From a8c253bdd5ecad4dd8c60271ea59ff599440e9f1 Mon Sep 17 00:00:00 2001 From: Elshimy Ziad Magdy Taha Date: Tue, 16 Dec 2025 17:19:44 +0500 Subject: [PATCH] used lever instead of greenhouse temporarily --- go.work | 1 + go.work.sum | 105 +++++--------- internal/pkg/domain/google-link.go | 1 - internal/pkg/gemini/gemini.go | 114 +++++++++++++++ internal/pkg/gemini/go.mod | 24 ++++ internal/pkg/gemini/go.sum | 120 ++++++++++++++++ internal/pkg/openrouter/openrouter.go | 50 ++----- libs/repo/job.go | 52 +++++-- services/api/go.mod | 8 +- services/api/go.sum | 21 +-- services/scraper-google/.env | 3 +- .../analyzer/get-job-description.go | 22 +-- services/scraper-google/go.mod | 11 +- services/scraper-google/go.sum | 40 +++++- services/scraper-google/main.go | 135 +++++++++++++++--- services/scraper-google/utils/get-html-raw.go | 135 +++++++++++++++--- services/scraper-google/utils/network.go | 45 ++++++ services/scraper-google/work.go | 30 +--- 18 files changed, 701 insertions(+), 216 deletions(-) create mode 100644 internal/pkg/gemini/gemini.go create mode 100644 internal/pkg/gemini/go.mod create mode 100644 internal/pkg/gemini/go.sum create mode 100644 services/scraper-google/utils/network.go diff --git a/go.work b/go.work index e8ae214..998a0ea 100644 --- a/go.work +++ b/go.work @@ -4,6 +4,7 @@ use ( . ./apps/cron-analyzer ./internal/pkg/domain + ./internal/pkg/gemini ./internal/pkg/infrastructure ./internal/pkg/openai ./internal/pkg/openrouter diff --git a/go.work.sum b/go.work.sum index e430d1b..af7ee3a 100644 --- a/go.work.sum +++ b/go.work.sum @@ -1,10 +1,15 @@ cel.dev/expr v0.16.0/go.mod h1:TRSuuV7DlVCE/uwv5QbAiW/v8l5O8C4eEPHeu7gf7Sg= cloud.google.com/go v0.112.1/go.mod h1:+Vbu+Y1UU+I1rjmzeMOb/8RfkKJK2Gyxi1X6jJCZLo4= -cloud.google.com/go/compute/metadata v0.5.0/go.mod h1:aHnloV2TPI38yx4s9+wAZhHykWvVCfu7hQbF+9CWoiY= +cloud.google.com/go/auth/oauth2adapt v0.2.4/go.mod h1:jC/jOpwFP6JBxhB3P5Rr0a9HLMC/Pe3eaL4NmdvqPtc= +cloud.google.com/go/compute/metadata v0.3.0/go.mod h1:zFmK7XCadkQkj6TtorcaGlCW1hT1fIilQDwofLpJ20k= cloud.google.com/go/iam v1.1.6/go.mod h1:O0zxdPeGBoFdWW3HWmBxJsk0pfvNM/p/qa82rWOGTwI= +cloud.google.com/go/iam v1.2.0/go.mod h1:zITGuWgsLZxd8OwAlX+eMFgZDXzBm7icj1PVTYG766Q= cloud.google.com/go/longrunning v0.5.5/go.mod h1:WV2LAxD8/rg5Z1cNW6FJ/ZpX4E4VnDnoTk0yawPBB7s= +cloud.google.com/go/longrunning v0.5.6/go.mod h1:vUaDrWYOMKRuhiv6JBnn49YxCPz2Ayn9GqyjaBT8/mA= cloud.google.com/go/spanner v1.56.0/go.mod h1:DndqtUKQAt3VLuV2Le+9Y3WTnq5cNKrnLb/Piqcj+h0= cloud.google.com/go/storage v1.38.0/go.mod h1:tlUADB0mAb9BgYls9lq+8MGkfzOXuLrnHXlpHmvFJoY= +cloud.google.com/go/storage v1.43.0/go.mod h1:ajvxEa7WmZS1PxvKRq4bq0tFT3vMd502JwstCcYv0Q0= +cloud.google.com/go/translate v1.10.3/go.mod h1:GW0vC1qvPtd3pgtypCv4k4U8B7EdgK9/QEF2aJEUovs= github.com/99designs/go-keychain v0.0.0-20191008050251-8e49817e8af4/go.mod h1:hN7oaIRCjzsZ2dE+yG5k+rsdt3qcwykqK6HVGcKwsw4= github.com/99designs/keyring v1.2.1/go.mod h1:fc+wB5KTk9wQ9sDx0kFXB3A0MaeGHM9AwRStKOQ5vOA= github.com/Azure/azure-sdk-for-go/sdk/azcore v1.4.0/go.mod h1:ON4tFdPTwRcgWEaVDrN3584Ef+b7GgSJaXxe5fW9t4M= @@ -16,11 +21,9 @@ github.com/Azure/go-autorest/autorest/date v0.3.0/go.mod h1:BI0uouVdmngYNUzGWeSY github.com/Azure/go-autorest/logger v0.2.1/go.mod h1:T9E3cAhj2VqvPOtCYAvby9aBXkZmbF5NWuPV8+WeEW8= github.com/Azure/go-autorest/tracing v0.6.0/go.mod h1:+vhtPC754Xsa23ID7GlGsrdKBpUA79WCAKPPZVC2DeU= github.com/ClickHouse/clickhouse-go v1.4.3/go.mod h1:EaI/sW7Azgz9UATzd5ZdZHRUhHgv5+JMS9NSr2smCJI= -github.com/PuerkitoBio/goquery v1.10.3/go.mod h1:tMUX0zDMHXYlAQk6p35XxQMqMweEKB7iK7iLNd4RH4Y= github.com/PuerkitoBio/purell v1.1.1/go.mod h1:c11w/QuzBsJSee3cPx9rAFu61PvFxuPbtSwDGJws/X0= github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578/go.mod h1:uGdkoq3SwY9Y+13GIhn11/XLaGBb4BfwItxLd5jeuXE= github.com/andybalholm/brotli v1.0.4/go.mod h1:fO7iG3H7G2nSZ7m0zPUDn85XEX2GTukHGRSepvi9Eig= -github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA= github.com/apache/arrow/go/v10 v10.0.1/go.mod h1:YvhnlEePVnBS4+0z3fhPfUy7W1Ikj0Ih0vcRo/gZ1M0= github.com/apache/thrift v0.16.0/go.mod h1:PHK3hniurgQaNMZYaCLEqXKsYK8upmhPbmdP2FXSqgU= github.com/aws/aws-sdk-go v1.49.6/go.mod h1:LF8svs817+Nz+DmiMQKTO3ubZ/6IaTpq3TjupRn3Eqk= @@ -48,6 +51,7 @@ github.com/cznic/mathutil v0.0.0-20180504122225-ca4c9f2c1369/go.mod h1:e6NPNENfs github.com/danieljoos/wincred v1.1.2/go.mod h1:GijpziifJoIBfYh+S7BbkdUTU4LfM+QnGqR5Vl2tAx0= github.com/dvsekhvalnov/jose2go v1.6.0/go.mod h1:QsHjhyTlD/lAVqn/NSbVZmSCGeDehTB/mPZadG+mhXU= github.com/edsrzf/mmap-go v0.0.0-20170320065105-0bce6a688712/go.mod h1:YO35OhQPt3KJa3ryjFM5Bs14WD66h8eGKpfaBNrHW5M= +github.com/eliben/go-sentencepiece v0.6.0/go.mod h1:nNYk4aMzgBoI6QFp4LUG8Eu1uO9fHD9L5ZEre93o9+c= github.com/envoyproxy/go-control-plane v0.13.0/go.mod h1:GRaKG3dwvFoTg4nj7aXdZnvMg4d7nvT/wl9WgVXn3Q8= github.com/envoyproxy/protoc-gen-validate v1.1.0/go.mod h1:sXRDRVmzEbkM7CVcM06s9shE/m23dg3wzjl0UWqJ2q4= github.com/form3tech-oss/jwt-go v3.2.5+incompatible/go.mod h1:pbq4aXjuKjdthFRnoDwaVPLA+WlJuPGy+QneDUgJi2k= @@ -62,17 +66,20 @@ github.com/godbus/dbus v0.0.0-20190726142602-4481cbc300e2/go.mod h1:bBOAhwG1umN6 github.com/golang-jwt/jwt/v4 v4.5.2/go.mod h1:m21LjoU+eqJr34lmDMbreY2eSTRJ1cv77w39/MY0Ch0= github.com/golang-sql/civil v0.0.0-20190719163853-cb61b32ac6fe/go.mod h1:8vg3r2VgvsThLBIFL93Qb5yWzgyZWhEmBwUJWevAkK0= github.com/golang-sql/sqlexp v0.1.0/go.mod h1:J4ad9Vo8ZCWQ2GMrC4UCQy1JpCbwU9m3EOqtpKwwwHI= -github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc= +github.com/golang/glog v1.2.2/go.mod h1:6AhwSGph0fcJtXVM/PEHPqZlFeoLxhs7/t5UDAwmO+w= github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps= github.com/golang/snappy v0.0.4/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q= github.com/google/flatbuffers v2.0.8+incompatible/go.mod h1:1AeVuKshWv4vARoZatz6mlQ0JxURH0Kv5+zNeJKJCa8= -github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY= +github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY= github.com/google/go-github/v39 v39.2.0/go.mod h1:C1s8C5aCC9L+JXIYpJM5GYytdX52vC1bLvHEF1IhBrE= +github.com/google/go-pkcs11 v0.3.0/go.mod h1:6eQoGcuNJpa7jnd5pMGdkSaQpNDYvPlXWMcjXXThLlY= github.com/google/go-querystring v1.1.0/go.mod h1:Kcdr2DB4koayq7X8pmAG4sNG59So17icRSOU623lUBU= +github.com/google/martian/v3 v3.3.3/go.mod h1:iEPrYcgCF7jA9OtScMFQyAlZZ4YXTKEtJ1E6RWzmBA0= github.com/google/s2a-go v0.1.7/go.mod h1:50CgR4k1jNlWBu4UfS4AcfhVe1r6pdZPygJ3R8F0Qdw= github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= github.com/googleapis/enterprise-certificate-proxy v0.3.2/go.mod h1:VLSiSSBs/ksPL8kq3OBOQ6WRI2QnaFynd1DCjZ62+V0= github.com/googleapis/gax-go/v2 v2.12.2/go.mod h1:61M8vcyyXR2kqKFxKrfA22jaA8JGF7Dc8App1U3H6jc= +github.com/googleapis/gax-go/v2 v2.13.0/go.mod h1:Z/fvTZXF8/uw7Xu5GuslPw+bplx6SS338j1Is2S+B7A= github.com/gorilla/handlers v1.4.2/go.mod h1:Qkdc/uu4tH4g6mTK6auzZ766c4CA0Ng8+o/OAirnOIQ= github.com/gsterjov/go-libsecret v0.0.0-20161001094733-a6f4afe4910c/go.mod h1:NMPJylDgVpX0MLRlPy15sqSwOFv/U1GZ2m21JhFfek0= github.com/hailocab/go-hostpool v0.0.0-20160125115350-e80d13ce29ed/go.mod h1:tMWxXQ9wFIaZeTI9F+hmhFiGpFmhOHzyShyFUhRm0H4= @@ -95,8 +102,8 @@ github.com/kballard/go-shellquote v0.0.0-20180428030007-95032a82bc51/go.mod h1:C github.com/klauspost/asmfmt v1.3.2/go.mod h1:AG8TuvYojzulgDAMCnYn50l/5QV3Bs/tp6j0HLHbNSE= github.com/klauspost/compress v1.15.11/go.mod h1:QPwzmACJjUTFsnSHH934V6woptycfrDDJnH7hvFVbGM= github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg= +github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk= github.com/ktrysmt/go-bitbucket v0.6.4/go.mod h1:9u0v3hsd2rqCHRIpbir1oP7F58uo5dq19sBYvuMoyQ4= -github.com/ledongthuc/pdf v0.0.0-20220302134840-0c2507a12d80/go.mod h1:imJHygn/1yfhB7XSJJKlFZKl/J+dCPAknuiaGOshXAs= github.com/markbates/pkger v0.15.1/go.mod h1:0JoVlrol20BSywW79rN3kdFFsE5xYM+rSCQDXbLhiuI= github.com/mattn/go-colorable v0.1.6/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc= github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM= @@ -114,7 +121,6 @@ github.com/nakagami/firebirdsql v0.0.0-20190310045651-3c02a58cfed8/go.mod h1:86w github.com/neo4j/neo4j-go-driver v1.8.1-0.20200803113522-b626aa943eba/go.mod h1:ncO5VaFWh0Nrt+4KT4mOZboaczBZcLuHrG+/sUeP8gI= github.com/onsi/ginkgo v1.16.4/go.mod h1:dX+/inL/fNMqNlz0e9LfyB9TswhZpCVdJM/Z6Vvnwo0= github.com/onsi/gomega v1.15.0/go.mod h1:cIuvLEne0aoVhAgh/O6ac0Op8WWw9H6eYCriF+tEHG0= -github.com/orisano/pixelmatch v0.0.0-20220722002657-fb0b55479cde/go.mod h1:nZgzbfBr3hhjoZnS66nKrHmduYNpc34ny7RK4z5/HM0= github.com/pierrec/lz4/v4 v4.1.16/go.mod h1:gZWDp/Ze/IJXGXf23ltt2EXimqmTUXEy0GFuRQyBid4= github.com/pkg/browser v0.0.0-20210911075715-681adbf594b8/go.mod h1:HKlIX3XHQyzLZPlr7++PzdhaXEj94dEiJgZDTsxEqUI= github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10/go.mod h1:t/avpk3KcrXxUnYOhZhMXJlSEyie6gQbtLq5NM3loB8= @@ -132,97 +138,52 @@ github.com/xdg-go/pbkdf2 v1.0.0/go.mod h1:jrpuAogTd400dnrH08LKmI/xc1MbPOebTwRqcT github.com/xdg-go/scram v1.1.1/go.mod h1:RaEWvsqvNKKvBPvcKeFjrG2cJqOkHTiyTpzz23ni57g= github.com/xdg-go/stringprep v1.0.3/go.mod h1:W3f5j4i+9rC0kuIEJL0ky1VpHXQU3ocBgklLGvcBnW8= github.com/youmark/pkcs8 v0.0.0-20181117223130-1be2e3e5546d/go.mod h1:rHwXgn7JulP+udvsHwJoVG1YGAP6VLg4y9I5dyZdqmA= -github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY= github.com/zeebo/xxh3 v1.0.2/go.mod h1:5NWz9Sef7zIDm2JHfFlcQvNekmcEl9ekUZQQKCYaDcA= gitlab.com/nyarla/go-crypt v0.0.0-20160106005555-d9a5dc2b789b/go.mod h1:T3BPAOm2cqquPa0MKWeNkmOM5RQsRhkrwMWonFMN7fE= go.mongodb.org/mongo-driver v1.7.5/go.mod h1:VXEWRZ6URJIkUq2SCAyapmhH0ZLRBP+FT4xhp5Zvxng= -go.opencensus.io v0.24.0/go.mod h1:vNK8G9p7aAivkbmorf4v+7Hgx+Zs0yY+0fOtgBfjQKo= go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.49.0/go.mod h1:Mjt1i1INqiaoZOMGR1RIUJN+i3ChKoFRqzrRQhlkbs0= +go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.54.0/go.mod h1:B9yO6b04uB80CzjedvewuqDhxJxi11s7/GtiGa8bAjI= go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.29.0/go.mod h1:jlRVBe7+Z1wyxFSUs48L6OBQZ5JwH2Hg/Vbl+t9rAgI= go.opentelemetry.io/otel/sdk v1.29.0/go.mod h1:pM8Dx5WKnvxLCb+8lG1PRNIDxu9g9b9g59Qr7hfAAok= go.opentelemetry.io/proto/otlp v1.3.1/go.mod h1:0X1WI4de4ZsLrrJNLAQbFeLCm3T7yBkR0XqQ7niQU+8= -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 v0.42.0/go.mod h1:4+rDnOTJhQCx2q7/j6rAN5XDw8kPjeaXEUR2eL94ix8= golang.org/x/exp v0.0.0-20230315142452-642cacee5cc0/go.mod h1:CxIveKay+FTh1D0yPZemJVgC/95VzuuOLq5Qi4xnoYc= -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/mod v0.27.0/go.mod h1:rWI627Fq0DEoudcK+MBkNkCe0EetEaDSwJJkCcjpazc= -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 v0.26.0/go.mod h1:5YKkiSynbBIh3p6iOc/vibscux0x38BZDkn8sCUPxHE= +golang.org/x/net v0.28.0/go.mod h1:yqtgsTWOOnlGLG9GFRrK3++bGOUEkNBoHZc8MEDWPNg= golang.org/x/net v0.43.0/go.mod h1:vhO1fvI4dGsIjh73sWfUVjj3N7CA9WkKJNQm2svM6Jg= +golang.org/x/oauth2 v0.22.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI= golang.org/x/oauth2 v0.27.0/go.mod h1:onh5ek6nERTohokkhCD/y2cV4Do3fxFHFuAejCkRWT8= -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 v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= golang.org/x/sync v0.16.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA= golang.org/x/sync v0.17.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI= -golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= -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/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/sys v0.22.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/sys v0.24.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= golang.org/x/sys v0.35.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k= -golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE= golang.org/x/telemetry v0.0.0-20240521205824-bda55230c457/go.mod h1:pRgIJT+bRLFKnoM1ldnzKoxTIn14Yxz928LQRYYgIN0= golang.org/x/telemetry v0.0.0-20250807160809-1a19826ec488/go.mod h1:fGb/2+tgXXjhjHsTNdVEEMZNWA0quBnfrO+AfoDSAKw= -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 v0.35.0/go.mod h1:TPGtkTLesOwf2DE8CgVYiZinHAOuy5AYUYT1lENIZnA= -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 v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI= +golang.org/x/text v0.17.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY= golang.org/x/text v0.29.0/go.mod h1:7MhJOA9CD2qZyOKYazxdYMF85OwPdEr9jTtBpO7ydH4= golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM= -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/tools v0.36.0 h1:kWS0uv/zsvHEle1LbV5LE8QujrxB3wfQyxHfhOk0Qkg= +golang.org/x/time v0.6.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM= golang.org/x/tools v0.36.0/go.mod h1:WBDiHKJK8YgLHlcQPYQzNCkUxUypCaa5ZegCVutKm+s= -golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028/go.mod h1:NDW/Ps6MPRej6fsCIbMTohpP40sJ/P/vI1MoTEGwX90= google.golang.org/api v0.169.0/go.mod h1:gpNOiMA2tZ4mf5R9Iwf4rK/Dcz0fbdIgWYWVoxmsyLg= +google.golang.org/api v0.197.0/go.mod h1:AuOuo20GoQ331nq7DquGHlU6d+2wN2fZ8O0ta60nRNw= +google.golang.org/appengine v1.6.8/go.mod h1:1jJ3jBArFh5pcgW8gCtRJnepW8FzD1V44FJffLiz/Ds= google.golang.org/genproto v0.0.0-20240213162025-012b6fc9bca9/go.mod h1:mqHbVIp48Muh7Ywss/AD6I5kNVKZMmAa/QEW58Gxp2s= +google.golang.org/genproto v0.0.0-20240903143218-8af14fe29dc1 h1:BulPr26Jqjnd4eYDVe+YvyR7Yc2vJGkO5/0UxD0/jZU= +google.golang.org/genproto v0.0.0-20240903143218-8af14fe29dc1/go.mod h1:hL97c3SYopEHblzpxRL4lSs523++l8DYxGM1FQiYmb4= google.golang.org/genproto/googleapis/api v0.0.0-20240814211410-ddb44dafa142/go.mod h1:d6be+8HhtEtucleCbxpPW9PA9XwISACu8nvpPqF0BVo= -google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU= +google.golang.org/genproto/googleapis/api v0.0.0-20240903143218-8af14fe29dc1/go.mod h1:qpvKtACPCQhAdu3PyQgV4l3LMXZEtft7y8QcarRsp9I= +google.golang.org/genproto/googleapis/rpc v0.0.0-20240814211410-ddb44dafa142/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU= +google.golang.org/genproto/googleapis/rpc v0.0.0-20240827150818-7e3bb234dfed/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU= +google.golang.org/grpc v1.66.0/go.mod h1:s3/l6xSSCURdVfAnL+TqCNMyTDAGN6+lZeVxnZR128Y= google.golang.org/grpc v1.67.0/go.mod h1:1gLDyUQU7CTLJI90u3nXZ9ekeghjeM7pTDZlqFNg2AA= -google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw= +gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q= gopkg.in/inf.v0 v0.9.1/go.mod h1:cWUDdTG/fYaXco+Dcufb5Vnc6Gp2YChqWtbxRZE0mXw= lukechampine.com/uint128 v1.2.0/go.mod h1:c4eWIwlEGaxC/+H1VguhU4PHXNWDCDMUlWdIWl2j1gk= modernc.org/b v1.0.0/go.mod h1:uZWcZfRj1BpYzfN9JTerzlNUnnPsV9O2ZA8JsRcubNg= diff --git a/internal/pkg/domain/google-link.go b/internal/pkg/domain/google-link.go index 3fd9102..e4e792d 100644 --- a/internal/pkg/domain/google-link.go +++ b/internal/pkg/domain/google-link.go @@ -1,7 +1,6 @@ package domain type GoogleLink struct { - ID int64 Title string Description string Link string diff --git a/internal/pkg/gemini/gemini.go b/internal/pkg/gemini/gemini.go new file mode 100644 index 0000000..db1ac6c --- /dev/null +++ b/internal/pkg/gemini/gemini.go @@ -0,0 +1,114 @@ +package gemini + +import ( + "context" + "encoding/json" + "fmt" + "log" + "strings" + + "github.com/jobs-scraper/internal/pkg/domain" + "google.golang.org/genai" +) + +type GeminiService struct { + client *genai.Client + model string +} + +func NewGeminiService(ctx context.Context, key, model string) (*GeminiService, error) { + config := genai.ClientConfig{ + APIKey: key, + } + client, err := genai.NewClient(ctx, &config) + + if err != nil { + return nil, err + } + + return &GeminiService{client: client, model: model}, nil +} + +func (gs *GeminiService) ParseJobData(ctx context.Context, htmlContent string) (*domain.JobDescription, error) { + prompt := fmt.Sprintf(`Extract job posting information from the following HTML content. + +CRITICAL RULES: +1. Return ONLY valid JSON - no markdown, no code blocks, no backticks, no explanations +2. Use SINGLE-LINE JSON (no pretty printing, no newlines inside the JSON) +3. All criteria values MUST be strings (never use booleans, numbers, or arrays) +4. Properly