Wikipedia talk:Bots/Requests for approval/Archive 3

This is an archive of past discussions about Wikipedia:Bots. Do not edit the contents of this page. If you wish to start a new discussion or revive an old one, please do so on the current talk page.

Archive 1

Archive 2

Archive 3

Archive 4

Archive 5

→

Archive 10

Process streamlining

Sorry, but I still can't figure when to grant access to a bot approved by the committe. Suggest the following setup:

User places a request on Page 1. Discussion takes place here.
Committee approves the request, moves the approved transcluded subpage to Page 2
Bureaucrat who has page 2 on his watchlist then comes around granting the flag. Archives the template to page 3.

How does this setup sound? =Nichalp «Talk»= 05:23, 3 December 2006 (UTC)

The approval process has been done readily by Redux and Taxman on numerous occasions without any problems. Perhaps I should explain how a bureaucrat should go about approving bots. When a bot is approved an approvals member places the new entry at Wikipedia:Bots/Requests for approval#Approved Requests. When you want to know if any bots need work, look there. The page itself is not editted that often except to add and remove (approved or otherwise) requests, so has been sufficient to merely watch the approvals page. I see no compelling reason to change how this works, although if there were enough people who wanted to we could. When a bot requires a flag, it will say so. So all you have to do is to look for something like "bot flag required" and take appropriate action. At that point it is the job of the bureaucrat to ensure that the approval is legitimate and properly sanctioned. The following diffs will show exactly how this is done: here and here. The last link to the log shows how the bureaucrat has to manually check the approval to ensure that the approval is valid. -- RM 18:14, 6 December 2006 (UTC)

With regards to your suggestion, transcluded subpages generally are only used for the initial approval. Since they are large and take up a lot of space, we only use them for new approvals. New tasks and approved tasks are just linked from the main page. In your example there is no reason to move a transcluded subpage, since once a bot is initially approved or denied, the subpage is then no longer transcluded. I've found that using everyone on one page streamlines the process. When I want to get an overview of what is going on, I have one central page to deal with, rather than a 3 page system. I think you'd find that others would agree. -- RM

Pockbot - request to un-archive approva request

PockBot's Request for Approval was arhived after I requested a suspension to allow me to complete the bot's development. I've now finished coding the bot and have run some test edits on it and it seems ot be working. Can I get the bot's RFA un-archived and the bot approved please? - PocklingtonDan 17:56, 6 December 2006 (UTC)

Done. -- RM 18:07, 6 December 2006 (UTC)

Thanks — Preceding unsigned comment added by PocklingtonDan (talk • contribs)

Interesting discussion

Something relevant that the Bot Approvals group may want to have a look at is being discussed at the Main Page's talk. It may involve the approval of an adminbot (basically, since it would be used exclusively to edit a protected page). Tito xd^(?!?) 04:05, 9 December 2006 (UTC)

WP:BAG

Moved section to Wikipedia talk:Bots/Approvals group. — xaosflux ^Talk 04:34, 4 January 2007 (UTC)

ProtectionBot Process

Since there has never been an adminbot approved from WP:BRFA, I'd like to figure out what people feel the process of Wikipedia:Bots/Requests for approval/ProtectionBot ought to be? Should it go to WP:RFA? Should it have a test period (before or after RFA?) Etc. I've been manually debugging using dummy pages and my admin account, and I believe I am about ready to go from the point of view of having an operational bot. So I guess the question is what now? Dragons flight 00:51, 2 January 2007 (UTC)

I think it should be manually assisted by a human admin. I suppose if it passes the RfA as a bot then it should be valid, but I would not support such and RfA, not if it was not human supervised. Even the best scripts screw up once in a while. But as far as I am concerned, and RfA with full disclosure is as valid as any other, regardless of the operator, human or computer. HighInBC ^{(Need help? Ask me)} 00:59, 2 January 2007 (UTC)

The point is to catch unprotected sections/images before the vandals that have been sticking mutilated penises on the Main Page do. The proposal, which has been heavily supported so far, is for an automatic bot. Running manually assisted defeats the point. Dragons flight 01:17, 2 January 2007 (UTC)

I would take it to RfA before having a bureaucrat flag it as a sysop. Better to get community input before anything is done. The only problem is that it would probably be opposed... (I would support it though) —Mets501 (talk) 01:26, 2 January 2007 (UTC)

Well, considering the limited scope of the bot, I would support the RfA, but only one that clearly limited the job description of the bot. Additional task would require additional community support.

I would say every task would need both the support of the bots approval and the community at large(by something life an RfA). My reaction to oppose was a bit knee-jerk, but keep in mind others will have the same reaction, HighInBC ^{(Need help? Ask me)} 03:40, 2 January 2007 (UTC)

This bot and it's task should have any trialing done via WP:RFBOT and then if warranted given a conditional trial period, with the condition being that the bot will need to pass a community-supported RFA. See Wikipedia:Requests for adminship/TawkerbotTorA for the last bot that attempted to gain an admin flag. — xaosflux ^Talk 03:48, 2 January 2007 (UTC)

After the discussion on the bot approval page concludes (note: I've added a few new questions and comments), I would suggest testing the bot on either another wiki or using user subpages here with example images (that aren't being used anywhere else). Following the test, the bot should then go to RfA; it should definitely go through RfA to gain a sysop flag, not only because of the page is where all sysop requests have been placed, but because of the wider participation level there. Thanks! Flcelloguy (A note?) 04:07, 2 January 2007 (UTC)

Concur with the above, it needs to go through RFA which so far has proved "challenging". Its a bit chicken and egg here, since the bot might be approved in principle here and rejected and RFA and vice-versa... ---pgk 18:29, 2 January 2007 (UTC)

Personally, I'm inclined to believe that RFA is actually a bad way to manage/approve bots, since that community is far less attuned to the relevant technical issues than this one, but I don't want to try and make exceptions on my behalf. If people believe that RFA is the necessary thing then that is what I will do. Dragons flight 21:40, 2 January 2007 (UTC)

RFA isn't to approve the bot, it's to approve the admin status. Technically you need both approvals to get an admin bot, assuming an RFA succeeded then approval here is unlikely to fail because there isn't a broader community support for such function, but may still fail if it is considered to have technical gaps which may cause problems (Of course they can mostly be fixed). The bot approval group doesn't have a remit to approve admin status and history has shown that the community as a whole is pretty resistant to the idea. --pgk 22:33, 2 January 2007 (UTC)

I'd say you would have to go through RFA for the reasons people mentioned such as wider participation, etc. You'll definitely get some less than helpful opposition, but that shouldn't be enough to sink a well thought out proposal. Thinking from the last experience, it seems you'd have a much better chance if you got it fully approved by all members of the BAG first. I think a large part of the last one not succeeding was due to outstanding objections of BAG members. So basically it needs both processes, but you'd have an easier time if there were no unresolved issues here. Add to that having a number of trusted people review the code and you'd have a good shot. My other thought is instead of getting the admin bit, the bot could just maintain a checkpage that tells the current status of the pages that need to be protected for the current day and a list of pages that need to be protected for the next day. A bot would be very valuable for maintaining that list, whether or not it had the admin bit. - Taxman ^Talk 22:51, 2 January 2007 (UTC)

Regarding the code, can I get a short list of people who want to review the code? I don't want to make it public because there are some aspects that could be very exploitable by vandals. It's about 500 lines of Python. I need to cleanup / comment it a bit more, but I would like to know who intends to seriously look at the code. Dragons flight 01:24, 3 January 2007 (UTC)

I know my way around Python and would like to look at it. I work on bots myself so I would be interested in another persons methods. Plus I am pretty good at finding serious bugs. My e-mail is set up. HighInBC ^{(Need help? Ask me)} 01:27, 3 January 2007 (UTC)

I would also like to take a look at it. Admittedly, I'm unfamiliar with Python, but I should be able to work through it and follow it through. Thanks for being so patient with our questions/comments! Flcelloguy (A note?) 01:38, 3 January 2007 (UTC)

Count me in -- Tawker 02:58, 3 January 2007 (UTC)

