diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..3997bea --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +*.db \ No newline at end of file diff --git a/cmd/serve/main.go b/cmd/serve/main.go index 66df405..f07a465 100644 --- a/cmd/serve/main.go +++ b/cmd/serve/main.go @@ -1,8 +1,10 @@ package main import ( + "log" "scrap/internal/config" "scrap/internal/db" + "scrap/internal/wikipediadl" ) func main() { @@ -10,4 +12,9 @@ func main() { db.Setup() defer db.Close() + + if err := wikipediadl.FetchArticles(); err != nil { + log.Println(err.Error()) + } + } diff --git a/config.json b/config.json index e210c76..e1c9923 100644 --- a/config.json +++ b/config.json @@ -1,3 +1,4 @@ { - "sql-tables-dir": "./sqltable/" + "sql-tables-dir": "./sqltable/", + "sql-database-name": "scrap.db" } \ No newline at end of file diff --git a/example.db b/example.db deleted file mode 100644 index dd49cbd..0000000 Binary files a/example.db and /dev/null differ diff --git a/go.mod b/go.mod index 83ffde0..782b439 100644 --- a/go.mod +++ b/go.mod @@ -2,4 +2,25 @@ module scrap go 1.24.4 -require github.com/mattn/go-sqlite3 v1.14.32 +require ( + github.com/gocolly/colly v1.2.0 + github.com/mattn/go-sqlite3 v1.14.32 +) + +require ( + github.com/PuerkitoBio/goquery v1.10.3 // indirect + github.com/andybalholm/cascadia v1.3.3 // indirect + github.com/antchfx/htmlquery v1.3.4 // indirect + github.com/antchfx/xmlquery v1.4.4 // indirect + github.com/antchfx/xpath v1.3.5 // indirect + github.com/gobwas/glob v0.2.3 // indirect + github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 // indirect + github.com/golang/protobuf v1.5.4 // indirect + github.com/kennygrant/sanitize v1.2.4 // indirect + github.com/saintfish/chardet v0.0.0-20230101081208-5e3ef4b5456d // indirect + github.com/temoto/robotstxt v1.1.2 // indirect + golang.org/x/net v0.44.0 // indirect + golang.org/x/text v0.29.0 // indirect + google.golang.org/appengine v1.6.8 // indirect + google.golang.org/protobuf v1.36.10 // indirect +) diff --git a/go.sum b/go.sum index 66f7516..0fe57bd 100644 --- a/go.sum +++ b/go.sum @@ -1,2 +1,117 @@ +github.com/PuerkitoBio/goquery v1.10.3 h1:pFYcNSqHxBD06Fpj/KsbStFRsgRATgnf3LeXiUkhzPo= +github.com/PuerkitoBio/goquery v1.10.3/go.mod h1:tMUX0zDMHXYlAQk6p35XxQMqMweEKB7iK7iLNd4RH4Y= +github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM= +github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA= +github.com/antchfx/htmlquery v1.3.4 h1:Isd0srPkni2iNTWCwVj/72t7uCphFeor5Q8nCzj1jdQ= +github.com/antchfx/htmlquery v1.3.4/go.mod h1:K9os0BwIEmLAvTqaNSua8tXLWRWZpocZIH73OzWQbwM= +github.com/antchfx/xmlquery v1.4.4 h1:mxMEkdYP3pjKSftxss4nUHfjBhnMk4imGoR96FRY2dg= +github.com/antchfx/xmlquery v1.4.4/go.mod h1:AEPEEPYE9GnA2mj5Ur2L5Q5/2PycJ0N9Fusrx9b12fc= +github.com/antchfx/xpath v1.3.3/go.mod h1:i54GszH55fYfBmoZXapTHN8T8tkcHfRgLyVwwqzXNcs= +github.com/antchfx/xpath v1.3.5 h1:PqbXLC3TkfeZyakF5eeh3NTWEbYl4VHNVeufANzDbKQ= +github.com/antchfx/xpath v1.3.5/go.mod h1:i54GszH55fYfBmoZXapTHN8T8tkcHfRgLyVwwqzXNcs= +github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8= +github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y= +github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8= +github.com/gocolly/colly v1.2.0 h1:qRz9YAn8FIH0qzgNUw+HT9UN7wm1oF9OBAilwEWpyrI= +github.com/gocolly/colly v1.2.0/go.mod h1:Hof5T3ZswNVsOHYmba1u03W65HDWgpV5HifSuueE0EA= +github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc= +github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 h1:f+oWsMOmNPc8JmEHVZIycC7hBoQxHH9pNKQORJNozsQ= +github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8/go.mod h1:wcDNUvekVysuuOpQKo3191zZyTpiI6se1N1ULghS0sw= +github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk= +github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY= +github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek= +github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps= +github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= +github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY= +github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8= +github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU= +github.com/kennygrant/sanitize v1.2.4 h1:gN25/otpP5vAsO2djbMhF/LQX6R7+O1TB4yv8NzpJ3o= +github.com/kennygrant/sanitize v1.2.4/go.mod h1:LGsjYYtgxbetdg5owWB2mpgUL6e2nfw2eObZ0u0qvak= github.com/mattn/go-sqlite3 v1.14.32 h1:JD12Ag3oLy1zQA+BNn74xRgaBbdhbNIDYvQUEuuErjs= github.com/mattn/go-sqlite3 