mirror of
https://github.com/webrecorder/browsertrix-crawler.git
synced 2025-10-19 06:23:16 +00:00
Support custom css selectors for extracting links (#689)
Support array of selectors via --selectLinks property in the form [css selector]->[property] or [css selector]->@[attribute].
This commit is contained in:
parent
2a9b152531
commit
d04509639a
11 changed files with 194 additions and 109 deletions
23
yarn.lock
23
yarn.lock
|
@ -1312,16 +1312,16 @@
|
|||
resolved "https://registry.yarnpkg.com/@ungap/structured-clone/-/structured-clone-1.2.0.tgz#756641adb587851b5ccb3e095daf27ae581c8406"
|
||||
integrity sha512-zuVdFrMJiuCDQUMCzQaD6KL28MjnqqN8XnAqiEq9PNm/hCPTSGfrXCOfwj1ow4LFb/tNymJPwsNbVePc1xFqrQ==
|
||||
|
||||
"@webrecorder/wabac@^2.20.0-beta.4":
|
||||
version "2.20.0-beta.4"
|
||||
resolved "https://registry.yarnpkg.com/@webrecorder/wabac/-/wabac-2.20.0-beta.4.tgz#c60fcd00f449cca52ce1a0bef305a06922c9e3e8"
|
||||
integrity sha512-enHYcZoqs7cOu2tdTqVeB/zB27uL4wmCMzvF55bJqdB8d5zgPpY+/fpRA3eLxGrPc0nFYAjsI/aNaa62FH7WKQ==
|
||||
"@webrecorder/wabac@^2.20.0":
|
||||
version "2.20.1"
|
||||
resolved "https://registry.yarnpkg.com/@webrecorder/wabac/-/wabac-2.20.1.tgz#58e397e2ef1c33de1bb37aa4f51fc7f3eec8a1f7"
|
||||
integrity sha512-RX+U6m7aVgvsAfLb9FuLY/PcHCNL5dc1FPaD0GnUiFgswSSe5v4MjIhqJNOnbrJYEcbib81AJfxNuvOyXAJDJQ==
|
||||
dependencies:
|
||||
"@peculiar/asn1-ecc" "^2.3.4"
|
||||
"@peculiar/asn1-schema" "^2.3.3"
|
||||
"@peculiar/x509" "^1.9.2"
|
||||
"@types/js-levenshtein" "^1.1.3"
|
||||
"@webrecorder/wombat" "^3.8.2"
|
||||
"@webrecorder/wombat" "^3.8.3"
|
||||
acorn "^8.10.0"
|
||||
auto-js-ipfs "^2.1.1"
|
||||
base64-js "^1.5.1"
|
||||
|
@ -1342,10 +1342,10 @@
|
|||
stream-browserify "^3.0.0"
|
||||
warcio "^2.3.1"
|
||||
|
||||
"@webrecorder/wombat@^3.8.2":
|
||||
version "3.8.2"
|
||||
resolved "https://registry.yarnpkg.com/@webrecorder/wombat/-/wombat-3.8.2.tgz#e46e18719834d633175eec52ce753a4dc4e48e27"
|
||||
integrity sha512-uUZr9V4UYpVOpM64Tm27ND/hMjDbT37+/qyNaNV6loqDuVzBVQh5w7SfTEy0Bbjj1MYyNZP244mOtWtotTpUEA==
|
||||
"@webrecorder/wombat@^3.8.3":
|
||||
version "3.8.3"
|
||||
resolved "https://registry.yarnpkg.com/@webrecorder/wombat/-/wombat-3.8.3.tgz#c5a077225d1a70def9fbbbfcd50fa4465d236546"
|
||||
integrity sha512-dqgoxigB3OdX5JeB3yxJrUNwFwUBlYC+LmGrLEgGeP259MFzXQLD2pmfuqGt5ygWvIv56SrAMV4sUceux07X2A==
|
||||
dependencies:
|
||||
warcio "^2.3.1"
|
||||
|
||||
|
@ -1963,6 +1963,11 @@ crypto-random-string@^4.0.0:
|
|||
dependencies:
|
||||
type-fest "^1.0.1"
|
||||
|
||||
css-selector-parser@^3.0.5:
|
||||
version "3.0.5"
|
||||
resolved "https://registry.yarnpkg.com/css-selector-parser/-/css-selector-parser-3.0.5.tgz#9b636ebccf7c4bcce5c1ac21ae27de9f01180ae9"
|
||||
integrity sha512-3itoDFbKUNx1eKmVpYMFyqKX04Ww9osZ+dLgrk6GEv6KMVeXUhUnp4I5X+evw+u3ZxVU6RFXSSRxlTeMh8bA+g==
|
||||
|
||||
data-uri-to-buffer@^5.0.1:
|
||||
version "5.0.1"
|
||||
resolved "https://registry.yarnpkg.com/data-uri-to-buffer/-/data-uri-to-buffer-5.0.1.tgz#db89a9e279c2ffe74f50637a59a32fb23b3e4d7c"
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue