dmoonfire/dosage
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Activity

s/baseurl/baseUrl/g

Browse source
This commit is contained in:
Bastian Kleineidam 2013-04-13 20:58:00 +02:00
parent c246b41d64
commit f15f993851
15 changed files with 119 additions and 119 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
dosagelib/plugins/a.py
View file

@ -18,9 +18,9 @@ class AbleAndBaker(_BasicScraper):
class AbsurdNotions(_BasicScraper): class AbsurdNotions(_BasicScraper):
baseurl = 'http://www.absurdnotions.org/' baseUrl = 'http://www.absurdnotions.org/'
url = baseurl + 'page129.html' url = baseUrl + 'page129.html'
stripUrl = baseurl + 'page%s.html' stripUrl = baseUrl + 'page%s.html'
firstStripUrl = stripUrl % '1' firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre('img', 'src', r'(an[^"]+)')) imageSearch = compile(tagre('img', 'src', r'(an[^"]+)'))
multipleImagesPerStrip = True multipleImagesPerStrip = True
@ -74,9 +74,9 @@ class AetheriaEpics(_BasicScraper):
class AfterStrife(_BasicScraper): class AfterStrife(_BasicScraper):
baseurl = 'http://afterstrife.com/' baseUrl = 'http://afterstrife.com/'
rurl = escape(baseurl) rurl = escape(baseUrl)
stripUrl = baseurl + '?p=%s' stripUrl = baseUrl + '?p=%s'
url = stripUrl % '262' url = stripUrl % '262'
firstStripUrl = stripUrl % '1' firstStripUrl = stripUrl % '1'
imageSearch = compile(r'<img src="(%sstrips/.+?)"' % rurl) imageSearch = compile(r'<img src="(%sstrips/.+?)"' % rurl)
@ -148,9 +148,9 @@ class AlienLovesPredator(_BasicScraper):
class AlienShores(_BasicScraper): class AlienShores(_BasicScraper):
baseurl = 'http://alienshores.com/' baseUrl = 'http://alienshores.com/'
rurl = escape(baseurl) rurl = escape(baseUrl)
url = baseurl + 'alienshores_band/' url = baseUrl + 'alienshores_band/'
stripUrl = url + '%s' stripUrl = url + '%s'
imageSearch = compile(tagre("img", "src", r'(%salienshores_band/wp-content/uploads/[^"]+)' % rurl)) imageSearch = compile(tagre("img", "src", r'(%salienshores_band/wp-content/uploads/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
@ -258,10 +258,10 @@ class Angels2200(_BasicScraper):
class Annyseed(_BasicScraper): class Annyseed(_BasicScraper):
baseurl = 'http://www.colourofivy.com/' baseUrl = 'http://www.colourofivy.com/'
rurl = escape(baseurl) rurl = escape(baseUrl)
url = baseurl + 'annyseed_webcomic_latest.htm' url = baseUrl + 'annyseed_webcomic_latest.htm'
stripUrl = baseurl + 'annyseed_webcomic%s.htm' stripUrl = baseUrl + 'annyseed_webcomic%s.htm'
imageSearch = compile(tagre("img", "src", r'(Annyseed[^"]+)')) imageSearch = compile(tagre("img", "src", r'(Annyseed[^"]+)'))
prevSearch = compile(r'<a href="(%s[^"]+)"><img src="Last.gif"' % rurl) prevSearch = compile(r'<a href="(%s[^"]+)"><img src="Last.gif"' % rurl)
help = 'Index format: nnn' help = 'Index format: nnn'
@ -297,11 +297,11 @@ class ASofterWorld(_BasicScraper):
class AstronomyPOTD(_BasicScraper): class AstronomyPOTD(_BasicScraper):
baseurl = 'http://antwrp.gsfc.nasa.gov/apod/' baseUrl = 'http://antwrp.gsfc.nasa.gov/apod/'
url = baseurl + 'astropix.html' url = baseUrl + 'astropix.html'
starter = bounceStarter(url, starter = bounceStarter(url,
compile(tagre("a", "href", r'(ap\d{6}\.html)') + "&gt;</a>")) compile(tagre("a", "href", r'(ap\d{6}\.html)') + "&gt;</a>"))
stripUrl = baseurl + 'ap%s.html' stripUrl = baseUrl + 'ap%s.html'
firstStripUrl = stripUrl % '061012' firstStripUrl = stripUrl % '061012'
imageSearch = compile(tagre("a", "href", r'(image/\d{4}/[^"]+)')) imageSearch = compile(tagre("a", "href", r'(image/\d{4}/[^"]+)'))
multipleImagesPerStrip = True multipleImagesPerStrip = True

