def set_argparser(argparser):
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
if "Database parameters" not in present_groups:
Database.set_argparser(argparser)
argparser.add_argument(
"--page-name",
default="ArchWiki:Maintenance Team",
help=
"the page name on the wiki to fetch and update (default: %(default)s)"
)
argparser.add_argument(
"--days",
action="store",
default=30,
type=int,
metavar="N",
help="the time span in days (default: %(default)s)")
argparser.add_argument(
"--min-edits",
action="store",
default=10,
type=int,
metavar="N",
help=
"minimum number of edits for moving into the \"active\" table (default: %(default)s)"
)
def set_argparser(argparser):
import ws.config
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
output = argparser.add_argument_group(title="output mode")
_g = output.add_mutually_exclusive_group()
# TODO: maybe leave only the short option to forbid configurability in config file
_g.add_argument("-s", "--save", action="store_true",
help="try to save the page (requires being logged in)")
_g.add_argument("-p", "--print", action="store_true",
help="print the updated text in the standard output (this is the default output method)")
group = argparser.add_argument_group(title="script parameters")
group.add_argument("-a", "--anonymous", action="store_true",
help="do not require logging in: queries may be limited to a lower rate")
# TODO: maybe leave only the short option to forbid configurability in config file
group.add_argument("-f", "--force", action="store_true",
help="try to update the page even if it was last saved in the same UTC day")
group.add_argument("--toc-languages", default="all", type=ws.config.argtype_comma_list_choices(["all"] + lang.get_internal_tags()),
help="a comma-separated list of language tags whose ToC pages should be updated (default: %(default)s)")
group.add_argument("--toc-page", default="Table of contents",
help="the page name on the wiki to fetch and update (the language suffix "
"is added automatically as necessary) (default: %(default)s)")
# TODO: no idea how to forbid setting this globally in the config...
group.add_argument("--summary", default="automatic update",
help="the edit summary to use when saving the page (default: %(default)s)")
def set_argparser(argparser):
import ws.config
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
output = argparser.add_argument_group(title="output mode")
_g = output.add_mutually_exclusive_group()
# TODO: maybe leave only the short option to forbid configurability in config file
_g.add_argument("-s", "--save", action="store_true",
help="try to save the page (requires being logged in)")
_g.add_argument("-p", "--print", action="store_true",
help="print the updated text in the standard output (this is the default output method)")
group = argparser.add_argument_group(title="script parameters")
group.add_argument("-a", "--anonymous", action="store_true",
help="do not require logging in: queries may be limited to a lower rate")
# TODO: maybe leave only the short option to forbid configurability in config file
group.add_argument("-f", "--force", action="store_true",
help="try to update the page even if it was last saved in the same UTC day")
group.add_argument("--toc-languages", default="en", type=ws.config.argtype_comma_list_choices(["all"] + lang.get_internal_tags()),
help="a comma-separated list of language tags whose ToC pages should be updated (default: %(default)s)")
group.add_argument("--toc-page", default="目次",
help="the page name on the wiki to fetch and update (the language suffix "
"is added automatically as necessary) (default: %(default)s)")
# TODO: no idea how to forbid setting this globally in the config...
group.add_argument("--summary", default="自動更新",
help="the edit summary to use when saving the page (default: %(default)s)")
def set_argparser(klass, argparser):
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
group = argparser.add_argument_group(title="script parameters")
if klass.force_interactive is False:
group.add_argument("-i",
"--interactive",
action="store_true",
help="enables interactive mode")
group.add_argument(
"--dry-run",
action="store_true",
help="enables dry-run mode (changes are only shown and discarded)")
mode = group.add_mutually_exclusive_group()
mode.add_argument("--first",
default=None,
metavar="TITLE",
help="the title of the first page to be processed")
mode.add_argument("--title",
help="the title of the only page to be processed")
group.add_argument(
"--lang",
default=None,
help=
"comma-separated list of language tags to process (default: all, choices: {})"
.format(lang.get_internal_tags()))
def set_argparser(argparser):
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
group = argparser.add_argument_group(title="script parameters")
group.add_argument("--interactive", default=True, metavar="BOOL", type=ws.config.argtype_bool, help="Enables interactive mode (default: %(default)s)")
group.add_argument("--spam-phrases", action="append", required=True, metavar="STR", help="A phrase considered as spam (this option can be specified multiple times).")
