Stowage/browsertrix-crawler
2
0
Fork 0
mirror of https://github.com/webrecorder/browsertrix-crawler.git synced 2025-10-19 06:23:16 +00:00
Code Issues Projects Releases Packages Wiki Activity

add support for sitemaps with --useSitemap flag, defaults to /sitemap.xml if no string provided

Browse source
This commit is contained in:
Ilya Kreymer 2020-11-14 21:55:02 +00:00
parent 92b251f0cb
commit 082667099d
3 changed files with 233 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

195
yarn.lock
View file

@ -39,16 +39,57 @@
minimatch "^3.0.4"
strip-json-comments "^3.1.1"
"@sindresorhus/is@^4.0.0":
version "4.0.0"
resolved "https://registry.yarnpkg.com/@sindresorhus/is/-/is-4.0.0.tgz#2ff674e9611b45b528896d820d3d7a812de2f0e4"
integrity sha512-FyD2meJpDPjyNQejSjvnhpgI/azsQkA4lGbuu5BQZfjvJ9cbRZXzeWL2HceCekW4lixO9JPesIIQkSoLjeJHNQ==
"@szmarczak/http-timer@^4.0.5":
version "4.0.5"
resolved "https://registry.yarnpkg.com/@szmarczak/http-timer/-/http-timer-4.0.5.tgz#bfbd50211e9dfa51ba07da58a14cdfd333205152"
integrity sha512-PyRA9sm1Yayuj5OIoJ1hGt2YISX45w9WcFbh6ddT0Z/0yaFxOtGLInr4jUfU1EAFVs0Yfyfev4RNwBlUaHdlDQ==
dependencies:
defer-to-connect "^2.0.0"
"@types/cacheable-request@^6.0.1":
version "6.0.1"
resolved "https://registry.yarnpkg.com/@types/cacheable-request/-/cacheable-request-6.0.1.tgz#5d22f3dded1fd3a84c0bbeb5039a7419c2c91976"
integrity sha512-ykFq2zmBGOCbpIXtoVbz4SKY5QriWPh3AjyU4G74RYbtt5yOc5OfaY75ftjg7mikMOla1CTGpX3lLbuJh8DTrQ==
dependencies:
"@types/http-cache-semantics" "*"
"@types/keyv" "*"
"@types/node" "*"
"@types/responselike" "*"
"@types/color-name@^1.1.1":
version "1.1.1"
resolved "https://registry.yarnpkg.com/@types/color-name/-/color-name-1.1.1.tgz#1c1261bbeaa10a8055bbc5d8ab84b7b2afc846a0"
integrity sha512-rr+OQyAjxze7GgWrSaJwydHStIhHq2lvY3BOC2Mj7KnzI7XK0Uw1TOOdI9lDoajEbSWLiYgoo4f1R51erQfhPQ==
"@types/http-cache-semantics@*":
version "4.0.0"
resolved "https://registry.yarnpkg.com/@types/http-cache-semantics/-/http-cache-semantics-4.0.0.tgz#9140779736aa2655635ee756e2467d787cfe8a2a"
integrity sha512-c3Xy026kOF7QOTn00hbIllV1dLR9hG9NkSrLQgCVs8NF6sBU+VGWjD3wLPhmh1TYAc7ugCFsvHYMN4VcBN1U1A==
"@types/keyv@*":
version "3.1.1"
resolved "https://registry.yarnpkg.com/@types/keyv/-/keyv-3.1.1.tgz#e45a45324fca9dab716ab1230ee249c9fb52cfa7"
integrity sha512-MPtoySlAZQ37VoLaPcTHCu1RWJ4llDkULYZIzOYxlhxBqYPB0RsRlmMU0R6tahtFe27mIdkHV+551ZWV4PLmVw==
dependencies:
"@types/node" "*"
"@types/node@*":
version "14.14.0"
resolved "https://registry.yarnpkg.com/@types/node/-/node-14.14.0.tgz#f1091b6ad5de18e8e91bdbd43ec63f13de372538"
