[HN Gopher] Ask HN: Has anybody built search on top of Anna's Ar...
       ___________________________________________________________________
        
       Ask HN: Has anybody built search on top of Anna's Archive?
        
       Wouldn't this basically give us Google Books and searchable Scihub
       at the same time?  What would it cost?
        
       Author : neonate
       Score  : 257 points
       Date   : 2025-06-04 01:47 UTC (21 hours ago)
        
       | ggm wrote:
       | You must mean free text search and page level return, because it
       | already has full metadata indexing.
       | 
       | The thing is AA doesn't hold the texts. They're disputable IPR
       | and even a derived work would be a legal target.
        
         | carlosjobim wrote:
         | > a derived work would be a legal target.
         | 
         | Why would it? Google isn't prosecuted for indexing the web.
        
           | 1970-01-01 wrote:
           | Oh it certainly is.
           | https://www.reuters.com/sustainability/boards-policy-
           | regulat...
        
             | trollbridge wrote:
             | That's not prosecution for indexing the web. Google is
             | being treated the same way AT&T was for telephones.
        
               | 1970-01-01 wrote:
               | https://harvardlawreview.org/print/vol-138/united-states-
               | v-g...
        
       | bhaney wrote:
       | Honestly I don't think it would be that costly, but it would take
       | a pretty long time to put together. I have a (few years old) copy
       | of Library Genesis converted to plaintext and it's around 1TB. I
       | think libgen proper was 50-100TB at the time, so we can probably
       | assume that AA (~1PB) would be around 10-20TB when converted to
       | plaintext. You'd probably spend several weeks torrenting a chunk
       | of the archive, converting everything in it to plaintext,
       | deleting the originals, then repeating with a new chunk until you
       | have plaintext versions of everything in the archive. Then
       | indexing all that for full text search would take even more
       | storage and even more time, but still perfectly doable on
       | commodity hardware.
       | 
       | The main barriers are going to be reliably extracting plaintext
       | from the myriad of formats in the archive, cleaning up the data,
       | and selecting a decent full text search database (god help you if
       | you pick wrong and decide you want to switch and re-index
       | everything later).
        
         | notpushkin wrote:
         | I think there's a couple ways to improve it:
         | 
         | 1. There's a lot of variants of the same book. We only need one
         | for the index. Perhaps for each ISBN, select the format easiest
         | to parse.
         | 
         | 2. We can download, convert and index top 100K books first,
         | launch with these, and then continue indexing and adding other
         | books.
        
           | palmfacehn wrote:
           | There should be a way to leverage compression when storing
           | multiple editions of the same book.
        
             | bawolff wrote:
             | From a good search perspective though you probably dont
             | want 500 different versions of the same book popping up for
             | a query
        
               | palmfacehn wrote:
               | Agreed. I would prefer to see a single result for a
               | single title. The option of pursuing different editions
               | should follow from there.
        
               | qingcharles wrote:
               | And without some sort of weighting system, it wouldn't
               | even know which one is the best one to show the user.
        
           | throwup238 wrote:
           | How are you going to download the top 100k? The only
           | reasonable way to download that many books from AA or Libgen
           | is to use the torrents, which are sorted sequentially by
           | upload date.
           | 
           | I tried to automate downloading just a thousand books and it
           | was unbearably slow, from IPFS or the mirrors both. I ended
           | up picking the individual files out of the torrents. Even
           | just identifying or deduping the top 100k would be a
           | significant task.
        
           | WillAdams wrote:
           | The thing is, for an ISBN, that is one edition, by one
           | publisher and one can easily have the same text under 3
           | different ISBNs from one publisher (hardcover, trade
           | paperback, mass-market paperback).
           | 
           | I count 80+ editions of J.R.R. Tolkien's _The Hobbit_ at:
           | 
           | https://tolkienlibrary.com/booksbytolkien/hobbit/editions.ph.
           | ..
           | 
           | granted some predate ISBNs, one is the 3D pop-up version, so
           | not a traditional text, and so forth, but filtering by ISBN
           | will _not_ filter out duplicates.
           | 
           | There is also the problem of the same work being published
           | under multiple titles (and also ISBNs) --- Hal Clement's
           | _Small Changes_ was re-published as _Space Lash_ and that
           | short story collection is now collected in:
           | 
           | https://www.goodreads.com/book/show/939760.Music_of_Many_Sph.
           | ..
           | 
           | along with others.
        