14
dosagelib/plugins/c.py
View file

@ -101,11 +101,11 @@ class ChainsawSuit(_BasicScraper):
class Champ2010(_BasicScraper): class Champ2010(_BasicScraper):
baseurl = 'http://jedcollins.com/champ2010/' baseUrl = 'http://jedcollins.com/champ2010/'
rurl = escape(baseurl) rurl = escape(baseUrl)
# the latest URL is hard coded since the comic is discontinued # the latest URL is hard coded since the comic is discontinued
url = baseurl + 'champ-12-30-10.html' url = baseUrl + 'champ-12-30-10.html'
stripUrl = baseurl + '%s.html' stripUrl = baseUrl + '%s.html'
firstStripUrl = stripUrl % 'champ1-1-10-fuck' firstStripUrl = stripUrl % 'champ1-1-10-fuck'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="Previous")) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="Previous"))
@ -323,9 +323,9 @@ class CrimsonDark(_BasicScraper):
class CraftedFables(_BasicScraper): class CraftedFables(_BasicScraper):
url = 'http://www.craftedfables.com/' url = 'http://www.craftedfables.com/'
baseurl = 'http://www.caf-fiends.net/' baseUrl = 'http://www.caf-fiends.net/'
rurl = escape(baseurl) rurl = escape(baseUrl)
stripUrl = baseurl + 'craftedfables/?p=%s' stripUrl = baseUrl + 'craftedfables/?p=%s'
imageSearch = compile(tagre("img", "src", r'(%scraftedfables/comics/[^"]+)' % rurl)) imageSearch = compile(tagre("img", "src", r'(%scraftedfables/comics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%scraftedfables/[^"]+)' % rurl) + prevSearch = compile(tagre("a", "href", r'(%scraftedfables/[^"]+)' % rurl) +
tagre("span", "class", r"prev")) tagre("span", "class", r"prev"))

6
dosagelib/plugins/creators.py
View file

@ -9,12 +9,12 @@ from ..util import tagre
_imageSearch = compile(tagre("a", "href", r'(/comics/\d+/[^"]+)')) _imageSearch = compile(tagre("a", "href", r'(/comics/\d+/[^"]+)'))
def add(name, path): def add(name, path):
baseurl = 'http://www.creators.com' baseUrl = 'http://www.creators.com'
classname = 'Creators_%s' % name classname = 'Creators_%s' % name
globals()[classname] = make_scraper(classname, globals()[classname] = make_scraper(classname,
name = 'Creators/' + name, name = 'Creators/' + name,
url = baseurl + path + '.html', url = baseUrl + path + '.html',
stripUrl = baseurl + path + '/%s.html', stripUrl = baseUrl + path + '/%s.html',
lang = 'es' if name.lower().endswith('spanish') else 'en', lang = 'es' if name.lower().endswith('spanish') else 'en',
imageSearch = _imageSearch, imageSearch = _imageSearch,
prevSearch = compile(tagre("a", "href", r'(%s/\d+\.html)' % path) + prevSearch = compile(tagre("a", "href", r'(%s/\d+\.html)' % path) +

