✨ Scrap site following rss / atom feed
This commit is contained in:
parent
5aae59a629
commit
4b57fd9f19
6
go.mod
6
go.mod
@ -24,9 +24,9 @@ require (
|
||||
|
||||
require (
|
||||
filippo.io/edwards25519 v1.1.0 // indirect
|
||||
github.com/PuerkitoBio/goquery v1.10.0 // indirect
|
||||
github.com/PuerkitoBio/goquery v1.10.1 // indirect
|
||||
github.com/andybalholm/brotli v1.1.1 // indirect
|
||||
github.com/andybalholm/cascadia v1.3.2 // indirect
|
||||
github.com/andybalholm/cascadia v1.3.3 // indirect
|
||||
github.com/antchfx/htmlquery v1.3.3 // indirect
|
||||
github.com/antchfx/xmlquery v1.4.2 // indirect
|
||||
github.com/antchfx/xpath v1.3.2 // indirect
|
||||
@ -61,6 +61,8 @@ require (
|
||||
github.com/mattn/go-isatty v0.0.20 // indirect
|
||||
github.com/mattn/go-runewidth v0.0.16 // indirect
|
||||
github.com/mitchellh/mapstructure v1.5.0 // indirect
|
||||
github.com/mmcdole/gofeed v1.3.0 // indirect
|
||||
github.com/mmcdole/goxpp v1.1.1 // indirect
|
||||
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
|
||||
github.com/modern-go/reflect2 v1.0.2 // indirect
|
||||
github.com/moul/http2curl v1.0.0 // indirect
|
||||
|
38
go.sum
38
go.sum
@ -4,10 +4,14 @@ git.solsynth.dev/hypernet/nexus v0.0.0-20241103165538-c0fec1084611 h1:ZEzUDsO88X
|
||||
git.solsynth.dev/hypernet/nexus v0.0.0-20241103165538-c0fec1084611/go.mod h1:PhLCv2lsNoscPVJbkWnxwQnJ141lc4RIEkVffrHwl4s=
|
||||
github.com/PuerkitoBio/goquery v1.10.0 h1:6fiXdLuUvYs2OJSvNRqlNPoBm6YABE226xrbavY5Wv4=
|
||||
github.com/PuerkitoBio/goquery v1.10.0/go.mod h1:TjZZl68Q3eGHNBA8CWaxAN7rOU1EbDz3CWuolcO5Yu4=
|
||||
github.com/PuerkitoBio/goquery v1.10.1 h1:Y8JGYUkXWTGRB6Ars3+j3kN0xg1YqqlwvdTV8WTFQcU=
|
||||
github.com/PuerkitoBio/goquery v1.10.1/go.mod h1:IYiHrOMps66ag56LEH7QYDDupKXyo5A8qrjIx3ZtujY=
|
||||
github.com/andybalholm/brotli v1.1.1 h1:PR2pgnyFznKEugtsUo0xLdDop5SKXd5Qf5ysW+7XdTA=
|
||||
github.com/andybalholm/brotli v1.1.1/go.mod h1:05ib4cKhjx3OQYUY22hTVd34Bc8upXjOLL2rKwwZBoA=
|
||||
github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss=
|
||||
github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=
|
||||
github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM=
|
||||
github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA=
|
||||
github.com/antchfx/htmlquery v1.3.3 h1:x6tVzrRhVNfECDaVxnZi1mEGrQg3mjE/rxbH2Pe6dNE=
|
||||
github.com/antchfx/htmlquery v1.3.3/go.mod h1:WeU3N7/rL6mb6dCwtE30dURBnBieKDC/fR8t6X+cKjU=
|
||||
github.com/antchfx/xmlquery v1.4.2 h1:MZKd9+wblwxfQ1zd1AdrTsqVaMjMCwow3IqkCSe00KA=
|
||||
@ -132,6 +136,10 @@ github.com/microsoft/go-mssqldb v0.17.0 h1:Fto83dMZPnYv1Zwx5vHHxpNraeEaUlQ/hhHLg
|
||||
github.com/microsoft/go-mssqldb v0.17.0/go.mod h1:OkoNGhGEs8EZqchVTtochlXruEhEOaO4S0d2sB5aeGQ=
|
||||
github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=
|
||||
github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
|
||||
github.com/mmcdole/gofeed v1.3.0 h1:5yn+HeqlcvjMeAI4gu6T+crm7d0anY85+M+v6fIFNG4=
|
||||
github.com/mmcdole/gofeed v1.3.0/go.mod h1:9TGv2LcJhdXePDzxiuMnukhV2/zb6VtnZt1mS+SjkLE=
|
||||
github.com/mmcdole/goxpp v1.1.1 h1:RGIX+D6iQRIunGHrKqnA2+700XMCnNv0bAOOv5MUhx8=
|
||||
github.com/mmcdole/goxpp v1.1.1/go.mod h1:v+25+lT2ViuQ7mVxcncQ8ch1URund48oH+jhjiwEgS8=
|
||||
github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
|
||||
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
|
||||
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
|
||||
@ -211,6 +219,10 @@ go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN8
|
||||
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 v0.0.0-20210921155107-089bfa567519/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 v0.32.0 h1:euUpcYgM8WcP71gNpTqQCn6rC2t6ULUPiOzfWaXVVfc=
|
||||
golang.org/x/crypto v0.32.0/go.mod h1:ZnnJkOaASj8g0AjIduWNlq2NRxL0PlBrbKVyZ6V/Ugc=
|
||||
golang.org/x/exp v0.0.0-20241009180824-f66d83c29e7c h1:7dEasQXItcW1xKJ2+gg5VOiBnqWrJc+rq0DPKyvvdbY=
|
||||
@ -218,6 +230,9 @@ golang.org/x/exp v0.0.0-20241009180824-f66d83c29e7c/go.mod h1:NQtJDoLvd6faHhE7m4
|
||||
golang.org/x/mod v0.4.2/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 v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
|
||||
golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
|
||||
golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
|
||||
golang.org/x/net v0.0.0-20190404232315-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 v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
|
||||
@ -226,12 +241,20 @@ golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug
|
||||
golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
|
||||
golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
|
||||
golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
|
||||
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 v0.34.0 h1:Mb7Mrk043xzHgnRM88suvJFwzVrRfHEHJEl5/71CKw0=
|
||||
golang.org/x/net v0.34.0/go.mod h1:di0qlW3YNM5oh6GqDGQr92MyTozJPmybPK4Ev/Gm31k=
|
||||
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
||||
golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/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 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ=
|
||||
golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
|
||||
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
|
||||
@ -247,19 +270,32 @@ golang.org/x/sys v0.0.0-20221010170243-090e33056c14/go.mod h1:oPkhp1MJrh7nUepCBc
|
||||
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.7.0/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 v0.29.0 h1:TPYlXGxvx1MGTn2GiZDhnjPA9wZzZeGKHHmKhHYvgaU=
|
||||
golang.org/x/sys v0.29.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
|
||||
golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=
|
||||
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
|
||||
golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
|
||||
golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
|
||||
golang.org/x/term v0.7.0/go.mod h1:P32HKFT3hSsZrRxla30E9HqToFYAQPCMs/zFMBUFqPY=
|
||||
golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
|
||||
golang.org/x/term v0.12.0/go.mod h1:owVbMEjm3cBLCHdkQu9b1opXd4ETQWc3BhuQGKgXgvU=
|
||||
golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
|
||||
golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
|
||||
golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=
|
||||
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
|
||||
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
|
||||
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
|
||||
golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ=
|
||||
golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
|
||||
golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
|
||||
golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
|
||||
golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
|
||||
golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
|
||||
golang.org/x/text v0.21.0 h1:zyQAAkrwaneQ066sspRyJaG9VNi/YJ1NfzcGB3hZ/qo=
|
||||
golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
|
||||
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
|
||||
@ -267,6 +303,8 @@ golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtn
|
||||
golang.org/x/tools v0.1.1/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
|
||||
golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
|
||||
golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
|
||||
golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58=
|
||||
golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
|
||||
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
|
||||
golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
|
||||
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
|
||||
|
@ -3,6 +3,7 @@ package models
|
||||
import (
|
||||
"crypto/md5"
|
||||
"encoding/hex"
|
||||
"time"
|
||||
|
||||
"git.solsynth.dev/hypernet/nexus/pkg/nex/cruda"
|
||||
"github.com/google/uuid"
|
||||
@ -11,13 +12,14 @@ import (
|
||||
type NewsArticle struct {
|
||||
cruda.BaseModel
|
||||
|
||||
Thumbnail string `json:"thumbnail"`
|
||||
Title string `json:"title"`
|
||||
Description string `json:"description"`
|
||||
Content string `json:"content"`
|
||||
URL string `json:"url"`
|
||||
Hash string `json:"hash" gorm:"uniqueIndex"`
|
||||
Source string `json:"source"`
|
||||
Thumbnail string `json:"thumbnail"`
|
||||
Title string `json:"title"`
|
||||
Description string `json:"description"`
|
||||
Content string `json:"content"`
|
||||
URL string `json:"url"`
|
||||
Hash string `json:"hash" gorm:"uniqueIndex"`
|
||||
Source string `json:"source"`
|
||||
PublishedAt *time.Time `json:"published_at"`
|
||||
}
|
||||
|
||||
func (v *NewsArticle) GenHash() *NewsArticle {
|
||||
|
@ -1,11 +1,14 @@
|
||||
package services
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"strconv"
|
||||
"time"
|
||||
|
||||
"git.solsynth.dev/hypernet/reader/pkg/internal/database"
|
||||
"git.solsynth.dev/hypernet/reader/pkg/internal/models"
|
||||
"github.com/mmcdole/gofeed"
|
||||
"github.com/rs/zerolog/log"
|
||||
"github.com/samber/lo"
|
||||
"github.com/sogko/go-wordpress"
|
||||
@ -59,6 +62,8 @@ func NewsSourceRead(src models.NewsSource, eager ...bool) ([]models.NewsArticle,
|
||||
return newsSourceReadWordpress(src, eager...)
|
||||
case "scrap":
|
||||
return newsSourceReadScrap(src)
|
||||
case "feed":
|
||||
return newsSourceReadFeed(src)
|
||||
default:
|
||||
return nil, fmt.Errorf("unsupported news source type: %s", src.Type)
|
||||
}
|
||||
@ -73,6 +78,10 @@ func newsSourceReadWordpress(src models.NewsSource, eager ...bool) ([]models.New
|
||||
URL: post.Link,
|
||||
Source: src.ID,
|
||||
}
|
||||
time, err := time.Parse("2006-01-02T15:04:05", post.DateGMT)
|
||||
if err == nil {
|
||||
article.PublishedAt = &time
|
||||
}
|
||||
article.GenHash()
|
||||
return *article
|
||||
}
|
||||
@ -109,6 +118,51 @@ func newsSourceReadWordpress(src models.NewsSource, eager ...bool) ([]models.New
|
||||
return result, nil
|
||||
}
|
||||
|
||||
func newsSourceReadFeed(src models.NewsSource) ([]models.NewsArticle, error) {
|
||||
pgConvert := func(article models.NewsArticle) models.NewsArticle {
|
||||
art := &article
|
||||
art.GenHash()
|
||||
art.Source = src.ID
|
||||
article = *art
|
||||
return article
|
||||
}
|
||||
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
|
||||
defer cancel()
|
||||
fp := gofeed.NewParser()
|
||||
feed, _ := fp.ParseURLWithContext(src.Source, ctx)
|
||||
|
||||
var result []models.NewsArticle
|
||||
for _, item := range feed.Items {
|
||||
parent := models.NewsArticle{
|
||||
Title: item.Title,
|
||||
Description: item.Description,
|
||||
}
|
||||
if item.PublishedParsed != nil {
|
||||
parent.PublishedAt = item.PublishedParsed
|
||||
}
|
||||
if item.Image != nil {
|
||||
parent.Thumbnail = item.Image.URL
|
||||
}
|
||||
if len(item.Content) > 0 {
|
||||
// Good website, provide content, skip scraping of it
|
||||
parent.Content = item.Content
|
||||
result = append(result, pgConvert(parent))
|
||||
} else {
|
||||
article, err := ScrapNews(item.Link, parent)
|
||||
if err != nil {
|
||||
log.Warn().Err(err).Str("url", item.Link).Msg("Failed to scrap a news article...")
|
||||
continue
|
||||
}
|
||||
result = append(result, pgConvert(*article))
|
||||
}
|
||||
|
||||
log.Debug().Str("url", item.Link).Msg("Scraped a news article...")
|
||||
}
|
||||
|
||||
return result, nil
|
||||
}
|
||||
|
||||
func newsSourceReadScrap(src models.NewsSource) ([]models.NewsArticle, error) {
|
||||
pgConvert := func(article models.NewsArticle) models.NewsArticle {
|
||||
art := &article
|
||||
|
@ -185,7 +185,7 @@ func ScrapNewsIndex(target string) []models.NewsArticle {
|
||||
return result
|
||||
}
|
||||
|
||||
func ScrapNews(target string) (*models.NewsArticle, error) {
|
||||
func ScrapNews(target string, parent ...models.NewsArticle) (*models.NewsArticle, error) {
|
||||
ua := viper.GetString("scraper.news_ua")
|
||||
if len(ua) == 0 {
|
||||
ua = ScrapNewsDefaultUA
|
||||
@ -212,21 +212,35 @@ func ScrapNews(target string) (*models.NewsArticle, error) {
|
||||
URL: target,
|
||||
}
|
||||
|
||||
if len(parent) > 0 {
|
||||
article.Content = parent[0].Content
|
||||
article.Thumbnail = parent[0].Thumbnail
|
||||
article.Description = parent[0].Description
|
||||
}
|
||||
|
||||
c.OnHTML("title", func(e *colly.HTMLElement) {
|
||||
article.Title = e.Text
|
||||
if len(article.Title) == 0 {
|
||||
article.Title = e.Text
|
||||
}
|
||||
})
|
||||
c.OnHTML("meta[name]", func(e *colly.HTMLElement) {
|
||||
switch e.Attr("name") {
|
||||
case "description":
|
||||
article.Description = e.Attr("content")
|
||||
if len(article.Description) == 0 {
|
||||
article.Description = e.Attr("content")
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
c.OnHTML("article", func(e *colly.HTMLElement) {
|
||||
article.Content, _ = e.DOM.Html()
|
||||
if len(article.Content) == 0 {
|
||||
article.Content, _ = e.DOM.Html()
|
||||
}
|
||||
})
|
||||
c.OnHTML("article img", func(e *colly.HTMLElement) {
|
||||
article.Thumbnail = e.Attr("src")
|
||||
if len(article.Thumbnail) == 0 {
|
||||
article.Thumbnail = e.Attr("src")
|
||||
}
|
||||
})
|
||||
|
||||
return article, c.Visit(target)
|
||||
|
@ -14,15 +14,15 @@ enabled = false
|
||||
[[sources]]
|
||||
id = "cnn-politics"
|
||||
label = "CNN Politics"
|
||||
type = "scrap"
|
||||
source = "https://www.cnn.com/politics"
|
||||
enabled = false
|
||||
type = "feed"
|
||||
source = "http://rss.cnn.com/rss/cnn_allpolitics.rss"
|
||||
enabled = true
|
||||
[[sources]]
|
||||
id = "bbc"
|
||||
label = "BBC News"
|
||||
type = "scrap"
|
||||
source = "https://www.bbc.com/news"
|
||||
enabled = true
|
||||
enabled = false
|
||||
|
||||
[debug]
|
||||
database = true
|
||||
|
Loading…
x
Reference in New Issue
Block a user