v1.14.32/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y= +github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= +github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= +github.com/saintfish/chardet v0.0.0-20230101081208-5e3ef4b5456d h1:hrujxIzL1woJ7AwssoOcM/tq5JjjG2yYOc8odClEiXA= +github.com/saintfish/chardet v0.0.0-20230101081208-5e3ef4b5456d/go.mod h1:uugorj2VCxiV1x+LzaIdVa9b4S4qGAcH6cbhh4qVxOU= +github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= +github.com/stretchr/testify v1.3.0 h1:TivCn/peBQ7UY8ooIcPgZFpTNSz0Q2U6UrFlUfqbe0Q= +github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= +github.com/temoto/robotstxt v1.1.2 h1:W2pOjSJ6SWvldyEuiFXNxz3xZ8aiWX5LbfDiOFd7Fxg= +github.com/temoto/robotstxt v1.1.2/go.mod h1:+1AmkuG3IYkh1kv0d2qEB9Le88ehNO0zwOr3ujewlOo= +github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY= +golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= +golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc= +golang.org/x/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc= +golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU= +golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8= +golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk= +golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4= +golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= +golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= +golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c= +golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c= +golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s= +golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg= +golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c= +golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs= +golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg= +golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk= +golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44= +golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM= +golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4= +golang.org/x/net v0.44.0 h1:evd8IRDyfNBMBTTY5XRF1vaZlD+EmWx6x8PkhR04H/I= +golang.org/x/net v0.44.0/go.mod h1:ECOoLqd5U3Lhyeyo/QDCEVQ4sNgYsqvCZ722XogGieY= +golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y= +golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= +golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= +golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= +golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE= +golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= +golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8= +golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k= +golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo= +golang.org/x/term v0.12.0/go.mod h1:owVbMEjm3cBLCHdkQu9b1opXd4ETQWc3BhuQGKgXgvU= +golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk= +golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY= +golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM= +golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= +golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= +golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ= +golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ= +golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8= +golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8= +golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE= +golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU= +golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU= +golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ= +golang.org/x/text v0.29.0 h1:1neNs90w9YzJ9BocxfsQNHKuAT4pkghyXc4nhZ6sJvk= +golang.org/x/text v0.29.0/go.mod h1:7MhJOA9CD2qZyOKYazxdYMF85OwPdEr9jTtBpO7ydH4= +golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= +golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= +golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc= +golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU= +golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58= +golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk= +golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +google.golang.org/appengine v1.6.8 h1:IhEN5q69dyKagZPYMSdIjS2HqprW324FRQZJcGqPAsM= +google.golang.org/appengine v1.6.8/go.mod h1:1jJ3jBArFh5pcgW8gCtRJnepW8FzD1V44FJffLiz/Ds= +google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw= +google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc= +google.golang.org/protobuf v1.36.10 h1:AYd7cD/uASjIL6Q9LiTjz8JLcrh/88q5UObnmY3aOOE= +google.golang.org/protobuf