Admittedly I'm unfamiliar with Python and probably won't have any amazingly insightful comments, but I'd love to take a look. alphachimp. 04:48, 3 January 2007 (UTC)

I think all members of the BAG should have it if they want it, and anyone else is up to your discretion. But do think about just making a checklist that the bot updates often. It would be nice if there was somewhere only admins could see it. - Taxman ^Talk 17:12, 3 January 2007 (UTC)

I would like to take a look at it as well if you don't mind. —Mets501 (talk) 19:06, 3 January 2007 (UTC)

I emailed each of you asking where to send the code. The four of you that have responded so far should now have a copy. Dragons flight 02:36, 5 January 2007 (UTC)

Thank you! Flcelloguy (A note?) 02:54, 6 January 2007 (UTC)

WP:BAG endorsement reqeusted

Regarding this bot's RFA request, I've added a section that may help assure the community of the willingness of us to stop this bot should it malfunction or be reprogrammed, please see Wikipedia:Requests for adminship/ProtectionBot in the section started with "WP:BAG bot policy enforcement:". Thank you, — xaosflux ^Talk 17:37, 7 January 2007 (UTC)

Second bot

I am almost done a second bot based on the response I got here:Wikipedia_talk:Administrator_intervention_against_vandalism#Possible_bot, and the idea being brought up here: Wikipedia:Bot_requests/Archive_8#WP:AIV-Clearing_Bot.3F. I will remove already blocked people from WP:AIV.

My question is do I create a new account for each bot I make, or can they share an account? HighInBC ^{(Need help? Ask me)} 00:47, 3 January 2007 (UTC)

Create a new account, it makes things a lot easier :) -- Tawker 00:59, 3 January 2007 (UTC)

If it's a bot that's continuous (i.e. running all the time) it's probably better to make a new account. —Mets501 (talk) 01:02, 3 January 2007 (UTC)

Will do, thanks for the tip. HighInBC ^{(Need help? Ask me)} 01:04, 3 January 2007 (UTC)

DomBot

DomBot (talk · contribs · deleted contribs · nuke contribs · logs · filter log · block user · block log) appears to be running tasks outside its assigned function: tagging a category for deletion [1], listing a cfd [2], reverting non-vandal edits [3] and leaving messages on user talk pages [4].I request a review of dombot's behaviour. Tim! 07:48, 5 January 2007 (UTC)

Anything really harmful, it may be outside it's scope but I don't see anything damaging in there -- Tawker 08:46, 5 January 2007 (UTC)

I posted this on AN, but maybe I should say it here too. I suspect the issue is simply that Internet Explorer remained logged in after an AWB bot run. alphachimp 09:08, 5 January 2007 (UTC)

That is why I use a different set of cookies and my own useragent hehe. HighInBC ^{(Need help? Ask me)} 17:45, 7 January 2007 (UTC)

Request BAG attention

To Wikipedia:Bots/Requests_for_approval/MartinBotII_4, whichis currently in a rather extended trial (which probably should have ended by now...). I've just got a box set up which can run the bot, and so would appreciate approval :) Thanks, Mart inp23 18:01, 5 January 2007 (UTC)

Thanks Mets501. Mart inp23 19:12, 6 January 2007 (UTC)

No problem. —Mets501 (talk) 19:44, 6 January 2007 (UTC)

In the interests of openness

MartinBotIII is currently performing a substing exercise on some of RefDeskBot's edits (which used a template which didn't work). I'm posting this here in the interests of openess - there should be no more than 1200 edits, at the throttle of 6 per minute. The bot will then do a very simple text replacement on the pages (after the substing). To make clear, there are some 600 pages, it of which will be edited twice. This is all being done in AWB, but the text replacement is outside of the bot's assigned task, so I'm inviting a BAG member to tell me to get approval, if I need it. Thanks, Mart inp23 18:01, 7 January 2007 (UTC)

So basically you'll be making edits like [5] and then replacing 2007 with 2006 and then 2008 with 2007? —Mets501 (talk) 18:35, 7 January 2007 (UTC)

Yes - exactly. It really just cleaning up the bad template, and fixing RefDeskBot's responsibility. The bot is being monitored, though is in automatic mode (doing substing right now). Will another BRFA be needed for the find-replace feature (I don't want to break any rules in a big way :)). Mart inp23 18:58, 7 January 2007 (UTC)

Consider it

Approved. —Mets501 (talk) 19:11, 7 January 2007 (UTC)

Many thanks Mart inp23 20:04, 7 January 2007 (UTC)

Threshhold for Bot Flag?

DaNumber1Bot bot was approved by Tawker to perform some fairly simple text replacements using AWB in NYC Subway related articles. Tawker said that a flag was unneeded (see [6]). My guess is that this bot will do a minimum of 200-300 edits within it's approval period. What's considered the threshold for the assignment of a flag? I've gotten some comments about the unflagged bot messing with watchlists. alphachimp 06:33, 17 January 2007 (UTC)

Generally the "rule" on bot flags was to do with edits a minute rather than total edits. I was told 2 edits a min + flag it, otherwise it's not really necessary and likely more work for our 'crats.

I don't see any harm in flagging the bots, so either way works - the no-botflag thing was to reduce work for the 'crats. -- Tawker 07:27, 17 January 2007 (UTC)

Right and if this will only be a single-run bot no need to really flag it either, as long as it isnt flooding the rc lists. — xaosflux ^Talk 03:04, 18 January 2007 (UTC)

Well bot flagging is incredibly easy for us. You guys in the BAG do all the work, and it's your heads on the line if you make a mistake :), so if you'd rather be more liberal in giving them out to save RC flooding go ahead, within reason. - Taxman ^Talk 23:01, 18 January 2007 (UTC)

Edit summaries

Can everybody make sure to include in the edit summary of Wikipedia:Bots/Requests for approval that you've approved a bot and that a flag is needed? I don't always load the page, it's much easier to use the history to check if a promotion is needed. Not a big deal, but it can help speed up the process. The latest one waited for 24 hrs just because I didn't see it. Not to pick on you Betacommand, just a request. - Taxman ^Talk 23:01, 18 January 2007 (UTC)

Request to join bot approval group

I have made a request to join the bot approval group here: Wikipedia talk:Bots/Approvals group#Request_to_join_bot_approval_group. I was not sure if that was the appropriate venue, so I am posting a link here. HighInBC ^{(Need help? Ask me)} 15:06, 20 January 2007 (UTC)

Uncategorised short articles, and tagging with {{stub}} instead of {{uncat}}

My bot is approved to tag uncategorised articles of various flavours, and there's a rather large backlog of these in the Jan. db dump. Many of these are very short articles, so it's probably more pragmatically useful to tag these with {tl|stub}}, rather than with {{uncat}}. The code would be identical (with an extra double-check for length of "live" article), and the effect very similar (unsorted stub vs. uncategorised article), but I thought I'd double-check with the BAG if it's felt that this would need separate task approval. I've already mentioned this at both WP:WSS and CAT:NOCAT, and I'll of course act in line with what they suggest for length threshold, whether the entire idea is a plan, etc. Alai 06:48, 29 January 2007 (UTC)

I'm not a BAG member, but I'd recommend that you get separate approval. {{uncat}} is objective and {{stub}} is subjective, and although I'm not sure whether this is enough of a difference to prevent a bot adding {{stub}} tags, I think it's enough of a difference that you should at least request approval for the new task. --ais523 09:24, 29 January 2007 (U T C)

That's a fair point, I'll do so. If the worst comes to the worst, I can always tag them into a temporary this-is-an-uncategorised-very-short-article-and-probably-a-stub maintenaince category... Alai 16:35, 29 January 2007 (UTC)

Concerns about Jogersbot

discussion moved to Wikipedia talk:Manual of Style (dates and numbers).

