Module:Webarchive/sandbox - Revision history

Zyxw: update pattern for finding Archive-It date

2023-08-09T17:18:44Z

update pattern for finding Archive-It date

← Previous revision		Revision as of 17:18, 9 August 2023
Line 371:		Line 371:
	Given a URI-path to Wayback (eg. /web/20160901010101/http://example.com )		Given a URI-path to Wayback (eg. /web/20160901010101/http://example.com )
	or Library of Congress Web Archives (eg. /all/20160901010101/http://example.com)		or Library of Congress Web Archives (eg. /all/20160901010101/http://example.com)
	or Archive-It (eg. /all/20190621232545/http://example.com or /~~org-467~~/~~20191016094633~~/http://example.com or /~~3348~~/~~20151201214156~~/http://example.com)		or Archive-It (eg. /all/20190621232545/http://example.com or /3348/20151201214156/http://example.com or /org-467/20191016094633/http://example.com)
	or UK Government Web Archive (eg. /ukgwa/20160901010101/http://example.com or /tna/20160901010101/http://example.com)		or UK Government Web Archive (eg. /ukgwa/20160901010101/http://example.com or /tna/20160901010101/http://example.com)

Line 391:		Line 391:
	local msg, snapdate;		local msg, snapdate;

	snapdate = path:gsub ('^/web/', ''):gsub ('^/all/', ''):gsub ('^/~~o?r?g?~~%-?%d%d%d~~/', ''):gsub ('^/o?r?g~~?%-?~~%d%d%d%d~~/', ''):gsub ('^/%d%d%d%d%d/', ''):gsub ('^/ukgwa/', ''):gsub ('^/tna/', ''):gsub ('^/', ''); -- remove leading /web/, /all/, /~~org-123~~/, /org-~~1234/, /123/, /1234/, /12345~~/, /ukgwa/, /tna/, or /		snapdate = path:gsub ('^/web/', ''):gsub ('^/all/', ''):gsub ('^/%d%d%d%d?%d?/', ''):gsub ('^/org%-%d%d%d%d?/', ''):gsub ('^/ukgwa/', ''):gsub ('^/tna/', ''):gsub ('^/', ''); -- remove leading /web/, /all/, /###/, /org-###/, /ukgwa/, /tna/, or /
	snapdate = snapdate:match ('^[^/]+'); -- get timestamp		snapdate = snapdate:match ('^[^/]+'); -- get timestamp
	if snapdate == "" then -- eg. /web//http.., etc.		if snapdate == "" then -- eg. /web//http.., etc.

Zyxw: update for Archive-It

2023-08-09T15:21:46Z

update for Archive-It

← Previous revision		Revision as of 15:21, 9 August 2023
Line 391:		Line 391:
	local msg, snapdate;		local msg, snapdate;

	snapdate = path:gsub ('^/web/', ''):gsub ('^/all/', ''):gsub ('^/~~org~~%-%d%d%d/', ''):gsub ('^/%d%d%d%d/', ''):gsub ('^/ukgwa/', ''):gsub ('^/tna/', ''):gsub ('^/', ''); -- remove leading /web/, /all/, /org-~~###~~/, /~~####~~/, /ukgwa/, /tna/, or /		snapdate = path:gsub ('^/web/', ''):gsub ('^/all/', ''):gsub ('^/o?r?g?%-?%d%d%d/', ''):gsub ('^/o?r?g?%-?%d%d%d%d/', ''):gsub ('^/%d%d%d%d%d/', ''):gsub ('^/ukgwa/', ''):gsub ('^/tna/', ''):gsub ('^/', ''); -- remove leading /web/, /all/, /org-123/, /org-1234/, /123/, /1234/, /12345/, /ukgwa/, /tna/, or /
	snapdate = snapdate:match ('^[^/]+'); -- get timestamp		snapdate = snapdate:match ('^[^/]+'); -- get timestamp
	if snapdate == "" then -- eg. /web//http.., etc.		if snapdate == "" then -- eg. /web//http.., etc.