integrity sha512-BfbIHP9IapdupGhq/hc+jT5dyiBVZ2DdeC5WwJWQWDb0GijQlzUFAeIQn/2GtvZcd2HVUU7An8felIICFTC2qg==
"@types/responselike@*", "@types/responselike@^1.0.0":
version "1.0.0"
resolved "https://registry.yarnpkg.com/@types/responselike/-/responselike-1.0.0.tgz#251f4fe7d154d2bad125abe1b429b23afd262e29"
integrity sha512-85Y2BjiufFzaMIlvJDvTTB8Fxl2xfLo4HgmHzVBz08w4wDePCTjYw66PdrolO0kzli3yam/YCgRufyo1DdQVTA==
dependencies:
"@types/node" "*"
"@types/yauzl@^2.9.1":
version "2.9.1"
resolved "https://registry.yarnpkg.com/@types/yauzl/-/yauzl-2.9.1.tgz#d10f69f9f522eef3cf98e30afb684a1e1ec923af"
@ -177,6 +218,24 @@ buffer@^5.2.1, buffer@^5.5.0:
base64-js "^1.0.2"
ieee754 "^1.1.4"
cacheable-lookup@^5.0.3:
version "5.0.3"
resolved "https://registry.yarnpkg.com/cacheable-lookup/-/cacheable-lookup-5.0.3.tgz#049fdc59dffdd4fc285e8f4f82936591bd59fec3"
integrity sha512-W+JBqF9SWe18A72XFzN/V/CULFzPm7sBXzzR6ekkE+3tLG72wFZrBiBZhrZuDoYexop4PHJVdFAKb/Nj9+tm9w==
cacheable-request@^7.0.1:
version "7.0.1"
resolved "https://registry.yarnpkg.com/cacheable-request/-/cacheable-request-7.0.1.tgz#062031c2856232782ed694a257fa35da93942a58"
integrity sha512-lt0mJ6YAnsrBErpTMWeu5kl/tg9xMAWjavYTN6VQXM1A/teBITuNcccXsCxF0tDQQJf9DfAaX5O4e0zp0KlfZw==
dependencies:
clone-response "^1.0.2"
get-stream "^5.1.0"
http-cache-semantics "^4.0.0"
keyv "^4.0.0"
lowercase-keys "^2.0.0"
normalize-url "^4.1.0"
responselike "^2.0.0"
callsites@^3.0.0:
version "3.1.0"
resolved "https://registry.yarnpkg.com/callsites/-/callsites-3.1.0.tgz#b3630abd8943432f54b3f0519238e33cd7df2f73"
@ -213,6 +272,13 @@ cliui@^7.0.0:
strip-ansi "^6.0.0"
wrap-ansi "^7.0.0"
clone-response@^1.0.2:
version "1.0.2"
resolved "https://registry.yarnpkg.com/clone-response/-/clone-response-1.0.2.tgz#d1dc973920314df67fbeb94223b4ee350239e96b"
integrity sha1-0dyXOSAxTfZ/vrlCI7TuNQI56Ws=
dependencies:
mimic-response "^1.0.0"
color-convert@^1.9.0:
version "1.9.3"
resolved "https://registry.yarnpkg.com/color-convert/-/color-convert-1.9.3.tgz#bb71850690e1f136567de629d2d5471deda4c1e8"
@ -258,11 +324,23 @@ debug@4, debug@^4.0.1, debug@^4.1.0, debug@^4.1.1:
dependencies:
ms "2.1.2"
decompress-response@^6.0.0:
version "6.0.0"
resolved "https://registry.yarnpkg.com/decompress-response/-/decompress-response-6.0.0.tgz#ca387612ddb7e104bd16d85aab00d5ecf09c66fc"
integrity sha512-aW35yZM6Bb/4oJlZncMH2LCoZtJXTRxES17vE3hoRiowU2kWHaJKFkSBDnDR+cm9J+9QhXmREyIfv0pji9ejCQ==
dependencies:
mimic-response "^3.1.0"
deep-is@^0.1.3:
version "0.1.3"
resolved "https://registry.yarnpkg.com/deep-is/-/deep-is-0.1.3.tgz#b369d6fb5dbc13eecf524f91b070feedc357cf34"
integrity sha1-s2nW+128E+7PUk+RsHD+7cNXzzQ=
defer-to-connect@^2.0.0:
version "2.0.0"
resolved "https://registry.yarnpkg.com/defer-to-connect/-/defer-to-connect-2.0.0.tgz#83d6b199db041593ac84d781b5222308ccf4c2c1"
integrity sha512-bYL2d05vOSf1JEZNx5vSAtPuBMkX8K9EUutg7zlKvTqKXHt7RhWJFbmd7qakVuf13i+IkGmp6FwSsONOf6VYIg==
devtools-protocol@0.0.799653:
version "0.0.799653"
resolved "https://registry.yarnpkg.com/devtools-protocol/-/devtools-protocol-0.0.799653.tgz#86fc95ce5bf4fdf4b77a58047ba9d2301078f119"
@ -540,6 +618,23 @@ globals@^12.1.0:
dependencies:
type-fest "^0.8.1"
got@^11.8.0:
version "11.8.0"
resolved "https://registry.yarnpkg.com/got/-/got-11.8.0.tgz#be0920c3586b07fd94add3b5b27cb28f49e6545f"
integrity sha512-k9noyoIIY9EejuhaBNLyZ31D5328LeqnyPNXJQb2XlJZcKakLqN5m6O/ikhq/0lw56kUYS54fVm+D1x57YC9oQ==
dependencies:
"@sindresorhus/is" "^4.0.0"
"@szmarczak/http-timer" "^4.0.5"
"@types/cacheable-request" "^6.0.1"
"@types/responselike" "^1.0.0"
cacheable-lookup "^5.0.3"
cacheable-request "^7.0.1"
decompress-response "^6.0.0"
http2-wrapper "^1.0.0-beta.5.2"
lowercase-keys "^2.0.0"
p-cancelable "^2.0.0"
responselike "^2.0.0"
has-flag@^3.0.0:
version "3.0.0"
resolved "https://registry.yarnpkg.com/has-flag/-/has-flag-3.0.0.tgz#b5d454dc2199ae225699f3467e5a07f3b955bafd"
@ -550,6 +645,19 @@ has-flag@^4.0.0:
resolved "https://registry.yarnpkg.com/has-flag/-/has-flag-4.0.0.tgz#944771fd9c81c81265c4d6941860da06bb59479b"
integrity sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==
http-cache-semantics@^4.0.0:
version "4.1.0"
resolved "https://registry.yarnpkg.com/http-cache-semantics/-/http-cache-semantics-4.1.0.tgz#49e91c5cbf36c9b94bcfcd71c23d5249ec74e390"
integrity sha512-carPklcUh7ROWRK7Cv27RPtdhYhUsela/ue5/jKzjegVvXDqM2ILE9Q2BGn9JZJh1g87cp56su/FgQSzcWS8cQ==
http2-wrapper@^1.0.0-beta.5.2:
version "1.0.0-beta.5.2"
resolved "https://registry.yarnpkg.com/http2-wrapper/-/http2-wrapper-1.0.0-beta.5.2.tgz#8b923deb90144aea65cf834b016a340fc98556f3"
integrity sha512-xYz9goEyBnC8XwXDTuC/MZ6t+MrKVQZOk4s7+PaDkwIsQd8IwqvM+0M6bA/2lvG8GHXcPdf+MejTUeO2LCPCeQ==
dependencies:
quick-lru "^5.1.1"
resolve-alpn "^1.0.0"
https-proxy-agent@^4.0.0:
version "4.0.0"
resolved "https://registry.yarnpkg.com/https-proxy-agent/-/https-proxy-agent-4.0.0.tgz#702b71fb5520a132a66de1f67541d9e62154d82b"
@ -634,6 +742,11 @@ js-yaml@^3.13.1:
argparse "^1.0.7"
esprima "^4.0.0"
json-buffer@3.0.1:
version "3.0.1"