         | serial_dev wrote:
         | The main barriers for me would be:
         | 
         | 1. Why? Who would use that? What's the problem with the other
         | search engines? How will it be paid for?
         | 
         | 2. Potential legal issues.
         | 
         | The technical barriers are at least challenging and
         | interesting.
         | 
         | Providing a service with significant upfront investment needs
         | with no product or service vision that I'll likely to be sued
         | for a couple of times a year, probably losing with who knows
         | what kind of punishment... I'll have to pass unfortunately.
        
           | namlem wrote:
           | It would be incredible for LLMs. Searching it, using it as
           | training data, etc. Would probably have to be done in Russia
           | or some other country that doesn't respect international
           | copyright though.
        
             | sam_lowry_ wrote:
             | LLMs already use it, dude )
        
               | exe34 wrote:
               | I think one use would be to search for information
               | directly from a book, rather than get a garbled/half-
               | hallucinated version of it.
        
               | jdironman wrote:
               | You don't need AI for that. I get the optimistic spirit
               | of what you mean though.
        
               | mdp2021 wrote:
               | Optimized information retrieval of complex text _is_ AI.
        
               | echollama wrote:
               | garbled/half-hallucinated is probably what you would've
               | gotten 8-12mo ago but now adays im sure with good
               | prompting you can pull value from any book.
        
             | jxjnskkzxxhx wrote:
             | Do you have a reason to believe this ain't already being
             | done? I would assume that the big guys like openai are
             | already training on basically all text in existence.
        
               | IlikeKitties wrote:
               | In fact, facebook torrented annas archive and got busted
               | for it, because of course they did:
               | 
               | https://torrentfreak.com/meta-torrented-over-81-tb-of-
               | data-t...
        
               | HDThoreaun wrote:
               | Every LLM maker probably did the same. Facebook just has
               | disgruntled employees who leaked it
        
               | gpm wrote:
               | Google goes around legally scanning every book they can
               | get their hands on with books.google.com. Legally
               | scanning every paper they can get their hands on with
               | scholar.google.com.
               | 
               | I doubt they'd resort to piracy for what is basically the
               | same information as what they've already legally
               | acquired...
        
               | lcnPylGDnU4H9OF wrote:
               | That is a good reason to think they did not but it
               | doesn't necessarily override reasons for them to do so.
               | Perhaps it's dubious that the subset of data they could
               | not legally get their hands on is an advantage for
               | training but I really don't know, and maybe nobody does.
               | Given that, Google's execs may have been in favor of
               | similar operations as Facebook's and their lawyers may
               | have been willing to approve them with similar
               | justifications.
        
               | ar_lan wrote:
               | Wasn't this confirmed what Meta does?
               | 
               | https://www.forbes.com/sites/danpontefract/2025/03/25/aut
               | hor...
        
             | executesorder66 wrote:
             | > or some other country that doesn't respect international
             | copyright though.
             | 
             | Like the US? OpenAI et al. don't give a shit.
        
               | TeMPOraL wrote:
               | There's a difference between feeding massive amounts of
               | copyrighted material to a training process that blends
               | them thoroughly and irreversibly, and doing all that in-
               | house, vs. offering people a service that indexes (and
               | possibly partially rehosts) that material, enabling and
               | encouraging users to engage directly in pirating concrete
               | copyrighted works.
        
               | corgi912 wrote:
               | There's this famous phrase in Russian that was born out
               | of a short interview with a woman, a strong Putin
               | supporter, that's often been used as a sarcastic remark
               | for pointing out someone's double standards and/or
               | hypocrisy.
               | 
               | It can be roughly translated to "you don't understand,
               | it's a completely different situation". That's what's
               | constantly on my mind when I'm reading discussions like
               | this one.
               | 
               | Everybody and their dog torrenting petabytes of data and
               | getting away with it (Meta is the only one that got
               | caught and they've still gotten away with doing it)?
               | 
               | The very same data poor American students were forced to
               | commit suicide over? The same data that average American
               | housewives were sued over for millions of dollars of
               | "damages"? The same data that often gets random German
               | plumbers or steelworkers to pay thousands of euros of
               | "fines" to the copyright mafia so they won't get sued and
               | have their lives ruined?
               | 
               | Yet when giant corporations are doing the exact same
               | thing on a massive scale, it's fine? It's not even the
               | same thing, an American student torrenting books isn't
               | making any money off it, while Meta very much is.
               | 
               | Of course it's not the same, a simple-minded and poorly
               | educated person like me isn't capable of understanding
               | the difference. You keep believing in your moral
               | superiority, the rest of the world has finally woken up.
        
               | Exoristos wrote:
               | There are those who are in charge and those who aren't.
        