escape all quotes inside strings using \" +5. Use only standard ASCII quotes ("), never smart quotes (" " ' ') + +Required fields: +- description: Full job description as a single string +- criteria: Object with keys like title, company, location, salary, skills, experience, job_type, remote + +Example (SINGLE LINE): +{"description":"Full job description text here...","criteria":{"title":"Software Engineer","location":"City, Country","salary":"$100k-$150k","skills":"Go, Python, Docker","experience":"3-5 years","job_type":"Full-time","remote":"Remote"}} + +HTML Content: +%s`, htmlContent) + response, err := gs.client.Models.GenerateContent( + ctx, + gs.model, + genai.Text(prompt), + nil, + ) + if err != nil { + return &domain.JobDescription{}, err + } + + jsonContent := response.Text() + + log.Printf("Raw API response for job description: %s", jsonContent) + + jsonContent = cleanMarkdownCodeBlocks(jsonContent) + + log.Printf("Cleaned JSON (first 500 chars): %s", jsonContent[:min(500, len(jsonContent))]) + + var result struct { + Description string `json:"description"` + Criteria map[string]string `json:"criteria"` + } + + if err := json.Unmarshal([]byte(jsonContent), &result); err != nil { + if syntaxErr, ok := err.(*json.SyntaxError); ok { + start := int(syntaxErr.Offset) - 50 + if start < 0 { + start = 0 + } + end := int(syntaxErr.Offset) + 50 + if end > len(jsonContent) { + end = len(jsonContent) + } + log.Printf("JSON parse error at position %d, context: ...%s...", syntaxErr.Offset, jsonContent[start:end]) + } + + return nil, fmt.Errorf("failed to parse JSON response: %v. Cleaned JSON length: %d", err, len(jsonContent)) + } + + jobDescription := &domain.JobDescription{ + Description: result.Description, + Criteria: result.Criteria, + } + + return jobDescription, nil +} + +// cleanMarkdownCodeBlocks removes markdown code block formatting from JSON response +func cleanMarkdownCodeBlocks(content string) string { + // Remove ```json prefix and ``` suffix if present + content = strings.TrimSpace(content) + + // Remove opening code block markers + if strings.HasPrefix(content, "```json") { + content = strings.TrimPrefix(content, "```json") + } else if strings.HasPrefix(content, "```") { + content = strings.TrimPrefix(content, "```") + } + + // Remove closing code block markers + content = strings.TrimSuffix(content, "```") + + return strings.TrimSpace(content) +} diff --git a/internal/pkg/gemini/go.mod b/internal/pkg/gemini/go.mod new file mode 100644 index 0000000..0129f29 --- /dev/null +++ b/internal/pkg/gemini/go.mod @@ -0,0 +1,24 @@ +module github.com/jobs-scraper/internal/pkg/gemini + +go 1.24.0 + +require google.golang.org/genai v1.39.0 + +require ( + cloud.google.com/go v0.116.0 // indirect + cloud.google.com/go/auth v0.9.3 // indirect + cloud.google.com/go/compute/metadata v0.5.0 // indirect + github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect + github.com/google/go-cmp v0.6.0 // indirect + github.com/google/s2a-go v0.1.8 // indirect + github.com/googleapis/enterprise-certificate-proxy v0.3.4 // indirect + github.com/gorilla/websocket v1.5.3 // indirect + go.opencensus.io v0.24.0 // indirect + golang.org/x/crypto v0.42.0 // indirect + golang.org/x/net v0.44.0 // indirect + golang.org/x/sys v0.36.0 // indirect + golang.org/x/text v0.29.0 // indirect + google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1 // indirect + google.golang.org/grpc v1.67.0 // indirect + google.golang.org/protobuf v1.34.2 // indirect +) diff --git a/internal/pkg/gemini/go.sum b/internal/pkg/gemini/go.sum new file mode 100644 index 0000000..0746482 --- /dev/null +++ b/internal/pkg/gemini/go.sum @@ -0,0 +1,120 @@ +cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw= +cloud.google.com/go v0.116.0 h1:B3fRrSDkLRt5qSHWe40ERJvhvnQwdZiHu0bJOpldweE= +cloud.google.com/go v0.116.0/go.mod h1:cEPSRWPzZEswwdr9BxE6ChEn01dWlTaF05LiC2Xs70U= +cloud.google.com/go/auth v0.9.3 h1:VOEUIAADkkLtyfr3BLa3R8Ed/j6w1jTBmARx+wb5w5U= +cloud.google.com/go/auth v0.9.3/go.mod h1:7z6VY+7h3KUdRov5F1i8NDP5ZzWKYmEPO842BgCsmTk= +cloud.google.com/go/compute/metadata v0.5.0 h1:Zr0eK8JbFv6+Wi4ilXAR8FJ3wyNdpxHKJNPos6LTZOY= +cloud.google.com/go/compute/metadata v0.5.0/go.mod h1:aHnloV2TPI38yx4s9+wAZhHykWvVCfu7hQbF+9CWoiY= +github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU= +github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU= +github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw= +github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc= +github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4= +github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4= +github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98= +github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c= +github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q= +github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc= +github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE= +github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc= +github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A= +github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U= +github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U= +github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8= +github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA= +github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs= +github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w= +github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0= +github.com/golang/protobuf v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QDs8UjoX8= +github.com/golang/protobuf v1.4.3/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI= +github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M= +github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU= +github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU= +github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= +github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= +github.com/google/go-cmp v0.5.3/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= +github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI= +github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY= +github.com/google/s2a-go v0.1.8 h1:zZDs9gcbt9ZPLV0ndSyQk6Kacx2g/X+SKYovpnz3SMM= +github.com/google/s2a-go v0.1.8/go.mod h1:6iNWHTpQ+nfNRN5E00MSdfDwVesa8hhS32PhPO8deJA= +github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= +github.com/googleapis/enterprise-certificate-proxy v0.3.4 h1:XYIDZApgAnrN1c855gTgghdIA6Stxb52D5RnLI1SLyw= +github.com/googleapis/enterprise-certificate-proxy v0.3.4/go.mod h1:YKe7cfqYXjKGpGvmSg28/fFvhNzinZQm8DGnaburhGA= +github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg= +github.com/gorilla/websocket v1.5.3/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE= +github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= +github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA= +github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= +github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw= +github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo= +github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= +github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU= +github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4= +go.opencensus.io v0.24.0 h1:y73uSU6J157QMP2kn2r30vwW1A2W2WFwSCGnAVxeaD0= +go.opencensus.io v0.24.0/go.mod h1:vNK8G9p7aAivkbmorf4v+7Hgx+Zs0yY+0fOtgBfjQKo= +golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= +golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto= +golang.org/x/crypto v0.42.0 h1:chiH31gIWm57EkTXpwnqf8qeuMUi0yekh6mT2AvFlqI= +golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA= +golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE= +golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU= +golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc= +golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= +golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= +golang.org/x/net