resolved "https://registry.yarnpkg.com/json-buffer/-/json-buffer-3.0.1.tgz#9338802a30d3b6605fbe0613e094008ca8c05a13"
integrity sha512-4bV5BfR2mqfQTJm+V5tPPdf+ZpuhiIvTuAB5g8kcrXOZpTT/QwwVRWBywX1ozr6lEuPdbHxwaJlm9G6mI2sfSQ==
json-schema-traverse@^0.4.1:
version "0.4.1"
resolved "https://registry.yarnpkg.com/json-schema-traverse/-/json-schema-traverse-0.4.1.tgz#69f6a87d9513ab8bb8fe63bdb0979c448e684660"
@ -644,6 +757,13 @@ json-stable-stringify-without-jsonify@^1.0.1:
resolved "https://registry.yarnpkg.com/json-stable-stringify-without-jsonify/-/json-stable-stringify-without-jsonify-1.0.1.tgz#9db7b59496ad3f3cfef30a75142d2d930ad72651"
integrity sha1-nbe1lJatPzz+8wp1FC0tkwrXJlE=
keyv@^4.0.0:
version "4.0.3"
resolved "https://registry.yarnpkg.com/keyv/-/keyv-4.0.3.tgz#4f3aa98de254803cafcd2896734108daa35e4254"
integrity sha512-zdGa2TOpSZPq5mU6iowDARnMBZgtCqJ11dJROFi6tg6kTn4nuUdU09lFyLFSaHrWqpIJ+EBq4E8/Dc0Vx5vLdA==
dependencies:
json-buffer "3.0.1"
levn@^0.4.1:
version "0.4.1"
resolved "https://registry.yarnpkg.com/levn/-/levn-0.4.1.tgz#ae4562c007473b932a6200d403268dd2fffc6ade"
@ -664,6 +784,21 @@ lodash@^4.17.14, lodash@^4.17.19:
resolved "https://registry.yarnpkg.com/lodash/-/lodash-4.17.20.tgz#b44a9b6297bcb698f1c51a3545a2b3b368d59c52"
integrity sha512-PlhdFcillOINfeV7Ni6oF1TAEayyZBoZ8bcshTHqOYJYlrqzRK5hagpagky5o4HfCzzd1TRkXPMFq6cKk9rGmA==
lowercase-keys@^2.0.0:
version "2.0.0"
resolved "https://registry.yarnpkg.com/lowercase-keys/-/lowercase-keys-2.0.0.tgz#2603e78b7b4b0006cbca2fbcc8a3202558ac9479"
integrity sha512-tqNXrS78oMOE73NMxK4EMLQsQowWf8jKooH9g7xPavRT706R6bkQJ6DY2Te7QukaZsulxa30wQ7bk0pm4XiHmA==
mimic-response@^1.0.0:
version "1.0.1"
resolved "https://registry.yarnpkg.com/mimic-response/-/mimic-response-1.0.1.tgz#4923538878eef42063cb8a3e3b0798781487ab1b"
integrity sha512-j5EctnkH7amfV/q5Hgmoal1g2QHFJRraOtmx0JpIqkxhBhI/lJSl1nMpQ45hVarwNETOoWEimndZ4QK0RHxuxQ==
mimic-response@^3.1.0:
version "3.1.0"
resolved "https://registry.yarnpkg.com/mimic-response/-/mimic-response-3.1.0.tgz#2d1d59af9c1b129815accc2c46a022a5ce1fa3c9"
integrity sha512-z0yWI+4FDrrweS8Zmt4Ej5HdJmky15+L2e6Wgn3+iK5fWzb6T3fhNFq2+MeTRb064c6Wr4N/wv0DzQTjNzHNGQ==
minimatch@^3.0.4:
version "3.0.4"
resolved "https://registry.yarnpkg.com/minimatch/-/minimatch-3.0.4.tgz#5166e286457f03306064be5497e8dbb0c3d32083"
@ -703,6 +838,11 @@ node-fetch@^2.6.1:
resolved "https://registry.yarnpkg.com/node-fetch/-/node-fetch-2.6.1.tgz#045bd323631f76ed2e2b55573394416b639a0052"
integrity sha512-V4aYg89jEoVRxRb2fJdAg8FHvI7cEyYdVAh94HH0UIK8oJxUfkjlDQN9RbMx+bEjP7+ggMiFRprSti032Oipxw==