               | TeMPOraL wrote:
               | Is there also a famous Russian phrase that translates to
               | "details are irrelevant, it kinda looks similar to me
               | therefore it's the same"? If not, there definitely should
               | be.
               | 
               | The details are the entire point. Arguing that a
               | corporation can get away doing something, while an
               | individual can't, isn't useful, because there are great
               | many of such somethings, and in most cases it turns out
               | perfectly reasonable, once you _dig into details_.
        
               | gosub100 wrote:
               | > that blends them thoroughly and irreversibly
               | 
               | It's okay, you can say 'laundering'
        
               | TeMPOraL wrote:
               | I can, but I don't, because that's at best an unintended
               | side effect.
        
               | r14c wrote:
               | That's Uber's Gambit. Nothing is illegal for large enough
               | corporations with strong network effects and deep
               | pockets.
        
               | TeMPOraL wrote:
               | That's not Uber's Gambit.
               | 
               | Uber was blatantly ignoring the local laws in order to
               | break into the market and quickly defeat local
               | competition. They used their infinite VC money supply to
               | interfere with and delay investigations and enforcement,
               | betting that if they do it fast enough, they'll have the
               | general population on their side.
               | 
               | LLM vendors found and exploited[0] a _legal uncertainty_
               | - correct me if I 'm wrong, but AFAIK it still isn't
               | settled whether or not their actions were actually
               | illegal. Unlike Uber, LLM vendors aren't breaking into
               | markets by ignoring the laws to outcompete incumbents,
               | and burning stupid amounts of money just to get away with
               | it. On the contrary, LLM vendors are simply providing an
               | actually useful product, and charging a reasonable price
               | for it, while reinvesting it into improving the product.
               | Effects it has on other markets aside[1], their business
               | model is just providing actual value in exchange for
               | money. _That 's much more direct and honest than most of
               | the tech industry_.
               | 
               | The product itself is also different. Uber is selling a
               | mirage, a "miracle" improvement that quickly turns not
               | so, and is destined to eventually destroy the markets it
               | disrupted. LLM vendors are developing and serving systems
               | that provide actual value to users, directly and
               | obviously so.
               | 
               | --
               | 
               | [0] - Probably walked into this without initially
               | realizing it. No one complained 5-10 years ago, where the
               | datasets were smaller and the resulting models had no
               | real-world utility. It's only when the models became
               | useful, that some people started looking for ways to make
               | them go away.
               | 
               | [1] - That's an unfortunate effect of it being a general
               | AI tool, and would be the same regardless of how it was
               | created.
        
               | sellmesoap wrote:
               | Ironically the low tech infringing proposal would lead to
               | more reliable results grounded in the raw contents of the
               | data, using less computing/power and without the
               | confidently incorrect sycophanty we see from the LLMs.
        
               | TeMPOraL wrote:
               | Nah. It would just lead to more of classical search.
               | Which is okay, as it always has been.
               | 
               | LLMs are not retrieval engines, and thinking them as such
               | is missing most of their value. LLMs are _understanding_
               | engines. Much like for humans, evaluating and
               | incorporating knowledge is necessary to build
               | understanding - however, _perfect recall is not_.
               | 
               | Another, arguably equivalent way of framing it: the job
               | of an LLM isn't to provide you with the facts; it's main
               | job is to _understand what you mean_. The  "WIM" in
               | "DWIM". Making it do that _does_ require stupid amounts
               | of data and tons of compute in training. Currently, there
               | 's no better way, and the only alternative system with
               | similar capabilities are... humans.
               | 
               | IOW, it's not even an apples to oranges comparison, it's
               | apples to gourmet chef.
        
               | freedomben wrote:
               | > > or some other country that doesn't respect
               | international copyright though.
               | 
               | > Like the US? OpenAI et al. don't give a shit.
               | 
               | OpenAI is not a country and therefore cannot make laws
               | that don't respect international (or domestic) copyright.
               | Also the US is a lot bigger than OpenAI and the big tech
               | corps, and the _law_ is very much on the side of
               | copyright holders in the US.
        
               | diggan wrote:
               | > the law is very much on the side of copyright holders
               | in the US.
               | 
               | Remind me again what the status of the case is with
               | Meta/Facebook using pirated material to train their
               | proprietary LLMs, and even seeding the data back to the
               | community while downloading it?
        
               | SR2Z wrote:
               | In progress. Nobody is expecting the original protections
               | afforded by copyright to apply here, but the fact that
               | the material is pirated is less relevant than whether or
               | not an LLM is a transformative use of the material.
               | 
               | We will almost certainly see copyright law weakened by
               | the case, but I do not believe that FB will get off with
               | no penalties.
        
