Skip to content

Commit

Permalink
on-demand initial browser
Browse files Browse the repository at this point in the history
  • Loading branch information
lizongying committed Nov 27, 2023
1 parent 44904c7 commit 7c81a24
Show file tree
Hide file tree
Showing 11 changed files with 216 additions and 18 deletions.
1 change: 1 addition & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -234,6 +234,7 @@ Crawler Options
set `mock_server.enable: true` to enable the mock Server.
* `WithItemDelay` sets the data saving interval.
* `WithItemConcurrency` sets the data saving parallelism.
* `WithCDP` initial browser.

### Item

Expand Down
1 change: 1 addition & 0 deletions README_CN.md
Original file line number Diff line number Diff line change
Expand Up @@ -222,6 +222,7 @@ crawler选项
* `WithMockServerRoutes` 设置模拟服务Route,包括内置或自定义的。不需要配置`mock_server.enable: true`
* `WithItemDelay` 设置数据保存间隔。
* `WithItemConcurrency` 设置数据保存并行数量。
* `WithCDP` 初始浏览器。

### 存储

Expand Down
3 changes: 2 additions & 1 deletion docs/content/en/docs/usage/options/_index.md
Original file line number Diff line number Diff line change
Expand Up @@ -69,4 +69,5 @@ Options refer to items that can be configured in the code.
* `WithMockServerRoutes` Configure development service routes, including built-in or custom ones. You don't need to
set `mock_server.enable: true` to enable the mock Server.
* `WithItemDelay` sets the data saving interval.
* `WithItemConcurrency` sets the data saving parallelism.
* `WithItemConcurrency` sets the data saving parallelism.
* `WithCDP` initial browser.
3 changes: 2 additions & 1 deletion docs/content/zh/docs/usage/options/_index.md
Original file line number Diff line number Diff line change
Expand Up @@ -60,4 +60,5 @@ title: 选项
* `WithLogger` 设置日志。
* `WithMockServerRoutes` 设置模拟服务Route,包括内置或自定义的。不需要配置`mock_server.enable: true`
* `WithItemDelay` 设置数据保存间隔。
* `WithItemConcurrency` 设置数据保存并行数量。
* `WithItemConcurrency` 设置数据保存并行数量。
* `WithCDP` 初始浏览器。
14 changes: 14 additions & 0 deletions go.mod
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ require (
github.com/aws/aws-sdk-go-v2 v1.23.1
github.com/aws/aws-sdk-go-v2/credentials v1.16.4
github.com/aws/aws-sdk-go-v2/service/s3 v1.44.0
github.com/docker/docker v24.0.7+incompatible
github.com/go-rod/rod v0.114.5
github.com/go-rod/stealth v0.4.9
github.com/go-sql-driver/mysql v1.7.1
Expand Down Expand Up @@ -35,6 +36,7 @@ require (
)

