fix: Resolves broken Scrapingrobot scraper on new installs.

closes #243
This commit is contained in:
towfiqi 2024-11-12 16:20:48 +06:00
parent d9d7c6347e
commit bc02c929ba
3 changed files with 116 additions and 31 deletions

141
package-lock.json generated
View File

@ -14,7 +14,7 @@
"axios": "^1.1.3",
"axios-retry": "^3.3.1",
"chart.js": "^3.9.1",
"cheerio": "^1.0.0-rc.12",
"cheerio": "^1.0.0",
"concurrently": "^7.6.0",
"cookies": "^0.8.0",
"croner": "^5.3.5",
@ -53,8 +53,8 @@
"@types/jsonwebtoken": "^8.5.9",
"@types/node": "18.11.0",
"@types/nodemailer": "^6.4.6",
"@types/react": "18.0.21",
"@types/react-dom": "18.0.6",
"@types/react": "18.2.0",
"@types/react-dom": "18.2.0",
"@types/react-timeago": "^4.1.3",
"@types/react-window": "^1.8.5",
"autoprefixer": "^10.4.12",
@ -2447,9 +2447,10 @@
"dev": true
},
"node_modules/@types/react": {
"version": "18.0.21",
"resolved": "https://registry.npmjs.org/@types/react/-/react-18.0.21.tgz",
"integrity": "sha512-7QUCOxvFgnD5Jk8ZKlUAhVcRj7GuJRjnjjiY/IUBWKgOlnvDvTMLD4RTF7NPyVmbRhNrbomZiOepg7M/2Kj1mA==",
"version": "18.2.0",
"resolved": "https://registry.npmjs.org/@types/react/-/react-18.2.0.tgz",
"integrity": "sha512-0FLj93y5USLHdnhIhABk83rm8XEGA7kH3cr+YUlvxoUGp1xNt/DINUMvqPxLyOQMzLmZe8i4RTHbvb8MC7NmrA==",
"license": "MIT",
"dependencies": {
"@types/prop-types": "*",
"@types/scheduler": "*",
@ -2457,10 +2458,11 @@
}
},
"node_modules/@types/react-dom": {
"version": "18.0.6",
"resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-18.0.6.tgz",
"integrity": "sha512-/5OFZgfIPSwy+YuIBP/FgJnQnsxhZhjjrnxudMddeblOouIodEQ75X14Rr4wGSG/bknL+Omy9iWlLo1u/9GzAA==",
"version": "18.2.0",
"resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-18.2.0.tgz",
"integrity": "sha512-8yQrvS6sMpSwIovhPOwfyNf2Wz6v/B62LFSVYQ85+Rq3tLsBIG7rP5geMxaijTUxSkrO6RzN/IRuIAADYQsleA==",
"dev": true,
"license": "MIT",
"dependencies": {
"@types/react": "*"
}
@ -3395,7 +3397,8 @@
"node_modules/boolbase": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/boolbase/-/boolbase-1.0.0.tgz",
"integrity": "sha512-JZOSA7Mo9sNGB8+UjSgzdLtokWAky1zbztM3WRLCbZ70/3cTANmQmOdR7y2g+J0e2WXywy1yS468tY+IruqEww=="
"integrity": "sha512-JZOSA7Mo9sNGB8+UjSgzdLtokWAky1zbztM3WRLCbZ70/3cTANmQmOdR7y2g+J0e2WXywy1yS468tY+IruqEww==",
"license": "ISC"
},
"node_modules/brace-expansion": {
"version": "1.1.11",
@ -3708,20 +3711,25 @@
"integrity": "sha512-Ro2JbLmvg83gXF5F4sniaQ+lTbSv18E+TIf2cOeiH1Iqd2PGFOtem+DUufMZsCJwFE7ywPOpfXFBwRTGq7dh6w=="
},
"node_modules/cheerio": {
"version": "1.0.0-rc.12",
"resolved": "https://registry.npmjs.org/cheerio/-/cheerio-1.0.0-rc.12.tgz",