               | gosub100 wrote:
               | The money is definitely in the side of big tech vs book
               | publishers. There may be a nominal settlement to end the
               | matter, perhaps after a decade of litigation
        
             | andrepd wrote:
             | > Would probably have to be done in Russia or some other
             | country that doesn't respect international copyright
             | though.
             | 
             | Incredible, several years of major American AI companies
             | showing that flaunting copyright only matters if it's
             | college kids torrenting shows or enthusiasts archiving
             | bootlegs on whatcd, but if it's big corpos doing it it's
             | necessary for innovation.
             | 
             | Yet some people still believe "it would have to be done in
             | evil Russia".
        
               | DataDaoDe wrote:
               | OP does have an exaggerated statement - its not like
               | there aren't laws in Russia or something and I largely
               | agree with your sentiment. I think there are levels to
               | this though and its pretty clear that Russia is much
               | riskier than the USA when it comes to IP - just look up
               | anything to do with insuring IP risk in Russia (here's
               | one such example: https://baa.no/en/articles/i-have-ip-
               | in-russia-is-my-ip-at-r...)
               | 
               | Also according to the office of US trade representative,
               | Russia is on the priority watch list of countries that do
               | not respect IP [1] and post 2022, largely due to the war,
               | Russia implemented measures negatively effecting IP
               | rights. [2,3]
               | 
               | If you think it isn't the case and Russia is just as
               | risky as the US when it comes to copyright and IP, I
               | would be interested to know why.
               | 
               | 1. https://ustr.gov/about/policy-offices/press-
               | office/press-rel... 2. https://www.papula-
               | nevinpat.com/executive-summary-the-ip-sit... 3.
               | https://www.taftlaw.com/news-events/law-bulletins/russia-
               | iss...
        
               | mdp2021 wrote:
               | > _evil_
               | 
               | In this case and context, a label like "evil" is a
               | twisted interpretation.
        
           | carlosjobim wrote:
           | > 1. Why? Who would use that?
           | 
           | Rather who would use a traditional search engine instead of a
           | book search engine, when the quality of the results from the
           | latter will be much superior?
           | 
           | People who need or want the highest quality information
           | available will pay for it. I'd easily pay for it.
        
           | bbor wrote:
           | 1. It'd be for the scientific community (broadly-construed).
           | Converting media that is currently completely un-indexed into
           | plaintext and offering a suite of search features for finding
           | content within it would be a game-changer, IMO! If you've
           | ever done a lit review for any field other than ML, I'm
           | guessing you know how reliant many fields are on relatively-
           | old books and articles (read: PDFs at best, paper-only at
           | worst) that you can basically only encounter via a) citation
           | chains, b) following an author, or c)
           | encyclopedias/textbooks.
           | 
           | 2. I really don't see how this could ever lead to any kind of
           | legal issue. You're not hosting any of the content itself,
           | just offering a search feature for it. GoodReads doesn't need
           | legal permission to index popular books, for example.
           | 
           | In general I get the sense that your comment is written from
           | the perspective of an entrepreneur/startup mindset. I'm sure
           | that's brought you meaning and maybe even some wealth, but
           | it's not a universal one! Some of us are more interested in
           | making something to advance humanity than something likely to
           | make a profit, even if we might look silly in the process.
        
             | Aachen wrote:
             | > I really don't see how this could ever lead to any kind
             | of legal issue. You're not hosting any of the content
             | itself, just offering a search feature for it.
             | 
             | You don't need to host copyrighted material. It's all about
             | _intent_. The Pirate Bay is (imo correctly, even if I
             | disagree with other aspects about copyright law and its
             | enforcement) seen as a place where people go to find ways
             | to not pay authors for their content. They never hosted a
             | copyrighted byte but they 're banned in some form (DNS, IP,
             | domain seizures) in many countries. Proxies of TPB also, so
             | being like an ISP for such a site is already enough,
             | whereas nobody is ordering blocks of Comcast's IP addresses
             | for providing access to websites with copyrighted material
             | because they didn't have a somewhat-provable intent to
             | provide copyright infringement
             | 
             | When I read the OP, I imagine this would link from the
             | search results directly to Anna's archive and sci-hub, but
             | I think you'd have to spin it as a general purpose search
             | page and ideally not even mention AA was one of the
             | sources, much less have links
             | 
             | (Don't get me wrong: everyone wants this except the lobby
             | of journals that presently own the rights)
             | 
             | It would be a real shame if an anonymous third party that's
             | definitely not the website operator made a Firefox add-on
             | that illegitimately inserts these links to search results
             | page though
        
               | DaSHacka wrote:
               | > When I read the OP, I imagine this would link from the
               | search results directly to Anna's archive and sci-hub
               | 
               | You could just give users ISBNs or link to the book's
               | metadata on openlibrary[0], both of which AA's native
               | search already does.
               | 
               | [0] https://openlibrary.org/
        
             | coolThingsFirst wrote:
             | Yeah but how does the search work, does it show a portion
             | of the text? If it's a portion of the text isn't that also
             | a part of the book?
        