v0.0.0-20190213061140-3a22650c66bd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= +golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg= +golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg= +golang.org/x/net v0.0.0-20201110031124-69a78807bb2b/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU= +golang.org/x/net v0.44.0 h1:evd8IRDyfNBMBTTY5XRF1vaZlD+EmWx6x8PkhR04H/I= +golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U= +golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.17.0 h1:l60nONMj9l5drqw6jlhIELNv9I0A4OFgRsG9k2oT9Ug= +golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.36.0 h1:KVRy2GtZBrk1cBYA7MKu5bEZFxQk4NIDV6RLVcC8o0k= +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 v0.29.0 h1:1neNs90w9YzJ9BocxfsQNHKuAT4pkghyXc4nhZ6sJvk= +golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= +golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= +golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY= +golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs= +golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q= +golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM= +google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4= +google.golang.org/genai v1.39.0 h1:80I1sYFGROliWNxEgPWDklNYVO8xq/bNvw70BFh6XmA= +google.golang.org/genai v1.39.0/go.mod h1:A3kkl0nyBjyFlNjgxIwKq70julKbIxpSxqKO5gw/gmk= +google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc= +google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc= +google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013/go.mod h1:NbSheEEYHJ7i3ixzK3sjbqSGDJWnxyFXZblF3eUsNvo= +google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1 h1:pPJltXNxVzT4pK9yD8vR9X75DaWYYmLGMsEvBfFQZzQ= +google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU= +google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c= +google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg= +google.golang.org/grpc v1.25.1/go.mod h1:c3i+UQWmh7LiEpx4sFZnkU36qjEYZ0imhYfXVyQciAY= +google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk= +google.golang.org/grpc v1.33.2/go.mod h1:JMHMWHQWaTccqQQlmk3MJZS+GWXOdAesneDmEnv2fbc= +google.golang.org/grpc v1.67.0 h1:IdH9y6PF5MPSdAntIcpjQ+tXO41pcQsfZV2RxtQgVcw= +google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8= +google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0= +google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM= +google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE= +google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo= +google.golang.org/protobuf v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU= +google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU= +google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU= +google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c= +google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg= +google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw= +gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= +gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= +honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= +honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= diff --git a/internal/pkg/openrouter/openrouter.go b/internal/pkg/openrouter/openrouter.go index ecdb8f6..9b2f750 100644 --- a/internal/pkg/openrouter/openrouter.go +++ b/internal/pkg/openrouter/openrouter.go @@ -21,16 +21,6 @@ type JobAnalysisResult struct { ImprovementSuggestions []string `json:"improvement_suggestions"` } -// ShouldApply returns true if the recommendation is to apply for the job -func (r *JobAnalysisResult) ShouldApply() bool { - return r.Recommendation == "apply" -} - -// IsHighConfidence returns true if the confidence score is 70 or above -func (r *JobAnalysisResult) IsHighConfidence() bool { - return r.ConfidenceScore >= 70 -} - type OpenRouterService struct { model string apiKey string @@ -85,7 +75,6 @@ func (s *OpenRouterService) AnalyzeJobDescription(cv string, jobDesc domain.JobD "improvement_suggestions": [string] }`, cv, jobDesc.Description, jobDesc.Criteria) - // Build and execute your request with a fluent API _, resp, err := client. NewChatCompletion(). WithModel(s.model). @@ -100,21 +89,16 @@ func (s *OpenRouterService) AnalyzeJobDescription(cv string, jobDesc domain.JobD return nil, fmt.Errorf("no response choices received from API") } - // Extract JSON from the response (handle markdown code blocks) jsonContent := resp.Choices[0].Message.Content - // Log the raw response for debugging log.Printf("Raw API response: %s", jsonContent) - // Check if response looks like HTML/XML (common error response format) if len(jsonContent) > 0 && jsonContent[0] == '<' { return nil, fmt.Errorf("API returned HTML/XML instead of JSON. This usually indicates an API error, authentication issue, or rate limiting. Response: %s", jsonContent[:min(200, len(jsonContent))]) } - // Clean up markdown code blocks if present jsonContent = cleanMarkdownCodeBlocks(jsonContent) - // Parse the JSON response into our struct var result JobAnalysisResult if err := json.Unmarshal([]byte(jsonContent), &result); err != nil { return nil, fmt.Errorf("failed to parse JSON response: %v. Raw response: %s", err, jsonContent[:min(200, len(jsonContent))]) @@ -123,7 +107,6 @@ func (s *OpenRouterService) AnalyzeJobDescription(cv string, jobDesc domain.JobD return &result, nil } -// min returns the smaller of two integers func min(a, b int) int { if a < b { return a @@ -136,10 +119,10 @@ func cleanMarkdownCodeBlocks(content string) string { content = strings.TrimSpace(content) // Remove markdown code blocks - if strings.HasPrefix(content, "```json") { - content = strings.TrimPrefix(content, "```json") - } else if strings.HasPrefix(content, "```") { - content = strings.TrimPrefix(content, "```") + if after, ok := strings.CutPrefix(content, "```json"); ok { + content = after + } else if after0, ok0 := strings.CutPrefix(content, "```"); ok0 { + content = after0 } content = strings.TrimSuffix(content, "```") @@ -155,7 +138,8 @@ func (s *OpenRouterService) CreateJobDescription(htmlContent string) (*domain.Jo log.Fatalf("Failed to create client: %v", err) } - prompt := fmt.Sprintf(`Extract job posting information from the following HTML content. + prompt := fmt.Sprintf(`You are a job posting data extractor. Analyze the HTML content and extract data according to this JSON structure: +{"description":"job description text","criteria":{"title":"Job Title","company":"Company","location":"Location","salary":"Salary","skills":"Skills","experience":"Experience","job_type":"Job Type","remote":"Remote"}} CRITICAL RULES: 1. Return ONLY valid JSON - no markdown, no code blocks, no backticks, no explanations @@ -163,15 +147,13 @@ CRITICAL RULES: 3. All criteria values MUST be strings (never use booleans, numbers, or arrays) 4. Properly escape all quotes inside strings using \" 5. Use only standard ASCII quotes ("), never smart quotes (" " ' ') +7. If no job description is found, use empty string for "description": "" +8. All criteria fields must be present with empty string "" if not found -Required fields: -- description: Full job description as a single string -- criteria: Object with keys like title, company, location, salary, skills, experience, job_type, remote +Example output: +{"description":"Develop software applications...","criteria":{"title":"Backend Engineer","company":"Tech Corp","location":"Remote","salary":"$120k","skills":"Go, Docker","experience":"3+ years","job_type":"Full-time","remote":"Yes"}} -Example (SINGLE LINE): -{"description":"Full job description text here...","criteria":{"title":"Software Engineer","location":"City, Country","salary":"$100k-$150k","skills":"Go, Python, Docker","experience":"3-5 years","job_type":"Full-time","remote":"Remote"}} - -HTML Content: +Extract from this HTML Content: %s`, htmlContent) _, resp, err := client. @@ -194,8 +176,6 @@ HTML Content: jsonContent = cleanMarkdownCodeBlocks(jsonContent) - log.Printf("Cleaned JSON (first 500 chars): %s", jsonContent[:min(500, len(jsonContent))]) - var result struct { Description string `json:"description"` Criteria map[string]string `json:"criteria"` @@ -203,10 +183,7 @@ HTML Content: if err := json.Unmarshal([]byte(jsonContent), &result); err != nil { if syntaxErr, ok := err.