Fix DoghouseDiaries
This commit is contained in:
parent
fc280badb6
commit
5e79ff9d84
1 changed files with 9 additions and 4 deletions
|
@ -193,15 +193,20 @@ class DoemainOfOurOwn(_ParserScraper):
|
||||||
help = 'Index format: yyyy-mm-dd'
|
help = 'Index format: yyyy-mm-dd'
|
||||||
|
|
||||||
|
|
||||||
class DogHouseDiaries(_BasicScraper):
|
class DoghouseDiaries(_ParserScraper):
|
||||||
url = 'http://thedoghousediaries.com/'
|
url = 'http://thedoghousediaries.com/'
|
||||||
rurl = escape(url)
|
|
||||||
stripUrl = url + '%s'
|
stripUrl = url + '%s'
|
||||||
firstStripUrl = stripUrl % '34'
|
firstStripUrl = stripUrl % '34'
|
||||||
prevSearch = compile(r"<a id='previouslink' href='(http://thedoghousediaries.com/\d+)'")
|
imageSearch = '//img[@class="imgcomic"]'
|
||||||
imageSearch = compile(r"<img src='(dhdcomics/[^']+)'")
|
textSearch = imageSearch + '/@title'
|
||||||
|
prevSearch = '//a[@id="previouslink"]'
|
||||||
|
nextSearch = '//a[@id="nextlink"]'
|
||||||
|
starter = bounceStarter
|
||||||
help = 'Index format: number'
|
help = 'Index format: number'
|
||||||
|
|
||||||
|
def namer(self, imageUrl, pageUrl):
|
||||||
|
return pageUrl.rsplit('/', 1)[-1] + '.' + imageUrl.rsplit('.', 1)[-1]
|
||||||
|
|
||||||
|
|
||||||
class DominicDeegan(_ParserScraper):
|
class DominicDeegan(_ParserScraper):
|
||||||
url = 'http://www.dominic-deegan.com/'
|
url = 'http://www.dominic-deegan.com/'
|
||||||
|
|
Loading…
Reference in a new issue