           | 1vuio0pswjnm7 wrote:
           | But he did not mention anything about creating a "service"
           | 
           | It could be his own copy for personal use
           | 
           | What if computers continue to become faster and storage
           | continues to become cheaper; what if "large" amounts data
           | continue to become more manageable
           | 
           | The data might seem large today, but it might not seem large
           | or unmanageable in the future
        
         | tomthe wrote:
         | I wonder if you could implement it with only static hosting?
         | 
         | We would need to split the index into a lot of smaller files
         | that can be practically downloaded by browsers, maybe 20 MB
         | each. The user types in a search query, the browser hashes the
         | query and downloads the corresponding index file which contains
         | only results for that hashed query. Then the browser sifts
         | quickly through that file and gives you the result.
         | 
         | Hosting this would be cheap, but the main barriers remain..
        
           | ThatPlayer wrote:
           | I've done something similar with a static hosted site I'm
           | working on. I opted to not reinvent the wheel, and just use
           | WASM Sqlite in the browser. Sqlite already splits the
           | database into fixed-size pages, so the driver using HTTP
           | Range Requests can download only the required pages. Just
           | have to make good indexes.
           | 
           | I can even use Sqlite's full-text search capabilities!
        
             | showerst wrote:
             | How would that scale to 10TB+ of plain text though?
             | Presumably the indexes would be many gigabytes, especially
             | with full text search.
        
               | wolfgang42 wrote:
               | The client only needs to get indexes for the specific
               | search; if the index is just a list of TF-IDF term scores
               | per document (which gets you a very reasonable start on
               | search relevance) some extremely back-of-the-envelope
               | math leads me to guess at an upper bound in the low tens
               | of megabytes per (non-stopword) term, which seems doable
               | for a client to download on demand.
        
             | qcic wrote:
             | Super interesting.
        
             | Aachen wrote:
             | I wonder if you could take this one step further and have
             | opaque queries using homomorphic encryption on the index
             | and then somehow extracting ranges around the document(s)
             | you're interested in
             | 
             | Inspired by: "Show HN: Read Wikipedia privately using
             | homomorphic encryption"
             | https://news.ycombinator.com/item?id=31668814
        
         | greggsy wrote:
         | It's trivial to normalise the various formats, and there were a
         | few libraries and ML models to help parse PDFs. I was tinkering
         | around with something like this for academic papers in Zotero,
         | and the main issue I ran into was words spilling over to the
         | next page, and footnotes. I totally gave up on that endeavour
         | several years ago, but the tooling has probably matured
         | exponentially since then.
         | 
         | As an example, all the academic paper hubs have been using this
         | technology for decades.
         | 
         | I'd wager that _all_ of the big Gen AI companies have planned
         | to use this exact dataset, and many or them probably have
         | already.
        
           | fake-name wrote:
           | > It's trivial to normalise the various formats,
           | 
           | Ha. Ha. ha ha ha.
           | 
           | As someone who as pretty broadly tried to normalize a pile of
           | books and documents I have legitimate access to, _no it is
           | not_.
           | 
           | You can get good results 80% of the time, usable but messy
           | results 18% of the time, and complete garbage the remaining
           | 2%. More effort seems to only result in marginal
           | improvements.
        
             | bawolff wrote:
             | 98% sounds good enough for the usecase suggested here.
        
               | pastage wrote:
               | Writing good validators for data is hard. You can be 100%
               | sure that there will be bad data in those 98%. From my
               | own experience I thought I had 50% of the books converted
               | correctly and then I found I still had junk data and gave
               | up, it is not an impossible problem I just was not
               | motivated to fix it on my own. Working with your own
               | copies is fine, but when you try to share that you get
               | into legal issues that I just do not feel are that
               | interesting to solve.
               | 
               | Edit: my point is that I would like to share my work but
               | that is hard to do in a legal way. That is the main
               | reason I gave up.
        
               | landl0rd wrote:
               | 2% garbage, if some of that garbage falls out the right
               | way, is more than enough to seriously degrade search
               | result quality.
        
               | carlosjobim wrote:
               | It's better than nothing, and nothing is what we
               | currently have.
        
         | trollbridge wrote:
         | Decent storage is $10/TB, so for $10,000 you could just keep
         | the entire 1PB of data.
         | 
         | A rather obvious question is if someone has trained an LLM on
         | this archive yet.
        
