Uživatel:ShadyMedic/SunnyBot
Z WikiSkript
Zde se budou objevovat mé poznámky o vývoji robota pro Wikiskripta.
Poznámky budou sloužit převážně mně pro poznamenávání si mého pokroku.
Robot využívá účet Uživatel:Sunny.
Odkazy[upravit | editovat zdroj]
- Stahovací stánka pro Pywikibot
- Speciální stránka k nastavování hesel pro boty
- Manuál k Pywikibot
- Vývoj prvního skriptu
- Aktuální seznam úkonů (hotových i plánovaných)
Zdrojové kódy[upravit | editovat zdroj]
Konfigurační soubory[upravit | editovat zdroj]
user-config.py
# This is an automatically generated file. You can find more
# configuration parameters in 'config.py' file or refer
# https://doc.wikimedia.org/pywikibot/master/api_ref/pywikibot.config.html
from typing import Optional, Union
from pywikibot.backports import Dict, List, Tuple
# The family of sites to be working on.
# Pywikibot will import families/xxx_family.py so if you want to change
# this variable, you have to ensure that such a file exists. You may use
# generate_family_file to create one.
family = 'wikiskripta'
# The site code (language) of the site to be working on.
mylang = 'cs'
# The dictionary usernames should contain a username for each site where you
# have a bot account. If you have a unique username for all sites of a
# family , you can use '*'
usernames['wikiskripta']['cs'] = 'Sunny'
# The list of BotPasswords is saved in another file. Import it if needed.
# See https://www.mediawiki.org/wiki/Manual:Pywikibot/BotPasswords to know how
# use them.
password_file = "user-password.py"
# ############# EXTERNAL EDITOR SETTINGS ##############
# The command for the editor you want to use. If set to True, Tkinter
# editor will be used. If set to False, no editor will be used. In
# script tests to be a noop (like /bin/true) so the script continues.
# If set to None, the EDITOR environment variable will be used as
# command. If EDITOR is not set, on windows plattforms it tries to
# determine the default text editor from registry. Finally, Tkinter is
# used as fallback.
editor: Union[bool, str, None] = None
# Warning: DO NOT use an editor which doesn't support Unicode to edit pages!
# You will BREAK non-ASCII symbols!
editor_encoding = 'utf-8'
# The temporary file name extension can be set in order to use syntax
# highlighting in your text editor.
editor_filename_extension = 'wiki'
# ############# LOGFILE SETTINGS ##############
# Defines for which scripts a logfile should be enabled. Logfiles will be
# saved in the 'logs' subdirectory.
#
# Example:
# log = ['redirect', 'replace', 'weblinkchecker']
# It is also possible to enable logging for all scripts, using this line:
# log = ['*']
# To disable all logging, use this:
# log = []
# Per default, no logging is enabled.
# This setting can be overridden by the -log or -nolog command-line arguments.
log: List[str] = []
# filename defaults to modulename-bot.log
logfilename: Optional[str] = None
# maximal size of a logfile in kilobytes. If the size reached that limit the
# logfile will be renamed (if logfilecount is not 0) and the old file is filled
# again. logfilesize must be an integer value
logfilesize = 1024
# Number of rotating logfiles are created. The older files get the higher
# number. If logfilecount is 0, no logfile will be archived but the current
# logfile will be overwritten if the file size reached the logfilesize above.
# If logfilecount is -1 there are no rotating logfiles but the files where
# renamed if the logfile is full. The newest file gets the highest number until
# some logfiles where deleted.
logfilecount = 5
# set to 1 (or higher) to generate "informative" messages to terminal
verbose_output = 0
# set to True to fetch the pywiki version online
log_pywiki_repo_version = False
# if True, include a lot of debugging info in logfile
# (overrides log setting above)
debug_log: List[str] = []
