diff --git a/Cargo.lock b/Cargo.lock
index 089cfe5..68dd02e 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -17,6 +17,76 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
 
+[[package]]
+name = "ahash"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2c99f64d1e06488f620f932677e24bc6e2897582980441ae90a671415bd7ec2f"
+dependencies = [
+ "cfg-if",
+ "getrandom 0.2.9",
+ "once_cell",
+ "version_check",
+]
+
+[[package]]
+name = "aho-corasick"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "43f6cb1bf222025340178f382c426f13757b2960e89779dfcb319c32542a5a41"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "anstream"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0ca84f3628370c59db74ee214b3263d58f9aadd9b4fe7e711fd87dc452b7f163"
+dependencies = [
+ "anstyle",
+ "anstyle-parse",
+ "anstyle-query",
+ "anstyle-wincon",
+ "colorchoice",
+ "is-terminal",
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41ed9a86bf92ae6580e0a31281f65a1b1d867c0cc68d5346e2ae128dddfa6a7d"
+
+[[package]]
+name = "anstyle-parse"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e765fd216e48e067936442276d1d57399e37bce53c264d6fefbe298080cb57ee"
+dependencies = [
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle-query"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5ca11d4be1bab0c8bc8734a9aa7bf4ee8316d462a08c6ac5052f888fef5b494b"
+dependencies = [
+ "windows-sys 0.48.0",
+]
+
+[[package]]
+name = "anstyle-wincon"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "180abfa45703aebe0093f79badacc01b8fd4ea2e35118747e5811127f926e188"
+dependencies = [
+ "anstyle",
+ "windows-sys 0.48.0",
+]
+
 [[package]]
 name = "anyhow"
 version = "1.0.71"
@@ -26,6 +96,12 @@ dependencies = [
  "backtrace",
 ]
 
+[[package]]
+name = "autocfg"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
+
 [[package]]
 name = "backtrace"
 version = "0.3.67"
@@ -41,6 +117,18 @@ dependencies = [
  "rustc-demangle",
 ]
 
+[[package]]
+name = "bitflags"
+version = "1.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
+
+[[package]]
+name = "byteorder"
+version = "1.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
+
 [[package]]
 name = "cc"
 version = "1.0.79"
@@ -53,12 +141,285 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
+[[package]]
+name = "clap"
+version = "4.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "401a4694d2bf92537b6867d94de48c4842089645fdcdf6c71865b175d836e9c2"
+dependencies = [
+ "clap_builder",
+ "clap_derive",
+ "once_cell",
+]
+
+[[package]]
+name = "clap_builder"
+version = "4.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72394f3339a76daf211e57d4bcb374410f3965dcc606dd0e03738c7888766980"
+dependencies = [
+ "anstream",
+ "anstyle",
+ "bitflags",
+ "clap_lex",
+ "strsim",
+]
+
+[[package]]
+name = "clap_derive"
+version = "4.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8cd2b2a819ad6eec39e8f1d6b53001af1e5469f8c177579cdaeb313115b825f"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.17",
+]
+
+[[package]]
+name = "clap_lex"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2da6da31387c7e4ef160ffab6d5e7f00c42626fe39aea70a7b0f1773f7dd6c1b"
+
+[[package]]
+name = "colorchoice"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "acbf1af155f9b9ef647e42cdc158db4b64a1b61f743629225fde6f3e0be2a7c7"
+
+[[package]]
+name = "convert_case"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6245d59a3e82a7fc217c5828a6692dbc6dfb63a0c8c90495621f7b9d79704a0e"
+
+[[package]]
+name = "cssparser"
+version = "0.29.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f93d03419cb5950ccfd3daf3ff1c7a36ace64609a1a8746d493df1ca0afde0fa"
+dependencies = [
+ "cssparser-macros",
+ "dtoa-short",
+ "itoa",
+ "matches",
+ "phf 0.10.1",
+ "proc-macro2",
+ "quote",
+ "smallvec",
+ "syn 1.0.109",
+]
+
+[[package]]
+name = "cssparser-macros"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dfae75de57f2b2e85e8768c3ea840fd159c8f33e2b6522c7835b7abac81be16e"
+dependencies = [
+ "quote",
+ "syn 1.0.109",
+]
+
+[[package]]
+name = "derive_more"
+version = "0.99.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fb810d30a7c1953f91334de7244731fc3f3c10d7fe163338a35b9f640960321"
+dependencies = [
+ "convert_case",
+ "proc-macro2",
+ "quote",
+ "rustc_version",
+ "syn 1.0.109",
+]
+
+[[package]]
+name = "dtoa"
+version = "0.4.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "56899898ce76aaf4a0f24d914c97ea6ed976d42fec6ad33fcbb0a1103e07b2b0"
+
+[[package]]
+name = "dtoa-short"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bde03329ae10e79ede66c9ce4dc930aa8599043b0743008548680f25b91502d6"
+dependencies = [
+ "dtoa",
+]
+
+[[package]]
+name = "ego-tree"
+version = "0.6.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a68a4904193147e0a8dec3314640e6db742afd5f6e634f428a6af230d9b3591"
+
+[[package]]
+name = "env_logger"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85cdab6a89accf66733ad5a1693a4dcced6aeff64602b634530dd73c1f3ee9f0"
+dependencies = [
+ "humantime",
+ "is-terminal",
+ "log",
+ "regex",
+ "termcolor",
+]
+
+[[package]]
+name = "errno"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4bcfec3a70f97c962c307b2d2c56e358cf1d00b558d74262b5f929ee8cc7e73a"
+dependencies = [
+ "errno-dragonfly",
+ "libc",
+ "windows-sys 0.48.0",
+]
+
+[[package]]
+name = "errno-dragonfly"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "aa68f1b12764fab894d2755d2518754e71b4fd80ecfb822714a1206c2aab39bf"
+dependencies = [
+ "cc",
+ "libc",
+]
+
+[[package]]
+name = "form_urlencoded"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a9c384f161156f5260c24a097c56119f9be8c798586aecc13afbcbe7b7e26bf8"
+dependencies = [
+ "percent-encoding",
+]
+
+[[package]]
+name = "futf"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df420e2e84819663797d1ec6544b13c5be84629e7bb00dc960d6917db2987843"
+dependencies = [
+ "mac",
+ "new_debug_unreachable",
+]
+
+[[package]]
+name = "fxhash"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c31b6d751ae2c7f11320402d34e41349dd1016f8d5d45e48c4312bc8625af50c"
+dependencies = [
+ "byteorder",
+]
+
+[[package]]
+name = "getopts"
+version = "0.2.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "14dbbfd5c71d70241ecf9e6f13737f7b5ce823821063188d7e46c41d371eebd5"
+dependencies = [
+ "unicode-width",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.1.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8fc3cb4d91f53b50155bdcfd23f6a4c39ae1969c2ae85982b135750cccaf5fce"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi 0.9.0+wasi-snapshot-preview1",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.2.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c85e1d9ab2eadba7e5040d4e09cbd6d072b76a557ad64e797c2cb9d4da21d7e4"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi 0.11.0+wasi-snapshot-preview1",
+]
+
 [[package]]
 name = "gimli"
 version = "0.27.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ad0a93d233ebf96623465aad4046a8d3aa4da22d4f4beba5388838c8a434bbb4"
 