While I don't disagree that the discussion on the bot function is better discussed at the talk page for the relevant MoS, I am concerned that there has been no discussion about whether or not a bot should be allowed to continue when editors have raised concerns. The bot has currently been suspended by its operator :-) (31 Jan) but was not when concerns were first raised:

Whyaduck 00:58, 27 January 2007 (UTC) at WP:AN/I
1. drawn to Joger's attention by Cowman109 01:04, 27 January 2007 (UTC) at User talk:Jogers
MoRsE 14:34, 30 January 2007 (UTC) at Talk:Timeline of aviation
Golden Wattle talk 20:49, 30 January 2007 (UTC) at User talk:Jogers and Wikipedia talk:AutoWikiBrowser#More on dates
Askari Mark 23:49, 30 January 2007 (UTC) at Wikipedia talk:WikiProject Aircraft
Akradecki 19:24, 31 January 2007 (UTC) at User talk:Jogers

When there are objections to the edits a bot is making, why is approval not suspended pending resolution?--Golden Wattle ^talk 21:08, 1 February 2007 (UTC)

I am not on the approvals group, though I imaging the approval will be suspended if and when there is a clear consensus to do so. HighInBC ^{(Need help? Ask me)} 21:15, 1 February 2007 (UTC)

No one in the approvals group has responded to my or other concerns despite my comments here and also on the bot approval page. There is no apparent procedure for objecting to a bot's activities or for obtaining consensus to suspend. If the bot had not stopped voluntarily ... these edits will be hard to reverse, particularly the longer the discussion takes about the MoS and none of the date discussions have ever been quick or conclusive.--Golden Wattle ^talk 21:23, 1 February 2007 (UTC)

The way I see it, this is not a problem with the bot, but a disagreement with the function the bot is serving. Since the bot operator has stopped voluntarily, what action should the group take? HighInBC ^{(Need help? Ask me)} 21:36, 1 February 2007 (UTC)

The bot carried on for more than 24 hours after objections were raised - ie voluntary cessation was not nearly quick enough. The operator even carried on ignoring queries altogether at one point until blocked for the purpose of drawing his attention to discussion querying his activities. This is a problem with the bot if it is not carrying out a universally agreed function. The MoS does not say for example that years must be linked for date preferences to work - for yearless dates, the MOS only deprecates the same because context might be lost (ie the date refers to this year but next year that might not be clear. The MoS does not mention date preferences as a reason for including the year. See Wikipedia:Manual of Style (dates and numbers)#Yearless dates. As Akradecki has pointed out, there has been discussion about piped dates - I do not think there is concensus to deprecate the piped year link one recent discussion. Moreover, I note that Wikipedia:Piped link is not even a guideline, it is a how-to. Akradecki also points out that some preferences are overridden in some contexts, for example resizing of thumbnails. Another user (in another discussion) has pointed out that mass edits to change dates are deprecated.

My question is though, what does it take to stop a bot? Where are the instructions to seek suspension so that a discussion can be had? As an admin I did not feel comfortable bout blocking the bot, I felt I had to to get the user to respond, having responded he kept on his merry way and I see no opportunity under the blocking policy to stop him again - what would stop him?--Golden Wattle ^talk 21:56, 1 February 2007 (UTC)

Please stop saying that I was ignoring queries until you blocked my bot. I already explained to you that the bot run in automatic mode. I wasn't around at that particular moment. Jogers (talk) 23:39, 1 February 2007 (UTC)

A bot can be blocked for many reasons, by any admin. While the approvals group's permission is needed to run a bot, this permission does not guarantee community acceptance. I don't see how the bot approval group revoking permission to this bot would have helped this situation, considering any admin has the power to stop the bot, and the community has the power to agree to stop it. I still am not sure that the consensus is against this bot. HighInBC ^{(Need help? Ask me)} 22:02, 1 February 2007 (UTC)

I can't see how you can see consensus one way or the other. At Wikipedia:Bots/Requests for approval/Jogersbot all I can see is an application by Jogers, discussion from three other editors, only one of which was really addressing the function itself. In the discussion Jogers notes potential for controversy "There is a long-standing guideline on WikiProject Music saying that piped links to "years in music" shouldn't be used at all. This seems to be somehow controversial though." Jogers has only dealt with one project, there are other projects which use the year in xxxx format, he did not consult with them. Above I have noted 5 overt objections. At Wikipedia talk:WikiProject Aircraft#"Year in aviation" vs. reader's date preference conflict 8 editors on the project have commented, not one in favour.

The blocking policy states Bots must have prior approval on Wikipedia:Bots/Requests for approval and may be blocked if an admin thinks they are malfunctioning in a damaging way - I am not sure that my views = malfunction in damaging way, hence I do not see I have authority to block.--Golden Wattle ^talk 22:17, 1 February 2007 (UTC)

That is an additional justification to block a bot, the standard reasons for blocking still apply to a bot. If you think it is going against consensus, talk to the human in charge, if they don't respond a block may be in order. It seems you talked to the human an the bot stopped, not sure what the approvals group can add to that. HighInBC ^{(Need help? Ask me)} 22:22, 1 February 2007 (UTC)

As the approver of this bot, I think it is best to temporarily suspend operations of this bot until consensus can be reached by all relevant WikiProjects about whether they want the change for their particular "xxxx in yyyy" series. Jogers, I recommend you go around to the different applicable projects and attempt to gain consensus, and then on your userpage post a link to the consensus for each project. Once consensus has been reached for a particular project, then you can start changing their "xxxx in yyyy" links. I should also mention that blocking a bot is no big deal. Look at some of the best bots; they've been blocked numerous times, sometimes for very trivial reasons. —Mets501 (talk) 22:55, 1 February 2007 (UTC)

Sure, I've already suspended the bot activity. I'm not sure if I have enough patience to discuss it over and over again at different WikiProjects as I'm already quite tired with this. We'll see if anybody else comments the issue at Wikipedia talk:Manual of Style (dates and numbers). Jogers (talk) 23:16, 1 February 2007 (UTC)

Question about scope

I wish to implement a new feature, discussed here: Wikipedia_talk:Administrator_intervention_against_vandalism#Possible_bot_feature.

Does this fall withing my current scope of approval, or should I do another feature request? HighInBC ^{(Need help? Ask me)} 01:43, 2 February 2007 (UTC)

Here is an example in my sandbox: [7]. It is already coded. HighInBC ^{(Need help? Ask me)} 02:45, 2 February 2007 (UTC)

Close enough, APPROVED. — xaosflux ^Talk 04:29, 2 February 2007 (UTC)

Question about approval time

I'm just curious (read: I'm not trying to rush anyone), how long does it usually take before a bot is approved? I haven't gotten any new comments in a couple of days. --Selket 21:56, 2 February 2007 (UTC)

Yeah, I was thinking about your bot, and wasn't quite sure if it was worth all of those edits to move a period, so I held back on responding. Anyone else have ideas? (See Wikipedia:Bots/Requests for approval/SelketBot. —Mets501 (talk) 22:13, 2 February 2007 (UTC)

Hey, I did try rushing people, and see where it got me. :) (No comments at all in 5+ days...) On SelketBot: that raises the more general point of "when is an edit too minor to be worth doing at all?" (or relatedly, to be worth doing en masse). I must admit I've made edits by hand just to move a comma or period (typically to MoSify "aesthetic quotes", especially if they're used inconsistently, or in articles using Commonwealth English)). It's hard to argue that where there's a clear consensus (or painfully hammered-out style guidance, as the case may be) that articles shouldn't be put into conformance with it; but equally, it hardly seems like an urgent matter. So firstly, is there actually a clear consensus for this particular matter, as a style issue? Would it be worth testing same with a trial run, and waiting a week afterwards to see if people irately put them back, or complain? (Acceptance in practice may be a different matter from apparent agreement on the guideline page.) And, is it worth considering "low priority status" for bot tasks there's general acceptance of being carried out, but are extremely minor in nature? That is, they'd be subject to tighter constraints on edit rate and times and days of operation. Alai 02:30, 4 February 2007 (UTC)

I think that something that causes great delays in the bot approval process are requests which are very specific and not for a standard task. For example, Alai, I don't know if there has been consensus for the tasks that your bots wants to do, or really the effects of the task, since I'm not very familiar with that area (WP:WSS and CAT:NOCAT). Something that would speed those approvals up would be a links to a place where consensus was formed, the task was discussed, and relevant policies, etc. Simple requests like this get approved in 6 minutes, and other requests don't. —Mets501 (talk) 02:36, 4 February 2007 (UTC)

See discussion at WSS here, and at NOCAT here. I linked to both pages in the request, and stated that's where the relevant discussion was -- seems pretty specific to me. If you feel you don't have the information to make a decision, it'd be more helpful to say so, rather than just quietly waiting. Alai 03:02, 4 February 2007 (UTC)

anonymous bot..

the ip address 128.97.70.155 (talk · contribs) appears to be a bot.. i don't know what should be done about this, i just thought i should let somebody know. 131.111.8.99 16:56, 7 February 2007 (UTC)

Thank you very much. I am not sure, but it looks like a legitimate bot that accidentally logged out, I have blocked the IP for anonymous users only, so if the user's bot logs in properly it should not be effected. HighInBC ^{(Need help? Ask me)} 17:08, 7 February 2007 (UTC)

that is the new WP 1.0 bot Betacommand ^{(talk • contribs • Bot)} 17:21, 7 February 2007 (UTC)

I figured as much, it looked legit, and I remembered the approval for that bot, that is why I did an anon only block, perhaps a loss of session data. HighInBC ^{(Need help? Ask me)} 17:27, 7 February 2007 (UTC)

Change of bot username

I've been working on HighInBCBot (with HighInBC's approval), and we have decided that it would be a good idea to rename the bot. We discussed the options, and I decided to post here for further advice on how to proceed. In the bot's approval it was determined that it did not need a bot flag, so the account is currently unflagged. The contributions of the account aren't particularly important, so moving them isn't really urgent, so I think HighInBC's suggestion to just create another account is best. Is any further BAG approval needed to do this? Does anyone have any other suggestions for a better way to effect the change? All input is appreciated. Thanks! —Krellis (Talk) 21:34, 27 February 2007 (UTC)

Just ask a b'crat to change the name and update relevant pages, and move the BRfA to the new name. That is the simplest thing. Betacommand ^{(talk • contribs • Bot)} 21:45, 27 February 2007 (UTC)

See WP:CHU. —METS501 (talk) 21:52, 27 February 2007 (UTC)

Okay, that was one of my thoughts, in the discussion on his talk page, HighInBC had mentioned that he was under the impression that CHU was difficult when there was significant edit history involved, so it would be easier to simply create a new account. If that's not the case, and/or CHU is otherwise simply the "better" way to do it, I have no problem going that route. —Krellis (Talk) 21:57, 27 February 2007 (UTC)

CHU is a real pain on the servers when a user has a lot of edits (that's why it has an edit cap). Creating a new account and mentioning the username of the old one on the new account would seem to be a sensible thing to do. --ais523 18:25, 28 February 2007 (U T C)

HighInBCBot has 349 edits, which is little consequence to load on the servers. Also, there's not been a cap on edit counts for WP:CHU for some time now. There used to be, but it was removed a while back. --Durin 20:52, 28 February 2007 (UTC)
If it only reached 349, then CHU would seem like a good idea. --ais523 09:26, 1 March 2007 (U T C)

Thanks everyone for the input, we've submitted a request on WP:CHU, hopefully Essjay will decide the dust has settled from the clerking debates soon and resume fulfilling requests, and we'll be on our way. —Krellis (Talk) 16:04, 1 March 2007 (UTC)

Done Hey, I exist too... :-) =Nichalp «Talk»= 07:28, 3 March 2007 (UTC)

Thanks! —Krellis (Talk) 16:20, 3 March 2007 (UTC)

Thanks for existing! ^HighInBC ^{(Need help? Ask me)} 16:22, 3 March 2007 (UTC)

A question

Does the operator of a bot have to have written the bot as well? ~Step trip 23:52, 6 March 2007 (UTC)

Nope. I operate a bot written by Krellis and HighinBC. alphachimp 23:56, 6 March 2007 (UTC)

But keep in mind that it is the operator who is responsible for any damage done by the bot because of faulty or malicious programming, not the the writer. So, beware when you accept coding from another person and you are the operator. Cbrown1023 talk 23:59, 6 March 2007 (UTC)

CommonsDelinker

CommonsDelinker (BRFA · contribs · actions log · block log · flag log · user rights) is now editing on en:, and has got a lot of edits already (more than the 500 for which it was approved for trials, but it seems to have been approved for editing on en: on Meta, if that makes sense). I suggest that its tasks page be reactivated/reclosed to allow for the new situation, and that it be given a bot flag so that it stops activating new-messages bars when changing images on Talk pages. --ais523 09:08, 15 March 2007 (U T C)

I've requested the bot flag immediately, so that should resolve the issue. There has been some discussion on my talk page about the approval, so it could change, but for now this should fix those problems. -- RM 12:45, 15 March 2007 (UTC)

No response there, so I've flagged it. Please let me know if anything changes. - Taxman ^Talk 15:43, 15 March 2007 (UTC)

Approval time

A question about the approval time has already been posed earlier (Question about approval time). But I don't think the question was really answered there, so I am posting it again. How long does it take to approve/disapprove a bot? I'm particularly interested in the maximum time it takes after all questions were answered.

The Requests for approvals page describes the time as reasonable which is a poor statement in my opinion, because it basically doesn't say anything. It's unprofessional and intransparent.

The bot policy article says, it might take up to one week. This would be a good time span, I think, and nobody will be angry when you're faster than that. Well, the reason why I'm writing this is that I posted my request for approval ten days ago and didn't even receive a comment from an approval group member yet. So, unfortunately, the goal to decide within a week seems unrealistic at the moment. I'm personally a bit disappointed but I hope my criticism here is constructive and my tone neutral anyway. Here are some suggestions:

The bot approval group should define a reasonable, realistic maximum decision time. This time can of course be exceeded when further discussion on a request is needed and done. I think that everyone will understand that.
Once defined, this time span should be the only one named at all relevant pages.
It seems to me that the group members currently look at the requests individually and comment on what they are interested in. Please find a way to make sure all requests are reviewed adequately. Assign the responsibility to one of your group members, if a request didn't get an answer after a few days. Or make a bot that notifies all group members if a request hasn't been reviewed within a certain time…
The approval group should appoint new members (I saw that some already applied) if you feel that that you cannot answer all requests appropriately within the defined time.
The bot approval group could profit from someone with management skills — there's no reason why all group members must be bot experts themselves. You might be able to improve the coordination of approvals with someone focusing on managing the procedure.

I'd be happy to hear the opinion of more than one approval group member. Please don't comment on my bot here (I'm just adding this because that's how the discussion about the approval time went off-topic last time). — Ocolon 19:36, 14 March 2007 (UTC)

If everything worked perfectly on this project, we'd be done. :) It's not so anything that needs doing needs someone to do it. If you can help with any of the above please do. The suggestion on a bot to track requests isn't a bad idea, something like WP:RFASUM that lists the last time each bot request has been edited and perhaps the last time edited by a BAG memeber. Other than that, you can't really enforce deadlines on volunteer work. - Taxman ^Talk 21:27, 14 March 2007 (UTC)

Echo much of Taxman, note though that although BAG doesn't have official "clerks", anyone is welcome to help with the clerk work. Some bag members only have expertise in some types of bots, and don't weigh in on other kinds, so that can lead to delay until they are reviewed. Although there are "time limits" in many project areas, such as xFD, RFA, etc; these are not "rules" and mroe reflect the community standard. Often bot requests are not out there to serve an urgent need of the community at large, and when they are (such as the replacement of recent high profile archiving bots) they are usually sent to speedy trials. — xaosflux ^Talk 01:38, 15 March 2007 (UTC)

I agree as well. Anyone at all who is familiar with a certain area can weigh in on a bot approval; confirmation from someone familiar with that area is very helpful in bot approvals. —METS501 (talk) 03:04, 15 March 2007 (UTC)

I definitely agree with you on this point. I didn't mean to belittle comments by non BAG members, they are as valuable as those of BAG members. But someone has to decide finally and the decision is made by a bot approval group member. I also see your point on the problem with enforcing deadlines on volunteer work. You're right. But when there's a chance to have a new, qualified BAG member, please take it. It will most probably reduce the approval time and the amount of request reviewing everyone of you has to do.

