feat(monitor/collectors/wikipedia): goquery-backed ITN parser (revid + entries with article slugs)
This commit is contained in:
parent
05ca2f529f
commit
85626a0e11
|
|
@ -23,7 +23,7 @@ require (
|
|||
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.33.0
|
||||
go.opentelemetry.io/otel/sdk v1.35.0
|
||||
go.opentelemetry.io/otel/trace v1.41.0
|
||||
golang.org/x/crypto v0.48.0
|
||||
golang.org/x/crypto v0.49.0
|
||||
golang.org/x/time v0.14.0
|
||||
google.golang.org/grpc v1.68.1
|
||||
)
|
||||
|
|
@ -32,6 +32,8 @@ require (
|
|||
dario.cat/mergo v1.0.2 // indirect
|
||||
github.com/Azure/go-ansiterm v0.0.0-20250102033503-faa5f7b0171c // indirect
|
||||
github.com/Microsoft/go-winio v0.6.2 // indirect
|
||||
github.com/PuerkitoBio/goquery v1.12.0 // indirect
|
||||
github.com/andybalholm/cascadia v1.3.3 // indirect
|
||||
github.com/cenkalti/backoff/v4 v4.3.0 // indirect
|
||||
github.com/cespare/xxhash/v2 v2.3.0 // indirect
|
||||
github.com/containerd/errdefs v1.0.0 // indirect
|
||||
|
|
@ -105,10 +107,10 @@ require (
|
|||
go.opentelemetry.io/otel/metric v1.41.0 // indirect
|
||||
go.opentelemetry.io/proto/otlp v1.4.0 // indirect
|
||||
go.yaml.in/yaml/v3 v3.0.3 // indirect
|
||||
golang.org/x/net v0.49.0 // indirect
|
||||
golang.org/x/net v0.52.0 // indirect
|
||||
golang.org/x/sync v0.20.0 // indirect
|
||||
golang.org/x/sys v0.42.0 // indirect
|
||||
golang.org/x/text v0.34.0 // indirect
|
||||
golang.org/x/text v0.35.0 // indirect
|
||||
google.golang.org/genproto/googleapis/api v0.0.0-20241209162323-e6fa225c2576 // indirect
|
||||
google.golang.org/genproto/googleapis/rpc v0.0.0-20241209162323-e6fa225c2576 // indirect
|
||||
google.golang.org/protobuf v1.36.8 // indirect
|
||||
|
|
|
|||
|
|
@ -8,6 +8,10 @@ github.com/Azure/go-ansiterm v0.0.0-20250102033503-faa5f7b0171c h1:udKWzYgxTojEK
|
|||
github.com/Azure/go-ansiterm v0.0.0-20250102033503-faa5f7b0171c/go.mod h1:xomTg63KZ2rFqZQzSB4Vz2SUXa1BpHTVz9L5PTmPC4E=
|
||||
github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
|
||||
github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
|
||||
github.com/PuerkitoBio/goquery v1.12.0 h1:pAcL4g3WRXekcB9AU/y1mbKez2dbY2AajVhtkO8RIBo=
|
||||
github.com/PuerkitoBio/goquery v1.12.0/go.mod h1:802ej+gV2y7bbIhOIoPY5sT183ZW0YFofScC4q/hIpQ=
|
||||
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/bsm/ginkgo/v2 v2.12.0 h1:Ny8MWAHyOepLGlLKYmXG4IEkioBysk6GpaRTLC8zwWs=
|
||||
github.com/bsm/ginkgo/v2 v2.12.0/go.mod h1:SwYbGRRDovPVboqFv0tPTcG1sN61LM1Z4ARdbAV9g4c=
|
||||
github.com/bsm/gomega v1.27.10 h1:yeMWxP2pV2fG3FgAODIY8EiRE3dy0aeFYt4l7wh6yKA=
|
||||
|
|
@ -79,6 +83,7 @@ github.com/goccy/go-json v0.10.3/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PU
|
|||
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 v0.5.6/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/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
|
||||
|
|
@ -206,6 +211,7 @@ github.com/tklauser/numcpus v0.11.0 h1:nSTwhKH5e1dMNsCdVBukSZrURJRoHbSEQjdEbY+9R
|
|||
github.com/tklauser/numcpus v0.11.0/go.mod h1:z+LwcLq54uWZTX0u/bGobaV34u6V7KNlTZejzM6/3MQ=
|
||||
github.com/valyala/fastjson v1.6.4 h1:uAUNq9Z6ymTgGhcm0UynUAB6tlbakBrz6CQFax3BXVQ=
|
||||
github.com/valyala/fastjson v1.6.4/go.mod h1:CLCAqky6SMuOcxStkYQvblddUtoRxhYMGLrsQns1aXY=
|
||||
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
|
||||
github.com/yusufpapurcu/wmi v1.2.4 h1:zFUKzehAFReQwLys1b/iSMl+JQGSCSjtVqQn9bBrPo0=
|
||||
github.com/yusufpapurcu/wmi v1.2.4/go.mod h1:SBZ9tNy3G9/m5Oi98Zks0QjeHVDvuK0qfxQmPyzfmi0=
