
class _DumbingOfAge(_BasicScraper):
|
||||
class DumbingOfAge(_BasicScraper):
|
||||
url = 'http://www.dumbingofage.com/'
|
||||
rurl = escape(url)
|
||||
stripUrl = url + '%s/'
|
||||
|
|
|
@ -152,8 +152,7 @@ class EmergencyExit(_BasicScraper):
|
|||
help = 'Index format: n'
|
||||
|
||||
|
||||
# XXX disallowed by robots.txt
|
||||
class _ErrantStory(_BasicScraper):
|
||||
class ErrantStory(_BasicScraper):
|
||||
url = 'http://www.errantstory.com/'
|
||||
stripUrl = url + '%s'
|
||||
imageSearch = compile(r'<img[^>]+?src="([^"]*?comics/.+?)"')
|
||||
|
|
|
@ -172,8 +172,7 @@ class Pimpette(_ParserScraper):
|
|||
help = 'Index format: yyyymmdd'
|
||||
|
||||
|
||||
# Broken navigation: prev link at http://planescapecomic.com/201.html points to same URL.
|
||||
class _PlanescapeSurvival(_BasicScraper):
|
||||
class PlanescapeSurvival(_BasicScraper):
|
||||
url = 'http://planescapecomic.com/'
|
||||
stripUrl = url + '%s.html'
|
||||
imageSearch = compile(r'src="(comics/.+?)"')
|
||||
|
|
|
@ -159,17 +159,6 @@ class SexyLosers(_BasicScraper):
|
|||
return index + '-' + title
|
||||
|
||||
|
||||
# XXX site has been hacked
|
||||
class _ShadowGirls(_BasicScraper):
|
||||
url = 'http://www.shadowgirlscomic.com/'
|
||||
stripUrl = url + 'comics/%s'
|
||||
firstStripUrl = stripUrl % 'book-1/chapter-1-broken-dreams/welcome'
|
||||
imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]*)'))
|
||||
prevSearch = compile(tagre("a", "href", r'([^"]*)', after='navi-prev'))
|
||||
help = 'Index format: custom'
|
||||
starter = indirectStarter(url, compile(tagre("a", "href", r'([^"]*/comics/[^"]+)')))
|
||||
|
||||
|
||||
class Sheldon(_BasicScraper):
|
||||
url = 'http://www.sheldoncomics.com/'
|
||||
rurl = escape(url)
|
||||
|
@ -209,14 +198,13 @@ class Shivae(_BasicScraper):
|
|||
help = 'Index format: yyyy/mm/dd/stripname'
|
||||
|
||||
|
||||
# XXX disallowed by robots.txt
|
||||
class _Shortpacked(_BasicScraper):
|
||||
url = 'http://www.shortpacked.com/'
|
||||
rurl = escape(url)
|
||||
stripUrl = url + '%s/'
|
||||
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
||||
prevSearch = compile(tagre("a", "href", r'(%s\d+/comic/[^"]+)' % rurl, after="prev"))
|
||||
help = 'Index format: yyyy/comic/book-nn/mm-name1/name2'
|
||||
class Shortpacked(_ParserScraper):
|
||||
url = 'http://www.shortpacked.com/index.php'
|
||||
stripUrl = url + '?id=%s'
|
||||
css = True
|
||||
imageSearch = 'img#comic'
|
||||
prevSearch = 'a.prev'
|
||||
help = 'Index format: nnn'
|
||||
|
||||
|
||||
class ShotgunShuffle(_BasicScraper):
|
||||
|
@ -452,14 +440,12 @@ class StandStillStaySilent(_ParserScraper):
|
|||
help = 'Index Format: number'
|
||||
|
||||
|
||||
# XXX disallowed by robots.txt
|
||||
class _StationV3(_BasicScraper):
|
||||
class StationV3(_ParserScraper):
|
||||
url = 'http://www.stationv3.com/'
|
||||
rurl = escape(url)
|
||||
stripUrl = url + 'd/%s.html'
|
||||
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
||||
prevSearch = compile(tagre("a", "href", r'(%sd/\d+\.html)' % rurl) +
|
||||
tagre("img", "src", r'http://www\.stationv3\.com/images/previous\.gif'))
|
||||
imageSearch = '//img[contains(@src,"/comics2/")]'
|
||||
prevSearch = '//a[img[contains(@src,"/previous2")]]'
|
||||
|
||||
help = 'Index format: yyyymmdd'
|
||||
|
||||
|
||||
|
|
|
@ -137,8 +137,7 @@ class ToonHole(_BasicScraper):
|
|||
return url in (self.stripUrl % "2013/03/if-game-of-thrones-was-animated",)
|
||||
|
||||
|
||||
# XXX disallowed by robots.txt
|
||||
class _TwoLumps(_BasicScraper):
|
||||
class TwoLumps(_BasicScraper):
|
||||
url = 'http://www.twolumps.net/'
|
||||
stripUrl = url + 'd/%s.html'
|
||||
imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)'))
|
||||
|
|
Loading…
Reference in a new issue