"arlonjaniscomicscom":{"name":"Arlo and Janis","link":'http://comics.com/arlo&janis/',"start":"2010-02-01","dbfile":dbdir + "comicdb.arlonjanis.csv"},
"bccomicscom":{"name":"B.C.","link":"http://comics.com/bc/","start":"2010-02-01","dbfile":dbdir + "comicdb.bc.csv"},
"ballard_streetcomicscom":{"name":"Ballard Street","link":"http://comics.com/ballard_street/","start":"2010-02-01","dbfile":dbdir + "comicdb.ballardstreet.csv"},
- "babyblues":{"name":"Baby Blues","link":"http://www.babyblues.com/","start":"01/19/2010","dbfile":dbdir + "comicdb.babyblues.csv"},
"bencomicscom":{"name":"Ben","link":'http://comics.com/ben/',"start":"2010-02-01","dbfile":dbdir + "comicdb.ben.csv"},
"bettycomicscom":{"name":"Betty","link":"http://comics.com/betty/","start":"2010-02-01","dbfile":dbdir + "comicdb.betty.csv"},
"big_natecomicscom":{"name":"Big Nate","link":"http://comics.com/big_nate/","start":"2010-02-01","dbfile":dbdir + "comicdb.bignate.csv"},
"amazing_spidermanckdm":{"name":"The Amazing Spider-Man","link":'http://content.comicskingdom.net/Spiderman/',"start":"20100209","dbfile":dbdir + "comicdb.spiderman.csv"},
"apartment_3-gckdm":{"name":"Apartment 3-G","link":'http://content.comicskingdom.net/Apartment_3-G/',"start":"20100209","dbfile":dbdir + "comicdb.partment3g.csv"},
"arcticckdm":{"name":"Arctic Circle","link":'http://content.comicskingdom.net/Arctic/',"start":"20100209","dbfile":dbdir + "comicdb.arctic.csv"},
+ "baby_bluesckdm":{"name":"Baby Blues","link":"http://content.comicskingdom.net/Baby_Blues/","start":"20100319","dbfile":dbdir + "comicdb.babybluesckdm.csv"},
"barney_googleckdm":{"name":"Barney Google and Snuffy Smith","link":'http://content.comicskingdom.net/Barney_Google/',"start":"20100209","dbfile":dbdir + "comicdb.barneygoogle.csv"},
"beetle_baileyckdm":{"name":"Beetle Bailey","link":'http://content.comicskingdom.net/Beetle_Bailey/',"start":"20100209","dbfile":dbdir + "comicdb.beetlebailey.csv"},
"better_halfckdm":{"name":"Better Half","link":'http://content.comicskingdom.net/Better_Half/',"start":"20100209","dbfile":dbdir + "comicdb.betterhalf.csv"},
"toddckdm":{"name":"Todd the Dinosaur","link":'http://content.comicskingdom.net/Todd/',"start":"20100209","dbfile":dbdir + "comicdb.todd.csv"},
"zippy_the_pinheadckdm":{"name":"Zippy the Pinhead","link":'http://content.comicskingdom.net/Zippy_the_Pinhead/',"start":"20100209","dbfile":dbdir + "comicdb.zippythepinhead.csv"},
"zitsckdm":{"name":"Zits","link":'http://content.comicskingdom.net/Zits/',"start":"20100209","dbfile":dbdir + "comicdb.zits.csv"},
- "calvinandhobbesmatinmaapallo":{"name":"Calvin and Hobbes","link":"http://matin.maapallo.org/site.pl/selain/?c=lassijaleevi&i=","start":"2008","dbfile":dbdir + "comicdb.calvinandhobbes.csv"},\r
- "viivijawagnermatinmaapallo":{"name":"Viivi ja Wagner","link":"http://matin.maapallo.org/site.pl/selain/?c=viivijawagner&i=","start":"2600","dbfile":dbdir + "comicdb.viivijawagner.csv"},\r
+ "viivijawagnerhesari":{"name":"Viivi ja Wagner","link":"http://www.hs.fi/viivijawagner/","start":"1135255013425","dbfile":dbdir + "comicdb.viivijawagner.csv"},
+ "fingerporihesari":{"name":"Fingerpori","link":"http://www.hs.fi/fingerpori/","start":"1135255790645","dbfile":dbdir + "comicdb.fingerpori.csv"},
# fetch earlier
def fetch_earlier(self, comic, earliest):
print "fetch before, " + comic + " earliest"
- if comic == "cyanide" or comic == "wulff" or comic == "babyblues" or comic[-9:] == "comicscom" or comic[-13:] == "matinmaapallo":
+ if comic == "cyanide" or comic == "wulff" or comic == "babyblues" or comic[-9:] == "comicscom" or comic[-6:] == "hesari":
print "getting get_prev_id..."