require (
github.com/Microsoft/go-winio v0.6.1 // indirect
github.com/PuerkitoBio/goquery v1.8.1 // indirect
github.com/andybalholm/cascadia v1.3.1 // indirect
github.com/antchfx/htmlquery v1.3.0 // indirect
Expand All @@ -52,12 +54,21 @@ require (
github.com/cloudflare/circl v1.3.3 // indirect
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
github.com/distribution/reference v0.5.0 // indirect
github.com/docker/distribution v2.8.3+incompatible // indirect
github.com/docker/go-connections v0.4.0 // indirect
github.com/docker/go-units v0.5.0 // indirect
github.com/gaukas/godicttls v0.0.4 // indirect
github.com/gogo/protobuf v1.3.2 // indirect
github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
github.com/golang/snappy v0.0.1 // indirect
github.com/klauspost/compress v1.16.7 // indirect
github.com/kr/pretty v0.3.1 // indirect
github.com/moby/term v0.5.0 // indirect
github.com/montanaflynn/stats v0.0.0-20171201202039-1bf9dbcd8cbe // indirect
github.com/morikuni/aec v1.0.0 // indirect
github.com/opencontainers/go-digest v1.0.0 // indirect
github.com/opencontainers/image-spec v1.0.2 // indirect
github.com/pierrec/lz4/v4 v4.1.15 // indirect
github.com/pmezard/go-difflib v1.0.0 // indirect
github.com/quic-go/quic-go v0.37.4 // indirect
Expand All @@ -76,7 +87,10 @@ require (
go.uber.org/dig v1.17.0 // indirect
go.uber.org/multierr v1.6.0 // indirect
go.uber.org/zap v1.23.0 // indirect
golang.org/x/mod v0.10.0 // indirect
golang.org/x/net v0.17.0 // indirect
golang.org/x/sync v0.2.0 // indirect
golang.org/x/sys v0.14.0 // indirect
golang.org/x/tools v0.9.1 // indirect
gotest.tools/v3 v3.5.1 // indirect
)
47 changes: 47 additions & 0 deletions go.sum
Original file line number Diff line number Diff line change
@@ -1,3 +1,7 @@
github.com/Azure/go-ansiterm v0.0.0-20210617225240-d185dfc1b5a1 h1:UQHMgLO+TxOElx5B5HZ4hJQsoJ/PvUvKRhJHDQXO8P8=
github.com/Azure/go-ansiterm v0.0.0-20210617225240-d185dfc1b5a1/go.mod h1:xomTg63KZ2rFqZQzSB4Vz2SUXa1BpHTVz9L5PTmPC4E=
github.com/Microsoft/go-winio v0.6.1 h1:9/kr64B9VUZrLm5YYwbGtUJnMgqWVOdUAXu6Migciow=
github.com/Microsoft/go-winio v0.6.1/go.mod h1:LRdKpFKfdobln8UmuiYcKPot9D2v6svN5+sAH+4kjUM=
github.com/PuerkitoBio/goquery v1.8.1 h1:uQxhNlArOIdbrH1tr0UXwdVFgDcZDrZVdcpygAcwmWM=
github.com/PuerkitoBio/goquery v1.8.1/go.mod h1:Q8ICL1kNUJ2sXGoAhPGUdYDJvgQgHzJsnnd3H7Ho5jQ=
github.com/andybalholm/brotli v1.0.6 h1:Yf9fFpf49Zrxb9NlQaluyE92/+X7UVHlhMNJN2sxfOI=
Expand Down Expand Up @@ -49,6 +53,16 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
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/distribution/reference v0.5.0 h1:/FUIFXtfc/x2gpa5/VGfiGLuOIdYa1t65IKK2OFGvA0=
github.com/distribution/reference v0.5.0/go.mod h1:BbU0aIcezP1/5jX/8MP0YiH4SdvB5Y4f/wlDRiLyi3E=
github.com/docker/distribution v2.8.3+incompatible h1:AtKxIZ36LoNK51+Z6RpzLpddBirtxJnzDrHLEKxTAYk=
github.com/docker/distribution v2.8.3+incompatible/go.mod h1:J2gT2udsDAN96Uj4KfcMRqY0/ypR+oyYUYmja8H+y+w=
github.com/docker/docker v24.0.7+incompatible h1:Wo6l37AuwP3JaMnZa226lzVXGA3F9Ig1seQen0cKYlM=
github.com/docker/docker v24.0.7+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk=