12
dosagelib/plugins/d.py
View file

@ -258,9 +258,9 @@ class DresdenCodak(_BasicScraper):
class DrFun(_BasicScraper): class DrFun(_BasicScraper):
baseurl = 'http://www.ibiblio.org/Dave/' baseUrl = 'http://www.ibiblio.org/Dave/'
url = baseurl + 'ar00502.htm' url = baseUrl + 'ar00502.htm'
stripUrl = baseurl + 'ar%s.htm' stripUrl = baseUrl + 'ar%s.htm'
firstStripUrl = stripUrl % '00001' firstStripUrl = stripUrl % '00001'
imageSearch = compile(tagre("a", "href", r'(Dr-Fun/df\d+/df[^"]+)')) imageSearch = compile(tagre("a", "href", r'(Dr-Fun/df\d+/df[^"]+)'))
multipleImagesPerStrip = True multipleImagesPerStrip = True
@ -280,9 +280,9 @@ class DrMcNinja(_BasicScraper):
class Drowtales(_BasicScraper): class Drowtales(_BasicScraper):
baseurl = 'http://www.drowtales.com/' baseUrl = 'http://www.drowtales.com/'
rurl = escape(baseurl) rurl = escape(baseUrl)
url = baseurl + 'mainarchive.php' url = baseUrl + 'mainarchive.php'
stripUrl = url + '?sid=%s' stripUrl = url + '?sid=%s'
firstStripUrl = stripUrl % '4192' firstStripUrl = stripUrl % '4192'
imageSearch = ( imageSearch = (

18
dosagelib/plugins/f.py
View file

@ -19,9 +19,9 @@ class FalconTwin(_BasicScraper):
class Fallen(_BasicScraper): class Fallen(_BasicScraper):
baseurl = 'http://www.fallencomic.com/' baseUrl = 'http://www.fallencomic.com/'
url = baseurl + 'fal-page.htm' url = baseUrl + 'fal-page.htm'
stripUrl = baseurl + 'pages/part%s/%s-p%s.htm' stripUrl = baseUrl + 'pages/part%s/%s-p%s.htm'
imageSearch = compile(r'<IMG SRC="(page/.+?)"', IGNORECASE) imageSearch = compile(r'<IMG SRC="(page/.+?)"', IGNORECASE)
prevSearch = compile(r'<A HREF="(.+?)"><FONT FACE="Courier">Back', IGNORECASE) prevSearch = compile(r'<A HREF="(.+?)"><FONT FACE="Courier">Back', IGNORECASE)
help = 'Index format: nn-m (comicNumber-partNumber)' help = 'Index format: nn-m (comicNumber-partNumber)'
@ -59,9 +59,9 @@ class FauxPas(_BasicScraper):
class FeyWinds(_BasicScraper): class FeyWinds(_BasicScraper):
baseurl = 'http://kitsune.rydia.net/' baseUrl = 'http://kitsune.rydia.net/'
url = baseurl + 'index.html' url = baseUrl + 'index.html'
stripUrl = baseurl + 'comic/page.php?id=%s' stripUrl = baseUrl + 'comic/page.php?id=%s'
imageSearch = compile(r"(../comic/pages//.+?)'") imageSearch = compile(r"(../comic/pages//.+?)'")
prevSearch = compile(r"(page.php\?id=.+?)'.+?navprevious.png") prevSearch = compile(r"(page.php\?id=.+?)'.+?navprevious.png")
help = 'Index format: n (unpadded)' help = 'Index format: n (unpadded)'
@ -89,9 +89,9 @@ class FirstWorldProblems(_BasicScraper):
class FlakyPastry(_BasicScraper): class FlakyPastry(_BasicScraper):
baseurl = 'http://flakypastry.runningwithpencils.com/' baseUrl = 'http://flakypastry.runningwithpencils.com/'
url = baseurl + 'index.php' url = baseUrl + 'index.php'
stripUrl = baseurl + 'comic.php?strip_id=%s' stripUrl = baseUrl + 'comic.php?strip_id=%s'
firstStripUrl = stripUrl % '0' firstStripUrl = stripUrl % '0'
imageSearch = compile(r'<img src="(comics/.+?)"') imageSearch = compile(r'<img src="(comics/.+?)"')
prevSearch = compile(r'<a href="(.+?)".+?btn_back') prevSearch = compile(r'<a href="(.+?)".+?btn_back')

8
dosagelib/plugins/g.py
View file

@ -20,12 +20,12 @@ class Galaxion(_BasicScraper):
class Garanos(_BasicScraper): class Garanos(_BasicScraper):
baseurl = 'http://garanos.alexheberling.com/' baseUrl = 'http://garanos.alexheberling.com/'
rurl = escape(baseurl) rurl = escape(baseUrl)
url = baseurl + 'pages/page-1/' url = baseUrl + 'pages/page-1/'
starter = indirectStarter(url, starter = indirectStarter(url,
compile(tagre("a", "href", r'(%spages/[^"]+)' % rurl, after="navi-last"))) compile(tagre("a", "href", r'(%spages/[^"]+)' % rurl, after="navi-last")))
stripUrl = baseurl + 'pages/page-%s' stripUrl = baseUrl + 'pages/page-%s'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%spages/[^"]+)' % rurl, after="prev")) prevSearch = compile(tagre("a", "href", r'(%spages/[^"]+)' % rurl, after="prev"))
help = 'Index format: n (unpadded)' help = 'Index format: n (unpadded)'

