Rewrite parse control using pywikibot.bot classes
To use the default pywikibot.classes making life easier at some point Beeing standardconform with pywikibot in handling args Related Task: [https://fs.golderweb.de/index.php?do=details&task_id=72 FS#72]
This commit is contained in:
172
reddiscparser.py
172
reddiscparser.py
@@ -22,11 +22,15 @@
|
|||||||
#
|
#
|
||||||
#
|
#
|
||||||
"""
|
"""
|
||||||
Script to parse all redpages in configured categories
|
Script to parse all reddisc pages in configured categories
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
|
||||||
import pywikibot
|
import pywikibot
|
||||||
from pywikibot import pagegenerators
|
from pywikibot import pagegenerators
|
||||||
|
from pywikibot.bot import ExistingPageBot, NoRedirectPageBot
|
||||||
|
|
||||||
import jogobot
|
import jogobot
|
||||||
|
|
||||||
@@ -34,51 +38,56 @@ import redpage
|
|||||||
import redfam
|
import redfam
|
||||||
|
|
||||||
|
|
||||||
def get_cat_pages( cat ):
|
class DiscussionParserBot(
|
||||||
|
# CurrentPageBot, # via next two sets 'current_page' on each treat()
|
||||||
|
ExistingPageBot, # CurrentPageBot only treats existing pages
|
||||||
|
NoRedirectPageBot ): # class which only treats non-redirects
|
||||||
"""
|
"""
|
||||||
Generates a iteratable generator-object with all pages listet in given
|
Botclass witch initialises the parsing process of Redundancy Discussions
|
||||||
category
|
|
||||||
|
|
||||||
@param cat Category to request
|
|
||||||
@type cat str
|
|
||||||
|
|
||||||
@returns generator Iteratable object with pages of given category
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
# Get site to work on from pywikibot config
|
def __init__( self, generator ):
|
||||||
site = pywikibot.Site()
|
|
||||||
|
|
||||||
# Retrieve the content of given category
|
|
||||||
category = pywikibot.Category( site, cat )
|
|
||||||
|
|
||||||
# Build an iteratable generator object with page objects for given category
|
|
||||||
generator = pagegenerators.CategorizedPageGenerator( category )
|
|
||||||
|
|
||||||
return generator
|
|
||||||
|
|
||||||
|
|
||||||
def main(*args):
|
|
||||||
"""
|
|
||||||
Handles process
|
|
||||||
"""
|
"""
|
||||||
|
Constructor
|
||||||
|
|
||||||
|
Parameters:
|
||||||
|
@param generator: The page generator that determines on which pages
|
||||||
|
to work.
|
||||||
|
@type generator: generator.
|
||||||
|
"""
|
||||||
|
super( DiscussionParserBot, self ).__init__(generator=generator)
|
||||||
|
|
||||||
|
def run( self ):
|
||||||
|
"""
|
||||||
|
Controls the overal parsing process, using super class for page switch
|
||||||
|
|
||||||
|
Needed to do things before/after treating pages is done
|
||||||
|
"""
|
||||||
try:
|
try:
|
||||||
jogobot.output( "BEGINN – parser-pages.py" )
|
|
||||||
|
|
||||||
# Iterate over configured categories
|
super( DiscussionParserBot, self ).run()
|
||||||
for cat in ( jogobot.config["redundances"]["redpage_cats"] ):
|
|
||||||
|
|
||||||
# Iterate over pages in current cat
|
except:
|
||||||
for page in get_cat_pages( cat ):
|
raise
|
||||||
|
|
||||||
# For pages configured to exclude, go on with next page
|
else:
|
||||||
if page.title() in (
|
|
||||||
|
# If successfully parsed all pages in cat, flush db write cache
|
||||||
|
redpage.RedPage.flush_db_cache()
|
||||||
|
|
||||||
|
def treat_page( self ):
|
||||||
|
"""
|
||||||
|
Handles work on current page
|
||||||
|
"""
|
||||||
|
|
||||||
|
# Short circuit excluded pages
|
||||||
|
if self.current_page.title() in (
|
||||||
jogobot.config["redundances"]["redpage_exclude"] ):
|
jogobot.config["redundances"]["redpage_exclude"] ):
|
||||||
|
|
||||||
continue
|
return
|
||||||
|
|
||||||
# Initiate RedPage object
|
# Initiate RedPage object
|
||||||
red_page = redpage.RedPage( page )
|
red_page = redpage.RedPage( self.current_page )
|
||||||
|
|
||||||
# Check whether parsing is needed
|
# Check whether parsing is needed
|
||||||
if red_page.is_parsing_needed():
|
if red_page.is_parsing_needed():
|
||||||
@@ -93,15 +102,96 @@ def main(*args):
|
|||||||
# If successfully parsed whole page, flush
|
# If successfully parsed whole page, flush
|
||||||
# db write cache
|
# db write cache
|
||||||
redfam.RedFamParser.flush_db_cache()
|
redfam.RedFamParser.flush_db_cache()
|
||||||
jogobot.output( "Page '%s' parsed" %
|
jogobot.output( "Page [[{redisc}]] parsed".format(
|
||||||
red_page.page.title() )
|
reddisc=red_page.page.title() ) )
|
||||||
else:
|
|
||||||
# If successfully parsed all pages in cat, flush db write cache
|
|
||||||
redpage.RedPage.flush_db_cache()
|
|
||||||
|
|
||||||
finally:
|
|
||||||
jogobot.output( "END – parser-pages.py" )
|
def main(*args): # noqa
|
||||||
pywikibot.stopme()
|
"""
|
||||||
|
Process command line arguments and invoke bot.