I'm going to add a bot tracking approval requests as described by Taxman to Wikipedia:Bot_requests. It sounds good. :) — Ocolon 16:50, 16 March 2007 (UTC)

If there is interest, my services are still available in this area. ^High_InBC^{(Need help? Ask me)} 16:54, 16 March 2007 (UTC)

I too would be glad to take on a role, if required. Mart inp23 17:31, 16 March 2007 (UTC)

I've always thought we could use more people. If another BAG member seconds the motion, I have no issue with adding more members. We just lost Essjay permanently (although perhaps he didn't do much with bots recently), and I myself have done little this year, so more members would be welcome, so long as properly qualified, but that's easy enough to check. -- RM 22:00, 16 March 2007 (UTC)

I agree, more people overseeing this page would be helpful in catching more potential issues. =Nichalp «Talk»= 08:51, 17 March 2007 (UTC)

I did a very quick look at the recent edit history of Martinp23 and HighInBC to see who has been active in discussions on bot approvals, and it seems that Martinp23 has done quite a lot recently. HighInBC had a recent request to join and the advice given at that time was to become more active commenting on bots. After a cursory look, I'd say that there have probably not been enough edits since then to merit a change. Now I have not looked in major detail, but I'd at least be willing to endorse Martinp23 for candidacy/consideration, but I'd suggest that HighInBC take the previous advice and become more active. Hopefully some BAG members will comment here soon. -- RM 02:46, 19 March 2007 (UTC)

I've looked at the last month of edits by Martinp23 and I'm happy with the level of contribution. Let's wait a while and see if some other BAG members bother to comment, but if not, I'll just make the appointment without discussion. Again, HighInBC needs to comment more on bot proccedings or else make a strong case for why such experience doesn't matter (due perhaps to other knowledge). -- RM 20:53, 19 March 2007 (UTC)

If you need my help let me know. ^High_InBC^{(Need help? Ask me)} 23:06, 21 March 2007 (UTC)

I think your help is appreciated at any request that you review! The request for approval page now features a fine tabular summary of the current approval process maintained by BAGBot. Just check were you are able to help. :-) — Ocolon 08:34, 22 March 2007 (UTC)

Related tasks

When does a bot operator need approval for small one-time jobs? In particular, {{BFT}} was deleted and I would like to use GimmeBot (talk · contribs) to remove the templates from the talk page. Gimmetrow 20:31, 19 March 2007 (UTC)

In general, if the task is small and similar enough to a task the bot is approved for, then just do it, but here because the bot is entering a whole new field I would request approval. Or just ask another bot to do it at WP:BOTREQ. Or just do it manually approving edits with AWB. —METS501 (talk) 20:38, 19 March 2007 (UTC)

The letter of the law states that all tasks performed automatically must have approval. Now, in the face of IAR and such, there is clearly some flexibility here. For example, if you use a bot without approval or for an unapproved task, you might get blocked. There have been cases where a bot operator was faced with a task that needed to be done in 24 hours, and as such he just went ahead and did it without approval. In cases like this, you need to judge whether or not what you are doing is controversial and be ready to answer for it if something goes wrong. Still, we have been reasonable in many cases. It is not uncommon for operators of interwiki bots to not be aware of the complex approvals process here on en and thus perform operations without seeking approval. In general if you have never run a bot, you should probably not be running unauthorized tasks ever. If you have a bot that's been approved and have performed some number of successful tasks, then you can use a bit more judgement. It's always a good idea to at least notify us of a new task. If it would be more work to go through an approvals process than it would be to actually do the task, then that may be one of those times. Of course no matter what you do, if you do it without approval, you do so at your own risk. Be warned! Perhaps we need a process for "request for quick approvals" or some such thing. -- RM 20:45, 19 March 2007 (UTC)

How would you verify that any task is run with manual approval? There seems to be a difference between a bot which runs unassisted, and a bot which is an extension of the editor. How is this addressed in the policy? Gimmetrow 21:00, 19 March 2007 (UTC)

It's based on trust. You just have to trust that the person is approving all edits and not doing it automatically. Basically, what RM and I are saying is to use your judgment. If a task needs doing, generally it's a good idea to seek approval, but if there is an urgent need for a small task and it is clearly, clearly uncontroversial (such as removing a deleted template), then you can go ahead and do it with an already-approved bot. —METS501 (talk) 01:16, 20 March 2007 (UTC)

A related task for my bot

My bot, Ocobot, had been approved for trials recently and is now awaiting final approval. During the trial run I realized how many broken links he detects. I don't think I and few other human members monitoring his dead links list will be able to remove/recover dead links as fast as the bot finds new ones. So I thought Ocobot could tag (talk pages) of articles containing broken links if nobody has taken care of the affected links on the dead links list within a week.

Similar requests have already been approved for trials (but expired): BezkingBot-Link, ShakingBot.

Shall I wait for approval of my current request and then request this as a new task or can this be included right now? — Ocolon 08:48, 22 March 2007 (UTC)

Feel free to add another new request. -- RM 19:15, 22 March 2007 (UTC)

Okay, thanks. I will do so when (if) the original request gets approved. — Ocolon 19:20, 22 March 2007 (UTC)

Betacommandbot's approval

It's unclear at the moment exactly how much approval BetacommandBot (BRFA · contribs · actions log · block log · flag log · user rights) has, which has sparked a threat at WP:BN; could some BAG members take a look at Wikipedia:Bureaucrats' noticeboard#Another bot deflagging? --ais523 17:04, 22 March 2007 (U T C)

See Wikipedia_talk:Bots/Approvals_group#Betacommand -- RM 23:55, 22 March 2007 (UTC)

BAGBot

I think BAGBot as down, as his bot table seems to have been last updated some time yesterday. --kingboyk 17:38, 29 March 2007 (UTC)

Bot request

Hello! This message is because I would like to let my bot run on this wikipedia. Its name is Synthebot. Its main activity is fixing interwiki links. For doing this, it uses the interwiki.py script of the pywikipedia package. It runs on demand, for specific categories based on the Interlingua wikipedia.

Some extra information about myself is that I am an administrator in the Interlingua wikipedia, and I actively collaborated in the Interlingua, English and Spanish wikipedias. For further questions, do not hesitate in contacting me at my talk page. Regards, Julian 22:20, 29 March 2007 (UTC)

Please file a Requests for approval as shown on the project page. we would be glad to see it. Betacommand ^{(talk • contribs • Bot)} 22:23, 29 March 2007 (UTC)

Reactivating

Hallo, in oct. 2006 I asked for a botflag for my PortalBot. Now I read, that something has expired (?). I need the bot not every week, but in sometimes, I need it. Is there a way to get the botflag now ? Augiasstallputzer 22:49, 29 March 2007 (UTC)

Your prior request at Wikipedia:Bots/Requests for approval/PortalBot can be reactivated, but the trial expired. A new one can be granted (there was an outstanding operator question that was never answered). To reactivate it, remove the closeout tags and retranslcude it on the requests page. — xaosflux ^Talk 02:00, 10 April 2007 (UTC)

Request Template

In the request template template, where it says ==[[User:BotName|BotName]]==, it can just say BotName. The pipe trick automatically puts the same thing but without the namespace, which makes it unnecessary to retype it. You can also do it for the "Operator" part. --TeckWiz ^ParlateContribs_@(Lets go Yankees!) 14:38, 9 April 2007 (UTC)

The problem with that is that on the input box the tempalte that is used to prepopulate the box already expands the piped link, to avoid this I think we'd have to fill that with nowiki's that would need to be removed, making it harder. Feel free to try to fix it at Wikipedia:Bots/Requests for approval/InputInit though! — xaosflux ^Talk 01:58, 10 April 2007 (UTC)

