# -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2013 Bastian Kleineidam from re import compile, escape from ..scraper import _BasicScraper from ..helpers import bounceStarter, queryNamer, indirectStarter from ..util import tagre class PandyLand(_BasicScraper): url = 'http://pandyland.net/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\d+/)' % rurl, after="prev")) help = 'Index format: number' class ParadigmShift(_BasicScraper): url = 'http://www.paradigmshiftmanga.com/' starter = indirectStarter(url, compile(tagre("a", "href", r'([^"]+)', after="next-comic-link"))) stripUrl = url + 'ps/%s.html' imageSearch = compile(tagre("img", "src", r'([^"]*comics/ps/[^"]*)')) prevSearch = compile(tagre("a", "href", r'([^"]+)', after="previous-comic-link")) help = 'Index format: custom' class ParallelUniversum(_BasicScraper): url = 'http://www.paralleluniversum.net/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '001-der-comic-ist-tot' imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s[^"]+/)' % rurl) + tagre("span", "class", "prev")) help = 'Index format: number-stripname' lang = 'de' class PartiallyClips(_BasicScraper): url = 'http://partiallyclips.com/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2001/10/28/screaming-woman' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/mm/dd/stripname' class PastelDefender(_BasicScraper): baseurl = 'http://www.pasteldefender.com/' url = baseurl + 'coverbackcover.html' stripUrl = baseurl + '%s.html' firstStripUrl = stripUrl % 'cover' imageSearch = compile(r'First Comic)Archives/Strip.+?|(?=.+?">Previous Comic)(?!.+?">First Comic)Strip.+?)"') help = 'Index format: n (unpadded)' class PennyAndAggie(_BasicScraper): url = 'http://pennyandaggie.com/' rurl = escape(url) stripUrl = url + 'index.php?p=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.pennyandaggie\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r"(index\.php\?p\=\d+)", quote="'") + tagre("img", "src", r'%simages/previous_day\.gif' % rurl, quote="")) starter = indirectStarter(url, prevSearch) help = 'Index format: n (unpadded)' class PennyArcade(_BasicScraper): url = 'http://penny-arcade.com/comic/' rurl = escape(url) starter = bounceStarter(url, compile(tagre("a", "href", r'(%s[^"]+)' % rurl, before="btnNext")) ) stripUrl = url + '%s' firstStripUrl = stripUrl % '1998/11/18' imageSearch = compile(tagre("img", "src", r'(http://art\.penny-arcade\.com/photos/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, before="btnPrev")) help = 'Index format: yyyy/mm/dd' @classmethod def namer(cls, imageUrl, pageUrl): dummy, yyyy, mm, dd = pageUrl.rsplit('/', 3) return '%04d%02d%02d' % (int(yyyy), int(mm), int(dd)) class PeppermintSaga(_BasicScraper): url = 'http://www.pepsaga.com/' rurl = escape(url) stripUrl = url + '?p=%s' firstStripUrl = stripUrl % '3' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev")) help = 'Index format: number' class PHDComics(_BasicScraper): baseurl = 'http://phdcomics.com/' url = baseurl + 'comics.php' stripUrl = baseurl + 'comics/archive.php?comicid=%s' firstStripUrl = stripUrl % '1' 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="") + tagre("img", "src", r'(?:comics/)?images/prev_button\.gif', quote="")) help = 'Index format: number' class PicPakDog(_BasicScraper): url = 'http://www.picpak.net/' rurl = escape(url) stripUrl = url + 'comic/%s/' firstStripUrl = stripUrl % 'dogs-cant-spell' imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/\d+-\d+-\d+-[^"]+\.png)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl, after="navi-prev")) help = 'Index format: stripname' class Pixel(_BasicScraper): url = 'http://pixelcomic.net/' rurl = escape(url) stripUrl = url + '%s' firstStripUrl = stripUrl % '000.shtml' imageSearch = compile(tagre("img", "src", r'(\d+\.png)')) prevSearch = compile(tagre("a", "href", r'(%s\d+\.(?:php|shtml))' % rurl, before="prev")) help = 'Index format: nnn' class PiledHigherAndDeeper(_BasicScraper): url = 'http://www.phdcomics.com/comics/archive.php' starter = bounceStarter(url, compile(r'')) stripUrl = url + '?comicid=%s' firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r'(http://www\.phdcomics\.com/comics/archive/phd\d+s?\.gif)', quote="")) prevSearch = compile(r'') help = 'Index format: n (unpadded)' namer = queryNamer('comicid', usePageUrl=True) class Pimpette(_BasicScraper): url = 'http://pimpette.ca/' stripUrl = url + 'index.php?date=%s' firstStripUrl = stripUrl % '20030905' imageSearch = compile(tagre("img", "src", r'(strips/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(index\.php\?date=\d+)') + "Previous") help = 'Index format: yyyymmdd' # Broken navigation: prev link at http://planescapecomic.com/201.html points to same URL. class _PlanescapeSurvival(_BasicScraper): url = 'http://planescapecomic.com/' stripUrl = url + '%s.html' imageSearch = compile(r'src="(comics/.+?)"') prevSearch = compile(r'Previous]+?>]+?src="/previouscomic.gif">') help = 'Index format: yyyymmdd' 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")) help = 'Index format: yyyy/mm/dd/stripname'