(*json.SyntaxError); ok { - start := int(syntaxErr.Offset) - 50 - if start < 0 { - start = 0 - } + start := max(int(syntaxErr.Offset)-50, 0) end := int(syntaxErr.Offset) + 50 if end > len(jsonContent) { end = len(jsonContent) @@ -222,6 +199,3 @@ HTML Content: return jobDescription, nil } - -// func (s *OpenRouterService) CreateCV(cv string, jobDesc domain.JobDescription) (*JobAnalysisResult, error) { -// } diff --git a/libs/repo/job.go b/libs/repo/job.go index 9a03ed5..e75044a 100644 --- a/libs/repo/job.go +++ b/libs/repo/job.go @@ -17,15 +17,52 @@ func NewJobRepository(db *sql.DB) *JobRepository { return &JobRepository{db: db} } +// JobExistsByLink checks if a job with the given link already exists in the database +func (r *JobRepository) JobExistsByLink(jobLink string) (bool, error) { + var exists bool + err := r.db.QueryRow("SELECT EXISTS(SELECT 1 FROM jobs WHERE job_link = $1)", jobLink).Scan(&exists) + if err != nil { + return false, fmt.Errorf("error checking job existence: %v", err) + } + return exists, nil +} + +// SaveJob saves a single job and returns the generated ID +func (r *JobRepository) SaveJob(job domain.Job) (int64, error) { + sqlStatement := ` + INSERT INTO jobs (title, company, company_link, location, job_link, job_timestamp, provider) + VALUES ($1, $2, $3, $4, $5, $6, $7) + ON CONFLICT (job_link) DO UPDATE SET + title = EXCLUDED.title, + company = EXCLUDED.company, + company_link = EXCLUDED.company_link, + location = EXCLUDED.location, + job_timestamp = EXCLUDED.job_timestamp, + provider = EXCLUDED.provider + RETURNING id + ` + + var id int64 + err := r.db.QueryRow(sqlStatement, + job.Title, job.Company, job.CompanyLink, job.Location, + job.JobLink, job.JobPostTime, job.Provider, + ).Scan(&id) + if err != nil { + return 0, fmt.Errorf("error inserting job: %v", err) + } + + return id, nil +} + func (r *JobRepository) SaveJobs(jobs []domain.Job) error { if len(jobs) == 0 { return nil } - // Deduplicate jobs by ID to avoid duplicate errors - jobMap := make(map[int64]domain.Job) + // Deduplicate jobs by job_link to avoid duplicate errors + jobMap := make(map[string]domain.Job) for _, job := range jobs { - jobMap[job.ID] = job + jobMap[job.JobLink] = job } // Convert to slice of pointers for the bulk function @@ -36,10 +73,9 @@ func (r *JobRepository) SaveJobs(jobs []domain.Job) error { } sqlTemplate := ` - INSERT INTO jobs (id, title, company, company_link, location, job_link, job_timestamp, provider) + INSERT INTO jobs (title, company, company_link, location, job_link, job_timestamp, provider) VALUES %s ON CONFLICT (job_link) DO UPDATE SET - id = EXCLUDED.id, title = EXCLUDED.title, company = EXCLUDED.company, company_link = EXCLUDED.company_link, @@ -112,14 +148,14 @@ func (r *JobRepository) GetJobByID(id int) (*domain.Job, error) { func prepareQueryCreateBulk(s string, models []*domain.Job) (string, []interface{}) { bf := bytes.Buffer{} - values := make([]interface{}, 0, len(models)*8) + values := make([]interface{}, 0, len(models)*7) for i, v := range models { - values = append(values, v.ID, v.Title, v.Company, + values = append(values, v.Title, v.Company, v.CompanyLink, v.Location, v.JobLink, v.JobPostTime, v.Provider, ) - numFields := 8 + numFields := 7 n := i * numFields bf.WriteString("(") diff --git a/services/api/go.mod b/services/api/go.mod index 1c207ab..e1a851f 100644 --- a/services/api/go.mod +++ b/services/api/go.mod @@ -25,12 +25,16 @@ require ( github.com/hashicorp/errwrap v1.1.0 // indirect github.com/hashicorp/go-multierror v1.1.1 // indirect github.com/josharian/intern v1.0.0 // indirect + github.com/kr/pretty v0.3.1 // indirect github.com/lib/pq v1.10.9 // indirect github.com/mailru/easyjson v0.7.6 // indirect github.com/rabbitmq/amqp091-go v1.10.0 // indirect + github.com/rogpeppe/go-internal v1.13.1 // indirect github.com/swaggo/files v0.0.0-20220610200504-28940afbdbfe // indirect - golang.org/x/net v0.38.0 // indirect - golang.org/x/tools v0.24.0 // indirect + golang.org/x/net v0.44.0 // indirect + golang.org/x/sync v0.17.0 // indirect + golang.org/x/tools v0.36.0 // indirect + gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c // indirect gopkg.in/yaml.v2 v2.4.0 // indirect ) diff --git a/services/api/go.sum b/services/api/go.sum index 8512564..9bf3e82 100644 --- a/services/api/go.sum +++ b/services/api/go.sum @@ -54,6 +54,8 @@ github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwA github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY= github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y= github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo= +github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI= +github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE= github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ= github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI= github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY= @@ -70,18 +72,21 @@ github.com/moby/term v0.5.0 h1:xt8Q1nalod/v7BqbG21f8mQPqH+xAaC9C3N3wfWbVP0= github.com/moby/term v0.5.0/go.mod h1:8FzsFHVUBGZdbDsJw/ot+X+d5HLUbvklYLJ9uGfcI3Y= github.com/morikuni/aec v1.0.0 h1:nP9CBfwrvYnBRgY6qfDQkygYDmYwOilePFkwzv4dU8A= github.com/morikuni/aec v1.0.0/go.mod h1:BbKIizmSmc5MMPqRYbxO4ZU0S0+P200+tUnFx7PXmsc= -github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e h1:fD57ERR4JtEqsWbfPhv4DMiApHyliiK5xCTNVSPiaAs= github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno= github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U= github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM= github.com/opencontainers/image-spec v1.1.0 h1:8SG7/vwALn54lVB/0yZ/MMwhFrPYtpEHQb2IpWsCzug= github.com/opencontainers/image-spec v1.1.0/go.mod h1:W4s4sFTMaBeK1BQLXbG4AdM2szdn85PY75RI83NrTrM= +github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA= github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4= github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= 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/rabbitmq/amqp091-go v1.10.0 h1:STpn5XsHlHGcecLmMFCtg7mqq0RnD+zFr4uzukfVhBw= github.com/rabbitmq/amqp091-go v1.10.0/go.mod h1:Hy4jKW5kQART1u+JkDTF9YYOQUHXqMuhrgxOEeS7G4o= +github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs= +github.com/rogpeppe/go-internal v1.13.1 h1:KvO1DLK/DRN07sQ1LQKScxyZJuNnedQ5/wKSR38lUII= +github.com/rogpeppe/go-internal v1.13.1/go.mod h1:uMEvuHeurkdAXX61udpOXGD/AzZDWNMNyH2VO9fmH0o= github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= @@ -105,13 +110,10 @@ go.opentelemetry.io/otel/trace v1.37.0 h1:HLdcFNbRQBE2imdSEgm/kwqmQj1Or1l/7bW6mx go.opentelemetry.io/otel/trace v1.37.0/go.mod h1:TlgrlQ+PtQO5XFerSPUYG0JSgGyryXewPGyayAWSBS0= go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto= go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE= -golang.org/x/mod v0.21.0 h1:vvrHzRwRfVKSiLrG+d4FMl/Qi4ukBCE6kZlTUkDYRT0= -golang.org/x/mod v0.21.0/go.mod h1:6SkKJ3Xj0I0BrPOZoBy3bdMptDDU9oJrpohJ3eWZ1fY= +golang.org/x/mod v0.27.0 h1:kb+q2PyFnEADO2IEF935ehFUXlWiNjJWtRNgBLSfbxQ= golang.org/x/net v0.0.0-20210805182204-aaa1db679c0d/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y= -golang.org/x/net v0.38.0 h1:vRMAPTMaeGqVhG5QyLJHqNDwecKTomGeqbnfZyKlBI8= -golang.org/x/net v0.38.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8= -golang.org/x/sync v0.12.0 h1:MHc5BpPuC30uJk597Ri8TV3CNZcTLu6B6z4lJy+g6Jw= -golang.org/x/sync v0.12.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA= +golang.org/x/net v0.44.0 h1:evd8IRDyfNBMBTTY5XRF1vaZlD+EmWx6x8PkhR04H/I= +golang.org/x/sync v0.17.0 h1:l60nONMj9l5drqw6jlhIELNv9I0A4OFgRsG9k2oT9Ug= golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.36.0 h1:KVRy2GtZBrk1cBYA7MKu5bEZFxQk4NIDV6RLVcC8o0k= @@ -119,12 +121,11 @@ golang.org/x/sys v0.36.