# ############# EXTERNAL SCRIPT PATH SETTINGS ##############
# Set your own script path to lookup for your script files.
#
# Your private script path is relative to your base directory.
# Subfolders must be delimited by '.'. every folder must contain
# an (empty) __init__.py file.
#
# The search order is
# 1. user_script_paths in the given order
# 2. scripts/userscripts
# 3. scripts
# 4. scripts/maintenance
# 5. pywikibot/scripts
#
# 2. - 4. are available in directory mode only
#
# sample:
# user_script_paths = ['scripts.myscripts']
user_script_paths: List[str] = []
# ############# EXTERNAL FAMILIES SETTINGS ##############
# Set your own family path to lookup for your family files.
#
# Your private family path may be either an absolute or a relative path.
# You may have multiple paths defined in user_families_paths list.
#
# You may also define various family files stored directly in
# family_files dict. Use the family name as dict key and the path or an
# url as value.
#
# samples:
# family_files['mywiki'] = 'https://de.wikipedia.org'
# user_families_paths = ['data/families']
user_families_paths: List[str] = []
# ############# IMAGE RELATED SETTINGS ##############
# If you set this to True, images will be uploaded to Wikimedia
# Commons by default.
upload_to_commons = False
# ############# SETTINGS TO AVOID SERVER OVERLOAD ##############
# Slow down the robot such that it never requests a second page within
# 'minthrottle' seconds. This can be lengthened if the server is slow,
# but never more than 'maxthrottle' seconds. However - if you are running
# more than one bot in parallel the times are lengthened.
#
# 'maxlag' is used to control the rate of server access (see below).
# Set minthrottle to non-zero to use a throttle on read access.
minthrottle = 0
maxthrottle = 60
# Slow down the robot such that it never makes a second page edit within
# 'put_throttle' seconds.
put_throttle: Union[int, float] = 10
# Sometimes you want to know when a delay is inserted. If a delay is larger
# than 'noisysleep' seconds, it is logged on the screen.
noisysleep = 3.0
# Defer bot edits during periods of database server lag. For details, see
# https://www.mediawiki.org/wiki/Manual:Maxlag_parameter
# You can set this variable to a number of seconds, or to None (or 0) to
# disable this behavior. Higher values are more aggressive in seeking
# access to the wiki.
# Non-Wikimedia wikis may or may not support this feature; for families
# that do not use it, it is recommended to set minthrottle (above) to
# at least 1 second.
maxlag = 5
# Maximum of pages which can be retrieved at one time from wiki server.
# -1 indicates limit by api restriction
step = -1
# Maximum number of times to retry an API request before quitting.
max_retries = 15
# Minimum time to wait before resubmitting a failed API request.
retry_wait = 5
# Maximum time to wait before resubmitting a failed API request.
retry_max = 120
# ############# DATABASE SETTINGS ##############
# Setting to connect the database or replica of the database of the wiki.
# db_name_format can be used to manipulate the dbName of site.
#
# Example for a pywikibot running on Wikimedia Cloud (Toolforge):
# db_hostname_format = '{0}.analytics.db.svc.wikimedia.cloud'
# db_name_format = '{0}_p'
# db_connect_file = user_home_path('replica.my.cnf')
db_hostname_format = 'localhost'
db_username = ''
db_password = ''
db_name_format = '{0}'
db_connect_file = user_home_path('.my.cnf')
# local port for mysql server
# ssh -L 4711:enwiki.analytics.db.svc.eqiad.wmflabs:3306 \
# user@login.toolforge.org
db_port = 3306
# ############# HTTP SETTINGS ##############
# Default socket timeout in seconds.
# DO NOT set to None to disable timeouts. Otherwise this may freeze your
# script.
# You may assign either a tuple of two int or float values for connection and
# read timeout, or a single value for both in a tuple.
socket_timeout = (6.05, 45)