github.com/docker/go-connections v0.4.0 h1:El9xVISelRB7BuFusrZozjnkIM5YnzCViNKohAFqRJQ=
github.com/docker/go-connections v0.4.0/go.mod h1:Gbd7IOopHjR8Iph03tsViu4nIes5XhDvyHbTtUxmeec=
github.com/docker/go-units v0.5.0 h1:69rxXcBk27SvSaaxTtLh/8llcHD8vYHT7WSdRZ/jvr4=
github.com/docker/go-units v0.5.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
github.com/gaukas/godicttls v0.0.4 h1:NlRaXb3J6hAnTmWdsEKb9bcSBD6BvcIjdGdeb0zfXbk=
github.com/gaukas/godicttls v0.0.4/go.mod h1:l6EenT4TLWgTdwslVb4sEMOCf7Bv0JAK67deKr9/NCI=
github.com/go-logr/logr v1.2.4 h1:g01GSCwiDw2xSZfjJ2/T9M+S6pFdcNtFYsp+Y43HYDQ=
Expand All @@ -62,6 +76,8 @@ github.com/go-sql-driver/mysql v1.7.1 h1:lUIinVbN1DY0xBg0eMOzmmtGoHwWBbvnWubQUrt
github.com/go-sql-driver/mysql v1.7.1/go.mod h1:OXbVy3sEdcQ2Doequ6Z5BW6fXNQTmx+9S1MCJN5yJMI=
github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572 h1:tfuBGBXKqDEevZMzYi5KSi8KkcZtzBcTgAUUtapy0OI=
github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572/go.mod h1:9Pwr4B2jHnOSGXyyzV8ROjYa2ojvAY6HCGYYfMoC3Ls=
github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
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/snappy v0.0.1 h1:Qgr9rKW7uDUkrbSmQeiDsGa8SjGyCOGtuasMWwvp2P4=
Expand All @@ -73,6 +89,8 @@ github.com/google/pprof v0.0.0-20210407192527-94a9f03dee38 h1:yAJXTCF9TqKcTiHJAE
github.com/google/pprof v0.0.0-20210407192527-94a9f03dee38/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
github.com/google/uuid v1.4.0 h1:MtMxsa51/r9yyhkyLsVeVt0B+BGQZzpQiTQ4eHZ8bc4=
github.com/google/uuid v1.4.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
github.com/klauspost/compress v1.13.6/go.mod h1:/3/Vjq9QcHkK5uEr5lBEmyoZ1iFhe47etQ6QUkpK6sk=
github.com/klauspost/compress v1.15.9/go.mod h1:PhcZ0MbTNciWF3rruxRgKxI5NkcHHrHUDtV4Yw2GlzU=
github.com/klauspost/compress v1.16.7 h1:2mk3MPGNzKyxErAw8YaohYh69+pa4sIQSC0fPGCFR9I=
Expand All @@ -99,12 +117,20 @@ github.com/lizongying/gooptimizer v1.0.2 h1:y3Wj5loP1RivhMV84Jc90lj1iO8MKQrWVq61
github.com/lizongying/gooptimizer v1.0.2/go.mod h1:BnXnAp+c+rxShQqzSHlH05KInoCp290fVOPomRjIbFQ=
github.com/mattn/go-sqlite3 v1.14.18 h1:JL0eqdCOq6DJVNPSvArO/bIV9/P7fbGrV00LZHc+5aI=
github.com/mattn/go-sqlite3 v1.14.18/go.mod h1:2eHXhiwb8IkHr+BDWZGa96P6+rkvnG63S2DGjv9HUNg=
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/montanaflynn/stats v0.0.0-20171201202039-1bf9dbcd8cbe h1:iruDEfMl2E6fbMZ9s0scYfZQ84/6SPL6zC8ACM2oIL0=
github.com/montanaflynn/stats v0.0.0-20171201202039-1bf9dbcd8cbe/go.mod h1:wL8QJuTMNUDYhXwkmfOly8iTdp5TEcJFWZD2D7SIkUc=
github.com/morikuni/aec v1.0.0 h1:nP9CBfwrvYnBRgY6qfDQkygYDmYwOilePFkwzv4dU8A=
github.com/morikuni/aec v1.0.0/go.mod h1:BbKIizmSmc5MMPqRYbxO4ZU0S0+P200+tUnFx7PXmsc=
github.com/onsi/ginkgo/v2 v2.9.5 h1:+6Hr4uxzP4XIUyAkg61dWBw8lb/gc4/X5luuxN/EC+Q=
github.com/onsi/ginkgo/v2 v2.9.5/go.mod h1:tvAoo1QUJwNEU2ITftXTpR7R1RbCzoZUOs3RonqW57k=
github.com/onsi/gomega v1.27.6 h1:ENqfyGeS5AX/rlXDd/ETokDz93u0YufY1Pgxuy/PvWE=
github.com/onsi/gomega v1.27.6/go.mod h1:PIQNjfQwkP3aQAH7lf7j87O/5FiNr+ZR8+ipb+qQlhg=
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 v1.0.2 h1:9yCKha/T5XdGtO0q9Q9a6T5NUCsTn/DrBg0D7ufOcFM=
github.com/opencontainers/image-spec v1.0.2/go.mod h1:BtxoFyWECRxE4U/7sNtV5W15zMzWCbyJoFRP3s7yZA0=
github.com/pierrec/lz4/v4 v4.1.15 h1:MO0/ucJhngq7299dKLwIMtgTfbkoSPF6AoMYDd8Q4q0=
github.com/pierrec/lz4/v4 v4.1.15/go.mod h1:gZWDp/Ze/IJXGXf23ltt2EXimqmTUXEy0GFuRQyBid4=
github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
Expand Down Expand Up @@ -159,6 +185,8 @@ github.com/ysmood/gson v0.7.3 h1:QFkWbTH8MxyUTKPkVWAENJhxqdBa4lYTQWqZCiLG6kE=
github.com/ysmood/gson v0.7.3/go.mod h1:3Kzs5zDl21g5F/BlLTNcuAGAYLKt2lV5G8D1zF3RNmg=
github.com/ysmood/leakless v0.8.0 h1:BzLrVoiwxikpgEQR0Lk8NyBN5Cit2b1z+u0mgL4ZJak=
github.com/ysmood/leakless v0.8.0/go.mod h1:R8iAXPRaG97QJwqxs74RdwzcRHT1SWCGTNqY8q0JvMQ=
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=
go.mongodb.org/mongo-driver v1.13.0 h1:67DgFFjYOCMWdtTEmKFpV3ffWlFnh+CYZ8ZS/tXWUfY=
go.mongodb.org/mongo-driver v1.13.0/go.mod h1:/rGBTebI3XYboVmgz+Wv3Bcbl3aD0QF9zl6kDDw18rQ=
Expand All @@ -175,14 +203,23 @@ go.uber.org/multierr v1.6.0/go.mod h1:cdWPpRnG4AhwMwsgIHip0KRBQjJy5kYEpYjJxpXp9i
go.uber.org/zap v1.23.0 h1:OjGQ5KQDEUawVHxNwQgPpiypGHOxo2mNZsOqTak4fFY=
go.uber.org/zap v1.23.0/go.mod h1:D+nX8jyLsMHMYrln8A0rJjFt/T/9/bGgIhAqxv5URuY=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
golang.org/x/crypto v0.14.0/go.mod h1:MVFd36DqK4CsrnJYDkBA3VC4m2GkXAM0PvzMCn4JQf4=
golang.org/x/crypto v0.15.0 h1:frVn1TEaCEaZcn3Tmd7Y2b5KKPaZ+I32Q2OA3kYp5TA=
golang.org/x/crypto v0.15.0/go.mod h1:4ChreQoLWfG3xLDer1WdlH5NdlQ3+mwnQq1YTKY+72g=
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
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 v0.10.0 h1:lFO9qtOdlre5W1jxS3r/4szv2/6iXxScdzjoBMXNhYk=
golang.org/x/mod v0.10.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
Expand All @@ -194,11 +231,15 @@ golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
golang.org/x/net v0.17.0 h1:pVaXccu2ozPjCXewfr1S7xza/zcXTity9cCdXQYSjIM=
golang.org/x/net v0.17.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/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 v0.2.0 h1:PUR+T4wwASmuSTYdKjYHI5TD22Wy5ogLU5qZCOLxBrI=
golang.org/x/sync v0.2.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
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 v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
Expand Down Expand Up @@ -231,15 +272,21 @@ golang.org/x/time v0.4.0 h1:Z81tqI5ddIoXDPvVQ7/7CC9TnLM7ubaFG2qXYd5BbYY=
golang.org/x/time v0.4.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
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 v0.9.1 h1:8WMNJAz3zrtPmnYC7ISf5dEn3MT0gY7jBJfw27yrrLo=
golang.org/x/tools v0.9.1/go.mod h1:owI94Op576fPu3cIGQeHs3joujW/2Oc6MtlxbF5dfNc=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127 h1:qIbj1fsPNlZgppZ+VLlY7N33q108Sa+fhmuc+sWQYwY=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/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 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gotest.tools/v3 v3.5.1 h1:EENdUnS3pdur5nybKYIh2Vfgc8IUNBjxDPSjtiJcOzU=
gotest.tools/v3 v3.5.1/go.mod h1:isy3WKz7GK6uNw/sbHzfKBLvlvXwUyV06n6brMxxopU=
24 changes: 16 additions & 8 deletions pkg/crawler.go
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,9 @@ type Crawler interface {
StartFromCLI() bool