group.add_argument("--spam-occurrences-threshold", type=int, default=5, help="Minimal number of phrases occurring on a page that triggers the spam filter.")
def set_argparser(argparser):
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
argparser.add_argument("--page-name", default="ArchWiki:Maintenance Team",
help="the page name on the wiki to fetch and update (default: %(default)s)")
argparser.add_argument("--days", action="store", default=30, type=int, metavar="N",
help="the time span in days (default: %(default)s)")
argparser.add_argument("--min-edits", action="store", default=10, type=int, metavar="N",
help="minimum number of edits for moving into the \"active\" table (default: %(default)s)")
def set_argparser(argparser):
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
if "Database parameters" not in present_groups:
Database.set_argparser(argparser)
output = argparser.add_argument_group(title="output")
# TODO: maybe leave only the short option to forbid configurability in config file
output.add_argument('-s', '--save', action='store_true',
help='try to save the page (requires being logged in)')
# FIXME: -c conflicts with -c/--config
# output.add_argument('-c', '--clipboard', action='store_true',
output.add_argument('--clipboard', action='store_true',
help='try to store the updated text in the clipboard')
output.add_argument('-p', '--print', action='store_true',
help='print the updated text in the standard output '
'(this is the default output method)')
usstats = argparser.add_argument_group(title="user statistics")
usstats.add_argument('--us-days-span', action='store', default=30,
type=int, dest='us_days', metavar='N',
help='the time span in days (default: %(default)s)')
usstats.add_argument('--us-min-tot-edits', action='store',
default=1000, type=int, dest='us_mintotedits', metavar='N',
help='minimum total edits for users with not enough '
'recent changes (default: %(default)s)')
usstats.add_argument('--us-min-rec-edits', action='store',
default=1, type=int, dest='us_minrecedits', metavar='N',
help='minimum recent changes for users with not enough '
'total edits (default: %(default)s)')
# TODO: main group for "script parameters" would be most logical, but
# but argparse does not display nested groups in the help page
group = argparser.add_argument_group(title="other parameters")
group.add_argument('-a', '--anonymous', action='store_true',
help='do not require logging in: queries may be limited to '
'a lower rate')
# TODO: maybe leave only the short option to forbid configurability in config file
group.add_argument('-f', '--force', action='store_true',
help='try to update the page even if it was last saved in '
'the same UTC day')
group.add_argument('--statistics-page', default='ArchWiki:Statistics',
help='the page name on the wiki to fetch and update '
'(default: %(default)s)')