# ############# COSMETIC CHANGES SETTINGS ##############
# The bot can make some additional changes to each page it edits, e.g. fix
# whitespace or positioning of category links.
# This is an experimental feature; handle with care and consider re-checking
# each bot edit if enabling this!
cosmetic_changes = False
# If cosmetic changes are switched on, and you also have several accounts at
# projects where you're not familiar with the local conventions, you probably
# only want the bot to do cosmetic changes on your "home" wiki which you
# specified in config.mylang and config.family.
# If you want the bot to also do cosmetic changes when editing a page on a
# foreign wiki, set cosmetic_changes_mylang_only to False, but be careful!
cosmetic_changes_mylang_only = True
# The dictionary cosmetic_changes_enable should contain a tuple of languages
# for each site where you wish to enable in addition to your own langlanguage
# (if cosmetic_changes_mylang_only is set)
# Please set your dictionary by adding such lines to your user config file:
# cosmetic_changes_enable['wikipedia'] = ('de', 'en', 'fr')
cosmetic_changes_enable: Dict[str, Tuple[str, ...]] = {}
# The dictionary cosmetic_changes_disable should contain a tuple of languages
# for each site where you wish to disable cosmetic changes. You may use it with
# cosmetic_changes_mylang_only is False, but you can also disable your own
# language. This also overrides the settings in the cosmetic_changes_enable
# dictionary. Please set your dict by adding such lines to your user config:
# cosmetic_changes_disable['wikipedia'] = ('de', 'en', 'fr')
cosmetic_changes_disable: Dict[str, Tuple[str, ...]] = {}
# cosmetic_changes_deny_script is a list of scripts for which cosmetic changes
# are disabled. You may add additional scripts by appending script names in
# your user config file ("+=" operator is strictly recommended):
# cosmetic_changes_deny_script += ['your_script_name_1', 'your_script_name_2']
# Appending the script name also works:
# cosmetic_changes_deny_script.append('your_script_name')
cosmetic_changes_deny_script = ['category_redirect', 'cosmetic_changes',
'newitem', 'touch']
# ############# FURTHER SETTINGS ##############
# Simulate settings
# Defines what additional actions the bots are NOT allowed to do (e.g. 'edit')
# on the wiki server. Allows simulation runs of bots to be carried out without
# changing any page on the server side. Use this setting to add more actions
# into user config file for wikis with extra write actions.
actions_to_block: List[str] = []
# Set simulate to True or use -simulate option to block all actions given
# above.
simulate: Union[bool, str] = False
# How many pages should be put to a queue in asynchronous mode.
# If maxsize is <= 0, the queue size is infinite.
# Increasing this value will increase memory space but could speed up
# processing. As higher this value this effect will decrease.
max_queue_size = 64
# Pickle protocol version to use for storing dumps.
# This config variable is not used for loading dumps.
# Version 0 is a more or less human-readable protocol
# Version 2 is common to both Python 2 and 3, and should
# be used when dumps are accessed by both versions.
# Version 3 is only available for Python 3
# Version 4 is only available for Python 3.4+
# Version 5 was added with Python 3.8
pickle_protocol = 2
# ############# INTERWIKI SETTINGS ##############
# Should interwiki.py report warnings for missing links between foreign
# languages?
interwiki_backlink = True
# Should interwiki.py display every new link it discovers?
interwiki_shownew = True
# Should interwiki.py output a graph PNG file on conflicts?
# You need pydot for this:
# https://pypi.org/project/pydot/
interwiki_graph = False
# Specifies that the robot should process that amount of subjects at a time,
# only starting to load new pages in the original language when the total
# falls below that number. Default is to process (at least) 100 subjects at
# once.
interwiki_min_subjects = 100
# If interwiki graphs are enabled, which format(s) should be used?
# Supported formats include png, jpg, ps, and svg. See:
# https://graphviz.org/docs/outputs/
# If you want to also dump the dot files, you can use this in your
# user config file:
# interwiki_graph_formats = ['dot', 'png']
# If you need a PNG image with an HTML image map, use this:
# interwiki_graph_formats = ['png', 'cmap']
# If you only need SVG images, use:
# interwiki_graph_formats = ['svg']
interwiki_graph_formats = ['png']
