From 23a466cd72a564d2372838cffb9efb78f133ee97 Mon Sep 17 00:00:00 2001 From: Egor Aristov Date: Wed, 7 May 2025 03:49:25 +0300 Subject: [PATCH] small fixes --- go.mod | 4 +- go.sum | 23 ++++- internal/api/http/pb/specs.pb.go | 93 ++++++++++--------- internal/extractors/pwextractor/pageparser.go | 9 +- proto/specs.proto | 2 +- 5 files changed, 73 insertions(+), 58 deletions(-) diff --git a/go.mod b/go.mod index bec423e..4312139 100644 --- a/go.mod +++ b/go.mod @@ -5,6 +5,7 @@ go 1.23.2 toolchain go1.24.0 require ( + github.com/AdguardTeam/urlfilter v0.20.0 github.com/ericchiang/css v1.4.0 github.com/felixge/fgprof v0.9.5 github.com/go-playground/validator/v10 v10.23.0 @@ -27,7 +28,6 @@ require ( require ( github.com/AdguardTeam/golibs v0.29.0 // indirect - github.com/AdguardTeam/urlfilter v0.20.0 // indirect github.com/BurntSushi/toml v1.2.1 // indirect github.com/alessandro-c/gomemcached-lock v1.0.0 // indirect github.com/armon/go-metrics v0.4.1 // indirect @@ -112,4 +112,4 @@ require ( olympos.io/encoding/edn v0.0.0-20201019073823-d3554ca0b0a3 // indirect ) -replace github.com/ericchiang/css => github.com/egor3f/css v0.0.0-20250115151140-52c8c51084e5 +replace github.com/ericchiang/css => github.com/egor3f/css v0.0.0-20250507004805-bfefe22b74a4 diff --git a/go.sum b/go.sum index 106ce3f..acb260a 100644 --- a/go.sum +++ b/go.sum @@ -93,8 +93,8 @@ github.com/deckarep/golang-set/v2 v2.7.0 h1:gIloKvD7yH2oip4VLhsv3JyLLFnC0Y2mlusg github.com/deckarep/golang-set/v2 v2.7.0/go.mod h1:VAky9rY/yGXJOLEDv3OMci+7wtDpOF4IN+y82NBOac4= github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f h1:lO4WD4F/rVNCu3HqELle0jiPLLBs70cWOduZpkS1E78= github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc= -github.com/egor3f/css v0.0.0-20250115151140-52c8c51084e5 h1:rqpFTlOasDC5OXOf8NA+XEdjPClBnPGxsQ484OXx6l4= -github.com/egor3f/css v0.0.0-20250115151140-52c8c51084e5/go.mod h1:sVSdL+MFR9Q4cKJMQzpIkHIDOLiK+7Wmjjhq7D+MubA= +github.com/egor3f/css v0.0.0-20250507004805-bfefe22b74a4 h1:hDS4GEOnI8sYW2BqAzN9EA9Ks/3yOQGhOoO4/sjpDzw= +github.com/egor3f/css v0.0.0-20250507004805-bfefe22b74a4/go.mod h1:sVSdL+MFR9Q4cKJMQzpIkHIDOLiK+7Wmjjhq7D+MubA= github.com/elliotchance/pie/v2 v2.7.0 h1:FqoIKg4uj0G/CrLGuMS9ejnFKa92lxE1dEgBD3pShXg= github.com/elliotchance/pie/v2 v2.7.0/go.mod h1:18t0dgGFH006g4eVdDtWfgFZPQEgl10IoEO8YWEq3Og= github.com/fatih/color v1.7.0/go.mod h1:Zm6kSWBoL9eyXnKyktHP6abPY2pDugNf5KwzbycvMj4= @@ -115,6 +115,8 @@ github.com/go-kit/kit v0.8.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2 github.com/go-kit/kit v0.9.