From fe02101a129e9b23411072e70d40957318c7ab1f Mon Sep 17 00:00:00 2001 From: Thomas Kosmas Date: Thu, 31 Oct 2024 14:40:33 +0200 Subject: [PATCH 1/2] Iframe support --- apps/api/src/lib/go-html-to-md/go.mod | 4 ++- apps/api/src/lib/go-html-to-md/go.sum | 33 ++----------------- .../src/lib/go-html-to-md/html-to-markdown.go | 4 +-- .../utils/removeUnwantedElements.ts | 2 +- 4 files changed, 8 insertions(+), 35 deletions(-) diff --git a/apps/api/src/lib/go-html-to-md/go.mod b/apps/api/src/lib/go-html-to-md/go.mod index 0836f441..ad50981f 100644 --- a/apps/api/src/lib/go-html-to-md/go.mod +++ b/apps/api/src/lib/go-html-to-md/go.mod @@ -2,7 +2,7 @@ module html-to-markdown.go go 1.19 -require github.com/JohannesKaufmann/html-to-markdown v1.6.0 +require github.com/tomkosm/html-to-markdown v0.0.0-20241031120941-3a729f6b7751 require ( github.com/PuerkitoBio/goquery v1.9.2 // indirect @@ -12,3 +12,5 @@ require ( gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c // indirect gopkg.in/yaml.v2 v2.4.0 // indirect ) + +replace github.com/JohannesKaufmann/html-to-markdown => github.com/tomkosm/html-to-markdown v0.0.0-20241031120941-3a729f6b7751 diff --git a/apps/api/src/lib/go-html-to-md/go.sum b/apps/api/src/lib/go-html-to-md/go.sum index 7961629d..a2c6c64f 100644 --- a/apps/api/src/lib/go-html-to-md/go.sum +++ b/apps/api/src/lib/go-html-to-md/go.sum @@ -1,12 +1,8 @@ -github.com/JohannesKaufmann/html-to-markdown v1.6.0 h1:04VXMiE50YYfCfLboJCLcgqF5x+rHJnb1ssNmqpLH/k= -github.com/JohannesKaufmann/html-to-markdown v1.6.0/go.mod h1:NUI78lGg/a7vpEJTz/0uOcYMaibytE4BUOQS8k78yPQ= github.com/PuerkitoBio/goquery v1.9.2 h1:4/wZksC3KgkQw7SQgkKotmKljk0M6V8TUvA8Wb4yPeE= github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk= 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/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= -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/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 v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0= @@ -15,27 +11,17 @@ 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= github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE= -github.com/pkg/errors v0.8.1/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/rogpeppe/go-internal v1.6.1 h1:/FiVV8dS/e+YqF2JvO3yXRFbBLTIuSDkuC7aBOAvL+k= github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc= github.com/sebdah/goldie/v2 v2.5.3 h1:9ES/mNN+HNUbNWpVAlrzuZ7jE+Nrczbj8uFRjM7624Y= -github.com/sebdah/goldie/v2 v2.5.3/go.mod h1:oZ9fp0+se1eapSRjfYbsV/0Hqhbuu3bJVvKI/NNtssI= -github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo= github.com/sergi/go-diff v1.3.1 h1:xkr+Oxo4BOQKmkn/B9eMK0g5Kg/983T9DqqPHwYqD+8= -github.com/sergi/go-diff v1.3.1/go.mod h1:aMJSSKb2lpPvRNec0+w3fl7LP9IOFzdc9Pa4NFbPK1I= -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 v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4= +github.com/tomkosm/html-to-markdown v0.0.0-20241031120941-3a729f6b7751 h1:l6JdzR2ry727okVeBxnH8nh3SAd7l/0gJTWbK/3UBRY= +github.com/tomkosm/html-to-markdown v0.0.0-20241031120941-3a729f6b7751/go.mod h1:I2mfsDlV0RelCsTjeYh9mdXdwD2M70rA7LT/y2girik= github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY= github.com/yuin/goldmark v1.7.1 h1:3bajkSilaCbjdKVsKdZjZCLBNPL9pYzrCakKaf4U49U= -github.com/yuin/goldmark v1.7.1/go.mod h1:uzxRWxtg69N339t3louHJ7+O03ezfj6PlliRlaOzY1E= 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 v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU= -golang.org/x/crypto v0.22.0/go.mod h1:vr6Su+7cTlO45qkww3VDJlzDn0ctJvRgYbC2NvXHt+M= -golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8= 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/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s= @@ -43,9 +29,6 @@ golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v 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 v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns= -golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg= -golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44= -golang.org/x/net v0.24.0/go.mod h1:2Q7sJY5mzlzWjKtYUEXSlBWCdyaioyXzRB2RtU8KVE8= golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac= golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM= golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= @@ -58,25 +41,15 @@ golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBc 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 v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= -golang.org/x/sys v0.19.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= -golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= 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 v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk= -golang.org/x/term v0.19.0/go.mod h1:2CuTdWZ7KHSQwUzKva0cbMg6q2DMI3Mmxp+gKJbskEk= -golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY= 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 v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU= -golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU= 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 v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc= @@ -84,10 +57,8 @@ golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU= golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/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/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= -gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk= gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q= gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI= -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/apps/api/src/lib/go-html-to-md/html-to-markdown.go b/apps/api/src/lib/go-html-to-md/html-to-markdown.go index 9905a69a..67c4276f 100644 --- a/apps/api/src/lib/go-html-to-md/html-to-markdown.go +++ b/apps/api/src/lib/go-html-to-md/html-to-markdown.go @@ -4,8 +4,8 @@ import ( "C" "log" - md "github.com/JohannesKaufmann/html-to-markdown" - "github.com/JohannesKaufmann/html-to-markdown/plugin" + md "github.com/tomkosm/html-to-markdown" + "github.com/tomkosm/html-to-markdown/plugin" ) //export ConvertHTMLToMarkdown diff --git a/apps/api/src/scraper/WebScraper/utils/removeUnwantedElements.ts b/apps/api/src/scraper/WebScraper/utils/removeUnwantedElements.ts index c2d588c7..1264f89a 100644 --- a/apps/api/src/scraper/WebScraper/utils/removeUnwantedElements.ts +++ b/apps/api/src/scraper/WebScraper/utils/removeUnwantedElements.ts @@ -29,7 +29,7 @@ export const removeUnwantedElements = ( } } - soup("script, style, iframe, noscript, meta, head").remove(); + soup("script, style, noscript, meta, head").remove(); if ( pageOptions.removeTags && From 367af9512fa47d9bd41fd9822b81031517b809c0 Mon Sep 17 00:00:00 2001 From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com> Date: Thu, 31 Oct 2024 10:53:47 -0300 Subject: [PATCH 2/2] added iframe links to extractLinksFromHTML --- apps/api/src/scraper/WebScraper/crawler.ts | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/apps/api/src/scraper/WebScraper/crawler.ts b/apps/api/src/scraper/WebScraper/crawler.ts index 72a49fd8..1ae166b4 100644 --- a/apps/api/src/scraper/WebScraper/crawler.ts +++ b/apps/api/src/scraper/WebScraper/crawler.ts @@ -333,6 +333,16 @@ export class WebCrawler { } }); + // Extract links from iframes with inline src + $("iframe").each((_, element) => { + const src = $(element).attr("src"); + if (src && src.startsWith("data:text/html")) { + const iframeHtml = decodeURIComponent(src.split(",")[1]); + const iframeLinks = this.extractLinksFromHTML(iframeHtml, url); + links = links.concat(iframeLinks); + } + }); + return links; }