# TODO: no idea how to forbid setting this globally in the config...
group.add_argument('--summary', default='automatic update',
help='the edit summary to use when saving the page '
'(default: %(default)s)')
def set_argparser(argparser):
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
output = argparser.add_argument_group(title="output")
# TODO: maybe leave only the short option to forbid configurability in config file
output.add_argument('-s', '--save', action='store_true',
help='try to save the page (requires being logged in)')
# FIXME: -c conflicts with -c/--config
# output.add_argument('-c', '--clipboard', action='store_true',
output.add_argument('--clipboard', action='store_true',
help='try to store the updated text in the clipboard')
output.add_argument('-p', '--print', action='store_true',
help='print the updated text in the standard output '
'(this is the default output method)')
usstats = argparser.add_argument_group(title="user statistics")
usstats.add_argument('--us-days-span', action='store', default=30,
type=int, dest='us_days', metavar='N',
help='the time span in days (default: %(default)s)')
usstats.add_argument('--us-min-tot-edits', action='store',
default=1000, type=int, dest='us_mintotedits', metavar='N',
help='minimum total edits for users with not enough '
'recent changes (default: %(default)s)')
usstats.add_argument('--us-min-rec-edits', action='store',
default=1, type=int, dest='us_minrecedits', metavar='N',
help='minimum recent changes for users with not enough '
'total edits (default: %(default)s)')
# TODO: main group for "script parameters" would be most logical, but
# but argparse does not display nested groups in the help page
group = argparser.add_argument_group(title="other parameters")
group.add_argument('-a', '--anonymous', action='store_true',
help='do not require logging in: queries may be limited to '
'a lower rate')
# TODO: maybe leave only the short option to forbid configurability in config file
group.add_argument('-f', '--force', action='store_true',
help='try to update the page even if it was last saved in '
'the same UTC day')
group.add_argument('--statistics-page', default='ArchWiki:Statistics',
help='the page name on the wiki to fetch and update '
'(default: %(default)s)')
# TODO: no idea how to forbid setting this globally in the config...
group.add_argument('--summary', default='automatic update',
help='the edit summary to use when saving the page '
'(default: %(default)s)')
def set_argparser(argparser):
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
if "Database parameters" not in present_groups:
Database.set_argparser(argparser)
group = argparser.add_argument_group(title="script parameters")
mode = group.add_mutually_exclusive_group()
mode.add_argument("--first", default=None, metavar="TITLE",
help="the title of the first page to be processed")
mode.add_argument("--title",
help="the title of the only page to be processed")
group.add_argument("--lang", default="en",
help="comma-separated list of language tags to process (default: en, choices: {})".format(lang.get_internal_tags()))
def api_mock(req_mock, module_mocker, title_context):
# create the API object
api_url = "http://wiki-scripts.localhost/api.php"
index_url = "http://wiki-scripts.localhost/index.php"
session = API.make_session()
api = API(api_url, index_url, session)
# register a callback function for dynamic responses
# https://requests-mock.readthedocs.io/en/latest/response.html#dynamic-response
def api_callback(request, context):
params = request.qs
if params.get("format") == ["json"
] and params.get("action") == ["query"]:
if params.get("meta") == ["siteinfo"] and params.get("siprop") == [
"general"
]:
# only props which may be relevant for tests are in the mocked response
general = {
"mainpage": "Main page",
"base":
"http://wiki-scripts.localhost/index.php/Main_page",
"sitename": "wiki-scripts tests",
"articlepath": "/index.php/$1",
"scriptpath": "",
"script": "/index.php",
"server": "http://wiki-scripts.localhost",
"servername": "wiki-scripts.localhost",