           | moffkalast wrote:
           | A rather obvious answer is Meta is currently being sued for
           | training Llama on Anna's archive.
           | 
           | You can be practically certain that every notable LLM has
           | been trained on it.
        
             | rthnbgrredf wrote:
             | > You can be practically certain that every notable LLM has
             | been trained on it.
             | 
             | But only Meta was kind of not so smart to publicly admit
             | it.
        
       | nextos wrote:
       | AFAIK, Z-Library already does this, to some extent. Basic full-
       | text queries do search inside the body of books and articles.
       | 
       | It's a bit smaller than Anna's Archive, as they do host their own
       | collections. From some locations, it's only easy to access
       | through Tor.
        
       | bravesoul2 wrote:
       | This works in various search engines
       | 
       | site:annas-archive.org avacado
        
         | qingcharles wrote:
         | It's not exactly clear, but OP is asking about indexing the
         | content of all the documents, not the metadata (e.g. titles
         | etc)
        
       | imdavidsantiago wrote:
       | As far as I know, no one has fully implemented full-text search
       | directly over Anna's Archive. Technically it's feasible with
       | tools like Meilisearch, Elasticsearch, or Lucene, but the main
       | challenges are:                   Converting all documents (PDFs,
       | EPUBs, etc.) to clean plaintext.              Indexing at scale
       | efficiently.              Managing potential legal issues.
       | 
       | Z-Library does something similar, but it's smaller in scope and
       | doesn't integrate AA's full catalog.
        
         | bendangelo wrote:
         | I've done something like this before. Meilisearch will not be
         | viable, because it indexes very slow and it takes up a lot of
         | space.
         | 
         | In my experience only Tantivy can index this much data. Check
         | out Lnx.
        
           | sam_lowry_ wrote:
           | Lucene would fo fine as well, I guess. As much as I like the
           | author of Tantivy, it is a toy compared to Lucene.
        
         | _ache_ wrote:
         | To manage the legal issues, you just have to put AI on the
         | search. "AI search".
        
       | DaSexiestAlive wrote:
       | Mebbe easier to just search Amazon or Goodreads. Like
       | site:amazon.ca <query words> as someone has mentioned below.
       | 
       | Every book has an ISBN 10 or 13 digit ISBN number to identify
       | them. Unless it's some self-pub/amateur-hour situation by some
       | paranoid prepper living in a faraday-cage-protected cage in
       | Arkansas or Florida it's likely a publication with a title, an
       | author and an ISBN number.
        
         | pigeons wrote:
         | What about pre-1970 books?
        
         | trollbridge wrote:
         | A self-pub amateur-hour book printed by a paranoid prepper
         | living in a faraday cage is exactly the type of book I'd
         | probably enjoy reading, but I doubt these exist anymore.
        
       | renegat0x0 wrote:
       | I have found some searche engines, but I do not think they're for
       | Anna's.
       | 
       | https://searchthearxiv.com/
       | 
       | https://refseek.com/
       | 
       | https://arxivxplorer.com/
        
       | simgt wrote:
       | Related question, has Anna's archive been thoroughly filtered for
       | non-copyright-related illegal material? Pedo, terrorism, etc.
       | I've considered downloading a few chunks of it but I'm worried of
       | ending up with content I really don't want to be anywhere near
       | from.
        
         | niux wrote:
         | How might you inadvertently download illegal content while
         | searching for legal content?
        
           | lukan wrote:
           | He said he wants to download lots of it in general, not
           | specifical. Legit question, if you end up with dark material.
           | 
           | I would assume pedo stuff is not really there, but the
           | anarchist cookbook and alike likely will be.
        
             | oguz-ismail wrote:
             | >I would assume pedo stuff is not really there
             | 
             | Search for "lolicon"
        
               | lukan wrote:
               | Well, I won't. But does it contain just text or real
               | pictures? That would make a big legal difference I
               | assume.
        
               | jxjnskkzxxhx wrote:
               | I thought that was anime pictures...?
        
               | areyourllySorry wrote:
               | a subset of that, yes. but that label implies more than
               | just that
        
             | DocTomoe wrote:
             | Considering the anarchist cookbook is just a rebranded
             | selection of freely-available US Army Field Manuals, ... I
             | don't see the problem.
        
               | lukan wrote:
               | I don't either, but many states have laws regarding books
               | on how to build bombs and they might get enforced more
               | than copyright.
        
               | srum wrote:
               | You can get in trouble for having it in the UK (though
               | not necessarily convicted)
               | 
               | https://news.sky.com/story/anarchist-cookbook-case-
               | student-j...
               | 
               | https://www.bbc.co.uk/news/uk-england-
               | oxfordshire-45841291
        
               | gosub100 wrote:
               | Not saying you're deceiving but can you show me where a
               | state has made a book about bombs illegal? It seems like
               | that would be a slam dunk 1A violation. And yes I'm aware
               | that states willfully violate 2A but I don't want to
               | discuss it here.
        
