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

Fix TheWhiteboard

Browse source
This commit is contained in:
Techwolf 2019-06-12 23:42:12 -07:00 committed by Tobias Gruetzmacher
parent b055a8574f
commit ed3acd2d2f
1 changed files with 6 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
dosagelib/plugins/t.py
View file

@ -109,13 +109,15 @@ class TheThinHLine(_TumblrScraper):
class TheWhiteboard(_ParserScraper): class TheWhiteboard(_ParserScraper):
BROKEN_PAGE_MIDDLE = compile(r'</body></html><') BROKEN_PAGE_MIDDLE = compile(r'</body></html>\n<')
url = 'http://www.the-whiteboard.com/' url = 'http://www.the-whiteboard.com/'
imageSearch = '//center/img' stripUrl = url + 'auto%s.html'
prevSearch = '//a[text()="previous"]' firstStripUrl = stripUrl % 'wb001'
imageSearch = '//img[contains(@src, "auto")]'
prevSearch = '//a[.//img[contains(@src, "previous")]]'
# Another ugly hack :(
def _parse_page(self, data): def _parse_page(self, data):
# Ugly hack to fix broken HTML
data = self.BROKEN_PAGE_MIDDLE.sub('<', data) data = self.BROKEN_PAGE_MIDDLE.sub('<', data)
return super(TheWhiteboard, self)._parse_page(data) return super(TheWhiteboard, self)._parse_page(data)