+[[package]]
+name = "heck"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
+
+[[package]]
+name = "hermit-abi"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fed44880c466736ef9a5c5b5facefb5ed0785676d0c02d612db14e54f0d84286"
+
+[[package]]
+name = "html5ever"
+version = "0.26.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bea68cab48b8459f17cf1c944c67ddc572d272d9f2b274140f223ecb1da4a3b7"
+dependencies = [
+ "log",
+ "mac",
+ "markup5ever",
+ "proc-macro2",
+ "quote",
+ "syn 1.0.109",
+]
+
+[[package]]
+name = "humantime"
+version = "2.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a3a5bfb195931eeb336b2a7b4d761daec841b97f947d34394601737a7bba5e4"
+
+[[package]]
+name = "idna"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e14ddfc70884202db2244c223200c204c2bda1bc6e0998d11b5e024d657209e6"
+dependencies = [
+ "unicode-bidi",
+ "unicode-normalization",
+]
+
+[[package]]
+name = "io-lifetimes"
+version = "1.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eae7b9aee968036d54dce06cebaefd919e4472e753296daccd6d344e3e2df0c2"
+dependencies = [
+ "hermit-abi",
+ "libc",
+ "windows-sys 0.48.0",
+]
+
+[[package]]
+name = "is-terminal"
+version = "0.4.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "adcf93614601c8129ddf72e2d5633df827ba6551541c6d8c59520a371475be1f"
+dependencies = [
+ "hermit-abi",
+ "io-lifetimes",
+ "rustix",
+ "windows-sys 0.48.0",
+]
+
 [[package]]
 name = "itoa"
 version = "1.0.6"
@@ -71,6 +432,54 @@ version = "0.2.144"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2b00cc1c228a6782d0f076e7b232802e0c5689d41bb5df366f2a6b6621cfdfe1"
 
+[[package]]
+name = "linux-raw-sys"
+version = "0.3.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ef53942eb7bf7ff43a617b3e2c1c4a5ecf5944a7c1bc12d7ee39bbb15e5c1519"
+
+[[package]]
+name = "lock_api"
+version = "0.4.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "435011366fe56583b16cf956f9df0095b405b82d76425bc8981c0e22e60ec4df"
+dependencies = [
+ "autocfg",
+ "scopeguard",
+]
+
+[[package]]
+name = "log"
+version = "0.4.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "518ef76f2f87365916b142844c16d8fefd85039bc5699050210a7778ee1cd1de"
+
+[[package]]
+name = "mac"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
+
+[[package]]
+name = "markup5ever"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a2629bb1404f3d34c2e921f21fd34ba00b206124c81f65c50b43b6aaefeb016"
+dependencies = [
+ "log",
+ "phf 0.10.1",
+ "phf_codegen 0.10.0",
+ "string_cache",
+ "string_cache_codegen",
+ "tendril",
+]
+
+[[package]]
+name = "matches"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2532096657941c2fea9c289d370a250971c689d4f143798ff67113ec042024a5"
+
 [[package]]
 name = "memchr"
 version = "2.5.0"
@@ -86,6 +495,18 @@ dependencies = [
  "adler",
 ]
 