|
||||
go.opentelemetry.io/auto/sdk v1.2.1 h1:jXsnJ4Lmnqd11kwkBV2LgLoFMZKizbCi5fNZ/ipaZ64=
|
||||
|
|
@ -232,23 +238,93 @@ go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
|
|||
go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
|
||||
go.yaml.in/yaml/v3 v3.0.3 h1:bXOww4E/J3f66rav3pX3m8w6jDE4knZjGOw8b5Y6iNE=
|
||||
go.yaml.in/yaml/v3 v3.0.3/go.mod h1:tBHosrYAkRZjRAOREWbDnBXUf08JOwYq++0QNwQiWzI=
|
||||
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/crypto v0.48.0 h1:/VRzVqiRSggnhY7gNRxPauEQ5Drw9haKdM0jqfcCFts=
|
||||
golang.org/x/crypto v0.48.0/go.mod h1:r0kV5h3qnFPlQnBSrULhlsRfryS2pmewsg+XfMgkVos=
|
||||
golang.org/x/crypto v0.49.0 h1:+Ng2ULVvLHnJ/ZFEq4KdcDd/cfjrrjjNSXNzxg0Y4U4=
|
||||
golang.org/x/crypto v0.49.0/go.mod h1:ErX4dUh2UM+CFYiXZRTcMpEcN8b/1gxEuv3nODoYtCA=
|
||||
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 v0.49.0 h1:eeHFmOGUTtaaPSGNmjBKpbng9MulQsJURQUAfUwY++o=
|
||||
golang.org/x/net v0.49.0/go.mod h1:/ysNB2EvaqvesRkuLAyjI1ycPZlQHM3q01F02UY/MV8=
|
||||
golang.org/x/net v0.52.0 h1:He/TN1l0e4mmR3QqHMT2Xab3Aj3L9qjbhRm78/6jrW0=
|
||||
golang.org/x/net v0.52.0/go.mod h1:R1MAz7uMZxVMualyPXb+VaqGSa3LIaUqk0eEt3w36Sw=
|
||||
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/sync v0.20.0 h1:e0PTpb7pjO8GAtTs2dQ6jYa5BWYlMuX047Dco/pItO4=
|
||||
golang.org/x/sync v0.20.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
|
||||
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
|
||||
golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||
golang.org/x/sys v0.0.0-20201204225414-ed752295db88/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.0.0-20210616094352-59db8d763f22/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/sys v0.42.0 h1:omrd2nAlyT5ESRdCLYdm3+fMfNFE/+Rf4bDIQImRJeo=
|
||||
golang.org/x/sys v0.42.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
|
||||
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/term v0.40.0 h1:36e4zGLqU4yhjlmxEaagx2KuYbJq3EwY8K943ZsHcvg=
|
||||
golang.org/x/term v0.40.0/go.mod h1:w2P8uVp06p2iyKKuvXIm7N/y0UCRt3UfJTfZ7oOpglM=
|
||||
golang.org/x/term v0.41.0 h1:QCgPso/Q3RTJx2Th4bDLqML4W6iJiaXFq2/ftQF13YU=
|
||||
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 v0.7.0/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 v0.34.0 h1:oL/Qq0Kdaqxa1KbNeMKwQq0reLCCaFtqu2eNuSeNHbk=
|
||||
golang.org/x/text v0.34.0/go.mod h1:homfLqTYRFyVYemLBFl5GgL/DWEiH5wcsQ5gSh1yziA=
|
||||
golang.org/x/text v0.35.0 h1:JOVx6vVDFokkpaq1AEptVzLTpDe9KGpj5tR4/X+ybL8=
|
||||
golang.org/x/text v0.35.0/go.mod h1:khi/HExzZJ2pGnjenulevKNX1W67CUy0AsXcNubPGCA=
|
||||
golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
|
||||
golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
|
||||
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/genproto/googleapis/api v0.0.0-20241209162323-e6fa225c2576 h1:CkkIfIt50+lT6NHAVoRYEyAvQGFM7xEwXUUywFvEb3Q=
|
||||
google.golang.org/genproto/googleapis/api v0.0.0-20241209162323-e6fa225c2576/go.mod h1:1R3kvZ1dtP3+4p4d3G8uJ8rFk/fWlScl38vanWACI08=
|
||||
|
|
|
|||
|
|
@ -0,0 +1,77 @@
|
|||
// ©AngelaMos | 2026
|
||||
// parser.go
|
||||
|
||||
package wikipedia
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"strings"
|
||||
|
||||
"github.com/PuerkitoBio/goquery"
|
||||
)
|
||||
|
||||
type Response struct {
|
||||
RevID int64
|
||||
HTML string
|
||||
}
|
||||
|
||||
type ITNEntry struct {
|
||||
Text string
|
||||
ArticleSlug string
|
||||
}
|
||||
|
||||
type rawAPI struct {
|
||||
Parse struct {
|
||||
Title string `json:"title"`
|
||||