# You can post the contents of your autonomous_problems.dat to the wiki,
# e.g. to https://de.wikipedia.org/wiki/Wikipedia:Interwiki-Konflikte .
# This allows others to assist you in resolving interwiki problems.
# To help these people, you can upload the interwiki graphs to your
# webspace somewhere. Set the base URL here, e.g.:
# 'https://www.example.org/~yourname/interwiki-graphs/'
interwiki_graph_url = None
# Save file with local articles without interwikis.
without_interwiki = False
# ############# SOLVE_DISAMBIGUATION SETTINGS ############
#
# Set disambiguation_comment[FAMILY][LANG] to a non-empty string to override
# the default edit comment for the solve_disambiguation bot.
#
# Use %s to represent the name of the disambiguation page being treated.
# Example:
#
# disambiguation_comment['wikipedia']['en'] = \
# 'Robot-assisted disambiguation ([[WP:DPL|you can help!]]): %s'
# Sorting order for alternatives. Set to True to ignore case for sorting order.
sort_ignore_case = False
# ############# WEBLINK CHECKER SETTINGS ##############
# How many external links should weblinkchecker.py check at the same time?
# If you have a fast connection, you might want to increase this number so
# that slow servers won't slow you down.
max_external_links = 50
report_dead_links_on_talk = False
# Don't alert on links days_dead old or younger
weblink_dead_days = 7
# ############# REPLICATION BOT SETTINGS ################
# You can add replicate_replace to your user config file.
#
# Use has the following format:
#
# replicate_replace = {
# 'wikipedia:li': {'Hoofdpagina': 'Veurblaad'}
# }
#
# to replace all occurrences of 'Hoofdpagina' with 'Veurblaad' when writing to
# liwiki. Note that this does not take the origin wiki into account.
replicate_replace: Dict[str, Dict[str, str]] = {}
user-password.py
# This is an automatically generated file used to store
# BotPasswords.
#
# As a simpler (but less secure) alternative to OAuth, MediaWiki allows bot
# users to uses BotPasswords to limit the permissions given to a bot.
# When using BotPasswords, each instance gets keys. This combination can only
# access the API, not the normal web interface.
#
# See https://www.mediawiki.org/wiki/Manual:Pywikibot/BotPasswords for more
# information.
('Sunny', BotPassword('SunnyBot', 'REDACTED'))
pywikibot/families/wikiskripta_family.py
from pywikibot import family
class Family(family.Family):
name = 'wikiskripta'
langs = {
'cs': 'www.wikiskripta.eu',
}
def scriptpath(self, code):
return ''
def protocol(self, code):
return 'HTTPS'
Skripty[upravit | editovat zdroj]
Nahraď text v pískovišti robota[upravit | editovat zdroj]
scripts\userscripts\Sunny-test1.py
"""Run this with:"""
"""python pwb.py Sunny-test1.py -search:Uživatel:Sunny/Pískoviště"""
#!/usr/bin/env python3
#
# (C) Pywikibot team, 2006-2022
#
# Distributed under the terms of the MIT license.
#
import pywikibot
from pywikibot import pagegenerators
from pywikibot.bot import (
AutomaticTWSummaryBot,
ConfigParserBot,
ExistingPageBot,
SingleSiteBot,
)
# This is required for the text that is shown when you run this script
# with the parameter -help.
docuReplacements = {'¶ms;': pagegenerators.parameterHelp} # noqa: N816
class SunnyBot(
# Refer pywikobot.bot for generic bot classes
SingleSiteBot, # A bot only working on one site
ConfigParserBot, # A bot which reads options from scripts.ini setting file
# CurrentPageBot, # Sets 'current_page'. Process it in treat_page method.
# # Not needed here because we have subclasses
ExistingPageBot, # CurrentPageBot which only treats existing pages
AutomaticTWSummaryBot, # Automatically defines summary; needs summary_key
):
"""
An incomplete sample bot.
:ivar summary_key: Edit summary message key. The message that should be
used is placed on /i18n subdirectory. The file containing these
messages should have the same name as the caller script (i.e. basic.py
in this case). Use summary_key to set a default edit summary message.