+[[package]]
+name = "new_debug_unreachable"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e4a24736216ec316047a1fc4252e27dabb04218aa4a3f37c6e7ddbf1f9782b54"
+
+[[package]]
+name = "nodrop"
+version = "0.1.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72ef4a56884ca558e5ddb05a1d1e7e1bfd9a68d9ed024c21704cc98872dae1bb"
+
 [[package]]
 name = "object"
 version = "0.30.3"
@@ -100,10 +521,161 @@ name = "om-wikiparser"
 version = "0.0.0"
 dependencies = [
  "anyhow",
+ "clap",
+ "env_logger",
+ "log",
+ "scraper",
  "serde",
  "serde_json",
+ "url",
+ "urlencoding",
 ]
 
+[[package]]
+name = "once_cell"
+version = "1.17.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9670a07f94779e00908f3e686eab508878ebb390ba6e604d3a284c00e8d0487b"
+
+[[package]]
+name = "parking_lot"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3742b2c103b9f06bc9fff0a37ff4912935851bee6d36f3c02bcc755bcfec228f"
+dependencies = [
+ "lock_api",
+ "parking_lot_core",
+]
+
+[[package]]
+name = "parking_lot_core"
+version = "0.9.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9069cbb9f99e3a5083476ccb29ceb1de18b9118cafa53e90c9551235de2b9521"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "redox_syscall",
+ "smallvec",
+ "windows-sys 0.45.0",
+]
+
+[[package]]
+name = "percent-encoding"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "478c572c3d73181ff3c2539045f6eb99e5491218eae919370993b890cdbdd98e"
+
+[[package]]
+name = "phf"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3dfb61232e34fcb633f43d12c58f83c1df82962dcdfa565a4e866ffc17dafe12"
+dependencies = [
+ "phf_shared 0.8.0",
+]
+
+[[package]]
+name = "phf"
+version = "0.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fabbf1ead8a5bcbc20f5f8b939ee3f5b0f6f281b6ad3468b84656b658b455259"
+dependencies = [
+ "phf_macros",
+ "phf_shared 0.10.0",
+ "proc-macro-hack",
+]
+
+[[package]]
+name = "phf_codegen"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cbffee61585b0411840d3ece935cce9cb6321f01c45477d30066498cd5e1a815"
+dependencies = [
+ "phf_generator 0.8.0",
+ "phf_shared 0.8.0",
+]
+
+[[package]]
+name = "phf_codegen"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fb1c3a8bc4dd4e5cfce29b44ffc14bedd2ee294559a294e2a4d4c9e9a6a13cd"
+dependencies = [
+ "phf_generator 0.10.0",
+ "phf_shared 0.10.0",
+]
+
+[[package]]
+name = "phf_generator"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "17367f0cc86f2d25802b2c26ee58a7b23faeccf78a396094c13dced0d0182526"
+dependencies = [
+ "phf_shared 0.8.0",
+ "rand 0.7.3",
+]
+
+[[package]]
+name = "phf_generator"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d5285893bb5eb82e6aaf5d59ee909a06a16737a8970984dd7746ba9283498d6"
+dependencies = [
+ "phf_shared 0.10.0",
+ "rand 0.8.5",
+]
+
+[[package]]
+name = "phf_macros"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "58fdf3184dd560f160dd73922bea2d5cd6e8f064bf4b13110abd81b03697b4e0"
+dependencies = [
+ "phf_generator 0.10.0",
+ "phf_shared 0.10.0",
+ "proc-macro-hack",
+ "proc-macro2",
+ "quote",
+ "syn 1.0.109",
+]
+
+[[package]]
+name = "phf_shared"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c00cf8b9eafe68dde5e9eaa2cef8ee84a9336a47d566ec55ca16589633b65af7"
+dependencies = [
+ "siphasher",
+]
+
+[[package]]
+name = "phf_shared"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6796ad771acdc0123d2a88dc428b5e38ef24456743ddb1744ed628f9815c096"
+dependencies = [
+ "siphasher",
+]
+
+[[package]]
+name = "ppv-lite86"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
+
+[[package]]
+name = "precomputed-hash"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c"
+
+[[package]]
+name = "proc-macro-hack"
+version = "0.5.20+deprecated"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc375e1527247fe1a97d8b7156678dfe7c1af2fc075c9a4db3690ecd2a148068"
+
 [[package]]
 name = "proc-macro2"
 version = "1.0.59"
@@ -122,18 +694,195 @@ dependencies = [
  "proc-macro2",
 ]
 