Zyxw: update for Archive-It

2023-08-09T15:16:31Z

update for Archive-It

← Previous revision		Revision as of 15:16, 9 August 2023
Line 371:		Line 371:
	Given a URI-path to Wayback (eg. /web/20160901010101/http://example.com )		Given a URI-path to Wayback (eg. /web/20160901010101/http://example.com )
	or Library of Congress Web Archives (eg. /all/20160901010101/http://example.com)		or Library of Congress Web Archives (eg. /all/20160901010101/http://example.com)
	or Archive-It (eg. /all/20190621232545/http://example.com)		or Archive-It (eg. /all/20190621232545/http://example.com or /org-467/20191016094633/http://example.com or /3348/20151201214156/http://example.com)
	or UK Government Web Archive (eg. /ukgwa/20160901010101/http://example.com or /tna/20160901010101/http://example.com)		or UK Government Web Archive (eg. /ukgwa/20160901010101/http://example.com or /tna/20160901010101/http://example.com)

Line 391:		Line 391:
	local msg, snapdate;		local msg, snapdate;

	snapdate = path:gsub ('^/web/', ''):gsub ('^/all/', ''):gsub ('^/ukgwa/', ''):gsub ('^/tna/', ''):gsub ('^/', ''); -- remove leading /web/, /all/, /ukgwa/, /tna/, or /		snapdate = path:gsub ('^/web/', ''):gsub ('^/all/', ''):gsub ('^/org%-%d%d%d/', ''):gsub ('^/%d%d%d%d/', ''):gsub ('^/ukgwa/', ''):gsub ('^/tna/', ''):gsub ('^/', ''); -- remove leading /web/, /all/, /org-###/, /####/, /ukgwa/, /tna/, or /
	snapdate = snapdate:match ('^[^/]+'); -- get timestamp		snapdate = snapdate:match ('^[^/]+'); -- get timestamp
	if snapdate == "" then -- eg. /web//http.., etc.		if snapdate == "" then -- eg. /web//http.., etc.

Zyxw: Extract date from URL for Archive-It, same as with Wayback, etc.

2023-08-09T14:36:44Z

Extract date from URL for Archive-It, same as with Wayback, etc.

← Previous revision		Revision as of 14:36, 9 August 2023
Line 371:		Line 371:
	Given a URI-path to Wayback (eg. /web/20160901010101/http://example.com )		Given a URI-path to Wayback (eg. /web/20160901010101/http://example.com )
	or Library of Congress Web Archives (eg. /all/20160901010101/http://example.com)		or Library of Congress Web Archives (eg. /all/20160901010101/http://example.com)
			or Archive-It (eg. /all/20190621232545/http://example.com)
	or UK Government Web Archive (eg. /ukgwa/20160901010101/http://example.com or /tna/20160901010101/http://example.com)		or UK Government Web Archive (eg. /ukgwa/20160901010101/http://example.com or /tna/20160901010101/http://example.com)

Line 863:		Line 864:
	end		end

	if 'wayback' == ulx.url1.service or 'locwebarchives' == ulx.url1.service or 'ukgwa' == ulx.url1.service then		if 'wayback' == ulx.url1.service or 'locwebarchives' == ulx.url1.service or 'archiveit' == ulx.url1.service or 'ukgwa' == ulx.url1.service then
	if date then		if date then
	if config.verifydates then		if config.verifydates then

WOSlinker: use require('strict') instead of require('Module:No globals')

2022-10-21T10:04:14Z

use require('strict') instead of require('Module:No globals')

← Previous revision		Revision as of 10:04, 21 October 2022
Line 11:		Line 11:
	]]		]]

	require('~~Module:No globals~~');		require('strict');
	local getArgs = require ('Module:Arguments').getArgs;		local getArgs = require ('Module:Arguments').getArgs;

GreenC at 17:18, 9 August 2022

2022-08-09T17:18:06Z

← Previous revision		Revision as of 17:18, 9 August 2022
Line 550:		Line 550:
	ulx[argurl2] = {}		ulx[argurl2] = {}
	ulx[argurl2]["url"] = args[argurl]		ulx[argurl2]["url"] = args[argurl]
	argdate = "date" .. j		argdate = "date" .. i
	if args[argdate] then		if args[argdate] then
	ulx[argurl2]["date"] = args[argdate]		ulx[argurl2]["date"] = args[argdate]
Line 557:		Line 557:
	end		end

	argtitle = "title" .. j		argtitle = "title" .. i
	if args[argtitle] then		if args[argtitle] then
	ulx[argurl2]["title"] = args[argtitle]		ulx[argurl2]["title"] = args[argtitle]