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as= github.com/go-logfmt/logfmt v0.3.0/go.mod h1:Qt1PoO58o5twSAckw1HlFXLmHsOX5/0LbT9GBnD5lWE= github.com/go-logfmt/logfmt v0.4.0/go.mod h1:3RMwSq7FuexP4Kalkev3ejPJsZTpXXBr9+V4qmtdjCk= +github.com/go-ole/go-ole v1.2.6 h1:/Fpf6oFPoeFik9ty7siob0G6Ke8QvQEuVcuChpwXzpY= +github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0= github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s= github.com/go-playground/assert/v2 v2.2.0/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4= github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA= @@ -264,6 +266,8 @@ github.com/leodido/go-urn v1.4.0 h1:WT9HwE9SGECu3lg4d/dIA+jxlljEa1/ffXKmRjqdmIQ= github.com/leodido/go-urn v1.4.0/go.mod h1:bvxc+MVxLKB4z00jd1z+Dvzr47oO32F/QSNjSBOlFxI= github.com/lib/pq v1.10.9 h1:YXG7RB+JIjhP29X+OtkiDnYaXQwpS4JEWq7dtCCRUEw= github.com/lib/pq v1.10.9/go.mod h1:AlVN5x4E4T544tWzH6hKfbfQvm3HdbOxrmggDNAPY9o= +github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0 h1:6E+4a0GO5zZEnZ81pIr0yLvtUWk2if982qA3F3QD6H4= +github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0/go.mod h1:zJYVVT2jmtg6P3p1VtQj7WsuWi/y4VnjVBn7F8KPB3I= github.com/lyft/protoc-gen-star/v2 v2.0.3/go.mod h1:amey7yeodaJhXSbf/TlLvWiqQfLOSpEk//mLlc+axEk= github.com/magefile/mage v1.14.0 h1:6QDX3g6z1YvJ4olPhT1wksUcSa/V0a1B+pJb73fBjyo= github.com/magefile/mage v1.14.0/go.mod h1:z5UZb/iS3GoOSn0JgWuiw7dxlurVYTu+/jHXqQg881A= @@ -288,7 +292,6 @@ github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5 github.com/mennanov/limiters v1.11.0 h1:nTv4uSl3EAc+2fO4B3LXfxkcQe58LeKF9vmwIa3m6Lo= github.com/mennanov/limiters v1.11.0/go.mod h1:NFf49GLfiywZ4DFkqK9Ne7e+Ckwl1q0eSU+ALwSAxBk= github.com/miekg/dns v1.1.26/go.mod h1:bPDLeHnStXmXAq1m/Ch/hvfNHr14JKNPMBo3VZKjuso= -github.com/miekg/dns v1.1.41 h1:WMszZWJG0XmzbK9FEmzH2TVcqYzFesusSIB41b8KHxY= github.com/miekg/dns v1.1.41/go.mod h1:p6aan82bvRIyn+zDIv9xYNUpwa73JcSh9BKwknJysuI= github.com/miekg/dns v1.1.61 h1:nLxbwF3XxhwVSm8g9Dghm9MHPaUZuqhPiGL+675ZmEs= github.com/miekg/dns v1.1.61/go.mod h1:mnAarhS3nWaW+NVP2wTkYVIZyHNJ098SJZUki3eykwQ= @@ -337,6 +340,8 @@ github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRI github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/posener/complete v1.1.1/go.mod h1:em0nMJCgc9GFtwrmVmEMR/ZL6WyhyjMBndrE9hABlRI= github.com/posener/complete v1.2.3/go.mod h1:WZIdtGGp+qx0sLrYKtIRAruyNpv6hFCicSgv7Sy7s/s= +github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c h1:ncq/mPwQF4JjgDlrVEn3C11VoGHZN7m8qihwgMEtzYw= +github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c/go.mod h1:OmDBASR4679mdNQnz2pUhc2G8CO2JrUAVFDRBDP/hJE= github.com/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw= github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5FsnadC4Ky3P0J6CfImo= github.com/prometheus/client_golang v1.4.0/go.mod h1:e9GMxYsXl05ICDXkRhurwBS4Q3OK1iX/F2sw+iXX5zU= @@ -358,6 +363,10 @@ github.com/samuel/go-zookeeper v0.0.0-20201211165307-7117e9ea2414 h1:AJNDS0kP60X github.com/samuel/go-zookeeper