+[[package]]
+name = "rand"
+version = "0.7.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6a6b1679d49b24bbfe0c803429aa1874472f50d9b363131f0e89fc356b544d03"
+dependencies = [
+ "getrandom 0.1.16",
+ "libc",
+ "rand_chacha 0.2.2",
+ "rand_core 0.5.1",
+ "rand_hc",
+ "rand_pcg",
+]
+
+[[package]]
+name = "rand"
+version = "0.8.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
+dependencies = [
+ "libc",
+ "rand_chacha 0.3.1",
+ "rand_core 0.6.4",
+]
+
+[[package]]
+name = "rand_chacha"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f4c8ed856279c9737206bf725bf36935d8666ead7aa69b52be55af369d193402"
+dependencies = [
+ "ppv-lite86",
+ "rand_core 0.5.1",
+]
+
+[[package]]
+name = "rand_chacha"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
+dependencies = [
+ "ppv-lite86",
+ "rand_core 0.6.4",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "90bde5296fc891b0cef12a6d03ddccc162ce7b2aff54160af9338f8d40df6d19"
+dependencies = [
+ "getrandom 0.1.16",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.6.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
+dependencies = [
+ "getrandom 0.2.9",
+]
+
+[[package]]
+name = "rand_hc"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ca3129af7b92a17112d59ad498c6f81eaf463253766b90396d39ea7a39d6613c"
+dependencies = [
+ "rand_core 0.5.1",
+]
+
+[[package]]
+name = "rand_pcg"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "16abd0c1b639e9eb4d7c50c0b8100b0d0f849be2349829c740fe8e6eb4816429"
+dependencies = [
+ "rand_core 0.5.1",
+]
+
+[[package]]
+name = "redox_syscall"
+version = "0.2.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fb5a58c1855b4b6819d59012155603f0b22ad30cad752600aadfcb695265519a"
+dependencies = [
+ "bitflags",
+]
+
+[[package]]
+name = "regex"
+version = "1.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d0ab3ca65655bb1e41f2a8c8cd662eb4fb035e67c3f78da1d61dffe89d07300f"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.7.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "436b050e76ed2903236f032a59761c1eb99e1b0aead2c257922771dab1fc8c78"
+
 [[package]]
 name = "rustc-demangle"
 version = "0.1.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d626bb9dae77e28219937af045c257c28bfd3f69333c512553507f5f9798cb76"
 
+[[package]]
+name = "rustc_version"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bfa0f585226d2e68097d4f95d113b15b83a82e819ab25717ec0590d9584ef366"
+dependencies = [
+ "semver",
+]
+
+[[package]]
+name = "rustix"
+version = "0.37.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "acf8729d8542766f1b2cf77eb034d52f40d375bb8b615d0b147089946e16613d"
+dependencies = [
+ "bitflags",
+ "errno",
+ "io-lifetimes",
+ "libc",
+ "linux-raw-sys",
+ "windows-sys 0.48.0",
+]
+
 [[package]]
 name = "ryu"
 version = "1.0.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f91339c0467de62360649f8d3e185ca8de4224ff281f66000de5eb2a77a79041"
 
+[[package]]
+name = "scopeguard"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
+
+[[package]]
+name = "scraper"
+version = "0.16.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "59e25654b5e9fd557a67dbaab5a5d36b8c448d0561beb4c041b6dbb902eddfa6"
+dependencies = [
+ "ahash",
+ "cssparser",
+ "ego-tree",
+ "getopts",
+ "html5ever",
+ "once_cell",
+ "selectors",
+ "smallvec",
+ "tendril",
+]
+
+[[package]]
+name = "selectors"
+version = "0.24.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0c37578180969d00692904465fb7f6b3d50b9a2b952b87c23d0e2e5cb5013416"
+dependencies = [
+ "bitflags",
+ "cssparser",
+ "derive_more",
+ "fxhash",
+ "log",
+ "phf 0.8.0",
+ "phf_codegen 0.8.0",
+ "precomputed-hash",
+ "servo_arc",
+ "smallvec",
+]
+
+[[package]]
+name = "semver"
+version = "1.0.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bebd363326d05ec3e2f532ab7660680f3b02130d780c299bca73469d521bc0ed"
+
 [[package]]
 name = "serde"
 version = "1.0.163"
@@ -151,7 +900,7 @@ checksum = "8c805777e3930c8883389c602315a24224bcc738b63905ef87cd1420353ea93e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.17",
 ]
 