GetStream() Stream

GetCDP() bool
WithCDP(bool) Crawler
}

type CrawlOption func(Crawler)
Expand Down Expand Up @@ -86,6 +89,11 @@ func WithItemConcurrency(concurrency uint8) CrawlOption {
crawler.WithItemConcurrency(concurrency)
}
}
func WithCDP(cdp bool) CrawlOption {
return func(crawler Crawler) {
crawler.WithCDP(cdp)
}
}

type CrawlerStatus uint8

Expand All @@ -99,19 +107,19 @@ const (
CrawlerStatusStopped
)

func (c *CrawlerStatus) String() string {
switch *c {
case 1:
func (c CrawlerStatus) String() string {
switch c {
case CrawlerStatusReady:
return "ready"
case 2:
case CrawlerStatusStarting:
return "starting"
case 3:
case CrawlerStatusRunning:
return "running"
case 4:
case CrawlerStatusIdle:
return "idle"
case 5:
case CrawlerStatusStopping:
return "stopping"
case 6:
case CrawlerStatusStopped:
return "stopped"
default:
return "unknown"
Expand Down
10 changes: 10 additions & 0 deletions pkg/crawler/crawler.go
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,16 @@ type Crawler struct {
ug *uid.Uid

stream pkg.Stream

cdp bool
}

func (c *Crawler) GetCDP() bool {
return c.cdp
}
func (c *Crawler) WithCDP(cdp bool) pkg.Crawler {
c.cdp = cdp
return c
}

func (c *Crawler) GetStream() pkg.Stream {
Expand Down
14 changes: 12 additions & 2 deletions pkg/downloader/downloader.go
Original file line number Diff line number Diff line change
Expand Up @@ -45,11 +45,16 @@ func (d *Downloader) Download(ctx pkg.Context, request pkg.Request) (response pk
client := d.httpClient
if request.GetClient() == pkg.ClientBrowser {
var b *browser.Browser
if d.browserManager == nil {
d.browserManager = new(browser.Manager).FromSpider(d.spider)
}

b, err = d.browserManager.Pop(context.Background())
if err != nil {
d.logger.Error(err)
return
}

client = b
defer d.browserManager.Put(b)
}
Expand Down Expand Up @@ -122,7 +127,10 @@ func (d *Downloader) spiderClosed(ctx pkg.Context) (err error) {
if ctx.GetSpider().GetStatus() != pkg.SpiderStatusStopped {
return
}
d.browserManager.Close()

if d.browserManager != nil {
d.browserManager.Close()
}
return
}
func (d *Downloader) FromSpider(spider pkg.Spider) pkg.Downloader {
Expand All @@ -133,8 +141,10 @@ func (d *Downloader) FromSpider(spider pkg.Spider) pkg.Downloader {
d.spider = spider
d.logger = spider.GetLogger()
d.httpClient = new(http_client.HttpClient).FromSpider(spider)
d.browserManager = new(browser.Manager).FromSpider(spider)
d.middlewares = new(middlewares.Middlewares).FromSpider(spider)
if spider.GetCrawler().GetCDP() {
d.browserManager = new(browser.Manager).FromSpider(d.spider)
}

spider.GetCrawler().GetSignal().RegisterSpiderChanged(d.spiderClosed)
return d
Expand Down
12 changes: 6 additions & 6 deletions pkg/spider.go
Original file line number Diff line number Diff line change
Expand Up @@ -355,17 +355,17 @@ const (

func (s SpiderStatus) String() string {
switch s {
case 1:
case SpiderStatusReady:
return "ready"
case 2:
case SpiderStatusStarting:
return "starting"
case 3:
case SpiderStatusRunning:
return "running"
case 4:
case SpiderStatusIdle:
return "idle"
case 5:
case SpiderStatusStopping:
return "stopping"
case 6:
case SpiderStatusStopped:
return "stopped"
default:
return "unknown"
Expand Down
Loading

0 comments on commit 7c81a24

Please sign in to comment.