|
||||||
|
|
||||||
|
If args is an empty list, sys.argv is used.
|
||||||
|
|
||||||
|
@param args: command line arguments
|
||||||
|
@type args: list of unicode
|
||||||
|
"""
|
||||||
|
|
||||||
|
# Process global arguments to determine desired site
|
||||||
|
local_args = pywikibot.handle_args(args)
|
||||||
|
|
||||||
|
# Get the jogobot-task_slug (basename of current file without ending)
|
||||||
|
task_slug = os.path.basename(__file__)[:-len(".py")]
|
||||||
|
|
||||||
|
# Before run, we need to check wether we are currently active or not
|
||||||
|
try:
|
||||||
|
# Will throw Exception if disabled/blocked
|
||||||
|
# jogobot.is_active( task_slug )
|
||||||
|
pass
|
||||||
|
|
||||||
|
except jogobot.jogobot.Blocked:
|
||||||
|
(type, value, traceback) = sys.exc_info()
|
||||||
|
jogobot.output( "\03{lightpurple} %s (%s)" % (value, type ),
|
||||||
|
"CRITICAL" )
|
||||||
|
|
||||||
|
except jogobot.jogobot.Disabled:
|
||||||
|
(type, value, traceback) = sys.exc_info()
|
||||||
|
jogobot.output( "\03{red} %s (%s)" % (value, type ),
|
||||||
|
"ERROR" )
|
||||||
|
|
||||||
|
# Bot/Task is active
|
||||||
|
else:
|
||||||
|
|
||||||
|
# This factory is responsible for processing command line arguments
|
||||||
|
# that are also used by other scripts and that determine on which pages
|
||||||
|
# to work on.
|
||||||
|
genFactory = pagegenerators.GeneratorFactory()
|
||||||
|
# The generator gives the pages that should be worked upon.
|
||||||
|
gen = None
|
||||||
|
|
||||||
|
# If always is True, bot won't ask for confirmation of edit (automode)
|
||||||
|
# always = False
|
||||||
|
|
||||||
|
# If force_reload is True, bot will always parse Countrylist regardless
|
||||||
|
# if parsing is needed or not
|
||||||
|
# force_reload = False
|
||||||
|
|
||||||
|
# Parse command line arguments
|
||||||
|
for arg in local_args:
|
||||||
|
if arg.startswith("-always"):
|
||||||
|
# always = True
|
||||||
|
pass
|
||||||
|
else:
|
||||||
|
genFactory.handleArg(arg)
|
||||||
|
|
||||||
|
if not gen:
|
||||||
|
|
||||||
|
# Check wether there are generators waiting for factoring, if not
|
||||||
|
# use configured categories
|
||||||
|
if not genFactory.gens:
|
||||||
|
|
||||||
|
# Create Generators for configured Categories
|
||||||
|
for category in jogobot.config["redundances"]["redpage_cats"]:
|
||||||
|
cgen = genFactory.getCategoryGen(
|
||||||
|
category,
|
||||||
|
gen_func=pagegenerators.CategorizedPageGenerator)
|
||||||
|
|
||||||
|
# If there is one, append to genFactory
|
||||||
|
if cgen:
|
||||||
|
genFactory.gens.append(cgen)
|
||||||
|
|
||||||
|
# Create combined Generator (Union of all Generators)
|
||||||
|
gen = genFactory.getCombinedGenerator()
|
||||||
|
|
||||||
|
if gen:
|
||||||
|
# Log beginning of parsing
|
||||||
|
jogobot.output( "{task_slug} invoked".format(task_slug=task_slug) )
|
||||||
|
|
||||||
|
# The preloading generator is responsible for downloading multiple
|
||||||
|
# pages from the wiki simultaneously.
|
||||||
|
gen = pagegenerators.PreloadingGenerator(gen)
|
||||||
|
DiscussionParserBot( gen ).run()
|
||||||
|
else:
|
||||||
|
pywikibot.showHelp()
|
||||||
|
|
||||||
if( __name__ == "__main__" ):
|
if( __name__ == "__main__" ):
|
||||||
main()
|
main()
|
||||||
|
|||||||
Reference in New Issue
Block a user