 [[package]]
@@ -165,6 +914,77 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "servo_arc"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d52aa42f8fdf0fed91e5ce7f23d8138441002fa31dca008acf47e6fd4721f741"
+dependencies = [
+ "nodrop",
+ "stable_deref_trait",
+]
+
+[[package]]
+name = "siphasher"
+version = "0.3.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7bd3e3206899af3f8b12af284fafc038cc1dc2b41d1b89dd17297221c5d225de"
+
+[[package]]
+name = "smallvec"
+version = "1.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a507befe795404456341dfab10cef66ead4c041f62b8b11bbb92bffe5d0953e0"
+
+[[package]]
+name = "stable_deref_trait"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3"
+
+[[package]]
+name = "string_cache"
+version = "0.8.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f91138e76242f575eb1d3b38b4f1362f10d3a43f47d182a5b359af488a02293b"
+dependencies = [
+ "new_debug_unreachable",
+ "once_cell",
+ "parking_lot",
+ "phf_shared 0.10.0",
+ "precomputed-hash",
+ "serde",
+]
+
+[[package]]
+name = "string_cache_codegen"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6bb30289b722be4ff74a408c3cc27edeaad656e06cb1fe8fa9231fa59c728988"
+dependencies = [
+ "phf_generator 0.10.0",
+ "phf_shared 0.10.0",
+ "proc-macro2",
+ "quote",
+]
+
+[[package]]
+name = "strsim"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
+
+[[package]]
+name = "syn"
+version = "1.0.109"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b64191b275b66ffe2469e8af2c1cfe3bafa67b529ead792a6d0160888b4237"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
 [[package]]
 name = "syn"
 version = "2.0.17"
@@ -176,8 +996,274 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "tendril"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d24a120c5fc464a3458240ee02c299ebcb9d67b5249c8848b09d639dca8d7bb0"
+dependencies = [
+ "futf",
+ "mac",
+ "utf-8",
+]
+
+[[package]]
+name = "termcolor"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "be55cf8942feac5c765c2c993422806843c9a9a45d4d5c407ad6dd2ea95eb9b6"
+dependencies = [
+ "winapi-util",
+]
+
+[[package]]
+name = "tinyvec"
+version = "1.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87cc5ceb3875bb20c2890005a4e226a4651264a5c75edb2421b52861a0a0cb50"
+dependencies = [
+ "tinyvec_macros",
+]
+
+[[package]]
+name = "tinyvec_macros"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
+
+[[package]]
+name = "unicode-bidi"
+version = "0.3.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "92888ba5573ff080736b3648696b70cafad7d250551175acbaa4e0385b3e1460"
+
 [[package]]
 name = "unicode-ident"
 version = "1.0.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b15811caf2415fb889178633e7724bad2509101cde276048e013b9def5e51fa0"
+
+[[package]]
+name = "unicode-normalization"
+version = "0.1.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c5713f0fc4b5db668a2ac63cdb7bb4469d8c9fed047b1d0292cc7b0ce2ba921"
+dependencies = [
+ "tinyvec",
+]
+
+[[package]]
+name = "unicode-width"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c0edd1e5b14653f783770bce4a4dabb4a5108a5370a5f5d8cfe8710c361f6c8b"
+
+[[package]]
+name = "url"
+version = "2.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0d68c799ae75762b8c3fe375feb6600ef5602c883c5d21eb51c09f22b83c4643"
+dependencies = [
+ "form_urlencoded",
+ "idna",
+ "percent-encoding",
+]
+
+[[package]]
+name = "urlencoding"
+version = "2.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e8db7427f936968176eaa7cdf81b7f98b980b18495ec28f1b5791ac3bfe3eea9"
+
+[[package]]
+name = "utf-8"
+version = "0.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9"
+
+[[package]]
+name = "utf8parse"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "711b9620af191e0cdc7468a8d14e709c3dcdb115b36f838e601583af800a370a"
+
+[[package]]
+name = "version_check"
+version = "0.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
+
+[[package]]
+name = "wasi"
+version = "0.9.0+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cccddf32554fecc6acb585f82a32a72e28b48f8c4c1883ddfeeeaa96f7d8e519"
+
+[[package]]
+name = "wasi"
+version = "0.11.0+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
+
+[[package]]
+name = "winapi"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
+dependencies = [
+ "winapi-i686-pc-windows-gnu",
+ "winapi-x86_64-pc-windows-gnu",
+]
+
+[[package]]
+name = "winapi-i686-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
+
+[[package]]
+name = "winapi-util"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70ec6ce85bb158151cae5e5c87f95a8e97d2c0c4b001223f33a334e3ce5de178"
+dependencies = [
+ "winapi",
+]
+
+[[package]]
+name = "winapi-x86_64-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
+
+[[package]]
+name = "windows-sys"
+version = "0.45.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "75283be5efb2831d37ea142365f009c02ec203cd29a3ebecbc093d52315b66d0"
+dependencies = [
+ "windows-targets 0.42.2",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
+dependencies = [
+ "windows-targets 0.48.0",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e5180c00cd44c9b1c88adb3693291f1cd93605ded80c250a75d472756b4d071"
+dependencies = [
+ "windows_aarch64_gnullvm 0.42.2",
+ "windows_aarch64_msvc 0.42.2",
+ "windows_i686_gnu 0.42.2",
+ "windows_i686_msvc 0.42.2",
+ "windows_x86_64_gnu 0.42.2",
+ "windows_x86_64_gnullvm 0.42.2",
+ "windows_x86_64_msvc 0.42.2",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7b1eb6f0cd7c80c79759c929114ef071b87354ce476d9d94271031c0497adfd5"
+dependencies = [
+ "windows_aarch64_gnullvm 0.48.0",
+ "windows_aarch64_msvc 0.48.0",
+ "windows_i686_gnu 0.48.0",
+ "windows_i686_msvc 0.48.0",
+ "windows_x86_64_gnu 0.48.0",
+ "windows_x86_64_gnullvm 0.48.0",
+ "windows_x86_64_msvc 0.48.0",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "597a5118570b68bc08d8d59125332c54f1ba9d9adeedeef5b99b02ba2b0698f8"