}
return {"batchcomplete": "", "query": {"general": general}}
# defaults
context.status_code = 404
context.reason = "Missing mock for the query parameters '{}'".format(
request.qs)
req_mock.get(api_url, json=api_callback)
req_mock.get(index_url,
status_code=404,
reason="Missing mocks for the index.php entry point")
# mock the title context class
mContext = module_mocker.patch(
"ws.parser_helpers.title.Context",
module_mocker.create_autospec(title_context))
# override the from_api method to always return the fixture
mContext.from_api = lambda api: title_context
return api
def set_argparser(argparser):
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
group = argparser.add_argument_group(title="script parameters")
group.add_argument("--tmp-dir", type=ws.config.argtype_dirname_must_exist, metavar="PATH", default="/tmp/wiki-scripts/",
help="temporary directory path (will be created if necessary, but parent directory must exist) (default: %(default)s)")
group.add_argument("-i", "--interactive", action="store_true",
help="run in interactive mode (should be used for testing)")
group.add_argument("--aurpkgs-url", default="https://aur.archlinux.org/packages.gz", metavar="URL",
help="the URL to packages.gz file on the AUR (default: %(default)s)")
group.add_argument("--report-dir", type=ws.config.argtype_existing_dir, default=".", metavar="PATH",
help="directory where the report should be saved (default: %(default)s)")
group.add_argument("--report-page", type=str, default=None, metavar="PATH",
help="existing report page on the wiki (default: %(default)s)")
def set_argparser(argparser):
# first try to set options for objects we depend on
present_groups = [group.title for group in argparser._action_groups]
if "Connection parameters" not in present_groups:
API.set_argparser(argparser)
if "Database parameters" not in present_groups:
Database.set_argparser(argparser)
group = argparser.add_argument_group(title="script parameters")
group.add_argument("-i", "--interactive", action="store_true",
help="enables interactive mode")
group.add_argument("--dry-run", action="store_true",
help="enables dry-run mode (changes are only shown and discarded)")
mode = group.add_mutually_exclusive_group()
mode.add_argument("--first", default=None, metavar="TITLE",
help="the title of the first page to be processed")
mode.add_argument("--title",
help="the title of the only page to be processed")
group.add_argument("--lang", default=None,
help="comma-separated list of language tags to process (default: all, choices: {})".format(lang.get_internal_tags()))
def from_argparser(klass, args, api=None):
if api is None:
api = API.from_argparser(args)
if args.lang:
tags = args.lang.split(",")
for tag in tags:
if tag not in lang.get_internal_tags():
# FIXME: more elegant solution
raise Exception("{} is not a valid language tag".format(tag))
langnames = {lang.langname_for_tag(tag) for tag in tags}
else:
langnames = set()
interactive = args.interactive if klass.force_interactive is False else True
return klass(api, interactive=interactive, dry_run=args.dry_run, first=args.first, title=args.title, langnames=langnames)
def from_argparser(klass, args, api=None, db=None):
if api is None:
api = API.from_argparser(args)
if db is None:
db = Database.from_argparser(args)
if args.lang:
tags = args.lang.split(",")
for tag in tags:
if tag not in lang.get_internal_tags():
# FIXME: more elegant solution
raise Exception("{} is not a valid language tag".format(tag))
langnames = {lang.langname_for_tag(tag) for tag in tags}
else:
langnames = set()
return klass(api, db, interactive=args.interactive, dry_run=args.dry_run, first=args.first, title=args.title, langnames=langnames, connection_timeout=args.connection_timeout, max_retries=args.connection_max_retries)
def from_argparser(klass, args, api=None, db=None):
if api is None:
api = API.from_argparser(args)
if db is None:
db = Database.from_argparser(args)
if args.lang:
tags = args.lang.split(",")
for tag in tags:
if tag not in lang.get_internal_tags():
# FIXME: more elegant solution
raise Exception("{} is not a valid language tag".format(tag))
langnames = {lang.langname_for_tag(tag) for tag in tags}
else:
langnames = set()
return klass(api, db, first=args.first, title=args.title, langnames=langnames, connection_timeout=args.connection_timeout, max_retries=args.connection_max_retries)
def from_argparser(klass, args, api=None):
if api is None:
api = API.from_argparser(args)
return klass(api, args)
def from_argparser(klass, args, api=None, db=None):
if api is None:
api = API.from_argparser(args)
if db is None:
db = Database.from_argparser(args)
return klass(api, db, args)
#! /usr/bin/env python3
import os.path
import datetime
from ws.client import API
api_url = "https://wiki.archlinux.org/api.php"
index_url = "https://wiki.arclinux.org/index.php"
cookie_path = os.path.expanduser("~/.cache/ArchWiki.cookie")
session = API.make_session(ssl_verify=True, cookie_file=cookie_path)
api = API(api_url, index_url, session)
# get list of all users, who:
# - are not bots
# - made at least one edit
# - have been active in the last 30 days
# - are not blocked
# the list can be sorted by:
# - editcount
# - recenteditcount
# - avgeditsperday (needs to be calculated)
users = list(
api.list(list="allusers",
aulimit="max",
auprop="blockinfo|editcount|registration",
auexcludegroup="bot",
auwitheditsonly="",
auactiveusers=""))
#! /usr/bin/env python3
import os.path
from collections import namedtuple
import itertools
from ws.client import API
import ws.ArchWiki.lang as lang
api_url = "https://wiki.archlinux.org/api.php"
cookie_path = os.path.expanduser("~/.cache/ArchWiki.cookie")
api = API(api_url, cookie_file=cookie_path, ssl_verify=True)
Page = namedtuple("Page", ["title", "langname", "pure"])
pages = []
for page in api.generator(generator="allpages", gaplimit="max", gapfilterredir="nonredirects"):
pure, langname = lang.detect_language(page["title"])
pages.append(Page(page["title"], langname, pure))
pages.sort(key=lambda page: (page.langname, page.pure))
groups = itertools.groupby(pages, key=lambda page: page.langname)
for langname, pages in groups:
print("== {} ==\n".format(langname))
for page in pages:
print("* [[:{}|{}]]".format(page.title, page.pure))
print()
#! /usr/bin/env python3
import os.path
from ws.client import API
from ws.diff import RevisionDiffer
api_url = "https://wiki.archlinux.org/api.php"
index_url = "https://wiki.arclinux.org/index.php"
cookie_path = os.path.expanduser("~/.cache/ArchWiki.cookie")
session = API.make_session(ssl_verify=True, cookie_file=cookie_path)
api = API(api_url, index_url, session)
# show the diff for two revisions, colorized for 256-color terminal
oldrevid = 625761
newrevid = 625800
diff = RevisionDiffer(api)
print(diff.diff(oldrevid, newrevid))
#! /usr/bin/env python3 import os.path from ws.client import API from ws.diff import diff_revisions api_url = "https://wiki.archlinux.org/api.php" index_url = "https://wiki.arclinux.org/index.php" session = API.make_session() api = API(api_url, index_url, session) # show the diff for two revisions, colorized for 256-color terminal oldrevid = 625761 newrevid = 625800 print(diff_revisions(api, oldrevid, newrevid))
logger.info("Plotting hist_active_users.png")
hist_active_users = []
num_bins = len(bin_edges) - 1
for i in range(num_bins):
# array of indexes for revisions in current bin
current_bin, = np.where(bin_indexes == i)
active_users = list(set([revisions[ii]["user"] for ii in current_bin]))
hist_active_users.append(len(active_users))
plot_date_bars(hist_active_users, bin_edges,
title="ArchWiki active users per month", ylabel="active users",
fname="stub/hist_active_users.png")
if __name__ == "__main__":
import ws.config
import ws.logging
argparser = ws.config.getArgParser(description="Create histogram charts for the statistics page")
API.set_argparser(argparser)
# TODO: script-specific arguments (e.g. output path)
args = argparser.parse_args()
# set up logging
ws.logging.init(args)
api = API.from_argparser(args)
db = ws.cache.AllRevisionsProps(api, args.cache_dir)
create_histograms(db["revisions"])
def from_argparser(klass, args, api=None):
if api is None:
api = API.from_argparser(args)
return klass(api, args.aurpkgs_url, args.tmp_dir, args.ssl_verify,
args.report_dir, args.report_page, args.interactive)
#! /usr/bin/env python3
import os.path
from ws.client import API
api_urls = [
"https://wiki.archlinux.org/api.php",
"https://wiki.archlinux.de/api.php",
]
index_url = "https://wiki.arclinux.org/index.php"
session = API.make_session()
for api_url in api_urls:
api = API(api_url, index_url, session)
prefixes = set()
for ns in api.site.namespaces:
if ns < 0:
continue
for page in api.generator(generator="allpages",
gaplimit="max",
gapfilterredir="nonredirects",
gapnamespace=ns,
prop="iwlinks",
iwprop="url",
iwlimit="max"):
for link in page.get("iwlinks", []):
prefixes.add(link["prefix"])
print("interwiki prefixes used on {}:".format(api.get_hostname()))
print(sorted(prefixes))
def from_argparser(klass, args, api=None, db=None):
if api is None:
api = API.from_argparser(args)
if db is None:
db = Database.from_argparser(args)
return klass(api, db, args.page_name, args.days, args.min_edits)
#! /usr/bin/env python3
import os.path
from ws.client import API
api_urls = [
"https://wiki.archlinux.org/api.php",
"https://wiki.archlinux.de/api.php",
]
cookie_path = os.path.expanduser("~/.cache/ArchWiki.cookie")
for api_url in api_urls:
api = API(api_url, cookie_file=cookie_path, ssl_verify=True)
prefixes = set()
for ns in api.site.namespaces:
if ns < 0:
continue
for page in api.generator(generator="allpages", gaplimit="max", gapfilterredir="nonredirects", gapnamespace=ns, prop="iwlinks", iwprop="url", iwlimit="max"):
for link in page.get("iwlinks", []):
prefixes.add(link["prefix"])
print("interwiki prefixes used on {}:".format(api.get_hostname()))
print(sorted(prefixes))
#! /usr/bin/env python3
import os.path
from ws.client import API
from ws.diff import RevisionDiffer
api_url = "https://wiki.archlinux.org/api.php"
cookie_path = os.path.expanduser("~/.cache/ArchWiki.cookie")
api = API(api_url, cookie_file=cookie_path, ssl_verify=True)
# show the diff for two revisions, colorized for 256-color terminal
oldrevid = 325013
newrevid = 325254
diff = RevisionDiffer(api)
print(diff.diff(oldrevid, newrevid))
def from_argparser(klass, args, api=None):
if api is None:
api = API.from_argparser(args)
return klass(api, args.spam_phrases, args.spam_occurrences_threshold, args.interactive)
def from_argparser(klass, args, api=None):
if api is None:
api = API.from_argparser(args)
return klass(api, args.cache_dir, args.page_name, args.days, args.min_edits)
#! /usr/bin/env python3
import os.path
from collections import namedtuple
import itertools
from ws.client import API
import ws.ArchWiki.lang as lang
api_url = "https://wiki.archlinux.org/api.php"
index_url = "https://wiki.arclinux.org/index.php"
session = API.make_session()
api = API(api_url, index_url, session)
Page = namedtuple("Page", ["title", "langname", "pure"])
pages = []
for page in api.generator(generator="allpages",
gaplimit="max",
gapfilterredir="nonredirects"):
pure, langname = lang.detect_language(page["title"])
pages.append(Page(page["title"], langname, pure))
pages.sort(key=lambda page: (page.langname, page.pure))
groups = itertools.groupby(pages, key=lambda page: page.langname)
for langname, pages in groups:
print("== {} ==\n".format(langname))
for page in pages:
print("* [[:{}|{}]]".format(page.title, page.pure))
xy=(x, y),
xytext=(5, 0),
textcoords="offset points",
ha="left",
va="top")
def plot_save(fname):
plt.savefig(fname, dpi=192)
if __name__ == "__main__":
import ws.config
argparser = ws.config.getArgParser()
API.set_argparser(argparser)
Database.set_argparser(argparser)
args = ws.config.parse_args(argparser)
api = API.from_argparser(args)
require_login(api)
db = Database.from_argparser(args)
users = [
"Alad", "Fengchao", "Indigo", "Kynikos", "Lahwaacz", "Lonaowna",
"Nl6720"
]
all_logs = list(db.query(list="logevents", letype="rights", ledir="newer"))
def from_argparser(klass, args, api=None):
if api is None:
api = API.from_argparser(args)
