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

xkcd now hone with xpaths

Browse source
This commit is contained in:
Damjan Košir 2016-08-18 21:28:25 +12:00
parent 9ba184eb43
commit c04c62e92b
1 changed files with 6 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
dosagelib/plugins/x.py
View file

@ -5,26 +5,20 @@
from __future__ import absolute_import, division, print_function
from re import compile
from ..scraper import _BasicScraper
from ..scraper import _ParserScraper
from ..helpers import bounceStarter
from ..util import tagre
class Xkcd(_BasicScraper):
class Xkcd(_ParserScraper):
name = 'xkcd'
url = 'http://xkcd.com/'
starter = bounceStarter
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src",
r'(//imgs\.xkcd\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/\d+/)', before="prev"))
nextSearch = compile(tagre("a", "href", r'(/\d+/)', before="next"))
imageSearch = '//div[@id="comic"]/img'
prevSearch = '//a[@rel="prev"]'
nextSearch = '//a[@rel="next"]'
help = 'Index format: n (unpadded)'
textSearch = compile(tagre("img", "title", r'([^"]+)',
before=r'//imgs\.xkcd\.com/comics/'))
textSearch = '//div[@id="comic"]/img/@title'
def namer(self, image_url, page_url):
index = int(page_url.rstrip('/').rsplit('/', 1)[-1])