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91ae572e1b79dba883e0d315474df7305d12f569b400fcf90581b06062f7e1bc"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e08e8864a60f06ef0d0ff4ba04124db8b0fb3be5776a5cd47641e942e58c4d43"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b2ef27e0d7bdfcfc7b868b317c1d32c641a6fe4629c171b8928c7b08d98d7cf3"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c61d927d8da41da96a81f029489353e68739737d3beca43145c8afec9a31a84f"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "622a1962a7db830d6fd0a69683c80a18fda201879f0f447f065a3b7467daa241"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "44d840b6ec649f480a41c8d80f9c65108b92d89345dd94027bfe06ac444d1060"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4542c6e364ce21bf45d69fdd2a8e455fa38d316158cfd43b3ac1c5b1b19f8e00"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8de912b8b8feb55c064867cf047dda097f92d51efad5b491dfb98f6bbb70cb36"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ca2b8a661f7628cbd23440e50b05d705db3686f894fc9580820623656af974b1"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26d41b46a36d453748aedef1486d5c7a85db22e56aff34643984ea85514e94a3"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7896dbc1f41e08872e9d5e8f8baa8fdd2677f29468c4e156210174edc7f7b953"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9aec5da331524158c6d1a4ac0ab1541149c0b9505fde06423b02f5ef0106b9f0"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1a515f5799fe4961cb532f983ce2b23082366b898e52ffbce459c86f67c8378a"
diff --git a/Cargo.toml b/Cargo.toml
index 6003f4e..3cc52c7 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -4,10 +4,20 @@ version = "0.0.0"
 license = "AGPL-3.0-only"
 edition = "2021"
 repository = "https://github.com/organicmaps/wikiparser/"
-
+default-run = "om-wikiparser"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
 anyhow = { version = "1.0.71", features = ["backtrace"] }
+clap = { version = "4.3.2", features = ["derive"] }
+env_logger = "0.10.0"
+log = "0.4.18"
+scraper = "0.16.0"
 serde = { version = "1.0.163", features = ["derive"] }
 serde_json = "1.0.96"
+url = "2.3.1"
+urlencoding = "2.1.2"
+
+[profile.release]
+debug = true
+overflow-checks = true
diff --git a/src/bin/simplify_html.rs b/src/bin/simplify_html.rs
new file mode 100644
index 0000000..d24c7f5
--- /dev/null
+++ b/src/bin/simplify_html.rs
@@ -0,0 +1,18 @@
+//! Apply html article simplification to stdin, and write it to stdout.
+//!
+//! Usage:
+//!     simplify_html < article.html > simplified.html
+use std::io::{stdin, stdout, Read, Write};
+
+use om_wikiparser::html::simplify;
+
+fn main() -> anyhow::Result<()> {
+    let mut input = String::new();
+    stdin().read_to_string(&mut input)?;
+
+    let output = simplify(&input);
+
+    stdout().write_all(output.as_bytes())?;
+
+    Ok(())
+}
diff --git a/src/html.rs b/src/html.rs
new file mode 100644
index 0000000..9143021
--- /dev/null
+++ b/src/html.rs
@@ -0,0 +1,68 @@
+use scraper::{ElementRef, Html, Selector};
+
+pub fn simplify(html: &str) -> String {
+    // TODO: handle multiple languages
+    let bad_sections = [
+        "External links",
+        "Sources",
+        "See also",
+        "Bibliography",
+        "Further reading",
+        "References",
+    ];
+
+    let mut document = Html::parse_document(html);
+
+    // TODO: evaluate this only once
+    let headers = Selector::parse("h1, h2, h3, h4, h5, h6, h7").unwrap();
+
+    let mut to_remove = Vec::new();
+
+    // remove sections
+    for header in document.select(&headers) {
+        // TODO: should this join all text nodes?
+        let Some(title) = header.text().next() else {
+            continue
+        };
+        if bad_sections.contains(&title) {
+            to_remove.push(header.id());
+            let header_level = header.value().name();
+            // strip trailing nodes
+            for sibling in header.next_siblings() {
+                if let Some(element) = sibling.value().as_element() {
+                    if element.name() == header_level {
+                        // TODO: should this check for a higher level?
+                        break;
+                    }
+                }
+                to_remove.push(sibling.id());
+            }
+        }
+    }
+
+    for id in to_remove.drain(..) {
+        if let Some(mut node) = document.tree.get_mut(id) {
+            node.detach();
+        }
+    }
+
+    // remove elements with no text that isn't whitespace
+
+    for element in document
+        .root_element()
+        .descendants()
+        .filter_map(ElementRef::wrap)
+    {
+        if element.text().all(|t| t.trim().is_empty()) {
+            to_remove.push(element.id());
+        }
+    }
+
+    for id in to_remove.drain(..) {
+        if let Some(mut node) = document.tree.get_mut(id) {
+            node.detach();
+        }
+    }
+
+    document.html()
+}
diff --git a/src/lib.rs b/src/lib.rs
new file mode 100644
index 0000000..5648444
--- /dev/null
+++ b/src/lib.rs
@@ -0,0 +1,2 @@
+pub mod html;
+pub mod wm;
diff --git a/src/main.rs b/src/main.rs
index f811ed2..477f604 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -1,40 +1,65 @@
 // Usage:
-//     pv ~/Downloads/enwiki-NS0-20230401-ENTERPRISE-HTML.json.tar.gz | tar xzO | cargo run --release > /dev/null
+//     # prep outputs from map generator
+//     cut -f 2 ~/Downloads/id_to_wikidata.csv > /tmp/wikidata_ids.txt
+//     tail -n +2 ~/Downloads/wiki_urls.txt | cut -f 3 > /tmp/wikipedia_urls.txt
+//     # feed gzipped tarfile
+//     pv ~/Downloads/enwiki-NS0-20230401-ENTERPRISE-HTML.json.tar.gz | tar xzO \
+//     | cargo run --release -- \
+//     --wikidata-ids /tmp/wikidata_ids.txt \
+//     --wikipedia-urls /tmp/wikipedia_urls.txt \
+//     output_dir
+use std::{
+    fs::File,
+    io::{stdin, BufRead, BufReader, Write},
+    path::PathBuf,
+};
 