:type summary_key: str
"""
use_redirects = False # treats non-redirects only
summary_key = 'basic-changing'
update_options = {
'replace': True, # delete old text and write the new text
'summary': 'Automatizovaná editace', # your own bot summary
'text': 'Sunny\'s first words.', # add this text from option. 'Test' is default
'top': False, # append text on top of the page
}
def treat_page(self) -> None:
"""Load the given page, do some changes, and save it."""
text = self.current_page.text
################################################################
# NOTE: Here you can modify the text in whatever way you want. #
################################################################
# If you find out that you do not want to edit this page, just return.
# Example: This puts Text on a page.
# Retrieve your private option
# Use your own text or use the default 'Test'
text_to_add = self.opt.text
if self.opt.replace:
# replace the page text
text = text_to_add
elif self.opt.top:
# put text on top
text = text_to_add + text
else:
# put text on bottom
text += text_to_add
# if summary option is None, it takes the default i18n summary from
# i18n subdirectory with summary_key as summary key.
self.put_current(text, summary=self.opt.summary)
def main(*args: str) -> None:
"""
Process command line arguments and invoke bot.
If args is an empty list, sys.argv is used.
:param args: command line arguments
"""
options = {}
# Process global arguments to determine desired site
local_args = pywikibot.handle_args(args)
# 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.
gen_factory = pagegenerators.GeneratorFactory()
# Process pagegenerators arguments
local_args = gen_factory.handle_args(local_args)
# Parse your own command line arguments
for arg in local_args:
arg, _, value = arg.partition(':')
option = arg[1:]
if option in ('summary', 'text'):
if not value:
pywikibot.input('Please enter a value for ' + arg)
options[option] = value
# take the remaining options as booleans.
# You will get a hint if they aren't pre-defined in your bot class
else:
options[option] = True
# The preloading option is responsible for downloading multiple
# pages from the wiki simultaneously.
gen = gen_factory.getCombinedGenerator(preload=True)
# check if further help is needed
if not pywikibot.bot.suggest_help(missing_generator=not gen):
# pass generator and private options to the bot
bot = SunnyBot(generator=gen, **options)
bot.run() # guess what it does
if __name__ == '__main__':
main()
Nahraď text v pískovišti robota bez využívání wrapperů[upravit | editovat zdroj]
scripts\userscripts\Sunny-test2.py
"""Run this with:"""
"""python pwb.py Sunny-test2.py"""
#!/usr/bin/env python3
#
# (C) Pywikibot team, 2006-2022
#
# Distributed under the terms of the MIT license.
#
import pywikibot
from pywikibot import pagegenerators
site = pywikibot.Site()
page = pywikibot.Page(site, "Uživatel:Sunny/Pískoviště")
page.text = "Sunny's 2nd words."
page.save("Automatizovaná editace")
Načti a vypiš zdrojový kód článku[upravit | editovat zdroj]
scripts\userscripts\Sunny-test3.py
"""Run this with:""" """python pwb.py Sunny-test3.py""" #!/usr/bin/env python3 # # (C) Pywikibot team, 2006-2022 # # Distributed under the terms of the MIT license. # import pywikibot from pywikibot import pagegenerators site = pywikibot.Site() page = pywikibot.Page(site, "Divertikly jícnu") print(page.text)
Přesuň odpovědi na cvičení z farmakologie do rozklikávacích spoilerů[upravit | editovat zdroj]
scripts\userscripts\Spoiler-answers.py
"""Run this with:"""
"""python pwb.py Spoiler-answers.py"""
#!/usr/bin/env python3
#
# (C) Pywikibot team, 2006-2022
#
# Distributed under the terms of the MIT license.
#
import pywikibot
from pywikibot import pagegenerators
urls = [
"Procvi%C4%8Dov%C3%A1n%C3%AD:Anxiolytikum",
"Procvi%C4%8Dov%C3%A1n%C3%AD:Antacidum",
"Procvi%C4%8Dov%C3%A1n%C3%AD:Antiagregans",
# atd.
]
i = 0
for url in urls:
i+=1
site = pywikibot.Site()
page = pywikibot.Page(site, url)
text = page.text
# Tento blok kódu byl vygenerován pomocí Bing AI
lines = text.split('\n')
new_lines = []
in_block = False
for line in lines:
if line.startswith(':'):
if not in_block:
new_lines.append('{{Rozbalit|Řešení|')
in_block = True
new_lines.append(line)
else:
if in_block:
new_lines.append('}}')
in_block = False
new_lines.append(line)
if in_block:
new_lines.append('}}')
new_text = '\n'.join(new_lines)
page.text = new_text
page.save("Zaspoilerování odpovědi/í || Sunny signs off")
print('Progress: ' + str(i) + '/' + str(len(urls)))
print()
print('Hotovo!')