normalize-url@^4.1.0:
version "4.5.0"
resolved "https://registry.yarnpkg.com/normalize-url/-/normalize-url-4.5.0.tgz#453354087e6ca96957bd8f5baf753f5982142129"
integrity sha512-2s47yzUxdexf1OhyRi4Em83iQk0aPvwTddtFz4hnSSw9dCEsLEGf6SwIO8ss/19S9iBb5sJaOuTvTGDeZI00BQ==
once@^1.3.0, once@^1.3.1, once@^1.4.0:
version "1.4.0"
resolved "https://registry.yarnpkg.com/once/-/once-1.4.0.tgz#583b1aa775961d4b113ac17d9c50baef9dd76bd1"
@ -722,6 +862,11 @@ optionator@^0.9.1:
type-check "^0.4.0"
word-wrap "^1.2.3"
p-cancelable@^2.0.0:
version "2.0.0"
resolved "https://registry.yarnpkg.com/p-cancelable/-/p-cancelable-2.0.0.tgz#4a3740f5bdaf5ed5d7c3e34882c6fb5d6b266a6e"
integrity sha512-wvPXDmbMmu2ksjkB4Z3nZWTSkJEb9lqVdMaCKpZUGJG9TMiNp9XcbG3fn9fPKjem04fJMJnXoyFPk2FmgiaiNg==
p-limit@^2.2.0:
version "2.3.0"
resolved "https://registry.yarnpkg.com/p-limit/-/p-limit-2.3.0.tgz#3dd33c647a214fdfffd835933eb086da0dc21db1"
@ -827,6 +972,11 @@ puppeteer-core@^5.3.1:
unbzip2-stream "^1.3.3"
ws "^7.2.3"
quick-lru@^5.1.1:
version "5.1.1"
resolved "https://registry.yarnpkg.com/quick-lru/-/quick-lru-5.1.1.tgz#366493e6b3e42a3a6885e2e99d18f80fb7a8c932"
integrity sha512-WuyALRjWPDGtt/wzJiadO5AXY+8hZ80hVpe6MyivgraREW751X3SbhRvG3eLKOYN+8VEvqLcf3wdnt44Z4S4SA==
readable-stream@^3.1.1, readable-stream@^3.4.0:
version "3.6.0"
resolved "https://registry.yarnpkg.com/readable-stream/-/readable-stream-3.6.0.tgz#337bbda3adc0706bd3e024426a286d4b4b2c9198"
@ -846,11 +996,23 @@ require-directory@^2.1.1:
resolved "https://registry.yarnpkg.com/require-directory/-/require-directory-2.1.1.tgz#8c64ad5fd30dab1c976e2344ffe7f792a6a6df42"
integrity sha1-jGStX9MNqxyXbiNE/+f3kqam30I=
resolve-alpn@^1.0.0:
version "1.0.0"
resolved "https://registry.yarnpkg.com/resolve-alpn/-/resolve-alpn-1.0.0.tgz#745ad60b3d6aff4b4a48e01b8c0bdc70959e0e8c"
integrity sha512-rTuiIEqFmGxne4IovivKSDzld2lWW9QCjqv80SYjPgf+gS35eaCAjaP54CCwGAwBtnCsvNLYtqxe1Nw+i6JEmA==
resolve-from@^4.0.0:
version "4.0.0"
resolved "https://registry.yarnpkg.com/resolve-from/-/resolve-from-4.0.0.tgz#4abcd852ad32dd7baabfe9b40e00a36db5f392e6"
integrity sha512-pb/MYmXstAkysRFx8piNI1tGFNQIFA3vkE3Gq4EuA1dF6gHp/+vgZqsCGJapvy8N3Q+4o7FwvquPJcnZ7RYy4g==
responselike@^2.0.0:
version "2.0.0"
resolved "https://registry.yarnpkg.com/responselike/-/responselike-2.0.0.tgz#26391bcc3174f750f9a79eacc40a12a5c42d7723"
integrity sha512-xH48u3FTB9VsZw7R+vvgaKeLKzT6jOogbQhEe/jewwnZgzPcnyWui2Av6JpoYZF/91uueC+lqhWqeURw5/qhCw==
dependencies:
lowercase-keys "^2.0.0"
rimraf@2.6.3:
version "2.6.3"