-use serde::Deserialize;
-use std::io::{self, stdin, BufRead, BufReader, Write};
+use anyhow::bail;
+use clap::Parser;
+#[macro_use]
+extern crate log;
 
-#[derive(Deserialize)]
-struct Page {
-    // TODO: check if CoW has a performance impact
-    name: String,
-    date_modified: String,
-    #[serde(default)]
-    url: String,
-    main_entity: Option<Wikidata>,
-    // TODO: see what impact parsing/unescaping/allocating this has
-    article_body: ArticleBody,
-    #[serde(default)]
-    redirects: Vec<Redirect>,
-}
+use om_wikiparser::{
+    html::simplify,
+    wm::{is_wikidata_match, is_wikipedia_match, parse_wikidata_file, parse_wikipedia_file, Page},
+};
 
-#[derive(Deserialize)]
-struct Wikidata {
-    identifier: String,
-}
-
-#[derive(Deserialize)]
-struct ArticleBody {
-    html: String,
-}
-
-#[derive(Deserialize)]
-struct Redirect {
-    url: String,
-    name: String,
+#[derive(Parser)]
+struct Args {
+    output_dir: PathBuf,
+    #[arg(long)]
+    wikidata_ids: Option<PathBuf>,
+    #[arg(long)]
+    wikipedia_urls: Option<PathBuf>,
 }
 
 fn main() -> anyhow::Result<()> {
+    env_logger::Builder::new()
+        .filter_level(log::LevelFilter::Info)
+        .parse_default_env()
+        .try_init()?;
+
+    let args = Args::parse();
+
+    info!("Loading urls");
+    let wikipedia_titles = args
+        .wikipedia_urls
+        .map(parse_wikipedia_file)
+        .transpose()?
+        .unwrap_or_default();
+
+    info!("Loading ids");
+    let wikidata_ids = args
+        .wikidata_ids
+        .map(parse_wikidata_file)
+        .transpose()?
+        .unwrap_or_default();
+
+    if !args.output_dir.is_dir() {
+        bail!("output dir {:?} does not exist", args.output_dir)
+    }
+
+    info!("Processing dump");
     let dump = BufReader::new(stdin());
 
     // TODO: compare different deserialization methods
@@ -45,10 +70,33 @@ fn main() -> anyhow::Result<()> {
             .and_then(|s| serde_json::from_str::<Page>(&s).map_err(anyhow::Error::new))
     });
 
-    let mut stdout = io::stdout();
     for page in stream {
         let page = page?;
-        writeln!(stdout, "{}", page.name)?;
+
+        if !(is_wikidata_match(&wikidata_ids, &page).is_some()
+            || is_wikipedia_match(&wikipedia_titles, &page).is_some())
+        {
+            continue;
+        }
+
+        let Some(qid) = page.main_entity.map(|e| e.identifier) else {
+            warn!("Page in list but without wikidata qid: {:?}", page.name);
+            continue;
+        };
+
+        let filename = args.output_dir.join(qid).with_extension("html");
+
+        debug!("{:?}: {:?}", page.name, filename);
+
+        if filename.exists() {
+            debug!("Exists, skipping");
+            continue;
+        }
+
+        let html = simplify(&page.article_body.html);
+
+        let mut file = File::create(filename)?;
+        file.write_all(html.as_bytes())?;
     }
 