Interwiki bots

Is there any coordination between interwiki bot operators? (Almost a rhetorical question as I'm pretty sure there isn't any, at least not formally). How many interwiki bots do we need? (as many as people apply for, or is there a sensible limit?) We approved one this morning from a French wikipedian, and now have another almost identical application, so I just wondered... --kingboyk 16:55, 13 April 2007 (UTC)

interwiki linking is never ending, its kinda like AVB or CAT:CSD. As long as we have growing wikis we need interwiki bots, and due to the size, and relative slowness of each bot I dont see a need to limit the number of bots. Betacommand ^{(talk • contribs • Bot)} 17:00, 13 April 2007 (UTC)

Do they all have identical scopes of operation? If some of them are only working on some subset of the wikis, the redundancy might be less than there appears. Alai 04:46, 14 April 2007 (UTC)

Overlapping bots

There has been several instances of deciding if a bot should be approved or not based on if a task is being performed by another bot. There is much need for redunancy in many bots for areas due simply to not all bot operators running dedicated always-on bots. A good example would be in most interwiki bots, or in Wikipedia:Categories_for_discussion/Working#Bots. Unless a bot is going to do a very specific task (especially one-time run type tasks) and/or be on a dedicated operating platform, having redunancy available is generally a good thing^TM; we've run in to many instances of "somethings not working" from users only to have a reply of "such-and-such bot is down right now". IMHO the determining factor is that if multiple bots are going to do the same task, they should produce the same result (within tolerance) and should be required to be aware of eachother (e.g. a newletter redunant bot would not deliver a newsletter to someone who already got it, and would reconfirm on edit conflicts). Any thaughts? — xaosflux ^Talk 05:26, 14 April 2007 (UTC)

I don't think we should deny a user the ability to run a similar bot. I may wish to run a bot at my convenience and leisure and tweak it to the latest standards without depending on someone else to do so. Wiki is afterall a open system, and by denying a user the chance to run such a bot reminds me of the patents and restricted copyrights scenario. We could always alert a user that a similar bot exists, and request that they provide a more detailed rationale for having a clone. =Nichalp «Talk»= 05:57, 14 April 2007 (UTC)

I think we need to be careful in this regard. Depening on the size and frequency of the task, we should take a different view of clones, For example, I'd have no problem approving multiple bots for fairly open tasks (where competance is shown), such as template substing and the like. If a bot is operating continuously (MartinBot, OrphanBot etc), then there can be no harm having clones, and I would encourage it to a certain level, to prevent the inevitable problems when people become over-reliant on the bot and it misses a run. On the other hand, I don't see the need for clones of bots which do closed, project specific tasks, such as newsletter delivery or updating a couple of status pages, which usually do just one small job on a certain schedule. Realistically, we should look at such requests and use common sense - if a clone is warranted, and the request meets all the usual criteria, we should approve. If the clone seems to just be there for the sake of having a bot, the task is small enough to be readily achieved by one bot, and a missed run won't cause the wiki to crash, I would be more inclined to reject the request on the grounds of it being unnecessary. The Wiki is, as Nichalp notes, an open system, and we should have a bias towards approval when looking at any request, though we also need to think of the potential problems should a bot account be compromised. Thanks, Mart inp23 16:09, 14 April 2007 (UTC)

Agree with you up to a point, and I'm fairly sure you're alluding to a certain case :) There are, of course, certain functions which ought to be done by one bot only (with perhaps a backup on standby), but these are exceptions to your general rule - if we had, say, 30 bots resetting Wikipedia:Introduction at half hour intervals the net result would be a reset every minute. Also agree with Martin that we should be defaulting towards approval but must always approach requests with a skeptic's eye: what could go wrong? Is this approval likely to end in tears on WP:ANI? Does the operator have the trust of the community? etc etc. --kingboyk 16:14, 14 April 2007 (UTC)

You're quite right, of course :). I think we should just follow WP:COMMONSENSE in terms of clone requests - you make a good point about the sandbox reseting, which would fall under continuous in what I wrote above. I do agree with the points you've raised there. Most clone requests which come through BRFA are using AWB, and most tasks on AWB are suitable for clones to do, as they are ever growing (ie, substing). If the task is pretty much the same day by day, and can be fully comleted in just one run, then there is much less of a need for clones. It's very hard to form a rule, as there will always be exceptions to it, though we are all capable of using our brains when looking at clone requests, and if they're quite reasonable and have a point, then there is no reason to reject. Mart inp23 16:27, 14 April 2007 (UTC)

I think you need more examples before being able to find enough patterns to make general rules. Examine each situation, but I encourage redundancy to avoid problems when a single bot fails. There is a need for cooperative clones, but bots with similar behavior yet different code should be encouraged so as to prevent the failure of a single technology from affecting all services. As previously mentioned, each situation will have to be considered; clones monitoring "Recent changes" will need to cooperate with each other more than bots which are slowly scanning through all articles (and therefore will be examining different articles). (SEWilco 22:20, 14 April 2007 (UTC))

For the previous example "30 bots resetting Wikipedia:Introduction at half hour intervals" I think that multiple bots should be running with the behavior "resetting Wikipedia:Introduction X minutes after the last change", where the "X" minutes is different for each bot. Normally the bot with the fastest cycle time will be the only one making changes, but others would take over if the first fails. (SEWilco 22:25, 14 April 2007 (UTC))

"X minutes after the last reset", perhaps, but yes, that's a good point indeed. --kingboyk 22:35, 14 April 2007 (UTC)

Yep agree. For example SB is having problems right now, and some of its work has been done by other bots in the past. Also some bots have "gone away" apparently permenantly. Rich Farmbrough, 13:22 27 April 2007 (GMT).

Operator response needed

We have a {{BAGAssistanceNeeded}} template; however, often an approval is held up because we need a response from the applicant. Might we create a template for this and ask the BAGBot to recognise it? --kingboyk 12:39, 17 April 2007 (UTC)

This is certianly something I'd like to see - it would be good if the bot could see the template on a page, and if it's there for, say, 48 hours, spam the operator's talk page. Mart inp23 12:51, 17 April 2007 (UTC)

Speaking of which, I don't mean to nag, but it's been 48 hours since my posting with no BAG response. --Selket ^Talk 23:38, 19 April 2007 (UTC)

Given that the BAG is a group, and the prospective op is a single user, this seems much less needed in the latter case than the former, given the option Martin mentions. OTOH it'd do no harm, esp. if the one is used as a backup for the latter. Alai 04:38, 22 April 2007 (UTC)

It's not meant to alert the user, it's so we and specifically BAGbot can keep better track of where the application is at. So, it does only half the job of {{BAGAssistanceNeeded}}. --kingboyk 10:46, 22 April 2007 (UTC)

Alerting the user, however, seems considerably the more important purpose. Alai 21:56, 22 April 2007 (UTC)

I'd think that would be best done by the user watchlisting the page, or by a note being left on their talk page. --kingboyk 22:17, 22 April 2007 (UTC)

Indeed. Alai 22:23, 22 April 2007 (UTC)

Perhaps I should clarify what I originally meant (although it's moot to me personally now, as I have left the BAG). Looking back at what I wrote it's less than clear so I understand why you'd bring me to task on it. It should have read something like:

"Often an approval is held up because we are awaiting a response from the applicant (who we might reasonably assume has watchlisted the request page). However, the application will still show on the table produced by BAGbot as pending, despite us being unable to proceed with the application for the moment. Might we, then, create a template to show that we're waiting for an answer and ask the BAGBot to recognise it? This would allow BAG members to skip requests which can't proceed for now." --kingboyk 22:29, 22 April 2007 (UTC)

I'm sure I'm not the only person with a watchlist so unwieldy that the parenthical assumption here isn't such a given as to obviate the need for further attempts at communication with the user, and I'm still of the view that that's the most important step in avoiding approval (or otherwise) being held up. If an {{OperatorResponseNeeded}} template would serve to remind people to poke the op after a certain length of time, or allow automating same, or otherwise assist the BAG in scanning the BRFA page, then all well and good (as a second order effect). Alai 22:47, 22 April 2007 (UTC)

OK, I understand your point and you're correct. However, we're talking at cross purposes somewhat :) You are right, though. Cheers. --kingboyk 22:51, 22 April 2007 (UTC)

Bot Question?