Vypiš názvy všech wiki článků, na něž vedou odkazy ze zadané stránky[upravit | editovat zdroj]
scripts\userscripts\Extract-links.py
"""Run this with:"""
"""python pwb.py Extract-links.py"""
#!/usr/bin/env python3
#
# (C) Pywikibot team, 2006-2022
#
# Distributed under the terms of the MIT license.
#
import pywikibot
import re
from pywikibot import pagegenerators
url = input("Zadejte URL stránky (ve formátu \"Jmenný prostor:Název stránky\"): ");
site = pywikibot.Site()
page = pywikibot.Page(site, url)
text = page.text
print('Extrahuji interní odkazy z wiki stránky...')
print()
# Tento blok kódu byl vygenerován pomocí Bing AI
pattern = r'\[\[(.+?)\]\]'
matches = re.findall(pattern, text)
internal_links = []
for match in matches:
if not match.startswith('http://') and not match.startswith('https://'):
link = re.split(r'(?<!\\)\|', match)[0]
print(link)
print()
print('Hotovo!')
[upravit | editovat zdroj]
scripts\userscripts\Templatify-navigation.py
"""Run this with:"""
"""python pwb.py Templatify-navigation.py"""
#!/usr/bin/env python3
#
# (C) Pywikibot team, 2006-2022
#
# Distributed under the terms of the MIT license.
#
import pywikibot
from pywikibot import pagegenerators
urls = [
"Procvičování:Patofyziologie krve",
"Procvičování:Patofyziologie krve/pokračování 1",
# atd.
]
i = 0
for url in urls:
i+=1
print("\nProcessing URL " + str(i) + "/" + str(len(urls)) + "... ", end="")
print("Loading " + url + "... ", end="")
site = pywikibot.Site()
page = pywikibot.Page(site, url)
text = page.text
replacement_text = """
{{navigace kvízy|portál=Portál:Procvičování patofyziologie}}
[[Procvičování diskuse:{{PAGENAME}} | Našli jste chybu? Napište!]]
[[Kategorie:Patofyziologie]]
"""
# Tento blok kódu byl napsán pomocí Bing AI
index = text.rfind("</quiz>")
if index != -1:
new_text = text[:index + len("</quiz>")] + replacement_text
else:
new_text = text
page.text = new_text
print('Saving... ')
page.save("Nahrazení navigačních tlačítek šablonou || Sunny signs off")
print('FINISHED!')
Ke všem obrázkům ploten s licencí umožňující přesun na Wikimedia Commons doplň šablonu {{Přesunout na commons}}[upravit | editovat zdroj]
scripts\userscripts\InsertCommonsTemplate.py
"""Run this with:"""
"""python pwb.py InsertCommonsTemplate.py"""
#!/usr/bin/env python3
#
# (C) Pywikibot team, 2006-2022
#
# Distributed under the terms of the MIT license.
#
import pywikibot
from pywikibot import pagegenerators
urls = [
"Soubor:B.cereus (2).jpg",
"Soubor:B.cereus (3).jpg",
# atd.
]
i = 0
for url in urls:
i+=1
print("\nProcessing URL " + str(i) + "/" + str(len(urls)) + "... ", end="")
print("Loading " + url + "... ", end="")
site = pywikibot.Site()
page = pywikibot.Page(site, url)
text = page.text
if (text.find("{{cc|by-sa|") == -1 and text.find("{{cc|by|") == -1):
print("Not eligable – unallowed licence")
else:
new_text = text + "\n\n{{Přesunout na commons}}"
page.text = new_text
print('Saving... ')
page.save("+š Přesunout na commons || Sunny signs off")
print('FINISHED!')