18
dosagelib/plugins/k.py
View file

@ -35,9 +35,9 @@ class KevinAndKell(_BasicScraper):
class Key(_BasicScraper): class Key(_BasicScraper):
baseurl = 'http://key.shadilyn.com/' baseUrl = 'http://key.shadilyn.com/'
url = baseurl + 'latestpage.html' url = baseUrl + 'latestpage.html'
stripUrl = baseurl + 'pages/%s.html' stripUrl = baseUrl + 'pages/%s.html'
imageSearch = compile(r'"((?:images/.+?)|(?:pages/images/.+?))"') imageSearch = compile(r'"((?:images/.+?)|(?:pages/images/.+?))"')
prevSearch = compile(r'</a><a href="(.+?html)".+?prev') prevSearch = compile(r'</a><a href="(.+?html)".+?prev')
help = 'Index format: nnn' help = 'Index format: nnn'
@ -54,9 +54,9 @@ class KickInTheHead(_BasicScraper):
class KillerKomics(_BasicScraper): class KillerKomics(_BasicScraper):
baseurl = 'http://www.killerkomics.com/web-comics/' baseUrl = 'http://www.killerkomics.com/web-comics/'
url = baseurl + 'index_ang.cfm' url = baseUrl + 'index_ang.cfm'
stripUrl = baseurl + '%s.cfm' stripUrl = baseUrl + '%s.cfm'
imageSearch = compile(r'<img src="(http://www.killerkomics.com/FichiersUpload/Comics/.+?)"') imageSearch = compile(r'<img src="(http://www.killerkomics.com/FichiersUpload/Comics/.+?)"')
prevSearch = compile(r'<div id="precedent"><a href="(.+?)"') prevSearch = compile(r'<div id="precedent"><a href="(.+?)"')
help = 'Index format: strip-name' help = 'Index format: strip-name'
@ -82,9 +82,9 @@ class Krakow(_BasicScraper):
class Kukuburi(_BasicScraper): class Kukuburi(_BasicScraper):
baseurl = 'http://www.kukuburi.com/' baseUrl = 'http://www.kukuburi.com/'
url = baseurl + 'current/' url = baseUrl + 'current/'
stripUrl = baseurl + 'v2/%s/' stripUrl = baseUrl + 'v2/%s/'
firstStripUrl = stripUrl % '2007/08/09/one' firstStripUrl = stripUrl % '2007/08/09/one'
imageSearch = compile(tagre("img", "src", r'(http://www\.kukuburi\.com/v2/comics/[^"]+)', after='alt="[^"]')) imageSearch = compile(tagre("img", "src", r'(http://www\.kukuburi\.com/v2/comics/[^"]+)', after='alt="[^"]'))
prevSearch = compile(r'nav-previous.+?"(http.+?)"') prevSearch = compile(r'nav-previous.+?"(http.+?)"')

8
dosagelib/plugins/n.py
View file

@ -141,10 +141,10 @@ class NobodyScores(_BasicScraper):
class NoNeedForBushido(_BasicScraper): class NoNeedForBushido(_BasicScraper):
baseurl = 'http://noneedforbushido.com/' baseUrl = 'http://noneedforbushido.com/'
rurl = escape(baseurl) rurl = escape(baseUrl)
url = baseurl + 'latest/' url = baseUrl + 'latest/'
stripUrl = baseurl + '%s/' stripUrl = baseUrl + '%s/'
imageSearch = compile(tagre("img", "src", r'(%scomics/comic/[^"]+)' % rurl)) imageSearch = compile(tagre("img", "src", r'(%scomics/comic/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="previous-comic-link")) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="previous-comic-link"))
help = 'Index format: yyyy/comic/nnn' help = 'Index format: yyyy/comic/nnn'