resolved "https://registry.yarnpkg.com/rimraf/-/rimraf-2.6.3.tgz#b2d104fe0d8fb27cf9e0a1cda8262dd3833c6cab"
@ -870,6 +1032,11 @@ safe-buffer@~5.2.0:
resolved "https://registry.yarnpkg.com/safe-buffer/-/safe-buffer-5.2.1.tgz#1eaf9fa9bdb1fdd4ec75f58f9cdb4e6b7827eec6"
integrity sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ==
sax@>=0.6.0:
version "1.2.4"
resolved "https://registry.yarnpkg.com/sax/-/sax-1.2.4.tgz#2816234e2378bddc4e5354fab5caa895df7100d9"
integrity sha512-NqVDv9TpANUjFm0N8uM5GxL36UgKi9/atZw+x7YFnQ8ckwFGKrl4xX4yWtrey3UJm5nP1kUbnYgLopqWNSRhWw==
semver@^7.2.1:
version "7.3.2"
resolved "https://registry.yarnpkg.com/semver/-/semver-7.3.2.tgz#604962b052b81ed0786aae84389ffba70ffd3938"
@ -887,6 +1054,14 @@ shebang-regex@^3.0.0:
resolved "https://registry.yarnpkg.com/shebang-regex/-/shebang-regex-3.0.0.tgz#ae16f1644d873ecad843b0307b143362d4c42172"
integrity sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==
sitemapper@^3.1.2:
version "3.1.2"
resolved "https://registry.yarnpkg.com/sitemapper/-/sitemapper-3.1.2.tgz#9bb980a394ffb0f9cf151fc7eae3d1bab6db04e5"
integrity sha512-jm97a1KME4Vkpt2mYtDuE5C6gneEvyb6ig+xXw/Hc9Arthkae0CKpNejE517eFPbG88znuTpUN/gSVFz3vMaEQ==
dependencies:
got "^11.8.0"
xml2js-es6-promise "^1.1.1"
slice-ansi@^2.1.0:
version "2.1.0"
resolved "https://registry.yarnpkg.com/slice-ansi/-/slice-ansi-2.1.0.tgz#cacd7693461a637a5788d92a7dd4fba068e81636"
@ -1075,6 +1250,26 @@ ws@^7.2.3:
resolved "https://registry.yarnpkg.com/ws/-/ws-7.3.1.tgz#d0547bf67f7ce4f12a72dfe31262c68d7dc551c8"
integrity sha512-D3RuNkynyHmEJIpD2qrgVkc9DQ23OrN/moAwZX4L8DfvszsJxpjQuUq3LMx6HoYji9fbIOBY18XWBsAux1ZZUA==
xml2js-es6-promise@^1.1.1:
version "1.1.1"
resolved "https://registry.yarnpkg.com/xml2js-es6-promise/-/xml2js-es6-promise-1.1.1.tgz#cd5688d9d6344e67c908f71e5b0a3d88d128e9a2"
integrity sha1-zVaI2dY0TmfJCPceWwo9iNEo6aI=
dependencies:
xml2js "^0.4.16"
xml2js@^0.4.16:
version "0.4.23"
resolved "https://registry.yarnpkg.com/xml2js/-/xml2js-0.4.23.tgz#a0c69516752421eb2ac758ee4d4ccf58843eac66"
integrity sha512-ySPiMjM0+pLDftHgXY4By0uswI3SPKLDw/i3UXbnO8M/p28zqexCUoPmQFrYD+/1BzhGJSs2i1ERWKJAtiLrug==
dependencies:
sax ">=0.6.0"
xmlbuilder "~11.0.0"
xmlbuilder@~11.0.0:
version "11.0.1"
resolved "https://registry.yarnpkg.com/xmlbuilder/-/xmlbuilder-11.0.1.tgz#be9bae1c8a046e76b31127726347d0ad7002beb3"
integrity sha512-fDlsI/kFEx7gLvbecc0/ohLG50fugQp8ryHzMTuW9vSa1GJ0XYWKnhsUx7oie3G98+r56aTQIUB4kht42R3JvA==
y18n@^5.0.1:
version "5.0.1"
resolved "https://registry.yarnpkg.com/y18n/-/y18n-5.0.1.tgz#1ad2a7eddfa8bce7caa2e1f6b5da96c39d99d571"