chore: -

README.md

@@ -18,12 +18,10 @@
 
 ## Features
 
-* Recursively crawls webpages URLs.
-* Parses sitemap
-* Parses robots.txt
-* Extracts URLs from documents *(i.e js, json, xml, csv, txt e.t.c)*.
-* Supports javaScript rendering *(including Single Page Applications such as Angular, React, e.t.c)*.
-* Supports customizable parallelism.
+* Parses sitemap for URLs
+* Parses `robots.txt` for URLs
+* Recursively crawls webpages for URLs.
+* Parses documents (`js`, `json`, `xml`, `csv`, `txt`, e.t.c) for URLs.
 
 ## Installation
 

go.mod

@@ -3,7 +3,6 @@ module github.com/hueristiq/hqcrawl3r
 go 1.20
 
 require (
-	github.com/chromedp/chromedp v0.9.1
 	github.com/gocolly/colly/v2 v2.1.0
 	github.com/hueristiq/hqgoutils v0.0.0-20230313202103-053eefb3d3ec
 	github.com/logrusorgru/aurora/v3 v3.0.0
@@ -17,17 +16,10 @@ require (
 	github.com/antchfx/htmlquery v1.2.3 // indirect
 	github.com/antchfx/xmlquery v1.2.4 // indirect
 	github.com/antchfx/xpath v1.1.8 // indirect
-	github.com/chromedp/cdproto v0.0.0-20230220211738-2b1ec77315c9 // indirect
-	github.com/chromedp/sysutil v1.0.0 // indirect
 	github.com/gobwas/glob v0.2.3 // indirect
-	github.com/gobwas/httphead v0.1.0 // indirect
-	github.com/gobwas/pool v0.2.1 // indirect
-	github.com/gobwas/ws v1.1.0 // indirect
 	github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e // indirect
 	github.com/golang/protobuf v1.4.2 // indirect
-	github.com/josharian/intern v1.0.0 // indirect
 	github.com/kennygrant/sanitize v1.2.4 // indirect
-	github.com/mailru/easyjson v0.7.7 // indirect
 	github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca // indirect
 	github.com/temoto/robotstxt v1.1.1 // indirect
 	golang.org/x/net v0.7.0 // indirect

go.sum

@@ -13,12 +13,6 @@ github.com/antchfx/xpath v1.1.6/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNY
 github.com/antchfx/xpath v1.1.8 h1:PcL6bIX42Px5usSx6xRYw/wjB3wYGkj0MJ9MBzEKVgk=
 github.com/antchfx/xpath v1.1.8/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
 github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
-github.com/chromedp/cdproto v0.0.0-20230220211738-2b1ec77315c9 h1:wMSvdj3BswqfQOXp2R1bJOAE7xIQLt2dlMQDMf836VY=
-github.com/chromedp/cdproto v0.0.0-20230220211738-2b1ec77315c9/go.mod h1:GKljq0VrfU4D5yc+2qA6OVr8pmO/MBbPEWqWQ/oqGEs=
-github.com/chromedp/chromedp v0.9.1 h1:CC7cC5p1BeLiiS2gfNNPwp3OaUxtRMBjfiw3E3k6dFA=
-github.com/chromedp/chromedp v0.9.1/go.mod h1:DUgZWRvYoEfgi66CgZ/9Yv+psgi+Sksy5DTScENWjaQ=
-github.com/chromedp/sysutil v1.0.0 h1:+ZxhTpfpZlmchB58ih/LBHX52ky7w2VhQVKQMucy3Ic=
-github.com/chromedp/sysutil v1.0.0/go.mod h1:kgWmDdq8fTzXYcKIBqIYvRRTnYb9aNS9moAV0xufSww=
 github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
@@ -27,12 +21,6 @@ github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.m
 github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
 github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y=
 github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8=
-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 v1.1.0 h1:7RFti/xnNkMJnrK7D1yQ/iCIB5OrrY/54/H930kIbHA=
-github.com/gobwas/ws v1.1.0/go.mod h1:nzvNcVha5eUziGrbxFCo6qFIojQHjJV5cLYIbezhfL0=
 github.com/gocolly/colly v1.2.0/go.mod h1:Hof5T3ZswNVsOHYmba1u03W65HDWgpV5HifSuueE0EA=
 github.com/gocolly/colly/v2 v2.1.0 h1:k0DuZkDoCsx51bKpRJNEmcxcp+W5N8ziuwGaSDuFoGs=
 github.com/gocolly/colly/v2 v2.1.0/go.mod h1:I2MuhsLjQ+Ex+IzK3afNS8/1qP3AedHOusRPcRdC5o0=
@@ -59,18 +47,10 @@ github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
 github.com/hueristiq/hqgoutils v0.0.0-20230313202103-053eefb3d3ec h1:rK/Tm5QTcb1hXThoQOQ+KnO6cmPDgrSBi5rPObo1OUM=
 github.com/hueristiq/hqgoutils v0.0.0-20230313202103-053eefb3d3ec/go.mod h1:owPR/GbpoJMI3Bvx2NMXqLcwb4p8pd6x2qzuebsgbHk=
 github.com/jawher/mow.cli v1.1.0/go.mod h1:aNaQlc7ozF3vw6IJ2dHjp2ZFiA4ozMIYY6PyuRJwlUg=
-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/kennygrant/sanitize v1.2.4 h1:gN25/otpP5vAsO2djbMhF/LQX6R7+O1TB4yv8NzpJ3o=
 github.com/kennygrant/sanitize v1.2.4/go.mod h1:LGsjYYtgxbetdg5owWB2mpgUL6e2nfw2eObZ0u0qvak=
-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/logrusorgru/aurora/v3 v3.0.0 h1:R6zcoZZbvVcGMvDCKo45A9U/lzYyzl5NfYIvznmDfE4=
 github.com/logrusorgru/aurora/v3 v3.0.0/go.mod h1:vsR12bk5grlLvLXAYrBsb5Oc/N+LxAlxggSjiwMnCUc=
-github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0=
-github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
-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/oxffaa/gopher-parse-sitemap v0.0.0-20191021113419-005d2eb1def4 h1:2vmb32OdDhjZf2ETGDlr9n8RYXx7c+jXPxMiPbwnA+8=
 github.com/oxffaa/gopher-parse-sitemap v0.0.0-20191021113419-005d2eb1def4/go.mod h1:2JQx4jDHmWrbABvpOayg/+OTU6ehN0IyK2EHzceXpJo=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
@@ -112,7 +92,6 @@ golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5h
 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 v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20201207223542-d4d67f95c62d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.6.0 h1:MVltZSvRTcU2ljQOhs94SXPftV6DCNnZViHeQps87pQ=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/term v0.5.0 h1:n2a8QNdAb0sZNpU9R1ALUXBbY+w51fCQDN+7EdxNBsY=