18
dosagelib/plugins/p.py
View file

@ -50,9 +50,9 @@ class PartiallyClips(_BasicScraper):
class PastelDefender(_BasicScraper): class PastelDefender(_BasicScraper):
baseurl = 'http://www.pasteldefender.com/' baseUrl = 'http://www.pasteldefender.com/'
url = baseurl + 'coverbackcover.html' url = baseUrl + 'coverbackcover.html'
stripUrl = baseurl + '%s.html' stripUrl = baseUrl + '%s.html'
firstStripUrl = stripUrl % 'cover' firstStripUrl = stripUrl % 'cover'
imageSearch = compile(r'<IMG SRC="(images/.+?)" WIDTH="742"') imageSearch = compile(r'<IMG SRC="(images/.+?)" WIDTH="742"')
prevSearch = compile(r'<A HREF="([^"]+)"><IMG SRC="images/back\.gif"') prevSearch = compile(r'<A HREF="([^"]+)"><IMG SRC="images/back\.gif"')
@ -107,9 +107,9 @@ class PeppermintSaga(_BasicScraper):
class PHDComics(_BasicScraper): class PHDComics(_BasicScraper):
baseurl = 'http://phdcomics.com/' baseUrl = 'http://phdcomics.com/'
url = baseurl + 'comics.php' url = baseUrl + 'comics.php'
stripUrl = baseurl + 'comics/archive.php?comicid=%s' stripUrl = baseUrl + 'comics/archive.php?comicid=%s'
firstStripUrl = stripUrl % '1' firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'(http://www\.phdcomics\.com/comics/archive/phd[^ ]+)', quote="")) imageSearch = compile(tagre("img", "src", r'(http://www\.phdcomics\.com/comics/archive/phd[^ ]+)', quote=""))
prevSearch = compile(tagre("a", "href", r'((?:comics/)?archive\.php\?comicid=\d+)', quote="") + prevSearch = compile(tagre("a", "href", r'((?:comics/)?archive\.php\?comicid=\d+)', quote="") +
@ -167,9 +167,9 @@ class _PlanescapeSurvival(_BasicScraper):
class PokeyThePenguin(_BasicScraper): class PokeyThePenguin(_BasicScraper):
baseurl = 'http://www.yellow5.com/pokey/archive/' baseUrl = 'http://www.yellow5.com/pokey/archive/'
url = baseurl + 'index558.html' url = baseUrl + 'index558.html'
stripUrl = baseurl + 'index%s.html' stripUrl = baseUrl + 'index%s.html'
firstStripUrl = stripUrl % '1' firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'(pokey\d+[^"]+)')) imageSearch = compile(tagre("img", "src", r'(pokey\d+[^"]+)'))
prevSearch = True prevSearch = True

6
dosagelib/plugins/q.py
View file

@ -17,9 +17,9 @@ class QuestionableContent(_BasicScraper):
class Qwantz(_BasicScraper): class Qwantz(_BasicScraper):
baseurl = 'http://www.qwantz.com/' baseUrl = 'http://www.qwantz.com/'
url = baseurl + 'index.php' url = baseUrl + 'index.php'
rurl = escape(baseurl) rurl = escape(baseUrl)
stripUrl = url + '?comic=%s' stripUrl = url + '?comic=%s'
firstStripUrl = stripUrl % '1' firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))

6
dosagelib/plugins/r.py
View file

@ -35,10 +35,10 @@ class RealmOfAtland(_BasicScraper):
class RedMeat(_BasicScraper): class RedMeat(_BasicScraper):
baseurl = 'http://www.redmeat.com/redmeat/' baseUrl = 'http://www.redmeat.com/redmeat/'
url = baseurl + 'current/index.html' url = baseUrl + 'current/index.html'
starter = bounceStarter(url, compile(r'<a href="(\.\./\d{4}-\d{2}-\d{2}/index\.html)">next</a>')) starter = bounceStarter(url, compile(r'<a href="(\.\./\d{4}-\d{2}-\d{2}/index\.html)">next</a>'))
stripUrl = baseurl + '%s/index.html' stripUrl = baseUrl + '%s/index.html'
firstStripUrl = stripUrl % '1996-06-10' firstStripUrl = stripUrl % '1996-06-10'
imageSearch = compile(r'<img src="(index-1\.gif)" width="\d+" height="\d+" [^>]*>') imageSearch = compile(r'<img src="(index-1\.gif)" width="\d+" height="\d+" [^>]*>')
prevSearch = compile(r'<a href="(\.\./\d{4}-\d{2}-\d{2}/index\.html)">previous</a>') prevSearch = compile(r'<a href="(\.\./\d{4}-\d{2}-\d{2}/index\.html)">previous</a>')