v0.0.0-20201211165307-7117e9ea2414/go.mod h1:gi+0XIa01GRL2eRQVjQkKGqKF3SF9vZR/HnPullcV2E= github.com/sean-/seed v0.0.0-20170313163322-e2103e2c3529 h1:nn5Wsu0esKSJiIVhscUtVbo7ada43DJhG55ua/hjS5I= github.com/sean-/seed v0.0.0-20170313163322-e2103e2c3529/go.mod h1:DxrIzT+xaE7yg65j358z/aeFdxmN0P9QXhEzd20vsDc= +github.com/shirou/gopsutil/v3 v3.24.5 h1:i0t8kL+kQTvpAYToeuiVk3TgDeKOFioZO3Ztz/iZ9pI= +github.com/shirou/gopsutil/v3 v3.24.5/go.mod h1:bsoOS1aStSs9ErQ1WWfxllSeS1K5D+U30r2NfcubMVk= +github.com/shoenig/go-m1cpu v0.1.6 h1:nxdKQNcEB6vzgA2E2bvzKIYRuNj7XNJ4S/aRSwKzFtM= +github.com/shoenig/go-m1cpu v0.1.6/go.mod h1:1JJMcUBvfNwpq05QDQVAnx3gUHr9IYF7GNg9SUEw2VQ= github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo= github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE= github.com/spf13/afero v1.3.3/go.mod h1:5KUK8ByomD5Ti5Artl0RtHeI5pTF7MIDuXL3yY520V4= @@ -388,6 +397,10 @@ github.com/tetratelabs/wazero v1.2.1 h1:J4X2hrGzJvt+wqltuvcSjHQ7ujQxA9gb6PeMs4ql github.com/tetratelabs/wazero v1.2.1/go.mod h1:wYx2gNRg8/WihJfSDxA1TIL8H+GkfLYm+bIfbblu9VQ= github.com/thanhpk/randstr v1.0.4 h1:IN78qu/bR+My+gHCvMEXhR/i5oriVHcTB/BJJIRTsNo= github.com/thanhpk/randstr v1.0.4/go.mod h1:M/H2P1eNLZzlDwAzpkkkUvoyNNMbzRGhESZuEQk3r0U= +github.com/tklauser/go-sysconf v0.3.12 h1:0QaGUFOdQaIVdPgfITYzaTegZvdCjmYO52cSFAEVmqU= +github.com/tklauser/go-sysconf v0.3.12/go.mod h1:Ho14jnntGE1fpdOqQEEaiKRpvIavV0hSfmBq8nJbHYI= +github.com/tklauser/numcpus v0.6.1 h1:ng9scYS7az0Bk4OZLvrNXNSAO2Pxr1XXRAPyjhIx+Fk= +github.com/tklauser/numcpus v0.6.1/go.mod h1:1XfjsgE2zo8GVw7POkMbHENHzVg3GzmoZ9fESEdAacY= github.com/tv42/httpunix v0.0.0-20150427012821-b75d8614f926/go.mod h1:9ESjWnEqriFuLhtthL60Sar/7RFoluCcXsuvEwTV5KM= github.com/valyala/bytebufferpool v1.0.0 h1:GqA5TC/0021Y/b9FG4Oi9Mr3q7XYx6KllzawFIhcdPw= github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc= @@ -400,6 +413,8 @@ github.com/wasilibs/nottinygc v0.4.0/go.mod h1:oDcIotskuYNMpqMF23l7Z8uzD4TC0WXHK github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74= github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74= 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.etcd.io/etcd/api/v3 v3.5.17 h1:cQB8eb8bxwuxOilBpMJAEo8fAONyrdXTHUNcMd8yT1w= go.etcd.io/etcd/api/v3 v3.5.17/go.mod h1:d1hvkRuXkts6PmaYk2Vrgqbv7H4ADfAKhyJqHNLJCB4= go.etcd.io/etcd/client/pkg/v3 v3.5.17 h1:XxnDXAWq2pnxqx76ljWwiQ9jylbpC4rvkAeRVOUKKVw= @@ -424,8 +439,6 @@ golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5y golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU= golang.org/x/crypto v0.32.0 h1:euUpcYgM8WcP71gNpTqQCn6rC2t6ULUPiOzfWaXVVfc= golang.org/x/crypto v0.32.0/go.mod h1:ZnnJkOaASj8g0AjIduWNlq2NRxL0PlBrbKVyZ6V/Ugc= -golang.org/x/exp v0.0.0-20230817173708-d852ddb80c63 h1:m64FZMko/V45gv0bNmrNYoDEq8U5YUhetc9cBWKS1TQ= -golang.org/x/exp