               | lukan wrote:
               | Not saying you cannot read, but if you would, the other
               | answer to my comment literally has such an example.
               | 
               | Germany is like this as well since a few years.
               | 
               | Not all states are within the US.
        
               | gosub100 wrote:
               | you're not saying I cannot read, but that type of
               | inflection is uncalled for. You have been reported to the
               | mods.
        
             | bilekas wrote:
             | I'm still not sure the question makes much sense, if it's a
             | general: "I want to support the project and so I want to
             | seed a large chunk" Okay, I guess it's your due diligence
             | to check, but there is a reporting feature built in, if
             | something is found, report it.
             | 
             | Aside from that, if you're searching for specific content,
             | the question is moot I guess.
             | 
             | I guess my confusion is what distinguishes this apart from
             | any other torrent ? That is, if the submitted content is
             | submitted at all.
        
               | lukan wrote:
               | I understood it as he or she wants to download large
               | chunks of potentially interesting books for offline use,
               | or once Anna goes down. So a broad filter. Not for
               | seeding.
               | 
               | But thanks for the explanation that there is a report
               | build in.
        
           | bordercases wrote:
           | Seeding torrrent blocks.
        
         | bilekas wrote:
         | This is a really strange question to be honest you could ask
         | this literally about any download let alone simply torrents of
         | documents.
        
           | gosub100 wrote:
           | It's the textbook example of the "chilling effect" created by
           | mass surveillance.
        
         | dns_snek wrote:
         | Download everything, we know that laws don't apply when you do
         | it on a large enough scale. Not legal advice.
        
           | lukan wrote:
           | I think you got that wrong. Laws only don't apply if _you_
           | are large enough. (Like Meta)
        
         | gosub100 wrote:
         | The team that curates it is very dedicated and wouldn't do such
         | a thing. The least of reasons being they don't want the heat
         | from it.
         | 
         | I'm not sure what other forms of information is illegal beyond
         | CP. In the US, bomb making instructions are not illegal. In
         | other dictatorships or zealous religious regimes, information
         | about democracy or works that insult Islam might be illegal
        
       | allenleein wrote:
       | Has anyone explored a different angle -- like mapping out the
       | 1,000 most frequently mentioned or cited books (across HN,
       | Substack, Twitter, etc.), then turning their raw content into
       | clean, structured data optimized for LLMs? Imagine curating these
       | into thematic shelves -- say, "Bill Gates' Bookshelf" or "HN
       | Canon" -- and building an indie portal where anyone can
       | semantically search across these high-signal texts. Kind of like
       | an AI-searchable personal library of the internet's favorite
       | books.
        
         | DocTomoe wrote:
         | Well, there's this: https://hacker-recommended-
         | books.vercel.app/category/0/all-t...
        
       | laserstrahl wrote:
       | There's an android app called OpenLip. [1]
       | 
       | Description:
       | 
       | Openlib is an open source app to download and read books from
       | shadow library (Anna's Archive). The App Has Built In Reader to
       | Read Books.
       | 
       | As Anna's Archive doesn't have an API, the app works by sending
       | requests to Anna's Archive and parses the response to objects.
       | The app extracts the mirrors from the responses, downloads the
       | book and stores it in the application's document directory.
       | 
       | Note : The app requires VPN to function properly . Without VPN
       | the might show the captcha required page even after completing
       | the captcha
       | 
       | Main Features:
       | 
       | Trending Books
       | 
       | Download And Read Books With In-Built Viewer
       | 
       | Supports Epub And Pdf Formats
       | 
       | Open Books With Your Favourite Ebooks Reader
       | 
       | Filter Books
       | 
       | Sort Books
       | 
       | [1]: https://f-droid.org/de/packages/com.app.openlib/
        
       | petra wrote:
       | Z-Library has a keyword search. Personally i didn't find it too
       | useful, especially given Google Books exists. It's not easy to
       | create a quality book search engine.
        
       | podgorniy wrote:
       | There is a search solution for zipped fb2 files. Not exactly what
       | you need, but it has potential.
       | 
       | The project has similar story to Anna's archive. There is 0.5 TB
       | of archived books, and the project creates index of all the books
       | with text, title and aruthor search capabilities, gives html UI
       | for search and reading. On weak machine it takes about 2 hours to
       | build that index.
       | 
       | So if you have zipped archives of fb2, you can use the project to
       | create web UI with search for those files. Without need of enough
       | space to unpack all the files.
       | 
       | You'll have to translate some russian though to get instructions
       | on how to set it up.
       | 
       | https://gitlab.com/opennota/fb2index/-/blob/master/README.ru...
        