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks= golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= -golang.org/x/tools v0.24.0 h1:J1shsA93PJUEVaUSaay7UXAyE8aimq3GW0pjlolpa24= -golang.org/x/tools v0.24.0/go.mod h1:YhNqVBIfWHdzvTLs0d8LCuMhkKUgSUKldakyV7W/WDQ= +golang.org/x/tools v0.36.0 h1:kWS0uv/zsvHEle1LbV5LE8QujrxB3wfQyxHfhOk0Qkg= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= -gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f h1:BLraFXnmrev5lT+xlilqcH8XK9/i0At2xKjWk4p6zsU= gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk= gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY= gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ= diff --git a/services/scraper-google/.env b/services/scraper-google/.env index 1faafa7..d1f2c0a 100644 --- a/services/scraper-google/.env +++ b/services/scraper-google/.env @@ -13,4 +13,5 @@ OPENAI_BASE_URL=https://hubai.loe.gg/v1 OPENAI_MODEL=gpt-4o-mini CV_AI_MODEL=alibaba/tongyi-deepresearch-30b-a3b:free -OPENROUTER_API_KEY=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 \ No newline at end of file +OPENROUTER_API_KEY=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 +GEMINI_API_KEY=AIzaSyBkGcsPdqhIrjg-wbLOuhAYmjOCt3A_zxM \ No newline at end of file diff --git a/services/scraper-google/analyzer/get-job-description.go b/services/scraper-google/analyzer/get-job-description.go index d912191..b5cb22a 100644 --- a/services/scraper-google/analyzer/get-job-description.go +++ b/services/scraper-google/analyzer/get-job-description.go @@ -5,27 +5,19 @@ import ( "os" "github.com/jobs-scraper/internal/pkg/domain" - "github.com/jobs-scraper/internal/pkg/openai" + "github.com/jobs-scraper/internal/pkg/openrouter" + // "github.com/jobs-scraper/internal/pkg/openai" // "github.com/jobs-scraper/internal/pkg/openrouter" ) func GetJobDescription(htmlContent string) (*domain.JobDescription, error) { - // apiKey := os.Getenv("OPENROUTER_API_KEY") - // model := os.Getenv("CV_AI_MODEL") - openAiapiKey := os.Getenv("OPENAI_API_KEY") - if openAiapiKey == "" { - return nil, fmt.Errorf("OPENAI_API_KEY environment variable is required") - } + openRouterApiKey := os.Getenv("OPENROUTER_API_KEY") + openRouterModel := os.Getenv("OPENROUTER_MODEL") + fmt.Println("key", openRouterApiKey) - openAiModel := os.Getenv("OPENAI_MODEL") - if openAiModel == "" { - openAiModel = "gpt-4o-mini" - } + client := openrouter.NewOpenRouterService(openRouterModel, openRouterApiKey) + result, err := client.CreateJobDescription(htmlContent) - openAiService := openai.NewOpenAIService(openAiapiKey, openAiModel) - - // client := openrouter.NewOpenRouterService(model, apiKey) - result, err := openAiService.CreateJobDescription(htmlContent) if err != nil { return nil, err } diff --git a/services/scraper-google/go.mod b/services/scraper-google/go.mod index 4563969..e143882 100644 --- a/services/scraper-google/go.mod +++ b/services/scraper-google/go.mod @@ -3,19 +3,26 @@ module github.com/jobs-scraper/services/scraper-google go 1.24.0 require ( + github.com/PuerkitoBio/goquery v1.10.3 github.com/chromedp/cdproto v0.0.0-20250803210736-d308e07a266d github.com/chromedp/chromedp v0.14.2 github.com/jobs-scraper/internal/pkg/infrastructure v0.0.0 + github.com/joho/godotenv v1.5.1 + github.com/levmv/sked v0.2.1 ) require ( + github.com/andybalholm/cascadia v1.3.3 // indirect github.com/chromedp/sysutil v1.1.0 // indirect github.com/go-json-experiment/json v0.0.0-20250725192818-e39067aee2d2 // indirect github.com/gobwas/httphead v0.1.0 // indirect github.com/gobwas/pool v0.2.1 // indirect github.com/gobwas/ws v1.4.0 // indirect - github.com/levmv/sked v0.2.1 // indirect - github.com/rabbitmq/amqp091-go v1.10.0 // indirect + github.com/golang-migrate/migrate/v4 v4.19.0 // indirect + github.com/hashicorp/errwrap v1.1.0 // indirect + github.com/hashicorp/go-multierror v1.1.1 // indirect + github.com/lib/pq v1.10.9 // indirect + golang.org/x/net v0.44.0 // indirect golang.org/x/sys v0.36.0 // indirect ) diff --git a/services/scraper-google/go.sum b/services/scraper-google/go.sum index 54c07b7..c5d03ed 100644 --- a/services/scraper-google/go.sum +++ b/services/scraper-google/go.sum @@ -1,27 +1,59 @@ +github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161 h1:L/gRVlceqvL25UVaW/CKtUDjefjrs0SPonmDGUVOYP0= +github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY= +github.com/PuerkitoBio/goquery v1.10.3 h1:pFYcNSqHxBD06Fpj/KsbStFRsgRATgnf3LeXiUkhzPo= +github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM= github.com/chromedp/cdproto v0.0.0-20250803210736-d308e07a266d h1:ZtA1sedVbEW7EW80Iz2GR3Ye6PwbJAJXjv7D74xG6HU= github.com/chromedp/cdproto v0.0.0-20250803210736-d308e07a266d/go.mod h1:NItd7aLkcfOA/dcMXvl8p1u+lQqioRMq/SqDp71Pb/k= github.com/chromedp/chromedp v0.14.2 h1:r3b/WtwM50RsBZHMUm9fsNhhzRStTHrKdr2zmwbZSzM= github.com/chromedp/chromedp v0.14.2/go.mod h1:rHzAv60xDE7VNy/MYtTUrYreSc0ujt2O1/C3bzctYBo= github.com/chromedp/sysutil v1.1.0 h1:PUFNv5EcprjqXZD9nJb9b/c9ibAbxiYo4exNWZyipwM= github.com/chromedp/sysutil v1.1.0/go.mod h1:WiThHUdltqCNKGc4gaU50XgYjwjYIhKWoHGPTUfWTJ8= +github.com/containerd/errdefs v1.0.0 h1:tg5yIfIlQIrxYtu9ajqY42W3lpS19XqdxRQeEwYG8PI= +github.com/containerd/errdefs/pkg v0.3.0 h1:9IKJ06FvyNlexW690DXuQNx2KA2cUJXx151Xdx3ZPPE= +github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= +github.com/dhui/dktest v0.4.6 h1:+DPKyScKSEp3VLtbMDHcUq6V5Lm5zfZZVb0Sk7Ahom4= +github.com/distribution/reference v0.6.0 h1:0IXCQ5g4/QMHHkarYzh5l+u8T3t73zM5QvfrDyIgxBk= +github.com/docker/docker v28.3.3+incompatible h1:Dypm25kh4rmk49v1eiVbsAtpAsYURjYkaKubwuBdxEI= +github.com/docker/go-connections v0.5.0 h1:USnMq7hx7gwdVZq1L49hLXaFtUdTADjXGp+uj1Br63c= +github.com/docker/go-units v0.5.0 h1:69rxXcBk27SvSaaxTtLh/8llcHD8vYHT7WSdRZ/jvr4= +github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg= github.com/go-json-experiment/json v0.0.0-20250725192818-e39067aee2d2 h1:iizUGZ9pEquQS5jTGkh4AqeeHCMbfbjeb0zMt0aEFzs= github.com/go-json-experiment/json v0.0.0-20250725192818-e39067aee2d2/go.mod h1:TiCD2a1pcmjd7YnhGH0f/zKNcCD06B029pHhzV23c2M= +github.com/go-logr/logr v1.4.3 h1:CjnDlHq8ikf6E492q6eKboGOC0T8CDaOvkHCIg8idEI= +github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag= github.com/gobwas/httphead v0.1.0 h1:exrUm0f4YX0L7EBwZHuCF4GDp8aJfVeBrlLQrs6NqWU= github.com/gobwas/httphead v0.1.0/go.mod h1:O/RXo79gxV8G+RqlR/otEwx4Q36zl9rqC5u12GKvMCM= github.com/gobwas/pool v0.2.1 h1:xfeeEhW7pwmX8nuLVlqbzVc7udMDrwetjEv+TZIz1og= github.com/gobwas/pool v0.2.1/go.mod h1:q8bcK0KcYlCgd9e7WYLm9LpyS+YeLd8JVDW6WezmKEw= github.com/gobwas/ws v1.4.0 h1:CTaoG1tojrh4ucGPcoJFiAQUAsEWekEWvLy7GsVNqGs= github.com/gobwas/ws v1.4.0/go.mod h1:G3gNqMNtPppf5XUz7O4shetPpcZ1VJ7zt18dlUeakrc= +github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q= +github.com/golang-migrate/migrate/v4 v4.19.0 h1:RcjOnCGz3Or6HQYEJ/EEVLfWnmw9KnoigPSjzhCuaSE= +github.com/hashicorp/errwrap v1.1.0 h1:OxrOeh75EUXMY8TBjag2fzXGZ40LB6IKw45YeGUDY2I= +github.com/hashicorp/go-multierror v1.1.1 h1:H5DkEtf6CXdFp0N0Em5UCwQpXMWke8IA0+lD48awMYo= +github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0= github.com/ledongthuc/pdf v0.0.0-20220302134840-0c2507a12d80 h1:6Yzfa6GP0rIo/kULo2bwGEkFvCePZ3qHDDTC3/J9Swo= github.com/ledongthuc/pdf v0.0.0-20220302134840-0c2507a12d80/go.mod h1:imJHygn/1yfhB7XSJJKlFZKl/J+dCPAknuiaGOshXAs= github.com/levmv/sked v0.2.1 h1:XMdLkbuajPM5LSzoBvNzalj6oYHkEfeA7/VPvkIHqs0= github.com/levmv/sked v0.2.1/go.mod h1:w9pFUIpZLPu0Jr2+2JqJtaEIHmwXcvjPHWm6pvbqHVQ= +github.com/lib/pq v1.10.9 h1:YXG7RB+JIjhP29X+OtkiDnYaXQwpS4JEWq7dtCCRUEw= +github.com/moby/docker-image-spec v1.3.1 h1:jMKff3w6PgbfSa69GfNg+zN/XLhfXJGnEx3Nl2EsFP0= +github.com/moby/term v0.5.0 h1:xt8Q1nalod/v7BqbG21f8mQPqH+xAaC9C3N3wfWbVP0= +github.com/morikuni/aec v1.0.0 h1:nP9CBfwrvYnBRgY6qfDQkygYDmYwOilePFkwzv4dU8A= +github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U= +github.com/opencontainers/image-spec v1.1.0 h1:8SG7/vwALn54lVB/0yZ/MMwhFrPYtpEHQb2IpWsCzug= github.com/orisano/pixelmatch v0.0.0-20220722002657-fb0b55479cde h1:x0TT0RDC7UhAVbbWWBzr41ElhJx5tXPWkIHA2HWPRuw= github.com/orisano/pixelmatch v0.0.0-20220722002657-fb0b55479cde/go.mod h1:nZgzbfBr3hhjoZnS66nKrHmduYNpc34ny7RK4z5/HM0= -github.com/rabbitmq/amqp091-go v1.10.0 h1:STpn5XsHlHGcecLmMFCtg7mqq0RnD+zFr4uzukfVhBw= -github.com/rabbitmq/amqp091-go v1.10.0/go.mod h1:Hy4jKW5kQART1u+JkDTF9YYOQUHXqMuhrgxOEeS7G4o= -go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto= -go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE= +github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4= +github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= +github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA= +go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA= +go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0 h1:TT4fX+nBOA/+LUkobKGW1ydGcn+G3vRw9+g5HwCphpk= +go.opentelemetry.io/otel v1.37.0 h1:9zhNfelUvx0KBfu/gb+ZgeAfAgtWrfHJZcAqFC228wQ= +go.opentelemetry.io/otel/metric v1.37.0 h1:mvwbQS5m0tbmqML4NqK+e3aDiO02vsf/WgbsdpcPoZE= +go.opentelemetry.io/otel/trace v1.37.0 h1:HLdcFNbRQBE2imdSEgm/kwqmQj1Or1l/7bW6mxVK7z4= +golang.org/x/net v0.44.0 h1:evd8IRDyfNBMBTTY5XRF1vaZlD+EmWx6x8PkhR04H/I= golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.36.0 h1:KVRy2GtZBrk1cBYA7MKu5bEZFxQk4NIDV6RLVcC8o0k= golang.org/x/sys v0.36.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks= +gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= diff --git a/services/scraper-google/main.go b/services/scraper-google/main.go index 2d8b812..adb30f9 100644 --- a/services/scraper-google/main.go +++ b/services/scraper-google/main.go @@ -2,9 +2,14 @@ package main import ( "context" + "encoding/json" + "fmt" "log" + "net/http" "os" + "os/exec" "os/signal" + "runtime" "syscall" "time" @@ -34,30 +39,52 @@ func main() { ctx, cancel := context.WithCancel(context.Background()) + // Launch Chrome once and share across all goroutines + wsURL, chromeCmd, err := launchChrome() + if err != nil { + log.Fatalf("Failed to launch Chrome: %v", err) + } + defer chromeCmd.Process.Kill() + log.Printf("Chrome launched with WebSocket URL: %s", wsURL) + sched := sked.New(ctx) googleLinkStream := make(chan domain.GoogleLink, 100) // pages := []int{0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100} - pages := []int{0} + pages := []int{100, 110, 120, 130} log.Println("Starting scraper with scheduler...") for _, page := range pages { go func() { log.Printf("Running initial scrape for page offset: %d, inital run", page) - Work(ctx)(page, googleLinkStream) + Work(ctx, wsURL)(page, googleLinkStream) }() + } + for _, page := range pages { sched.Schedule(func(ctx context.Context) { log.Printf("Running scheduled scrape for page offset: %d", page) - Work(ctx)(page, googleLinkStream) + Work(ctx, wsURL)(page, googleLinkStream) }).Every(time.Hour * 24) } go func() { for googleLink := range googleLinkStream { - log.Printf("Received job: %s ", googleLink.CompanyName) - htmlRaw, url, err := utils.GetHTMLRaw(ctx, googleLink) + + exists, err := jobRepo.JobExistsByLink(googleLink.Link) + + if err != nil { + log.Printf("Error checking if job exists for link %s: %v", googleLink.Link, err) + continue + } + + if exists { + log.Printf("Job already exists, skipping: %s", googleLink.Link) + continue + } + + htmlRaw, url, err := utils.GetHTMLRaw(ctx, wsURL, googleLink) if err != nil { log.Printf("Error fetching HTML raw for link %s: %v", googleLink.Link, err) @@ -65,7 +92,6 @@ func main() { } result, err := analyzer.GetJobDescription(htmlRaw) - if err != nil { log.Printf("Error analyzing job description for link %s: %v", googleLink.Link, err) continue @@ -73,35 +99,37 @@ func main() { now := time.Now() + // Save the main job job := domain.Job{ - ID: googleLink.ID, Title: googleLink.Title, Company: googleLink.CompanyName, - CompanyLink: googleLink.Link, + CompanyLink: url, Location: result.Criteria["location"], - JobLink: url, + JobLink: googleLink.Link, Provider: domain.Google, JobPostTime: &now, Status: domain.JobStatusCreated, } + jobID, err := jobRepo.SaveJob(job) + if err != nil { + log.Printf("Failed to save job: %v", err) + continue + } + + // Save job description jobDescription := domain.JobDescription{ - JobID: googleLink.ID, + JobID: jobID, Description: result.Description, Criteria: result.Criteria, } - if err := jobRepo.SaveJobs([]domain.Job{job}); err != nil { - log.Printf("Failed to save job %d: %v", googleLink.ID, err) - continue - } - if err := jobDescRepo.SaveJobDescriptions([]domain.JobDescription{jobDescription}); err != nil { - log.Printf("Failed to save job description for job %d: %v", googleLink.ID, err) + log.Printf("Failed to save job description for job %d: %v", jobID, err) continue } - log.Printf("Successfully saved job: %s from %s (ID: %d)", job.Title, job.Company, job.ID) + log.Printf("Successfully saved job: %s from %s (ID: %d)", job.Title, job.Company, jobID) } }() @@ -114,5 +142,76 @@ func main() { <-c cancel() log.Println("Shutting down scraper...") - +} + +// launchChrome starts Chrome with remote debugging and returns the WebSocket URL +func launchChrome() (string, *exec.Cmd, error) { + var chromePath string + switch runtime.GOOS { + case "darwin": + chromePath = "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" + case "linux": + chromePath = "google-chrome" + case "windows": + chromePath = "C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe" + default: + return "", nil, fmt.Errorf("unsupported OS: %s", runtime.GOOS) + } + + // Kill any existing Chrome debug instances first + exec.Command("pkill", "-f", "remote-debugging-port=9222").Run() + time.Sleep(500 * time.Millisecond) + + cmd := exec.Command(chromePath, + "--remote-debugging-port=9222", + "--no-first-run", + "--no-default-browser-check", + "--disable-background-networking", + "--disable-extensions", + "--disable-sync", + "--disable-translate", + "--metrics-recording-only", + "--safebrowsing-disable-auto-update", + "--user-data-dir=/tmp/chrome-debug-profile", + // "--incognito", + // "--headless", + ) + + if err := cmd.Start(); err != nil { + return "", nil, fmt.Errorf("failed to start Chrome: %w", err) + } + + // Poll the debug endpoint to get the WebSocket URL + var wsURL string + for i := 0; i < 50; i++ { + time.Sleep(200 * time.Millisecond) + resp, err := http.Get("http://127.0.0.1:9222/json/version") + if err != nil { + continue + } + + var result struct { + WebSocketDebuggerURL string `json:"webSocketDebuggerUrl"` + } + if err := json.NewDecoder(resp.Body).Decode(&result); err != nil { + resp.Body.Close() + continue + } + resp.Body.Close() + + if result.WebSocketDebuggerURL != "" { + wsURL = result.WebSocketDebuggerURL + break + } + } + + if wsURL == "" { + cmd.Process.Kill() + return "", nil, fmt.Errorf("timeout waiting for Chrome WebSocket URL") + } + + // Wait for Chrome to be fully ready to accept connections + time.Sleep(1 * time.Second) + + return wsURL, cmd, nil } diff --git a/services/scraper-google/utils/get-html-raw.go b/services/scraper-google/utils/get-html-raw.go index 73e1d2c..3993fcc 100644 --- a/services/scraper-google/utils/get-html-raw.go +++ b/services/scraper-google/utils/get-html-raw.go @@ -13,36 +13,21 @@ import ( "github.com/jobs-scraper/internal/pkg/domain" ) -func GetHTMLRaw(ctx context.Context, googleLink domain.GoogleLink) (string, string, error) { - // Set up chromedp options - opts := append(chromedp.DefaultExecAllocatorOptions[:], - chromedp.Flag("headless", true), - chromedp.Flag("no-sandbox", true), // Required for Docker - chromedp.Flag("disable-gpu", true), // Recommended for Docker - chromedp.Flag("disable-dev-shm-usage", true), // Prevents crashes in Docker - chromedp.Flag("disable-blink-features", "AutomationControlled"), - chromedp.Flag("excludeSwitches", "enable-automation"), - chromedp.UserAgent("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"), - chromedp.WindowSize(1920, 1080), - ) - - allocCtx, allocCancel := chromedp.NewExecAllocator(ctx, opts...) +func GetHTMLRaw(ctx context.Context, wsURL string, googleLink domain.GoogleLink) (string, string, error) { + // Connect to the shared Chrome instance + allocCtx, allocCancel := chromedp.NewRemoteAllocator(ctx, wsURL) defer allocCancel() browserCtx, browserCancel := chromedp.NewContext(allocCtx) defer browserCancel() - // Add timeout for the entire operation - timeoutCtx, timeoutCancel := context.WithTimeout(browserCtx, 30*time.Second) - defer timeoutCancel() - var htmlContent string var finalURL string - err := chromedp.Run(timeoutCtx, + err := chromedp.Run(browserCtx, chromedp.Navigate(googleLink.Link), chromedp.WaitVisible("body", chromedp.ByQuery), - chromedp.Sleep(2*time.Second), // Wait for JS to render + WaitForNetworkIdle(10*time.Second), // Wait for all network requests to complete chromedp.Location(&finalURL), chromedp.OuterHTML("html", &htmlContent, chromedp.ByQuery), ) @@ -62,7 +47,7 @@ func GetHTMLRaw(ctx context.Context, googleLink domain.GoogleLink) (string, stri // Remove unwanted elements doc.Find("script, style, nav, footer, header, .ads, .sidebar").Remove() - log.Printf(" Received: %s from %s\n, ID: %d", googleLink.Title, googleLink.CompanyName, googleLink.ID) + log.Printf("Received: %s from %s", googleLink.Title, googleLink.CompanyName) // Extract text content var content strings.Builder @@ -93,3 +78,111 @@ func extractHostname(urlStr string) (string, error) { } return parsedURL.Hostname(), nil } + +// ClickSelector clicks on an element using the provided selector string +// Selector format: "css:selector" or "xpath:selector" +func ClickSelector(ctx context.Context, selector string) error { + if selector == "" { + return fmt.Errorf("empty selector") + } + + parts := strings.SplitN(selector, ":", 2) + if len(parts) != 2 { + return fmt.Errorf("invalid selector format: %s", selector) + } + + selectorType := parts[0] + selectorValue := parts[1] + + var err error + switch selectorType { + case "css": + err = chromedp.Run(ctx, + chromedp.WaitVisible(selectorValue, chromedp.ByQuery), + chromedp.Click(selectorValue, chromedp.ByQuery), + ) + case "xpath": + err = chromedp.Run(ctx, + chromedp.WaitVisible(selectorValue, chromedp.BySearch), + chromedp.Click(selectorValue, chromedp.BySearch), + ) + default: + return fmt.Errorf("unknown selector type: %s", selectorType) + } + + if err != nil { + return fmt.Errorf("failed to click selector %s: %w", selector, err) + } + + log.Printf("Successfully clicked on selector: %s", selector) + return nil +} + +// GetHTMLRawWithRetry fetches HTML and can retry with a selector click if needed +func GetHTMLRawWithRetry(ctx context.Context, wsURL string, googleLink domain.GoogleLink, selector string) (string, string, error) { + // Connect to the shared Chrome instance + allocCtx, allocCancel := chromedp.NewRemoteAllocator(ctx, wsURL) + defer allocCancel() + + browserCtx, browserCancel := chromedp.NewContext(allocCtx) + defer browserCancel() + + timeoutCtx, timeoutCancel := context.WithTimeout(browserCtx, 45*time.Second) + defer timeoutCancel() + + var htmlContent string + var finalURL string + + // Navigate to the page + err := chromedp.Run(timeoutCtx, + chromedp.Navigate(googleLink.Link), + chromedp.WaitVisible("body", chromedp.ByQuery), + WaitForNetworkIdle(5*time.Second), + ) + if err != nil { + return "", "", fmt.Errorf("failed to navigate: %w", err) + } + + // If a selector is provided, click on it + if selector != "" { + if err := ClickSelector(timeoutCtx, selector); err != nil { + log.Printf("Failed to click selector %s: %v", selector, err) + // Continue anyway, we'll get whatever HTML we can + } else { + // Wait for the new page to load after clicking + _ = chromedp.Run(timeoutCtx, + chromedp.WaitVisible("body", chromedp.ByQuery), + WaitForNetworkIdle(5*time.Second), + ) + } + } + + // Get the final HTML + err = chromedp.Run(timeoutCtx, + chromedp.Location(&finalURL), + chromedp.OuterHTML("html", &htmlContent, chromedp.ByQuery), + ) + if err != nil { + return "", "", fmt.Errorf("failed to get HTML: %w", err) + } + + // Parse and clean HTML + doc, err := goquery.NewDocumentFromReader(strings.NewReader(htmlContent)) + if err != nil { + return "", "", fmt.Errorf("failed to parse HTML: %w", err) + } + + doc.Find("script, style, nav, footer, header, .ads, .sidebar").Remove() + + var content strings.Builder + doc.Find("body").Each(func(i int, s *goquery.Selection) { + content.WriteString(s.Text()) + }) + + hostname, err := extractHostname(finalURL) + if err != nil { + return cleanText(content.String()), googleLink.Link, nil + } + + return cleanText(content.String()), hostname, nil +} diff --git a/services/scraper-google/utils/network.go b/services/scraper-google/utils/network.go new file mode 100644 index 0000000..e02d1cd --- /dev/null +++ b/services/scraper-google/utils/network.go @@ -0,0 +1,45 @@ +package utils + +import ( + "context" + "time" + + "github.com/chromedp/cdproto/page" + "github.com/chromedp/chromedp" +) + +// WaitForNetworkIdle waits for the network to be idle (no pending requests) +// for the specified duration. This is useful for pages that load content dynamically. +func WaitForNetworkIdle(timeout time.Duration) chromedp.ActionFunc { + return func(ctx context.Context) error { + // Enable lifecycle events + if err := page.SetLifecycleEventsEnabled(true).Do(ctx); err != nil { + return err + } + + ch := make(chan struct{}, 1) + cctx, cancel := context.WithCancel(ctx) + defer cancel() + + chromedp.ListenTarget(cctx, func(ev interface{}) { + if e, ok := ev.(*page.EventLifecycleEvent); ok { + if e.Name == "networkIdle" { + select { + case ch <- struct{}{}: + default: + } + } + } + }) + + select { + case <-ch: + return nil + case <-time.After(timeout): + // Timeout reached, but don't error - page may still be usable + return nil + case <-ctx.Done(): + return ctx.Err() + } + } +} diff --git a/services/scraper-google/work.go b/services/scraper-google/work.go index 72bbe60..4d35a7b 100644 --- a/services/scraper-google/work.go +++ b/services/scraper-google/work.go @@ -10,31 +10,20 @@ import ( "github.com/jobs-scraper/services/scraper-google/utils" ) -func Work(mainCtx context.Context) func(page int, stream chan<- domain.GoogleLink) { - +func Work(mainCtx context.Context, wsURL string) func(page int, stream chan<- domain.GoogleLink) { return func(page int, stream chan<- domain.GoogleLink) { - query := "site:boards.greenhouse.io (Software OR Backend OR Full-Stack) Engineer" + // query := "site:boards.greenhouse.io (Software OR Backend OR Full-Stack) Engineer inurl:gh_jid" + query := `site:lever.co (Software OR Backend OR Full-Stack) Engineer lang:en` - opts := append(chromedp.DefaultExecAllocatorOptions[:], - chromedp.Flag("headless", true), - chromedp.Flag("no-sandbox", true), - chromedp.Flag("disable-gpu", true), - chromedp.Flag("disable-dev-shm-usage", true), - chromedp.Flag("disable-blink-features", "AutomationControlled"), - chromedp.Flag("excludeSwitches", "enable-automation"), - chromedp.Flag("disable-web-security", false), - chromedp.UserAgent("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"), - chromedp.WindowSize(1920, 1080), - ) - allocCtx, cancel := chromedp.NewExecAllocator(mainCtx, opts...) - defer cancel() + // Connect to the shared Chrome instance + allocCtx, allocCancel := chromedp.NewRemoteAllocator(mainCtx, wsURL) + defer allocCancel() ctx, cancel := chromedp.NewContext(allocCtx) defer cancel() var nodes []*cdp.Node - // start = 0, start = 10, start = 20 and so on for offset pagination err := chromedp.Run(ctx, chromedp.Navigate(utils.BuildUrl(query, page)), ) @@ -80,13 +69,6 @@ func Work(mainCtx context.Context) func(page int, stream chan<- domain.GoogleLin log.Printf("Failed to get link for node %d: %v", i, err) } - result.ID, err = utils.ExtractJobId(result.Link) - - if err != nil { - log.Printf("Failed to extract job ID for node %d: %v (link: %s)", i, err, result.Link) - continue - } - result.CompanyName, err = utils.ExtractCompanyName(result.Link) if err != nil {