v0.0.0-20230817173708-d852ddb80c63/go.mod h1:0v4NqG35kSWCMzLaMeX+IQrlSnVE/bqGSyC2cz/9Le8= golang.org/x/exp v0.0.0-20240909161429-701f63a606c0 h1:e66Fs6Z+fZTbFBAxKfP3PALWBtpfqks2bwGcexMxgtk= golang.org/x/exp v0.0.0-20240909161429-701f63a606c0/go.mod h1:2TbTHSBQa924w8M6Xs1QcRcFwyucIwBGpK1p2f1YFFY= golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA= diff --git a/internal/api/http/pb/specs.pb.go b/internal/api/http/pb/specs.pb.go index 554a6cb..9efede8 100644 --- a/internal/api/http/pb/specs.pb.go +++ b/internal/api/http/pb/specs.pb.go @@ -75,7 +75,7 @@ type Specs struct { SelectorTitle string `protobuf:"bytes,3,opt,name=selector_title,json=selectorTitle,proto3" json:"selector_title" validate:"selector"` SelectorLink string `protobuf:"bytes,4,opt,name=selector_link,json=selectorLink,proto3" json:"selector_link" validate:"selector"` SelectorDescription string `protobuf:"bytes,5,opt,name=selector_description,json=selectorDescription,proto3" json:"selector_description" validate:"omitempty,selector"` - SelectorAuthor string `protobuf:"bytes,6,opt,name=selector_author,json=selectorAuthor,proto3" json:"selector_author" validate:"selector"` + SelectorAuthor string `protobuf:"bytes,6,opt,name=selector_author,json=selectorAuthor,proto3" json:"selector_author" validate:"omitempty,selector"` SelectorCreated string `protobuf:"bytes,7,opt,name=selector_created,json=selectorCreated,proto3" json:"selector_created" validate:"selector"` CreatedExtractFrom ExtractFrom `protobuf:"varint,11,opt,name=created_extract_from,json=createdExtractFrom,proto3,enum=rssalchemy.ExtractFrom" json:"created_extract_from"` CreatedAttributeName string `protobuf:"bytes,12,opt,name=created_attribute_name,json=createdAttributeName,proto3" json:"created_attribute_name"` @@ -206,7 +206,7 @@ var file_proto_specs_proto_rawDesc = string([]byte{ 0x0a, 0x11, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x2f, 0x73, 0x70, 0x65, 0x63, 0x73, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x12, 0x0a, 0x72, 0x73, 0x73, 0x61, 0x6c, 0x63, 0x68, 0x65, 0x6d, 0x79, 0x1a, 0x13, 0x74, 0x61, 0x67, 0x67, 0x65, 0x72, 0x2f, 0x74, 0x61, 0x67, 0x67, 0x65, 0x72, 0x2e, 0x70, - 0x72, 0x6f, 0x74, 0x6f, 0x22, 0xb6, 0x08, 0x0a, 0x05, 0x53, 0x70, 0x65, 0x63, 0x73, 0x12, 0x30, + 0x72, 0x6f, 0x74, 0x6f, 0x22, 0xc0, 0x08, 0x0a, 0x05, 0x53, 0x70, 0x65, 0x63, 0x73, 0x12, 0x30, 0x0a, 0x03, 0x75, 0x72, 0x6c, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x42, 0x1e, 0x9a, 0x84, 0x9e, 0x03, 0x19, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x75, 0x72, 0x6c, 0x22, 0x20, 0x76, 0x61, 0x6c, 0x69, 0x64, 0x61, 0x74, 0x65, 0x3a, 0x22, 0x75, 0x72, 0x6c, 0x22, 0x52, 0x03, 0x75, 0x72, 0x6c, @@ -233,52 +233,53 @@ var file_proto_specs_proto_rawDesc = string([]byte{ 0x76, 0x61, 0x6c, 0x69, 0x64, 0x61, 0x74, 