         | tangus wrote:
         | But fb2 files are marked up text, which is (relatively) trivial
         | to index. The bulk of Anna's Archive's books are made of from
         | scanned images.
        
         | jmb99 wrote:
         | Worth mentioning that 0.5TB is tiny compared to Anna's, which
         | currently sits around 1.1PB.
        
       | Quin-tus wrote:
       | https://book-finder.tiiny.site/
       | 
       | More: https://rentry.co/StellaOctangulaIsCool
        
         | HelloUsername wrote:
         | > https://book-finder.tiiny.site/
         | 
         | That just redirects to https://yandex.com/search
        
           | Quin-tus wrote:
           | Well yeah but with a specific query with which you can search
           | multiple libraries
        
       | xbmcuser wrote:
       | Facebook did it's ai is trained on it so you can use that.
        
       | teekert wrote:
       | Probably this was already done at Google, Meta, X _and_ OpenAI,
       | before training their LLMs.
        
         | maartin0 wrote:
         | There's actually section in the Wikipedia page that explicitly
         | says DeepSeek was trained on it
        
       | net01 wrote:
       | They did! They conducted a competition https://annas-
       | archive.org/blog/all-isbns-winners.html , in which a few
       | submissions exceeded the minimum requirements and implemented a
       | good search tool & visualiser.
        
         | carlosjobim wrote:
         | How is this a text search of the books?
        
           | outside1234 wrote:
           | The original question the poster made was not clear, so this
           | is also an answer to it. It depends on what they meant by
           | "search"
        
         | perdomon wrote:
         | I think OP was more interested in the ability to text search
         | through the contents. This competition was great and some of
         | the entries were really informative, but none of them included
         | a full text search of the contents of all books.
        
       | carlosjobim wrote:
       | A functional full text search of the shadow libraries would be
       | massive. It would have a comparable impact on humanity to the
       | impact AI will have. And it's probably not difficult technically.
       | Let's start a project to get this done!
       | 
       | Edit: I have had this exact project as my dream for a couple of
       | years, and even experimented a little bit. But I'm not a
       | programmer, so I can only understand theoretically what would be
       | needed for this to work.
       | 
       | Anybody with the same dream, send me an e-mail to
       | booksearch@fastmail.com and let's see what we can do to get the
       | ball rolling!
        
       | 1970-01-01 wrote:
       | Don't do it. Just because you can, doesn't mean you should. Do
       | you know if they have anywhere near the legal muscle to push back
       | the flood of legal notices if you did this? Assume it survives
       | because it doesn't have a wide open barn door to the public.
        
         | bethekidyouwant wrote:
         | It wouldn't be called full text search of AA, It would be
         | called full tech search of every book in the world.
        
           | 1970-01-01 wrote:
           | You are asking a judge to consider that a book is ok to
           | scrape because it's part of a much larger collection of
           | books, perhaps the biggest and best collection, and therefore
           | it's all OK because at scale means good.
        
             | calibas wrote:
             | Google already successfully argued in court that creating
             | an online search index of books constitutes fair use: https
             | ://en.wikipedia.org/wiki/Authors_Guild,_Inc._v._Google,....
        
               | 1970-01-01 wrote:
               | The index isn't the full content. The OP search is about
               | indexing the entire contents of the book for verbatim
               | information retrieval.
        
       | hbartab wrote:
       | Seeing as OpenAI & Co were trained on torrented books from
       | similar places, I'm sure that ChatGPT provides an adequate search
       | layer on top of Anna's Archive, though it is not as free from
       | confabulations as one might hope for in a search engine.
       | 
       | Edit: grammar
        
       | underlines wrote:
       | yes, every major llm company did it:
       | 
       | illegally using annas archive, the pile, common crawl, their own
       | crawl, books2, libgen etc. and embed it into high dimensional
       | space and do next token prediction on it.
        
       | whimsicalism wrote:
       | small number of people willing to put in significant engineering
       | hours for something that would be illegal and non-monetizable
        
       | coolThingsFirst wrote:
       | No, because you can't avert the legal issues of doing that.
        
       | jimmydoe wrote:
       | Facebook said they leeched it, and Anna once mentioned a few
       | companies most of them from China paid for it, so I assume the
       | answer is yes someone has the data and very likely built the
       | search, but no one will open it given the legal and reputation
       | risk.
        
       ___________________________________________________________________
       (page generated 2025-06-04 23:01 UTC)