Add support for SurvivingTheWorld and TumbleDryComics (#84)
This commit is contained in:
parent
0973570295
commit
233da3e052
2 changed files with 43 additions and 0 deletions
|
@ -492,3 +492,23 @@ class StuffNoOneToldMe(_BasicScraper):
|
|||
|
||||
class SupernormalStep(_ComicControlScraper):
|
||||
url = 'http://supernormalstep.com/'
|
||||
|
||||
|
||||
class SurvivingTheWorld(_ParserScraper):
|
||||
url = 'http://survivingtheworld.net/'
|
||||
stripUrl = url + '%s'
|
||||
firstStripUrl = stripUrl % 'Lesson1.html'
|
||||
imageSearch = [
|
||||
'//div[@class="img"]/img', # When there's one image per strip
|
||||
'//div[@class="img"]/p/img', # When there's multiple images per strip
|
||||
'//td/img' # Special case for Lesson1296.html
|
||||
]
|
||||
prevSearch = [
|
||||
'//li[@class="previous"]/a',
|
||||
'//td/a' # Special case for Lesson1296.html
|
||||
]
|
||||
multipleImagesPerStrip = True
|
||||
help = 'Index format: name'
|
||||
|
||||
def getIndexStripUrl(self, index):
|
||||
return self.stripUrl % index + ".html"
|
||||
|
|
|
@ -147,6 +147,29 @@ class TracyAndTristan(_BasicScraper):
|
|||
help = 'Index format: number'
|
||||
|
||||
|
||||
class TumbleDryComics(_WordPressScraper):
|
||||
url = 'http://tumbledrycomics.com/'
|
||||
firstStripUrl = url + 'comic/we-need-to-get-high-jpg/'
|
||||
textSearch = '//div[@id="comic"]//img/@alt'
|
||||
multipleImagesPerStrip = True
|
||||
adult = True
|
||||
help = 'Index format: name'
|
||||
|
||||
def getIndexStripUrl(self, index):
|
||||
return self.url + "comics/" + index
|
||||
|
||||
def namer(self, image_url, page_url):
|
||||
# Most images have the date they were posted in the filename
|
||||
# For those that don't we can get the month and year from the image url
|
||||
parts = image_url.split('/')
|
||||
year = parts[5]
|
||||
month = parts[6]
|
||||
filename = parts[7]
|
||||
if not filename.startswith(year):
|
||||
filename = year + "-" + month + "-" + filename
|
||||
return filename
|
||||
|
||||
|
||||
class TwoGuysAndGuy(_BasicScraper):
|
||||
url = 'http://www.twogag.com/'
|
||||
rurl = escape(url)
|
||||
|
|
Loading…
Reference in a new issue