RevID int64 `json:"revid"`
|
||||
Text struct {
|
||||
Star string `json:"*"`
|
||||
} `json:"text"`
|
||||
} `json:"parse"`
|
||||
}
|
||||
|
||||
func DecodeResponse(body []byte) (Response, error) {
|
||||
var r rawAPI
|
||||
if err := json.Unmarshal(body, &r); err != nil {
|
||||
return Response{}, fmt.Errorf("decode wikipedia response: %w", err)
|
||||
}
|
||||
return Response{RevID: r.Parse.RevID, HTML: r.Parse.Text.Star}, nil
|
||||
}
|
||||
|
||||
func ParseEntries(html string) []ITNEntry {
|
||||
if strings.TrimSpace(html) == "" {
|
||||
return nil
|
||||
}
|
||||
doc, err := goquery.NewDocumentFromReader(strings.NewReader(html))
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
var out []ITNEntry
|
||||
doc.Find("ul li").Each(func(_ int, s *goquery.Selection) {
|
||||
text := strings.TrimSpace(s.Text())
|
||||
if text == "" {
|
||||
return
|
||||
}
|
||||
entry := ITNEntry{Text: text}
|
||||
if href, ok := s.Find("a").First().Attr("href"); ok {
|
||||
if slug := slugFromHref(href); slug != "" {
|
||||
entry.ArticleSlug = slug
|
||||
}
|
||||
}
|
||||
out = append(out, entry)
|
||||
})
|
||||
return out
|
||||
}
|
||||
|
||||
func slugFromHref(href string) string {
|
||||
const prefix = "/wiki/"
|
||||
if !strings.HasPrefix(href, prefix) {
|
||||
return ""
|
||||
}
|
||||
slug := strings.TrimPrefix(href, prefix)
|
||||
if hash := strings.Index(slug, "#"); hash >= 0 {
|
||||
slug = slug[:hash]
|
||||
}
|
||||
return slug
|
||||
}
|
||||
|
|
@ -0,0 +1,58 @@
|
|||
// ©AngelaMos | 2026
|
||||
// parser_test.go
|
||||
|
||||
package wikipedia_test
|
||||
|
||||
import (
|
||||
"os"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"github.com/carterperez-dev/monitor-the-situation/backend/internal/collectors/wikipedia"
|
||||
)
|
||||
|
||||
func TestParser_ExtractsITNEntriesFromFixture(t *testing.T) {
|
||||
body, err := os.ReadFile("testdata/itn_response.json")
|
||||
require.NoError(t, err)
|
||||
|
||||
resp, err := wikipedia.DecodeResponse(body)
|
||||
require.NoError(t, err)
|
||||
require.NotZero(t, resp.RevID)
|
||||
|
||||
entries := wikipedia.ParseEntries(resp.HTML)
|
||||
require.GreaterOrEqual(t, len(entries), 1)
|
||||
for _, e := range entries {
|
||||
require.NotEmpty(t, e.Text)
|
||||
}
|
||||
hasLink := false
|
||||
for _, e := range entries {
|
||||
if e.ArticleSlug != "" {
|
||||
hasLink = true
|
||||
break
|
||||
}
|
||||
}
|
||||
require.True(t, hasLink, "at least one entry should carry an article slug")
|
||||
}
|
||||
|
||||
func TestParser_HandlesEmptyHTML(t *testing.T) {
|
||||
entries := wikipedia.ParseEntries("")
|
||||
require.Empty(t, entries)
|
||||
}
|
||||
|
||||
func TestParser_StripsHTMLTagsFromText(t *testing.T) {
|
||||
entries := wikipedia.ParseEntries(`<ul><li>Plain <b>bold</b> headline with <a href="/wiki/Topic">link</a>.</li></ul>`)
|
||||
require.Len(t, entries, 1)
|
||||
require.Contains(t, entries[0].Text, "Plain")
|
||||
require.Contains(t, entries[0].Text, "bold")
|
||||
require.Contains(t, entries[0].Text, "link")
|
||||
require.NotContains(t, entries[0].Text, "<b>")
|
||||
require.Equal(t, "Topic", entries[0].ArticleSlug)
|
||||
}
|
||||
|
||||
func TestParser_SkipsListItemsWithoutLinks(t *testing.T) {
|
||||
entries := wikipedia.ParseEntries(`<ul><li>Has <a href="/wiki/Foo">link</a></li><li>No link here</li></ul>`)
|
||||
require.Len(t, entries, 2)
|
||||
require.Equal(t, "Foo", entries[0].ArticleSlug)
|
||||
require.Empty(t, entries[1].ArticleSlug)
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue