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

Code cleanup.

Browse source
This commit is contained in:
Bastian Kleineidam 2013-03-07 18:22:39 +01:00
parent 9729c3aebf
commit 736d9aa8cf
1 changed files with 13 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
dosagelib/scraper.py
View file

@ -9,25 +9,15 @@ from .output import out
class _BasicScraper(object): class _BasicScraper(object):
'''Base class with scrape functions for comics. '''Base class with scrape functions for comics.'''
@type url: C{string} # The URL for the comic strip
@cvar url: The URL for the comic strip. url = None
@type stripUrl: C{string}
@cvar stripUrl: A string that is interpolated with the strip index
to yield the URL for a particular strip.
@type firstStripUrl: C{string} optional
@cvar firstStripUrl: Stop searching for previous URLs at this URL.
If not set and no previous URL is found a warning is printed.
@type imageSearch: C{regex}
@cvar imageSearch: A compiled regex that will locate the strip image URL
when applied to the strip page.
@type prevSearch: C{regex}
@cvar prevSearch: A compiled regex that will locate the URL for the
previous strip when applied to a strip page.
'''
# stop at this URL # A string that is interpolated with the strip index to yield the URL for a particular strip.
stripUrl = None
# Stop search for previous URLs at this URL
firstStripUrl = None firstStripUrl = None
# if more than one image per URL is expected # if more than one image per URL is expected
@ -42,6 +32,12 @@ class _BasicScraper(object):
# a description of the comic contents # a description of the comic contents
description = '' description = ''
# compiled regular expression that will locate the URL for the previous strip in a page
prevSearch = None
# compiled regular expression that will locate the strip image URLs strip in a page
imageSearch = None
# usually the index format help # usually the index format help
help = '' help = ''