comicid = self.get_prev_id(comic,earliest)
if not comicid:
def fetch_newer(self, comic, newest):
- if comic == "cyanide" or comic == "wulff" or comic == "babyblues" or comic[-9:] == "comicscom" or comic[-13:] == "matinmaapallo":
+ if comic == "cyanide" or comic == "wulff" or comic == "babyblues" or comic[-9:] == "comicscom" or comic[-6:] == "hesari":
comicid = self.get_next_id(comic,newest)
if not comicid:
print "already at last comic"
s = f.read()
f.close()
return self.parse_comics_com(comic, s, 'next')
- elif comic[-13:] == "matinmaapallo":\r
- realcomic = string.split( comic, 'matinmaapallo', 1)\r
- linkname = realcomic[0]\r
- link = "http://matin.maapallo.org/site.pl/selain/?c=" + linkname + "&i=" + str(number)\r
- print "link: " + link\r
- try:\r
- f = urllib2.urlopen(link)\r
- hcode = f.code\r
- except:\r
- hcode = 404\r
- print "got hcode = " + str(hcode) + "\n"\r
- print "I am now here"\r
- if (hcode != 200):\r
- return False\r
- else:\r
- print "checking next matin maapallo issue.."\r
- s = f.read()\r
- f.close()\r
- # title:\r
- splt = string.split(s, 'seuraava', 1)\r
- if len(splt) < 2:\r
- print "no 'prev' found"\r
- return False\r
- else:\r
- next = str( int(number) + 1 )\r
- print "got next: " + next\r
- return next\r
+ elif comic[-6:] == "hesari":
+ realcomic = string.split( comic, 'hesari', 1)
+ linkname = realcomic[0]
+ link = comics[comic]['link'] + str(number)
+ print "link: " + link
+ try:
+ f = urllib2.urlopen(link)
+ hcode = f.code
+ except:
+ hcode = 404
+ print "got hcode = " + str(hcode) + "\n"
+ if (hcode != 200):
+ return False
+ else:
+ print "checking next HS issue..."
+ s = f.read()
+ f.close()
+ # title:
+ vw = string.split(s, '<div id=\"VW_container\">',1)
+ vw2=string.split(vw[1], '<div class=\"next\"', 1)
+ vw3=string.split(vw2[1], '</div>', 1)
+ splt = string.split(vw3[0], 'Seuraava', 1)
+ if len(splt) < 2:
+ print "no 'next' found"
+ return False
+ else:
+ splt3=string.split(vw3[0], '<a href=\"http://www.hs.fi/' + linkname + '/', 1)
+ splt4=string.split(splt3[1], '\" class=\"vw\"', 1)
+ next = splt4[0]
+ print "got next: " + next
+ return next
else:
return False
s = f.read()
f.close()
return self.parse_comics_com(comic, s, 'prev')
- elif comic[-13:] == 'matinmaapallo':\r
- print "checking matin maapallo..."\r
- prevint = int( number ) - 1\r
- if ( prevint == 0 ):\r
- print "cannot go previous"\r
- return False\r
- else:\r
- print "got number: " + number\r
- print "got previous: " + str(prevint)\r
- return str(prevint)
+ elif comic[-6:] == 'hesari':
+ print "checking prev..."