0x65, 0x3a, 0x22, 0x6f, 0x6d, 0x69, 0x74, 0x65, 0x6d, 0x70, 0x74, 0x79, 0x2c, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x22, 0x52, 0x13, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x44, 0x65, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x69, - 0x6f, 0x6e, 0x12, 0x58, 0x0a, 0x0f, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x61, - 0x75, 0x74, 0x68, 0x6f, 0x72, 0x18, 0x06, 0x20, 0x01, 0x28, 0x09, 0x42, 0x2f, 0x9a, 0x84, 0x9e, - 0x03, 0x2a, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, + 0x6f, 0x6e, 0x12, 0x62, 0x0a, 0x0f, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x61, + 0x75, 0x74, 0x68, 0x6f, 0x72, 0x18, 0x06, 0x20, 0x01, 0x28, 0x09, 0x42, 0x39, 0x9a, 0x84, 0x9e, + 0x03, 0x34, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x61, 0x75, 0x74, 0x68, 0x6f, 0x72, 0x22, 0x20, 0x76, 0x61, 0x6c, 0x69, 0x64, 0x61, 0x74, - 0x65, 0x3a, 0x22, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x22, 0x52, 0x0e, 0x73, 0x65, - 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x41, 0x75, 0x74, 0x68, 0x6f, 0x72, 0x12, 0x5b, 0x0a, 0x10, - 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x63, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, - 0x18, 0x07, 0x20, 0x01, 0x28, 0x09, 0x42, 0x30, 0x9a, 0x84, 0x9e, 0x03, 0x2b, 0x6a, 0x73, 0x6f, - 0x6e, 0x3a, 0x22, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x63, 0x72, 0x65, 0x61, - 0x74, 0x65, 0x64, 0x22, 0x20, 0x76, 0x61, 0x6c, 0x69, 0x64, 0x61, 0x74, 0x65, 0x3a, 0x22, 0x73, - 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x22, 0x52, 0x0f, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, - 0x6f, 0x72, 0x43, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x12, 0x6b, 0x0a, 0x14, 0x63, 0x72, 0x65, - 0x61, 0x74, 0x65, 0x64, 0x5f, 0x65, 0x78, 0x74, 0x72, 0x61, 0x63, 0x74, 0x5f, 0x66, 0x72, 0x6f, - 0x6d, 0x18, 0x0b, 0x20, 0x01, 0x28, 0x0e, 0x32, 0x17, 0x2e, 0x72, 0x73, 0x73, 0x61, 0x6c, 0x63, - 0x68, 0x65, 0x6d, 0x79, 0x2e, 0x45, 0x78, 0x74, 0x72, 0x61, 0x63, 0x74, 0x46, 0x72, 0x6f, 0x6d, - 0x42, 0x20, 0x9a, 0x84, 0x9e, 0x03, 0x1b, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x63, 0x72, 0x65, - 0x61, 0x74, 0x65, 0x64, 0x5f, 0x65, 0x78, 0x74, 0x72, 0x61, 0x63, 0x74, 0x5f, 0x66, 0x72, 0x6f, - 0x6d, 0x22, 0x52, 0x12, 0x63, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x45, 0x78, 0x74, 0x72, 0x61, - 0x63, 0x74, 0x46, 0x72, 0x6f, 0x6d, 0x12, 0x58, 0x0a, 0x16, 0x63, 0x72, 0x65, 0x61, 0x74, 0x65, - 0x64, 0x5f, 0x61, 0x74, 0x74, 0x72, 0x69, 0x62, 0x75, 0x74, 0x65, 0x5f, 0x6e, 0x61, 0x6d, 0x65, - 0x18, 0x0c, 0x20, 0x01, 0x28, 0x09, 0x42, 0x22, 0x9a, 0x84, 0x9e, 0x03, 0x1d, 0x6a, 0x73, 0x6f, - 0x6e, 0x3a, 0x22, 0x63, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x5f, 0x61, 0x74, 0x74, 0x72, 0x69, - 0x62, 0x75, 0x74, 0x65, 0x5f, 