     Ok(())
diff --git a/src/wm/mod.rs b/src/wm/mod.rs
new file mode 100644
index 0000000..ceb39fb
--- /dev/null
+++ b/src/wm/mod.rs
@@ -0,0 +1,177 @@
+//! Wikimedia types
+use std::{
+    collections::HashSet,
+    ffi::OsStr,
+    fs::{self},
+    num::ParseIntError,
+    str::FromStr,
+};
+
+use anyhow::{anyhow, bail, Context};
+
+use url::Url;
+
+mod page;
+pub use page::Page;
+
+/// Read from a file of urls on each line.
+pub fn parse_wikidata_file(path: impl AsRef<OsStr>) -> anyhow::Result<HashSet<WikidataQid>> {
+    let contents = fs::read_to_string(path.as_ref())?;
+    contents
+        .lines()
+        .enumerate()
+        .map(|(i, line)| {
+            WikidataQid::from_str(line).with_context(|| {
+                let line_num = i + 1;
+                format!("bad QID value on line {line_num}: {line:?}")
+            })
+        })
+        .collect()
+}
+
+/// Read article titles from a file of urls on each line.
+pub fn parse_wikipedia_file(
+    path: impl AsRef<OsStr>,
+) -> anyhow::Result<HashSet<WikipediaTitleNorm>> {
+    let contents = fs::read_to_string(path.as_ref())?;
+    contents
+        .lines()
+        .enumerate()
+        .map(|(i, line)| {
+            WikipediaTitleNorm::from_url(line).with_context(|| {
+                let line_num = i + 1;
+                format!("bad wikipedia url on line {line_num}: {line:?}")
+            })
+        })
+        .collect()
+}
+
+pub fn is_wikidata_match(ids: &HashSet<WikidataQid>, page: &Page) -> Option<WikidataQid> {
+    let Some(wikidata) = &page.main_entity else { return None;};
+    let wikidata_id = &wikidata.identifier;
+    let wikidata_id = match WikidataQid::from_str(wikidata_id) {
+        Ok(qid) => qid,
+        Err(e) => {
+            eprintln!("Could not parse QID: {:?}: {}", wikidata_id, e);
+            return None;
+        }
+    };
+
+    ids.get(&wikidata_id).map(|_| wikidata_id)
+}
+
+pub fn is_wikipedia_match(
+    titles: &HashSet<WikipediaTitleNorm>,
+    page: &Page,
+) -> Option<WikipediaTitleNorm> {
+    // TODO: handle multiple languages
+    let title = WikipediaTitleNorm::from_title(&page.name, "en");
+
+    if titles.get(&title).is_some() {
+        return Some(title);
+    }
+
+    for redirect in &page.redirects {
+        let title = WikipediaTitleNorm::from_title(&redirect.name, "en");
+
+        if titles.get(&title).is_some() {
+            return Some(title);
+        }
+    }
+
+    None
+}
+
+/// Wikidata QID/Q Number
+///
+/// See https://www.wikidata.org/wiki/Wikidata:Glossary#QID
+///
+/// ```
+/// use std::str::FromStr;
+/// use om_wikiparser::wm::WikidataQid;
+///
+/// let with_q = WikidataQid::from_str("Q12345").unwrap();
+/// let without_q = WikidataQid::from_str("12345").unwrap();
+/// assert_eq!(with_q, without_q);
+/// ```
+#[derive(Debug, PartialOrd, Ord, PartialEq, Eq, Hash)]
+pub struct WikidataQid(u32);
+
+impl FromStr for WikidataQid {
+    type Err = ParseIntError;
+
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        let s = s.strip_prefix('Q').unwrap_or(s);
+        u32::from_str(s).map(WikidataQid)
+    }
+}
+
+/// Normalized wikipedia article title that can compare:
+/// - titles `Spatial Database`
+/// - urls `https://en.wikipedia.org/wiki/Spatial_database#Geodatabase`
+/// - osm-style tags `en:Spatial Database`
+///
+/// ```
+/// use om_wikiparser::wm::WikipediaTitleNorm;
+///
+/// let url = WikipediaTitleNorm::from_url("https://en.wikipedia.org/wiki/Article_Title/").unwrap();
+/// let title = WikipediaTitleNorm::from_title("Article Title", "en");
+/// assert_eq!(url, title);
+/// ```
+#[derive(Debug, PartialOrd, Ord, PartialEq, Eq, Hash)]
+pub struct WikipediaTitleNorm {
+    lang: String,
+    name: String,
+}
+
+impl WikipediaTitleNorm {
+    fn normalize_title(title: &str) -> String {
+        // TODO: compare with generator url creation
+        title.replace(' ', "_")
+    }
+
+    // https://en.wikipedia.org/wiki/Article_Title
+    pub fn from_url(url: &str) -> anyhow::Result<Self> {
+        let url = Url::parse(url)?;
+
+        let (subdomain, host) = url
+            .host_str()
+            .ok_or(anyhow!("Expected host"))?
+            .split_once('.')
+            .ok_or(anyhow!("Expected subdomain"))?;
+        if host != "wikipedia.org" {
+            bail!("Expected wikipedia.org for domain")
+        }
+        let lang = subdomain;
+
+        let mut paths = url.path_segments().ok_or(anyhow!("Expected path"))?;
+
+        let root = paths
+            .next()
+            .ok_or(anyhow!("Expected first segment in path"))?;
+
+        if root != "wiki" {
+            bail!("Expected 'wiki' in path")
+        }
+
+        let title = paths
+            .next()
+            .ok_or(anyhow!("Expected second segment in path"))?;
+        let title = urlencoding::decode(title)?;
+
+        Ok(Self::from_title(&title, lang))
+    }
+
+    // en:Article Title
+    fn _from_osm_tag(tag: &str) -> anyhow::Result<Self> {
+        let (lang, title) = tag.split_once(':').ok_or(anyhow!("Expected ':'"))?;
+
+        Ok(Self::from_title(title, lang))
+    }
+
+    pub fn from_title(title: &str, lang: &str) -> Self {
+        let name = Self::normalize_title(title);
+        let lang = lang.to_owned();
+        Self { name, lang }
+    }
+}
diff --git a/src/wm/page.rs b/src/wm/page.rs
new file mode 100644
index 0000000..b830fd9
--- /dev/null
+++ b/src/wm/page.rs
@@ -0,0 +1,36 @@
+use serde::Deserialize;
+
+/// Deserialized Wikimedia Enterprise API Article
+///
+/// For all available fields, see https://enterprise.wikimedia.com/docs/data-dictionary/
+#[allow(dead_code)] // TODO: reevaluate fields
+#[derive(Deserialize)]
+pub struct Page {
+    // TODO: check if CoW has a performance impact
+    pub name: String,
+    pub date_modified: String,
+    #[serde(default)]
+    pub url: String,
+    pub main_entity: Option<Wikidata>,
+    // TODO: see what impact parsing/unescaping/allocating this has
+    pub article_body: ArticleBody,
+    #[serde(default)]
+    pub redirects: Vec<Redirect>,
+}
+
+#[derive(Deserialize)]
+pub struct Wikidata {
+    pub identifier: String,
+}
+
+#[derive(Deserialize)]
+pub struct ArticleBody {
+    pub html: String,
+}
+
+#[allow(dead_code)] // TODO: reevaluate fields
+#[derive(Deserialize)]
+pub struct Redirect {
+    pub url: String,
+    pub name: String,
+}