14
dosagelib/plugins/s.py
View file

@ -316,9 +316,9 @@ class SodiumEyes(_BasicScraper):
class Sorcery101(_BasicScraper): class Sorcery101(_BasicScraper):
description = u'Welcome to the site of Kel McDonald, professional comic illustrator and writer.' description = u'Welcome to the site of Kel McDonald, professional comic illustrator and writer.'
baseurl = 'http://www.sorcery101.net/' baseUrl = 'http://www.sorcery101.net/'
url = baseurl + 'sorcery-101/' url = baseUrl + 'sorcery-101/'
rurl = escape(baseurl) rurl = escape(baseUrl)
stripUrl = url + '%s/' stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl)) imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%ssorcery-101/[^"]+)' % rurl, after="previous-")) prevSearch = compile(tagre("a", "href", r'(%ssorcery-101/[^"]+)' % rurl, after="previous-"))
@ -475,10 +475,10 @@ class SomethingPositive(_BasicScraper):
class StarCrossdDestiny(_BasicScraper): class StarCrossdDestiny(_BasicScraper):
description = u'Furturistic fantasy. A group of outcasts fight to survive in a world that shuns them as freaks.' description = u'Furturistic fantasy. A group of outcasts fight to survive in a world that shuns them as freaks.'
baseurl = 'http://www.starcrossd.net/' baseUrl = 'http://www.starcrossd.net/'
rurl = escape(baseurl) rurl = escape(baseUrl)
url = baseurl + 'comic.html' url = baseUrl + 'comic.html'
stripUrl = baseurl + 'archives/%s.html' stripUrl = baseUrl + 'archives/%s.html'
firstStripUrl = stripUrl % '00000001' firstStripUrl = stripUrl % '00000001'
imageSearch = compile(tagre("img", "src", r'(%s(?:ch1|strips|book2)/[^"]+)' % rurl)) imageSearch = compile(tagre("img", "src", r'(%s(?:ch1|strips|book2)/[^"]+)' % rurl))
prevSearch = compile(r'<a href="(%s(?:ch1/)?archives/\d+\.html)"[^>]*"[^"]*"[^>]*>prev' % rurl, IGNORECASE) prevSearch = compile(r'<a href="(%s(?:ch1/)?archives/\d+\.html)"[^>]*"[^"]*"[^>]*>prev' % rurl, IGNORECASE)

20
dosagelib/plugins/t.py
View file

@ -37,14 +37,14 @@ class TheNoob(_BasicScraper):
class TheOrderOfTheStick(_BasicScraper): class TheOrderOfTheStick(_BasicScraper):
baseurl = 'http://www.giantitp.com/' baseUrl = 'http://www.giantitp.com/'
url = baseurl + 'comics/oots0863.html' url = baseUrl + 'comics/oots0863.html'
stripUrl = baseurl + 'comics/oots%s.html' stripUrl = baseUrl + 'comics/oots%s.html'
firstStripUrl = stripUrl % '0001' firstStripUrl = stripUrl % '0001'
imageSearch = compile(r'<IMG src="(/comics/images/[^"]+)">') imageSearch = compile(r'<IMG src="(/comics/images/[^"]+)">')
prevSearch = compile(r'<A href="(/comics/oots\d{4}\.html)"><IMG src="/Images/redesign/ComicNav_Back.gif"') prevSearch = compile(r'<A href="(/comics/oots\d{4}\.html)"><IMG src="/Images/redesign/ComicNav_Back.gif"')
help = 'Index format: n (unpadded)' help = 'Index format: n (unpadded)'
starter = indirectStarter(baseurl, compile(r'<A href="(/comics/oots\d{4}\.html)"')) starter = indirectStarter(baseUrl, compile(r'<A href="(/comics/oots\d{4}\.html)"'))
@classmethod @classmethod
def namer(cls, imageUrl, pageUrl): def namer(cls, imageUrl, pageUrl):
@ -52,9 +52,9 @@ class TheOrderOfTheStick(_BasicScraper):
class TheParkingLotIsFull(_BasicScraper): class TheParkingLotIsFull(_BasicScraper):
baseurl = 'http://plif.courageunfettered.com/' baseUrl = 'http://plif.courageunfettered.com/'
url = baseurl + 'archive/arch2002.htm' url = baseUrl + 'archive/arch2002.htm'
stripUrl = baseurl + 'archive/arch%s.htm' stripUrl = baseUrl + 'archive/arch%s.htm'
firstStripUrl = stripUrl % '1998' firstStripUrl = stripUrl % '1998'
imageSearch = compile(r'<td align="center"><A TARGET=_parent HREF="(wc\d+\..+?)">') imageSearch = compile(r'<td align="center"><A TARGET=_parent HREF="(wc\d+\..+?)">')
multipleImagesPerStrip = True multipleImagesPerStrip = True
@ -147,9 +147,9 @@ class TheWhiteboard(_BasicScraper):
class HMHigh(_BasicScraper): class HMHigh(_BasicScraper):
name = 'TheFallenAngel/HMHigh' name = 'TheFallenAngel/HMHigh'
baseurl = 'http://www.thefallenangel.co.uk/' baseUrl = 'http://www.thefallenangel.co.uk/'
url = baseurl + 'hmhigh/' url = baseUrl + 'hmhigh/'
rurl = escape(baseurl) rurl = escape(baseUrl)
stripUrl = url + '?id=%s' stripUrl = url + '?id=%s'
imageSearch = compile(r'<img src="(%shmhigh/img/comic/.+?)"' % rurl) imageSearch = compile(r'<img src="(%shmhigh/img/comic/.+?)"' % rurl)
prevSearch = compile(r' <a href="(%s.+?)" title=".+?">Prev</a>' % rurl) prevSearch = compile(r' <a href="(%s.+?)" title=".+?">Prev</a>' % rurl)

6
dosagelib/plugins/u.py
View file

@ -20,9 +20,9 @@ class Undertow(_BasicScraper):
class UnicornJelly(_BasicScraper): class UnicornJelly(_BasicScraper):
baseurl = 'http://unicornjelly.com/' baseUrl = 'http://unicornjelly.com/'
url = baseurl + 'uni666.html' url = baseUrl + 'uni666.html'
stripUrl = baseurl + 'uni%s.html' stripUrl = baseUrl + 'uni%s.html'
firstStripUrl = stripUrl % '001' firstStripUrl = stripUrl % '001'
imageSearch = compile(r'</TABLE>(?:<FONT COLOR="BLACK">)?<IMG SRC="(images/[^"]+)" WIDTH=') imageSearch = compile(r'</TABLE>(?:<FONT COLOR="BLACK">)?<IMG SRC="(images/[^"]+)" WIDTH=')
prevSearch = compile(r'<A HREF="(uni\d{3}[bcs]?\.html)">(<FONT COLOR="BLACK">)?<IMG SRC="images/back00\.gif"') prevSearch = compile(r'<A HREF="(uni\d{3}[bcs]?\.html)">(<FONT COLOR="BLACK">)?<IMG SRC="images/back00\.gif"')