0x6e, 0x61, 0x6d, 0x65, 0x22, 0x52, 0x14, 0x63, 0x72, 0x65, 0x61, - 0x74, 0x65, 0x64, 0x41, 0x74, 0x74, 0x72, 0x69, 0x62, 0x75, 0x74, 0x65, 0x4e, 0x61, 0x6d, 0x65, - 0x12, 0x65, 0x0a, 0x10, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x63, 0x6f, 0x6e, - 0x74, 0x65, 0x6e, 0x74, 0x18, 0x08, 0x20, 0x01, 0x28, 0x09, 0x42, 0x3a, 0x9a, 0x84, 0x9e, 0x03, - 0x35, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, - 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x22, 0x20, 0x76, 0x61, 0x6c, 0x69, 0x64, 0x61, 0x74, 0x65, 0x3a, 0x22, 0x6f, 0x6d, 0x69, 0x74, 0x65, 0x6d, 0x70, 0x74, 0x79, 0x2c, 0x73, 0x65, 0x6c, - 0x65, 0x63, 0x74, 0x6f, 0x72, 0x22, 0x52, 0x0f, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, - 0x43, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x12, 0x61, 0x0a, 0x12, 0x73, 0x65, 0x6c, 0x65, 0x63, - 0x74, 0x6f, 0x72, 0x5f, 0x65, 0x6e, 0x63, 0x6c, 0x6f, 0x73, 0x75, 0x72, 0x65, 0x18, 0x09, 0x20, - 0x01, 0x28, 0x09, 0x42, 0x32, 0x9a, 0x84, 0x9e, 0x03, 0x2d, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, - 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x65, 0x6e, 0x63, 0x6c, 0x6f, 0x73, 0x75, - 0x72, 0x65, 0x22, 0x20, 0x76, 0x61, 0x6c, 0x69, 0x64, 0x61, 0x74, 0x65, 0x3a, 0x22, 0x73, 0x65, - 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x22, 0x52, 0x11, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, - 0x72, 0x45, 0x6e, 0x63, 0x6c, 0x6f, 0x73, 0x75, 0x72, 0x65, 0x12, 0x41, 0x0a, 0x0e, 0x63, 0x61, - 0x63, 0x68, 0x65, 0x5f, 0x6c, 0x69, 0x66, 0x65, 0x74, 0x69, 0x6d, 0x65, 0x18, 0x0a, 0x20, 0x01, - 0x28, 0x09, 0x42, 0x1a, 0x9a, 0x84, 0x9e, 0x03, 0x15, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x63, - 0x61, 0x63, 0x68, 0x65, 0x5f, 0x6c, 0x69, 0x66, 0x65, 0x74, 0x69, 0x6d, 0x65, 0x22, 0x52, 0x0d, - 0x63, 0x61, 0x63, 0x68, 0x65, 0x4c, 0x69, 0x66, 0x65, 0x74, 0x69, 0x6d, 0x65, 0x2a, 0x2b, 0x0a, - 0x0b, 0x45, 0x78, 0x74, 0x72, 0x61, 0x63, 0x74, 0x46, 0x72, 0x6f, 0x6d, 0x12, 0x0d, 0x0a, 0x09, - 0x49, 0x6e, 0x6e, 0x65, 0x72, 0x54, 0x65, 0x78, 0x74, 0x10, 0x00, 0x12, 0x0d, 0x0a, 0x09, 0x41, - 0x74, 0x74, 0x72, 0x69, 0x62, 0x75, 0x74, 0x65, 0x10, 0x01, 0x42, 0x16, 0x5a, 0x14, 0x69, 0x6e, - 0x74, 0x65, 0x72, 0x6e, 0x61, 0x6c, 0x2f, 0x61, 0x70, 0x69, 0x2f, 0x68, 0x74, 0x74, 0x70, 0x2f, - 0x70, 0x62, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x33, + 0x65, 0x63, 0x74, 0x6f, 0x72, 0x22, 0x52, 0x0e, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, + 0x41, 0x75, 0x74, 0x68, 0x6f, 0x72, 0x12, 0x5b, 0x0a, 0x10, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, + 0x6f, 0x72, 0x5f, 0x63, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x18, 0x07, 0x20, 0x01, 0x28, 0x09, + 0x42, 0x30, 0x9a, 0x84, 0x9e, 0x03, 0x2b, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x73, 0x65, 0x6c, + 