Some fixes...

AbstruseGoose: fixed prev
Carciphona: fixed latest
Curtailed: fixed image and prev (moved to WP)
DorkTower: fixed image search
GrrlPower: fixed site name issue
MadamAndEve: archive not updated in a long time, but current strip is.
Works, but needs to be run daily.
PennyArcade: fixed namer
PvPonline: fixed prev

dosagelib/plugins/a.py

@@ -36,7 +36,8 @@ class AbstruseGoose(_BasicScraper):
     stripUrl = url + '%s'
     firstStripUrl = stripUrl % '1'
     imageSearch = compile(tagre('img', 'src', r'(http://abstrusegoose\.com/strips/[^<>"]+)'))
-    prevSearch = compile(tagre('a', 'href', r'(%s\d+)' % rurl) + r'&laquo; Previous</a>')
+    prevSearch = compile(tagre('a', 'href', r'(%s\d+)' % rurl) + r'&laquo; Previous')
+    nextSearch = compile(tagre('a', 'href', r'(%s\d+)' % rurl) + r'Next &raquo;')
     help = 'Index format: n (unpadded)'
     textSearch = compile(tagre("img", "title", r'([^"]+)'))
 

dosagelib/plugins/c.py

@@ -46,8 +46,7 @@ class Carciphona(_BasicScraper):
     stripUrl = url + 'view.php?page=%s&chapter=%s'
     imageSearch = compile(tagre("div", "style", r'background-image:url\((_pages[^)]*)\)'))
     prevSearch = compile(tagre("a", "href", r'(view\.php\?[^"]*)', after="prevarea"))
-    latestSearch = compile(tagre("a", "href", r'(view\.php\?[^"]*)') +
+    latestSearch = compile(tagre("a", "href", r'(view\.php\?page=[0-9]+[^"]*)'))
-      tagre("span", "class", "linkslast"))
     help = 'Index format: None'
     starter = indirectStarter(url, latestSearch)
 
@@ -385,8 +384,8 @@ class Curtailed(_BasicScraper):
     stripUrl = url + '%s/'
     firstStripUrl = stripUrl % '2012/04/08/sneeze'
     rurl = escape(url)
-    imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]*)' % rurl))
+    imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/[0-9]+/[^"]*)' % rurl))
-    prevSearch = compile(tagre("a", "href", r'(%s\d{4}/[^"]*)' % rurl, after="navi-prev"))
+    prevSearch = compile('<a href="([^"]*)" class="comic-nav-base comic-nav-previous"')
     help = 'Index format: yyyy/mm/dd/stripname'
 
 

dosagelib/plugins/d.py

@@ -243,7 +243,7 @@ class DorkTower(_BasicScraper):
     rurl = escape(url)
     stripUrl = url + '%s/'
     firstStripUrl = stripUrl % '1997/01/01/shadis-magazine-strip-1'
-    imageSearch = compile(tagre("img", "src", r'(%sfiles/\d+/\d+/[^"]+\.gif)' % rurl))
+    imageSearch = compile(tagre("div", "class", "entry-content") + "\s*<p>\s*" + tagre("img", "src", r'(%sfiles/[0-9]+/[0-9]+/[^"]*Dork[^"]+\.(?:gif|jpg))' % rurl, after=' alt'))
     prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl)+"Previous")
     help = 'Index format: yyyy/mm/dd/stripname-dd-mm-yy'
 

dosagelib/plugins/g.py

@@ -189,12 +189,12 @@ class GoneWithTheBlastwave(_BasicScraper):
 
 class GrrlPower(_BasicScraper):
     description = u'Grrl Power - A webcomic about superheroines.'
-    url = 'http://www.grrlpowercomic.com/'
+    url = 'http://grrlpowercomic.com/'
     rurl = escape(url)
     stripUrl = url + 'archives/%s'
     firstStripUrl = stripUrl % '48'
-    imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
+    imageSearch = compile(tagre("img", "src", r'(.*/comics/[^"]+)'))
-    prevSearch = compile(tagre("a", "href", r'(%sarchives/\d+)' % rurl, after="navi-prev"))
+    prevSearch = compile(tagre("a", "href", r'(.*/archives/\d+)', after="navi-prev"))
     help = 'Index format: number'
 
 

dosagelib/plugins/m.py

@@ -17,12 +17,10 @@ class MacHall(_BasicScraper):
     help = 'Index format: yyyy-mm-dd'
 
 
-# broken links - disable for now
 class MadamAndEve(_BasicScraper):
-    url = 'http://www.madamandeve.co.za/week_of_cartns.php'
+    url = 'http://www.madamandeve.co.za/'
     stripUrl = None
-    imageSearch = compile(r'<IMG BORDER="0" SRC="(cartoons/me\d{6}\.(gif|jpg))">')
+    imageSearch = compile(tagre('img', 'src', r'(/cartoons/me\d{6}\.(gif|jpg))'))
-    prevSearch = compile(r'<a href="(weekend_cartoon.php)"')
     multipleImagesPerStrip = True
 
 

dosagelib/plugins/p.py

@@ -112,8 +112,8 @@ class PennyArcade(_BasicScraper):
 
     @classmethod
     def namer(cls, imageUrl, pageUrl):
-        dummy, yyyy, mm, dd = pageUrl.rsplit('/', 3)
+        p = pageUrl.split('/')
-        return '%04d%02d%02d' % (int(yyyy), int(mm), int(dd))
+        return '%04d%02d%02d' % (int(p[4]), int(p[5]), int(p[6]))
 
 
 class PeppermintSaga(_BasicScraper):
@@ -266,5 +266,5 @@ class PvPonline(_BasicScraper):
     url = 'http://pvponline.com/comic'
     stripUrl = url + '%s'
     imageSearch = compile(tagre("img", "src", r'(http://s3[^"]+\.amazonaws\.com/pvponlinenew/img/comic/\d+/\d+/pvp[^"]+\.jpg)'))
-    prevSearch = compile(tagre("a", "href", r'(/comic/[^"]+)', after="Previous"))
+    prevSearch = compile(tagre("a", "href", r'(/comic/[^"]+)', after="left divider"))
     help = 'Index format: yyyy/mm/dd/stripname'