52
dosagelib/plugins/w.py
View file

@ -75,18 +75,18 @@ class WeCanSleepTomorrow(_BasicScraper):
class WhiteNinja(_BasicScraper): class WhiteNinja(_BasicScraper):
baseurl = 'http://www.whiteninjacomics.com/' baseUrl = 'http://www.whiteninjacomics.com/'
url = baseurl + 'comics.shtml' url = baseUrl + 'comics.shtml'
stripUrl = baseurl + 'comics/%s.shtml' stripUrl = baseUrl + 'comics/%s.shtml'
imageSearch = compile(r'<img src=(/images/comics/(?!t-).+?\.gif) border=0') imageSearch = compile(r'<img src=(/images/comics/(?!t-).+?\.gif) border=0')
prevSearch = compile(r'(/comics/.+?shtml).+?previous') prevSearch = compile(r'(/comics/.+?shtml).+?previous')
help = 'Index format: s (comic name)' help = 'Index format: s (comic name)'
class WhiteNoise(_BasicScraper): class WhiteNoise(_BasicScraper):
baseurl = 'http://www.wncomic.com/' baseUrl = 'http://www.wncomic.com/'
url = baseurl + 'archive.php' url = baseUrl + 'archive.php'
stripUrl = baseurl + 'archive_comments.php?strip_id=%s' stripUrl = baseUrl + 'archive_comments.php?strip_id=%s'
firstStripUrl = stripUrl % '1' firstStripUrl = stripUrl % '1'
imageSearch = compile(r'(istrip_files/strips/.+?)"') imageSearch = compile(r'(istrip_files/strips/.+?)"')
prevSearch = compile(r'</a><a href="(.+?)"><img src="images/top_back.jpg" ') prevSearch = compile(r'</a><a href="(.+?)"><img src="images/top_back.jpg" ')
@ -94,10 +94,10 @@ class WhiteNoise(_BasicScraper):
class WhyTheLongFace(_BasicScraper): class WhyTheLongFace(_BasicScraper):
baseurl = 'http://www.absurdnotions.org/' baseUrl = 'http://www.absurdnotions.org/'
rurl = escape(baseurl) rurl = escape(baseUrl)
url = baseurl + 'wtlf200709.html' url = baseUrl + 'wtlf200709.html'
stripUrl = baseurl + 'wtlf%s.html' stripUrl = baseUrl + 'wtlf%s.html'
firstStripUrl = stripUrl % '200306' firstStripUrl = stripUrl % '200306'
imageSearch = compile(r'<img src="(%swtlf.+?|lf\d+.\w{1,4})"' % rurl, IGNORECASE) imageSearch = compile(r'<img src="(%swtlf.+?|lf\d+.\w{1,4})"' % rurl, IGNORECASE)
multipleImagesPerStrip = True multipleImagesPerStrip = True
@ -134,26 +134,26 @@ class Wondermark(_BasicScraper):
class WorldOfMrToast(_BasicScraper): class WorldOfMrToast(_BasicScraper):
baseurl = 'http://www.theimaginaryworld.com/' baseUrl = 'http://www.theimaginaryworld.com/'
url = baseurl + 'mrTcomicA.html' url = baseUrl + 'mrTcomicA.html'
stripUrl = baseurl + '%s.html' stripUrl = baseUrl + '%s.html'
imageSearch = compile(tagre("img", "src", r'(comic[^"]+)')) imageSearch = compile(tagre("img", "src", r'(comic[^"]+)'))
# list the archive links since there is no prev/next navigation # list the archive links since there is no prev/next navigation
prevurls = ( prevurls = (
url, url,
baseurl + 'mrTcomicW02.html', baseUrl + 'mrTcomicW02.html',
baseurl + 'mrTcomicW01.html', baseUrl + 'mrTcomicW01.html',
baseurl + 'mrGcomic03.html', baseUrl + 'mrGcomic03.html',
baseurl + 'mrGcomic02.html', baseUrl + 'mrGcomic02.html',
baseurl + 'mrGcomic01.html', baseUrl + 'mrGcomic01.html',
baseurl + 'mrTcomicT05.html', baseUrl + 'mrTcomicT05.html',
baseurl + 'mrTcomicT04.html', baseUrl + 'mrTcomicT04.html',
baseurl + 'mrTcomicT03.html', baseUrl + 'mrTcomicT03.html',
baseurl + 'mrTcomicT02.html', baseUrl + 'mrTcomicT02.html',
baseurl + 'mrTcomicT01.html', baseUrl + 'mrTcomicT01.html',
baseurl + 'mrTcomicIW3.html', baseUrl + 'mrTcomicIW3.html',
baseurl + 'mrTcomicIW2.html', baseUrl + 'mrTcomicIW2.html',
baseurl + 'mrTcomicIW1.html', baseUrl + 'mrTcomicIW1.html',
) )
firstStripUrl = prevurls[-1] firstStripUrl = prevurls[-1]
multipleImagesPerStrip = True multipleImagesPerStrip = True