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x63, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x22, 0x20, 0x76, + 0x61, 0x6c, 0x69, 0x64, 0x61, 0x74, 0x65, 0x3a, 0x22, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, + 0x72, 0x22, 0x52, 0x0f, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x43, 0x72, 0x65, 0x61, + 0x74, 0x65, 0x64, 0x12, 0x6b, 0x0a, 0x14, 0x63, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x5f, 0x65, + 0x78, 0x74, 0x72, 0x61, 0x63, 0x74, 0x5f, 0x66, 0x72, 0x6f, 0x6d, 0x18, 0x0b, 0x20, 0x01, 0x28, + 0x0e, 0x32, 0x17, 0x2e, 0x72, 0x73, 0x73, 0x61, 0x6c, 0x63, 0x68, 0x65, 0x6d, 0x79, 0x2e, 0x45, + 0x78, 0x74, 0x72, 0x61, 0x63, 0x74, 0x46, 0x72, 0x6f, 0x6d, 0x42, 0x20, 0x9a, 0x84, 0x9e, 0x03, + 0x1b, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x63, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x5f, 0x65, + 0x78, 0x74, 0x72, 0x61, 0x63, 0x74, 0x5f, 0x66, 0x72, 0x6f, 0x6d, 0x22, 0x52, 0x12, 0x63, 0x72, + 0x65, 0x61, 0x74, 0x65, 0x64, 0x45, 0x78, 0x74, 0x72, 0x61, 0x63, 0x74, 0x46, 0x72, 0x6f, 0x6d, + 0x12, 0x58, 0x0a, 0x16, 0x63, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x5f, 0x61, 0x74, 0x74, 0x72, + 0x69, 0x62, 0x75, 0x74, 0x65, 0x5f, 0x6e, 0x61, 0x6d, 0x65, 0x18, 0x0c, 0x20, 0x01, 0x28, 0x09, + 0x42, 0x22, 0x9a, 0x84, 0x9e, 0x03, 0x1d, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x63, 0x72, 0x65, + 0x61, 0x74, 0x65, 0x64, 0x5f, 0x61, 0x74, 0x74, 0x72, 0x69, 0x62, 0x75, 0x74, 0x65, 0x5f, 0x6e, + 0x61, 0x6d, 0x65, 0x22, 0x52, 0x14, 0x63, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x41, 0x74, 0x74, + 0x72, 0x69, 0x62, 0x75, 0x74, 0x65, 0x4e, 0x61, 0x6d, 0x65, 0x12, 0x65, 0x0a, 0x10, 0x73, 0x65, + 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x18, 0x08, + 0x20, 0x01, 0x28, 0x09, 0x42, 0x3a, 0x9a, 0x84, 0x9e, 0x03, 0x35, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, + 0x22, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, + 0x74, 0x22, 0x20, 0x76, 0x61, 0x6c, 0x69, 0x64, 0x61, 0x74, 0x65, 0x3a, 0x22, 0x6f, 0x6d, 0x69, + 0x74, 0x65, 0x6d, 0x70, 0x74, 0x79, 0x2c, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x22, + 0x52, 0x0f, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x43, 0x6f, 0x6e, 0x74, 0x65, 0x6e, + 0x74, 0x12, 0x61, 0x0a, 0x12, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x5f, 0x65, 0x6e, + 0x63, 0x6c, 0x6f, 0x73, 0x75, 0x72, 0x65, 0x18, 0x09, 0x20, 0x01, 0x28, 0x09, 0x42, 0x32, 0x9a, + 0x84, 0x9e, 0x03, 0x2d, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, + 0x6f, 0x72, 0x5f, 0x65, 0x6e, 0x63, 0x6c, 0x6f, 0x73, 0x75, 0x72, 0x65, 0x22, 0x20, 0x76, 0x61, + 0x6c, 0x69, 0x64, 0x61, 0x74, 0x65, 0x3a, 0x22, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, + 0x22, 0x52, 0x11, 0x73, 0x65, 0x6c, 0x65, 0x63, 0x74, 0x6f, 