Zyxw: tweak comments

2022-01-28T03:59:02Z

tweak comments

← Previous revision		Revision as of 03:59, 28 January 2022
Line 851:		Line 851:
	elseif 'mdy' == date then		elseif 'mdy' == date then
	date = nil; -- if date extracted from URL,		date = nil; -- if date extracted from URL,
	ldf = 'mdy'; -- then date=mdy overrides iso		ldf = 'mdy'; -- then \|date=mdy overrides iso
	elseif 'dmy' == date then		elseif 'dmy' == date then
	date = nil; -- if date extracted from URL,		date = nil; -- if date extracted from URL,
	ldf = 'dmy'; -- then date=dmy overrides iso		ldf = 'dmy'; -- then \|date=dmy overrides iso
	elseif 'ymd' == date then		elseif 'ymd' == date then
	date = nil; -- if date extracted from URL,		date = nil; -- if date extracted from URL,
	ldf = 'ymd'; -- then date=ymd overrides iso		ldf = 'ymd'; -- then \|date=ymd overrides iso
	else		else
	date, ldf = decode_date (date); -- get an iso format date from date and get date's original format		date, ldf = decode_date (date); -- get an iso format date from date and get date's original format

Zyxw: test worked, add comments

2022-01-28T03:55:21Z

test worked, add comments

← Previous revision		Revision as of 03:55, 28 January 2022
Line 850:		Line 850:
	ldf = 'iso'; -- set to default format		ldf = 'iso'; -- set to default format
	elseif 'mdy' == date then		elseif 'mdy' == date then
	date = nil;		date = nil; -- if date extracted from URL,
	ldf = 'mdy';		ldf = 'mdy'; -- then date=mdy overrides iso
	elseif 'dmy' == date then		elseif 'dmy' == date then
	date = nil;		date = nil; -- if date extracted from URL,
	ldf = 'dmy';		ldf = 'dmy'; -- then date=dmy overrides iso
	elseif 'ymd' == date then		elseif 'ymd' == date then
	date = nil;		date = nil; -- if date extracted from URL,
	ldf = 'ymd';		ldf = 'ymd'; -- then date=ymd overrides iso
	else		else
	date, ldf = decode_date (date); -- get an iso format date from date and get date's original format		date, ldf = decode_date (date); -- get an iso format date from date and get date's original format

Zyxw: test

2022-01-28T03:14:17Z

test

← Previous revision		Revision as of 03:14, 28 January 2022
Line 850:		Line 850:
	ldf = 'iso'; -- set to default format		ldf = 'iso'; -- set to default format
	elseif 'mdy' == date then		elseif 'mdy' == date then
	date = '';		date = nil;
	ldf = 'mdy';		ldf = 'mdy';
	elseif 'dmy' == date then		elseif 'dmy' == date then
	date = '';		date = nil;
	ldf = 'dmy';		ldf = 'dmy';
	elseif 'ymd' == date then		elseif 'ymd' == date then
	date = '';		date = nil;
	ldf = 'ymd';		ldf = 'ymd';
	else		else

Zyxw: test

2022-01-28T02:59:19Z

test

← Previous revision		Revision as of 02:59, 28 January 2022
Line 849:		Line 849:
	date = 'index';		date = 'index';
	ldf = 'iso'; -- set to default format		ldf = 'iso'; -- set to default format
			elseif 'mdy' == date then
			date = '';
			ldf = 'mdy';
			elseif 'dmy' == date then
			date = '';
			ldf = 'dmy';
			elseif 'ymd' == date then
			date = '';
			ldf = 'ymd';
	else		else
	date, ldf = decode_date (date); -- get an iso format date from date and get date's original format		date, ldf = decode_date (date); -- get an iso format date from date and get date's original format