Sorry if this is the wrong place for this question, but I havn't been able to figure out anywhere else to ask.

I'm not sure if what I'm doing is considered to be a bot or not. I'm not trying to edit articles, but I do want to screen scrape maybe 150 a week. I have been using PHP CURL to obtain small portions of articles, caching them, and checking once a week for changes.

This worked fine for a couple of months and then a few weeks ago I started getting the following message:

The Wikimedia Foundation servers are currently experiencing technical difficulties.
The problem is most likely temporary and will hopefully be fixed soon. Please check back in a few minutes.
If reporting this error to the Wikimedia System Administrators, please include the following details:
Request: GET http://en.wikipedia.org/wiki/Cinco_De_Mayo, from 64.202.165.201 via sq24.wikimedia.org (squid/2.6.STABLE12) to ()
Error: ERR_ACCESS_DENIED, errno [No Error] at Sun, 06 May 2007 01:04:31 GMT

Because of the ERR_ACCESS_DENIED above, I'm concerned I'm doing this the wrong way and have gotten blocked; and indeed the IP address above seems to be blocked (http://en.wikipedia.org/w/index.php?title=Special%3AIpblocklist&action=search&limit=&ip=64.202.165.201) but I don't think it's related to me because that's dated last summer. I've only been doing this a few months and when this problem started I was on a different IP address (64.202.165.132).

I would very much appreciate it if someone could tell me if what I'm doing is allowable and whether registering as a bot would solve my problem.

If it helps, this is the PHP CURL function I'm using:

function getURL($domain, $url)
 {
 $domain = "en.wikipedia.org"; // Force - debugging
 $url = "/wiki/Cinco_De_Mayo";
 $ch = curl_init();
 curl_setopt($ch, CURLOPT_URL, $domain. $url);
 curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
 curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
 curl_setopt($ch, CURLOPT_REFERER, "http://DaysUntil.com/");
 curl_setopt($ch, CURLOPT_USERAGENT, $_SERVER['HTTP_USER_AGENT']);
 // curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.0.6) Gecko/20060728 Firefox/1.5.0.6"
 // curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)");
 $result = curl_exec($ch);
 curl_close ($ch); 
 return $result;
 }

Thanks, Symmetric 04:25, 6 May 2007 (UTC)

If you're not editing and just viewing articles, then registering and getting approval for the bot makes no difference. I would recommend however, if it suits your purposes, that you download a database dump or (if you need live pages) use Special:Export, as it is less taxing on the servers. But 150 hits a week is basically nothing either way, so I wouldn't worry about it :-) —METS501 (talk) 04:33, 6 May 2007 (UTC)

Thanks, so it sounds like what I'm doing is ok as long as I keep the traffic low. That's good. I guess if I can fix it, I'd rather keep it the way it is for now (since it DID work and it's simple). I may look at the dump or special:export options in the future (might be a lot of work to implement). Do you have any idea where I can find out what might cause the ERR_ACCESS_DENIED error? If it's not the blocked IP address I'm at a loss (I did request it be unblocked). I also found some references to Wikipedia blocking certain user agents, but I haven't been able to figure out which ones, and that seems unlikely too since I'm just specifying a common browser. But SOMETHING changed in mid-March. Symmetric 06:27, 6 May 2007 (UTC)

My Perl's gotten a bit rusty, so pardon me if I say rubbish here, but both lines that set a USER_AGENT seem to be commented out, so I don't actually know what user agent ID does that code send. Anywho, you can have a look at Wikiepdia's robots.txt file, which is located here and search for clues. An "access denied" error looks like a user agent problem to me. Миша 13 13:23, 6 May 2007 (UTC)

It's PHP, not Perl, and there are actually three lines that set the user agent, with the first line not commented out. It's a bit confusing though, I must admit, and I was about the say the same thing as you. Symmetric; the only advice I can give you is to start debugging and changing things to see what exactly is causing the problem. Jayden54 13:39, 6 May 2007 (UTC)

Sorry, I left those comments in to indicate a few user agents I've tried. $_SERVER['HTTP_USER_AGENT'] transfers the agent from the browser used to access the script, which I think should work if access from my browser works. I've tried a bunch of others but it fails no matter what I use. As far as debugging, the script works fine on other sites (google, yahoo, etc.) so it's something specific to Wikipedia. I was thinking it might be IP blocking, even though the IP I had when this started doesn't seem to be blocked. I read somewhere that logging in as a bot hides your IP, so I thought if someone else on my shared GoDaddy host was causing me to get blocked with them (or if I somehow caused it), I could fix it that way. The other possibility I can think of is that there's something else in the header that Wikipedea recently started looking at that I now need to set, but I don't know how to figure out what that might be. Symmetric 16:36, 6 May 2007 (UTC)

Are you having the same problem as is mentioned at the bottom of WP:BONB? Does the fix mentioned there (using a unique UserAgent that contains your bot's username) work for you? --ais523 12:38, 9 May 2007 (U T C)

How does one ask for a review of a bot and bot operator?

There is currently a thread at the admins' noticeboard involving Scepbot and Metsbot and the fact that they were having trouble parsing some double redirects in Guettarda's userspace. While double redirects should be fixed in article and article talk space, I'm not sure why there is any urgency in fixing them in user space. The only pages that linked to Guettarda's double-redirected pages were other pages in Guettarda's userspace, so the chance of an encyclopedia reader encountering them is virtually nil. And having bots edit another user's userspace, unless it is urgent, is rude as far as I am concerned. Will has replied in the thread that he can not stop his bot from editing userspace, which looks like an alarming lack of control, or at least a disturbing unwillingness to deal with the issue. Will's unwillingless to deal with the problem led to Guettarda escalating the situation by protecting the double redirects, which led to a further escalation when Evula invaded Guettarda's space to delete the pages.

I would like to request a review of both Metsbot and Scepbot based on this report. Is it appropriate for these bots to edit in someone else's user space? Have Will and Mets' responses to the complaint met community expectations for bot owners? Thanks. Thatcher131 13:24, 16 May 2007 (UTC)

Double redirects slow down the server, they should all be fixed, userspace or not. What can be benefited by not fixing them? Editing another person's userspace is not rude unless you do it in a rude fashion. ^High_InBC^{(Need help? Ask me)} 13:30, 16 May 2007 (UTC)

How can double redirects slow down the server if they are never accessed? Except for Scepbot, who but Guettarda would be accessing User:Guettarda/Sandbox 4? Thatcher131 14:09, 16 May 2007 (UTC)

How do you clear the backlog of double redirects without getting these double redirects that are not being used? You pretty much have to get them all. I ask again, what is benefited by not fixing them? What is the harm in fixing a double redirect in someone's userspace? ^High_InBC^{(Need help? Ask me)} 14:13, 16 May 2007 (UTC)

I think that several people made bad decisions in this situations, but one of the bad decisions was to forcibly fix the protected redirects without prior consultation in order to make the bot happy. "What is benefited by not fixing them" is civility and respect. Sceptre should have excluded the bot from Guettarda's user space as a matter of common courtesy if for no other reason, Guettarda should not have protected the redirects to purposely hang the bot, and Evula should not have manually fixed the protected redirects without first asking Guettarda. If the protected redirects broke the bot, Sceptre could have dealt with 99.9% of the backlog by excluding his bot from Guettarda's user space. If the protected redirects broke the bot, and it was not possible to at least temporarily exclude the bot from those pages, then the bot should have been stopped until the situation could have been dealt with calmly. There are thousands of backlogs on wikipedia and to think that this particular backlog must be dealt with so urgently as to justify this level of bad feelings is to vastly overinflate the importance of the bot. Thatcher131 14:27, 16 May 2007 (UTC)