+ realcomic = string.split( comic, 'hesari', 1)
+ linkname = realcomic[0]
+ link = comics[comic]['link'] + str(number)
+ print "link: " + link
+ try:
+ f = urllib2.urlopen(link)
+ hcode = f.code
+ except:
+ hcode = 404
+ print "got hcode = " + str(hcode) + "\n"
+ if (hcode != 200):
+ return False
+ else:
+ print "checking prev HS issue.."
+ s = f.read()
+ f.close()
+ # title:
+ vw = string.split(s, '<div id=\"VW_container\">',1)
+ vw2=string.split(vw[1], '<div class=\"previous\"', 1)
+ vw3=string.split(vw2[1], '</div>', 1)
+ splt = string.split(vw3[0], 'Edellinen', 1)
+ if len(splt) < 2:
+ print "no 'prev' found"
+ return False
+ else:
+ splt3=string.split(vw3[0], '<a href=\"http://www.hs.fi/' + linkname + '/', 1)
+ splt4=string.split(splt3[1], '\" class=\"vw\"', 1)
+ next = splt4[0]
+ print "got prev: " + next
+ return next
else:
return False
link = "http://www.babyblues.com/archive/index.php?formname=getstrip&GoToDay=" + str(number)
elif comic[-9:] == 'comicscom':
link = comics[comic]['link'] + str(number) + "/"
- elif comic[-13:] == 'matinmaapallo':
+ elif comic[-6:] == 'hesari':
link = comics[comic]['link'] + str(number)
elif comic[-4:] == 'ckdm':
splt = string.rsplit(comics[comic]['link'], "/", 2)
return False
print "link: " + link
- try:
- f = urllib2.urlopen(link)
- hcode = f.code
- except:
- hcode = 404
- print "got hcode = " + str(hcode) + "\n"
+ #try:
+ f = urllib2.urlopen(link)
+ hcode = f.code
+ #except:
+ # hcode = 404
+ print "got hcode = " + str(hcode) + "asdf\n"
if (hcode != 200):
return False
else:
url = self.parse_comics_com(comic, f.read(), 'url')
f.close()
title = number
- elif comic[-13:] == 'matinmaapallo':
- # matin maapallo links is type .gif
+ elif comic[-6:] == 'hesari':
+ # HS images are usually type .gif
s = f.read()
f.close()
- splt = string.split(s, 'http://matin.maapallo.org/kuvatuuppari/', 1)
+ splt = string.split(s, 'http://www.hs.fi/kuvat/iso_webkuva/', 1)
#print "splitted" + "\n"
- flnm = string.split(splt[1], ".gif", 1)
+ flnm = string.split(splt[1], "\" align=", 1)
#print flnm[0] + "\n" + "url: "
- url = 'http://matin.maapallo.org/kuvatuuppari/' + flnm[0] + '.gif'
+ url = 'http://www.hs.fi/kuvat/iso_webkuva/' + flnm[0]
#print url
- splt3 = string.split(s, '<h4>', 1)
- splt4 = string.split(splt3[1], '</h4>', 1)
- title = splt4[0]
- print title
+ splt3 = string.split(s, '<div id=\"VW_container\">',1)
+ splt4 = string.split(splt3[1], '<p>', 1)
+ splt5 = string.split(splt4[1], '</p>', 1)
+ title = splt5[0]
+ #print title
filename = str(number) + ".gif"
irow = [comic,number,link,url,filename,title]
return irow
-
elif comic[-4:] == 'ckdm':
url = link
title = number[:4] + "-" + number[4:6] + "-" + number[6:8]
def get_size_settings(self):
# defaults = {'width':480,'height':230}
- # options: w 798 700 600 500 480 400
- # options: h 420 360 310 270 240 200
+ # options: w 798 - 400
+ # options: h 420 - 200
print "checking to see if config file is available"
if os.path.isfile(sizefile) == True:
print "found " + sizefile