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

Fixes and Additions...

Browse source 
Fixed SabrinaOnline
Fixed SMBC
Added StandStillStaySilent (partial, prevsearch not working yet)
This commit is contained in:
DirkReiners 2015-04-29 10:37:14 -05:00
parent 749beff7a3
commit 1438330a94
1 changed files with 14 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
dosagelib/plugins/s.py
View file

@ -22,7 +22,7 @@ class SabrinaOnline(_BasicScraper):
def starter(cls): def starter(cls):
"""Pick last one in a list of archive pages.""" """Pick last one in a list of archive pages."""
archive = cls.url + 'archive.html' archive = cls.url + 'archive.html'
data = getPageContent(archive, cls.session)[0] data = getPageContent(archive, cls.session)
search = compile(tagre("a", "href", r"(\d\d\d\d-\d\d.html)")) search = compile(tagre("a", "href", r"(\d\d\d\d-\d\d.html)"))
archivepages = search.findall(data) archivepages = search.findall(data)
return cls.url + archivepages[-1] return cls.url + archivepages[-1]
@ -87,9 +87,9 @@ class ScenesFromAMultiverse(_BasicScraper):
firstStripUrl = stripUrl % '2010/06/14/parenthood' firstStripUrl = stripUrl % '2010/06/14/parenthood'
imageSearch = ( imageSearch = (
compile(tagre("div", "id", "comic") + r"\s*" + compile(tagre("div", "id", "comic") + r"\s*" +
tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl)), tagre("img", "src", r'(.*amultiverse.com/wp-content/uploads/\d+/\d+/[^"]+)')),
compile(tagre("div", "id", "comic") + r"\s*" + tagre("a", "href", r'[^"]*') + compile(tagre("div", "id", "comic") + r"\s*" + tagre("a", "href", r'[^"]*') +
tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl)), tagre("img", "src", r'(.*amultiverse.com/wp-content/uploads/\d+/\d+/[^"]+)')),
) )
prevSearch = compile(tagre("a", "href", r'(%scomic/\d+\d+/\d+/\d+/[^"]+)' % rurl, after="prev")) prevSearch = compile(tagre("a", "href", r'(%scomic/\d+\d+/\d+/\d+/[^"]+)' % rurl, after="prev"))
help = 'Index format: yyyy/mm/dd/stripname' help = 'Index format: yyyy/mm/dd/stripname'
@ -279,15 +279,20 @@ class SluggyFreelance(_BasicScraper):
help = 'Index format: yymmdd' help = 'Index format: yymmdd'
class SMBC(_BasicScraper): class SMBC(_ParserScraper):
url = 'http://www.smbc-comics.com/' url = 'http://www.smbc-comics.com/'
rurl = escape(url) rurl = escape(url)
stripUrl = url + '?id=%s' stripUrl = url + '?id=%s'
firstStripUrl = stripUrl % '1' firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r"(%scomics/\d{8}(?:\w2?|-\d)?\.\w{3})\s*" % rurl, quote="'")) imageSearch = '//img[@id="comic"]'
prevSearch = compile(tagre("a", "href", r'([^"]+)#comic', after="backRollover")) prevSearch = '//a[@class="prev"]'
help = 'Index format: nnnn' help = 'Index format: nnnn'
@classmethod
def namer(cls, imageUrl, pageUrl):
"""Remove random noise from name."""
return imageUrl.rsplit('-', 1)[-1]
def shouldSkipUrl(self, url, data): def shouldSkipUrl(self, url, data):
"""Skip promo or missing update pages.""" """Skip promo or missing update pages."""
return url in ( return url in (
@ -437,13 +442,13 @@ class SPQRBlues(_BasicScraper):
help = 'Index format: number' help = 'Index format: number'
class StandStillStaySilent(_BasicScraper): class StandStillStaySilent(_ParserScraper):
url = 'http://www.sssscomic.com/comic.php' url = 'http://www.sssscomic.com/comic.php'
rurl = escape(url) rurl = escape(url)
stripUrl = url + '?page=%s' stripUrl = url + '?page=%s'
firstStripUrl = stripUrl % '1' firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'(comicpages/[^"]+)', before="comicnormal")) imageSearch = '//img[@class="comicnormal"]'
prevSearch = compile(tagre("a", "href", r"([^']+)", quote="'") + tagre("div", "id", r'navprev')) prevSearch = '//a//div[@id="navprev"]'
help = 'Index Format: number' help = 'Index Format: number'