v1.36.10/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco= diff --git a/internal/config/setup.go b/internal/config/setup.go index 63869de..71c607a 100644 --- a/internal/config/setup.go +++ b/internal/config/setup.go @@ -6,7 +6,8 @@ import ( ) type AppConfig struct { - SqlTablesDir string `json:"sql-tables-dir"` + SqlTablesDir string `json:"sql-tables-dir"` + SqlDatabaseName string `json:"sql-database-name"` } var appConfigInstance *AppConfig diff --git a/internal/db/setup.go b/internal/db/setup.go index 0ea40d2..d56bcf5 100644 --- a/internal/db/setup.go +++ b/internal/db/setup.go @@ -12,7 +12,9 @@ import ( var dbInstance *sql.DB func Setup() { - db, err := sql.Open("sqlite3", "./example.db") + cfg := config.GetAppConfig() + + db, err := sql.Open("sqlite3", cfg.SqlDatabaseName) if err != nil { panic(err) } diff --git a/internal/wikipediadl/downloadarticles.go b/internal/wikipediadl/downloadarticles.go new file mode 100644 index 0000000..2d308ab --- /dev/null +++ b/internal/wikipediadl/downloadarticles.go @@ -0,0 +1,79 @@ +package wikipediadl + +import ( + "compress/bzip2" + "encoding/xml" + "flag" + "fmt" + "io" + "log" + "net/http" +) + +type Page struct { + Title string `xml:"title"` + Revision Revision `xml:"revision"` +} + +type Revision struct { + Text string `xml:"text"` +} + +func DownloadArticles() { + url := "https://dumps.wikimedia.org/plwiki/latest/plwiki-latest-pages-articles1.xml-p1p187037.bz2" + + limiter := flag.Int("limit", 10, "Number of articles to process; 0 means all") + flag.Parse() + + log.Printf("Downloading chunk: %s", url) + resp, err := http.Get(url) + if err != nil { + log.Fatalf("Failed to download chunk: %v", err) + } + defer resp.Body.Close() + + if resp.StatusCode != 200 { + body, _ := io.ReadAll(io.LimitReader(resp.Body, 1024)) + log.Fatalf("Bad response status: %s\nBody: %s", resp.Status, string(body)) + } + + bz2Reader := bzip2.NewReader(resp.Body) + dec := xml.NewDecoder(bz2Reader) + + count := 0 + for { + tok, err := dec.Token() + if err != nil { + if err == io.EOF { + log.Println("Reached end of chunk") + break + } + log.Fatalf("XML token error: %v", err) + } + + switch se := tok.(type) { + case xml.StartElement: + if se.Name.Local == "page" { + var p Page + if err := dec.DecodeElement(&p, &se); err != nil { + log.Printf("Error decoding page: %v", err) + continue + } + + count++ + fmt.Printf("---- Article %d ----\n", count) + fmt.Printf("Title: %s\n", p.Title) + // fmt.Println("Content:") + // fmt.Println(p.Revision.Text) + fmt.Println("--------------------\n") + + if *limiter > 0 && count >= *limiter { + log.Printf("Reached limit of %d articles, stopping.", *limiter) + return + } + } + } + } + + log.Printf("Done. Total articles processed: %d", count) +} diff --git a/internal/wikipediadl/error.go b/internal/wikipediadl/error.go new file mode 100644 index 0000000..755fe66 --- /dev/null +++ b/internal/wikipediadl/error.go @@ -0,0 +1,7 @@ +package wikipediadl + +import "errors" + +var ( + ErrArticleFetchFailed = errors.New("wikipediadl: failed to fetch articles") +) diff --git a/internal/wikipediadl/fetcharticles.go b/internal/wikipediadl/fetcharticles.go new file mode 100644 index 0000000..c1cac77 --- /dev/null +++ b/internal/wikipediadl/fetcharticles.go @@ -0,0 +1,71 @@ +package wikipediadl + +import ( + "fmt" + "log" + "strings" + + "github.com/gocolly/colly" +) + +const ( + DumpDomain = "dumps.wikimedia.org" + DumpUrl = "https://dumps.wikimedia.org/plwiki/latest/" +) + +func getScraper() *colly.Collector { + s := colly.NewCollector( + colly.AllowedDomains(DumpDomain), + ) + + return s +} + +func getAllArticles(s *colly.Collector) []string { + articles := []string{} + + s.OnHTML("a", func(h *colly.HTMLElement) { + article := h.Attr("href") + if !isValidArticle(article) { + return + } + + articles = append(articles, h.Attr("href")) + + }) + + s.OnError(func(r *colly.Response, err error) { + log.Println(r.Request.URL) + }) + + s.Visit(DumpUrl) + + return articles +} + +func isValidArticle(a string) bool { + const ( + validPrefix = "plwiki-latest-pages-articles" + validSuffix = ".bz2" + ) + + if !strings.HasPrefix(a, validPrefix) || !strings.HasSuffix(a, validSuffix) { + return false + } + + article, _ := strings.CutPrefix(a, validPrefix) + + articleIndex := article[0] + return articleIndex >= 48 && articleIndex <= 57 +} + +func FetchArticles() error { + scraper := getScraper() + + articles := getAllArticles(scraper) + for _, a := range articles { + fmt.Println(a) + } + + return nil +}