return klass(api, args)
#! /usr/bin/env python3
import os.path
from ws.client import API
api_url = "https://wiki.archlinux.org/api.php"
cookie_path = os.path.expanduser("~/.cache/ArchWiki.cookie")
api = API(api_url, cookie_file=cookie_path, ssl_verify=True)
# allpages
# see list of parameters: https://www.mediawiki.org/wiki/API:Allpages
for page in api.generator(generator="allpages", gaplimit="max"):
print(page["title"])
# allcategories
# see list of parameters: https://www.mediawiki.org/wiki/API:Allcategories
#for page in api.generator(generator="allcategories", gaclimit="max"):
# print(page["title"])
# categorymembers
# see list of parameters: https://www.mediawiki.org/wiki/API:Categorymembers
#for page in api.generator(generator="categorymembers", gcmtitle="Category:English", gcmlimit="max"):
# print(page["title"])
# transclusions
# see list of parameters: https://www.mediawiki.org/wiki/API:Embeddedin
#for page in api.generator(generator="embeddedin", geititle="Template:AUR", geilimit="max"):
# print(page["title"])
#! /usr/bin/env python3
import os.path
from ws.client import API
api_url = "https://wiki.archlinux.org/api.php"
index_url = "https://wiki.arclinux.org/index.php"
cookie_path = os.path.expanduser("~/.cache/ArchWiki.cookie")
session = API.make_session(ssl_verify=True, cookie_file=cookie_path)
api = API(api_url, index_url, session)
# allpages
# see list of parameters: https://www.mediawiki.org/wiki/API:Allpages
for page in api.generator(generator="allpages", gaplimit="max"):
print(page["title"])
# allcategories
# see list of parameters: https://www.mediawiki.org/wiki/API:Allcategories
#for page in api.generator(generator="allcategories", gaclimit="max"):
# print(page["title"])
# categorymembers
# see list of parameters: https://www.mediawiki.org/wiki/API:Categorymembers
#for page in api.generator(generator="categorymembers", gcmtitle="Category:English", gcmlimit="max"):
# print(page["title"])
# transclusions
# see list of parameters: https://www.mediawiki.org/wiki/API:Embeddedin
#for page in api.generator(generator="embeddedin", geititle="Template:AUR", geilimit="max"):
#! /usr/bin/env python3
import os.path
import datetime
from ws.client import API
api_url = "https://wiki.archlinux.org/api.php"
cookie_path = os.path.expanduser("~/.cache/ArchWiki.cookie")
api = API(api_url, cookie_file=cookie_path, ssl_verify=True)
# get list of all users, who:
# - are not bots
# - made at least one edit
# - have been active in the last 30 days
# - are not blocked
# the list can be sorted by:
# - editcount
# - recenteditcount
# - avgeditsperday (needs to be calculated)
users = list(api.list(list="allusers", aulimit="max", auprop="blockinfo|editcount|registration", auexcludegroup="bot", auwitheditsonly="", auactiveusers=""))
users = [user for user in users if user.get("blockid") is None]
# prepare sorting by avgeditsperday
now = datetime.datetime.utcnow()
for user in users:
# exclude users with no registration date (some weird anomaly) TODO: investigate
if user["registration"] == "":
#! /usr/bin/env python3
import os.path
from ws.client import API
api_url = "https://wiki.archlinux.org/api.php"
index_url = "https://wiki.arclinux.org/index.php"
session = API.make_session()
api = API(api_url, index_url, session)
# allpages
# see list of parameters: https://www.mediawiki.org/wiki/API:Allpages
for page in api.generator(generator="allpages", gaplimit="max"):
print(page["title"])
# allcategories
# see list of parameters: https://www.mediawiki.org/wiki/API:Allcategories
#for page in api.generator(generator="allcategories", gaclimit="max"):
# print(page["title"])
# categorymembers
# see list of parameters: https://www.mediawiki.org/wiki/API:Categorymembers
#for page in api.generator(generator="categorymembers", gcmtitle="Category:English", gcmlimit="max"):
# print(page["title"])
# transclusions
# see list of parameters: https://www.mediawiki.org/wiki/API:Embeddedin
#for page in api.generator(generator="embeddedin", geititle="Template:AUR", geilimit="max"):
# print(page["title"])