How exactly is it discourteous to fix a double redirect on someone's userpage? It is standard maintenance, what is the big deal? You don't need to ask people for every little thing you do, like handling a template rename, or fixing a double redirect, or removing fair use images. This is not rude, I don't see how it can be. ^High_InBC^{(Need help? Ask me)} 17:07, 16 May 2007 (UTC)

Well, I think there is an attitude problem here. When an editor says "please don't edit my user space" it seems that engaging the user in a conversation, including bringing it other respected editors' opinions to gently persuade the editor, would have been a better response than to continue to try to edit the user's space and then post to the noticeboard, "this user's userspace breaks my bot!" The fact that something may be done is rarely the same thing as saying it must be done now and I am still unconvinced that this was an urgent problem. Fixing these redirects was never such a critical priority as to demand steamrolling another editor's heartfelt objections, even if the objections were ultimately not founded in policy. And you have yet to explain why it was impossible to temporarily exclude userspace from the bot's field of operations so it could continue its maintenance task in article space without breaking. Thatcher131 17:18, 16 May 2007 (UTC)

Cleaning out double redirects is one of the many backlogs that need to be cleared, this really is no big deal. No reason to skip userspace, because it needs to be done too. People do not own their userspace, and this is really not doing anything to userspace that changes anything content wise, it is simply maintenance. I think this is making a mountain out of a molehill. ^High_InBC^{(Need help? Ask me)} 17:27, 16 May 2007 (UTC)

Someone probably is making a mountain out of a molehill but I don't think it's me. It appears that both Scepbot and Metsbot fixed the redirects on May 11, and Guettarda reverted both times and then protected. When Scepbot broke on the protected redirects, Sceptre asked Guettarda on May 13 to fix them and Guettarda said no. At that point, Sceptre had two options. He could have said, "Wikipedia policy is to avoid double redirects even in user space, but since you are an admin I will trust you to do the right thing." Instead, Sceptre basically replied, "I'm right and you're wrong", was unwilling or unable to exclude Guettarda's user page so he could run his bot, and so found someone at the noticeboard to "fix" the problem for him. I would like to think that Be nice to other people even if you are right and they are wrong ranks higher on the Wikipedia principles scale than avoid double redirects. For the same reason I am concerned that you (HighInBC), whom I generally like and respect, seem to be following the He's right and Guettarda is wrong track rather than the "'Be nice"' track. We're not talking here about disruptive userboxes or vandalism where I'm right and you're wrong really does override Be nice; we're talking about a few extra CPU cycles to serve some userpages that have no incoming links. If double redirects really are server poison, how many went unfixed for the two days that Guettarda's redirects were protected because Sceptre insisted on fixing them (since both Mets501 and Martinp23 seem to think it is relatively trvial to exclude userspace, the fact that Sceptre had to go to the noticeboard to find another admin to "fix" the problem shows that this was more about getting his way than about fixing redirects). For me, this boils down to the fact that Sceptre (and some others) elevated his bot's performance of a mundane maintenance task over the principle of Be nice to other people even if you are right and they are wrong. That may not be a reason to review Scepbot's scope, but it's not the way this place is supposed to work. Thatcher131 18:52, 16 May 2007 (UTC)

I do tend to agree with HighInBC, but admit to not having read the noticeboard post. If you wish to challenge a bot approval for a task, then I see no problem with you retreiving it from the archive, transluding it back onto the main BRFA page, and starting a discussion. Either that, or start a new BRFA request page, and transclude it, but rather than request a new bot, request review of another. Martinp23 13:36, 16 May 2007 (UTC)

I've posted on WP:AN. In response to your specific question, Thatcher131, a discussion at AN/ANI/anywhere else, which generates a consensus, can result in the removal of the approval for a certain task. Similar discussion caould take place on the various bot related talk pages, or in a transclusion of a "case page" on WP:BRFA. HTH, Martinp23 13:51, 16 May 2007 (UTC)

I know that Will (Sceptre) has been part of the discussion of this issue, but has Mets501 (the operator of MetsBot) been advised of these concerns or the ANI thread? He is a member of the bot approvals group and an administrator and has in the past been very responsive to MetsBot-related questions and issues. (According to his userpage, he's also supposed to be on a wikibreak studying for AP exams, but from his contributions it would appear he's almost as unable to take a real wikibreak as I am. :) ) Newyorkbrad 15:19, 16 May 2007 (UTC)

I just stumbled across this discussion, and am sorry that there's been a big conflict. I'll no longer fix double redirects in User: and User talk: space. If anything like this happens in the future, just contact me on my talk page, and I'll make sure to address your concerns. —METS501 (talk) 17:52, 16 May 2007 (UTC)

For me, seeing the discussion on the noticeboard, the problem was not that the bots went into Guettarda's user space to fix the redirects, but that after Guettarda objected, Sceptre forced the issue (see above). Thatcher131 18:52, 16 May 2007 (UTC)

Haha, you're probably right, but still, my comment holds —METS501 (talk) 20:46, 16 May 2007 (UTC)

Question about exclusion from WP:BOT

I posted this message on WP:BOT Talk page. I am not sure where the best forum is for getting a response. Crum375 20:01, 25 May 2007 (UTC)

How does one ask for a bot to stop?

I posted my concerns regarding Android Mouse Bot 3 at this policy page. Has the execution of the bot been discussed? Am I the only one thinking that it creates havoc? If I am not the only one, could one reconsider its approval and discuss it again? Mlewan 19:06, 26 May 2007 (UTC)

There are a variety of places. If the bot is going crazy performing tasks which it is not approved to do and it needs to be blocked urgently, then report it at WP:AIV. If you disagree with a task the bot is currently performing, then the best places are the bot owner's talk page (if they are around) or WP:ANI. To discuss the merits of a bot which is not currently running, any places is basically OK; local WikiProject talk pages, the bot owner's talk page, this page, etc. If consensus has been reached anywhere that a bot should not be running, report it to this page and approval will be withdrawn. —METS501 (talk) 19:34, 26 May 2007 (UTC)

Am I doing something wrong?

My interwiki bot -- SmeiraBot -- had been approved for trial. I started using it to do automatic corrections in the links from articles on US cities to their corresponding articles in the Volapük wikipedia. In the first few days it went OK (though I always got a message saying: 'Your bot is not listed in the list of bots'); now I get an error message saying the page in question is locked, and I have to modify it manually, from my user account. Have I done something wrong? --Smeira 10:16, 19 June 2007 (UTC)

This is because you don't have a bot flag yet (fully approved). When you show the guys at your request for bot approval a few diffs of some edits, and they're happy, it will be approved and given a bot flag - then you should be able to run it smoothly. E ^talk 10:30, 19 June 2007 (UTC)

Well, here is one of the latest examples, and here is another one. To whom should I show them? Is placing them in this page already enough? --Smeira 11:06, 19 June 2007 (UTC)

You really need to put the request in on Wikipedia:Bots/Requests for approval and go through the approval procedure. Reedy Boy 20:47, 19 June 2007 (UTC)

He already has. It's listed in the Bots in a trial period section. He's asking how to get his trial period approved. -- JLaTondre 23:18, 19 June 2007 (UTC)

It looks like your bot wasn't logged in[1][2]. You need to do your trial edits under your bot account. Thanks. -- JLaTondre 23:18, 19 June 2007 (UTC)

OK, it looks like the problem was that I hadn't done a login.py -all to make sure I was logged in on wikipedia before running my bot. I didn't know that was necessary; my apologies. My bot is now running as SmeiraBot, and there are already a few changes(here). The changes will come in slowly, because this bot only change links to the Volapük wikipedia if they already exist and are wrong. (By the way, do you happen to know how I could incorporate the 'login.py -all' into the script itself, rather than having to run it independently before starting the bot?) --Smeira 01:22, 20 June 2007 (UTC)

BAG Joining

Hey, I have been asked to post a notification of my request to join the Bot Approvals Group on here. It can be found at Wikipedia talk:Bots/Approvals group#Joining. Thanks! Matt/TheFearow (Talk) (Contribs) (Bot) 02:09, 22 June 2007 (UTC)