Ke všem souborům co nemají šablonu {{Soubor}}, jsou hostována na WikiSkriptech a nejsou přesměrováními doplň šablonu {{Soubor bez Informací}}[upravit | editovat zdroj]
scripts\userscripts\InsertNoFileInfoTemplate.py
"""Run this with:"""
"""python pwb.py Templatify-navigation.py"""
#!/usr/bin/env python3
#
# (C) Pywikibot team, 2006-2022
#
# Distributed under the terms of the MIT license.
#
import pywikibot
import requests
import urllib
from pywikibot import pagegenerators
pages = [
"Soubor:Bazofil 4 upr.jpg",
"Soubor:Centrální kanál mícha – upr.jpg",
# atd.
]
i = 0
missing_pages = []
missing_files = []
affected_pages = []
invalid_pages = []
for pg in pages:
i+=1
print("Processing page " + str(i) + "/" + str(len(pages)) + "... ", end="")
print("Loading " + pg + ("."*(80-len(pg))) + " ", end="")
file_url = 'https://wikiskripta.eu/api.php?action=query&format=json&formatversion=2&titles=' + urllib.parse.quote(pg) + '&prop=imageinfo&iiprop=url'
file_info_response = requests.get(file_url)
file_info_data = file_info_response.json()
file_info = file_info_data['query']['pages'][0]
if ("missing" in file_info and file_info["missing"] == True):
# Stránka nenalezena, ale soubor existuje? Tahle podmínka by se již nejspíš neměla spouštět, zůstala tady když tato situace nastávala kvůli tomu, že jsem zapomněl urlencodovat názvy článků se znaky "+" a "&".
missing_pages.append(f'"{pg}"')
print('\033[93m' + "MISSING." + '\033[0m', end="")
skip = False;
elif (not "imageinfo" in file_info):
# Stránka souboru existuje, ale soubor není nahrán (stránka byla nejspíš založena manuálně, ne formulářem pro nahrátí souboru)
missing_files.append(f'"{pg}"')
print('\033[93m' + "NO FILE." + '\033[0m', end="")
skip = True
elif file_info['imageinfo'][0]['descriptionurl'].startswith('https://www.wikiskripta.eu'):
# Soubor i stárnka existuje a soubor je hostován přímo na WikiSkriptech
print('\033[92m' + "ACCEPTED" + '\033[0m', end="")
skip = False;
else:
# Stránka existuje, ale soubor je hostován na Commons
print('\033[91m' + "REJECTED" + '\033[0m')
skip = True;
if not skip:
try:
site = pywikibot.Site()
page = pywikibot.Page(site, pg)
text = page.text
if (text.find("{{Soubor") != -1):
# Odchytí i soubory, co už šablonu {{Soubor bez informací}} mají
if (text.find("{{Soubor bez informací}}") != -1):
# Stránka byla ovlivněna v minulosti, ale lze předpokládat, že tímto botem, tak jí přidáme do seznamu
affected_pages.append(f'{pg}')
print("..... Not eligable – Template present")
elif (text.find("#PŘESMĚRUJ") != -1):
print("..... Not eligable – Redirect")
else:
new_text = text + "\n\n{{Soubor bez informací}}"
page.text = new_text
affected_pages.append(f'{pg}')
print("..... " + '\033[94m' + "Modifying" + '\033[0m')
page.save("+š Soubor bez informací || Sunny signs off")
except Exception:
# Všechny možné chyby, nastané vzácně, nejčastěji kvůli bugnutému souboru od uživatele Dummy, nutno vyřešit manuálně
invalid_pages.append(f'{pg}')
print("..... " + '\033[91m' + "ERROR: INVALID PAGE: " + pg + '\033[0m')
# Save the list to a text file
with open('missing_pages.txt', 'w') as f:
f.write('\n'.join(missing_pages))
with open('missing_files.txt', 'w') as f:
f.write('\n'.join(missing_files))
with open('invalid_pages.txt', 'w') as f:
f.write('\n'.join(invalid_pages))
with open('affected_pages.txt', 'w') as f:
f.write('\n'.join(affected_pages))
print('FINISHED!')
