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

All scrapers must have an URL.

Browse source
This commit is contained in:
Bastian Kleineidam 2013-04-26 06:53:05 +02:00
parent 6244ab9af6
commit cafa37fcb1
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
dosagelib/plugins/s.py
View file

@ -11,7 +11,7 @@ from ..util import tagre, getPageContent
class SabrinaOnline(_BasicScraper): class SabrinaOnline(_BasicScraper):
description = u'Skunks, computers and porn' description = u'Skunks, computers and porn'
baseUrl = 'http://sabrina-online.com/' url = 'http://sabrina-online.com/'
imageSearch = compile(tagre("a", "href", r'(strips/[^"]*)')) imageSearch = compile(tagre("a", "href", r'(strips/[^"]*)'))
prevSearch = compile(tagre("a", "href", r"(\d\d\d\d-\d\d.html)") + prevSearch = compile(tagre("a", "href", r"(\d\d\d\d-\d\d.html)") +
tagre("img", "src", "b_back.gif")) tagre("img", "src", "b_back.gif"))
@ -22,11 +22,11 @@ class SabrinaOnline(_BasicScraper):
@classmethod @classmethod
def starter(cls): def starter(cls):
"""Pick last one in a list of archive pages.""" """Pick last one in a list of archive pages."""
url = cls.baseUrl + 'archive.html' archive = cls.url + 'archive.html'
data, baseUrl = getPageContent(url, cls.session) data = getPageContent(archive, cls.session)[0]
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.baseUrl + archivepages[-1] return cls.url + archivepages[-1]
class SailorsunOrg(_BasicScraper): class SailorsunOrg(_BasicScraper):