0x72, 0x45, 0x6e, 0x63, 0x6c, 0x6f, + 0x73, 0x75, 0x72, 0x65, 0x12, 0x41, 0x0a, 0x0e, 0x63, 0x61, 0x63, 0x68, 0x65, 0x5f, 0x6c, 0x69, + 0x66, 0x65, 0x74, 0x69, 0x6d, 0x65, 0x18, 0x0a, 0x20, 0x01, 0x28, 0x09, 0x42, 0x1a, 0x9a, 0x84, + 0x9e, 0x03, 0x15, 0x6a, 0x73, 0x6f, 0x6e, 0x3a, 0x22, 0x63, 0x61, 0x63, 0x68, 0x65, 0x5f, 0x6c, + 0x69, 0x66, 0x65, 0x74, 0x69, 0x6d, 0x65, 0x22, 0x52, 0x0d, 0x63, 0x61, 0x63, 0x68, 0x65, 0x4c, + 0x69, 0x66, 0x65, 0x74, 0x69, 0x6d, 0x65, 0x2a, 0x2b, 0x0a, 0x0b, 0x45, 0x78, 0x74, 0x72, 0x61, + 0x63, 0x74, 0x46, 0x72, 0x6f, 0x6d, 0x12, 0x0d, 0x0a, 0x09, 0x49, 0x6e, 0x6e, 0x65, 0x72, 0x54, + 0x65, 0x78, 0x74, 0x10, 0x00, 0x12, 0x0d, 0x0a, 0x09, 0x41, 0x74, 0x74, 0x72, 0x69, 0x62, 0x75, + 0x74, 0x65, 0x10, 0x01, 0x42, 0x16, 0x5a, 0x14, 0x69, 0x6e, 0x74, 0x65, 0x72, 0x6e, 0x61, 0x6c, + 0x2f, 0x61, 0x70, 0x69, 0x2f, 0x68, 0x74, 0x74, 0x70, 0x2f, 0x70, 0x62, 0x62, 0x06, 0x70, 0x72, + 0x6f, 0x74, 0x6f, 0x33, }) var ( diff --git a/internal/extractors/pwextractor/pageparser.go b/internal/extractors/pwextractor/pageparser.go index b2c9a53..425f7ce 100644 --- a/internal/extractors/pwextractor/pageparser.go +++ b/internal/extractors/pwextractor/pageparser.go @@ -103,10 +103,11 @@ func (p *pageParser) extractPost(post playwright.Locator) (models.FeedItem, erro item.Description = newLocator(post, p.task.SelectorDescription).First().InnerText() } - item.AuthorName = newLocator(post, p.task.SelectorAuthor).First().InnerText() - - item.AuthorLink = newLocator(post, p.task.SelectorAuthor).First().GetAttribute("href") - item.AuthorLink = absUrl(item.AuthorLink, page) + if len(p.task.SelectorAuthor) > 0 { + item.AuthorName = newLocator(post, p.task.SelectorAuthor).First().InnerText() + item.AuthorLink = newLocator(post, p.task.SelectorAuthor).First().GetAttribute("href") + item.AuthorLink = absUrl(item.AuthorLink, page) + } if len(p.task.SelectorContent) > 0 { item.Content = p.extractContent(post) diff --git a/proto/specs.proto b/proto/specs.proto index 29dc311..a48f477 100644 --- a/proto/specs.proto +++ b/proto/specs.proto @@ -17,7 +17,7 @@ message Specs { string selector_title = 3 [(tagger.tags) = "json:\"selector_title\" validate:\"selector\""]; string selector_link = 4 [(tagger.tags) = "json:\"selector_link\" validate:\"selector\""]; string selector_description = 5 [(tagger.tags) = "json:\"selector_description\" validate:\"omitempty,selector\""]; - string selector_author = 6 [(tagger.tags) = "json:\"selector_author\" validate:\"selector\""]; + string selector_author = 6 [(tagger.tags) = "json:\"selector_author\" validate:\"omitempty,selector\""]; string selector_created = 7 [(tagger.tags) = "json:\"selector_created\" validate:\"selector\""]; ExtractFrom created_extract_from = 11 [(tagger.tags) = "json:\"created_extract_from\""];