added a CMS ComicControl, moved some existing comics there, added StreetFighter and Metacarpolis

This commit is contained in:
Damjan Košir 2015-08-03 22:40:06 +12:00
parent 648a84e38e
commit f8a163a361
4 changed files with 29 additions and 17 deletions

View file

@ -0,0 +1,29 @@
# -*- coding: utf-8 -*-
from dosagelib.helpers import indirectStarter
from ..scraper import make_scraper, _ParserScraper
def add(name, url, firstUrl=None, starter=None, textSearch=None, lang=None):
attrs = dict(
name=name,
url=url,
imageSearch=['//div[@id="cc-comicbody"]//img'],
prevSearch=['//a[@rel="prev"]']
)
if lang:
attrs['lang'] = lang
if firstUrl:
attrs['firstUrl'] = url + firstUrl
if starter:
attrs['starter'] = starter
if textSearch:
attrs['textSearch'] = textSearch
globals()[name] = make_scraper(name, _ParserScraper, **attrs)
add('GoGetARoomie', 'http://www.gogetaroomie.com')
add('KiwiBlitz', 'http://www.kiwiblitz.com')
add('LetsSpeakEnglish', 'http://www.marycagle.com')
add('Metacarpolis', 'http://www.metacarpolis.com')
add('Spinnerette', 'http://www.spinnyverse.com')
add('StreetFighter', 'http://www.streetfightercomics.com')

View file

@ -131,13 +131,6 @@ class GoblinsComic(_BasicScraper):
help = 'Index format: ddmmyyyy'
class GoGetARoomie(_ParserScraper):
url = 'http://www.gogetaroomie.com/index.php'
imageSearch = '//div[@id="cc-comicbody"]//img'
prevSearch = '//a[@rel="prev"]'
help = 'Index format: nnn'
class GoneWithTheBlastwave(_BasicScraper):
url = 'http://www.blastwave-comic.com/index.php?p=comic&nro=1'
starter = indirectStarter(url,

View file

@ -47,11 +47,6 @@ class KillerKomics(_BasicScraper):
prevSearch = compile(r'<div id="precedent"><a href="(.+?)"')
help = 'Index format: strip-name'
class KiwiBlitz(_ParserScraper):
url = 'http://www.kiwiblitz.com/'
imageSearch = '//div[@id="cc-comicbody"]//img'
prevSearch = '//a[@rel="prev"]'
# XXX disallowed by robots.txt
class _Kofightclub(_BasicScraper):

View file

@ -48,11 +48,6 @@ class LeastICouldDo(_BasicScraper):
compile(tagre("a", "href", r'(%scomic/\d+/)' % rurl, after="feature-comic")))
help = 'Index format: yyyymmdd'
class LetsSpeakEnglish(_ParserScraper):
url = 'http://www.marycagle.com/'
imageSearch = '//div[@id="cc-comicbody"]//img'
prevSearch = '//a[@rel="prev"]'
class Lint(_BasicScraper):
url = 'http://www.purnicellin.com/lint/'