"integrity": "sha512-VqR8m68vM46BNnuZ5NtnGBKIE/DfN0cRIzg9n40EIq9NOv90ayxLBXA8fXC5gquFRGJSTRqBq25Jt2ECLR431Q==",
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/cheerio/-/cheerio-1.0.0.tgz",
"integrity": "sha512-quS9HgjQpdaXOvsZz82Oz7uxtXiy6UIsIQcpBj7HRw2M63Skasm9qlDocAM7jNuaxdhpPU7c4kJN+gA5MCu4ww==",
"license": "MIT",
"dependencies": {
"cheerio-select": "^2.1.0",
"dom-serializer": "^2.0.0",
"domhandler": "^5.0.3",
"domutils": "^3.0.1",
"htmlparser2": "^8.0.1",
"parse5": "^7.0.0",
"parse5-htmlparser2-tree-adapter": "^7.0.0"
"domutils": "^3.1.0",
"encoding-sniffer": "^0.2.0",
"htmlparser2": "^9.1.0",
"parse5": "^7.1.2",
"parse5-htmlparser2-tree-adapter": "^7.0.0",
"parse5-parser-stream": "^7.1.2",
"undici": "^6.19.5",
"whatwg-mimetype": "^4.0.0"
},
"engines": {
"node": ">= 6"
"node": ">=18.17"
},
"funding": {
"url": "https://github.com/cheeriojs/cheerio?sponsor=1"
@ -3731,6 +3739,7 @@
"version": "2.1.0",
"resolved": "https://registry.npmjs.org/cheerio-select/-/cheerio-select-2.1.0.tgz",
"integrity": "sha512-9v9kG0LvzrlcungtnJtpGNxY+fzECQKhK4EGJX2vByejiMX84MFNQw4UxPJl3bFbTMw+Dfs37XaIkCwTZfLh4g==",
"license": "BSD-2-Clause",
"dependencies": {
"boolbase": "^1.0.0",
"css-select": "^5.1.0",
@ -3743,6 +3752,15 @@
"url": "https://github.com/sponsors/fb55"
}
},
"node_modules/cheerio/node_modules/whatwg-mimetype": {
"version": "4.0.0",
"resolved": "https://registry.npmjs.org/whatwg-mimetype/-/whatwg-mimetype-4.0.0.tgz",
"integrity": "sha512-QaKxh0eNIi2mE9p2vEdzfagOKHCcj1pJ56EEHGQOVxp8r9/iszLUUV7v89x9O1p/T+NlTM5W7jW6+cz4Fq1YVg==",
"license": "MIT",
"engines": {
"node": ">=18"
}
},
"node_modules/chokidar": {
"version": "3.5.3",
"resolved": "https://registry.npmjs.org/chokidar/-/chokidar-3.5.3.tgz",
@ -4490,6 +4508,7 @@
"version": "5.1.0",
"resolved": "https://registry.npmjs.org/css-select/-/css-select-5.1.0.tgz",
"integrity": "sha512-nwoRF1rvRRnnCqqY7updORDsuqKzqYJ28+oSMaJMMgOauh3fvwHqMS7EZpIPqK8GL+g9mKxF1vP/ZjSeNjEVHg==",
"license": "BSD-2-Clause",
"dependencies": {
"boolbase": "^1.0.0",
"css-what": "^6.1.0",
@ -4505,6 +4524,7 @@
"version": "6.1.0",
"resolved": "https://registry.npmjs.org/css-what/-/css-what-6.1.0.tgz",
"integrity": "sha512-HTUrgRJ7r4dsZKU6GjmpfRK1O76h97Z8MfS1G0FozR+oF2kG6Vfe8JE6zwrkbxigziPHinCJ+gCPjA9EaBDtRw==",
"license": "BSD-2-Clause",
"engines": {
"node": ">= 6"
},
@ -4930,6 +4950,7 @@
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-2.0.0.tgz",
"integrity": "sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg==",
"license": "MIT",
"dependencies": {
"domelementtype": "^2.3.0",
"domhandler": "^5.0.2",
@ -4948,7 +4969,8 @@
"type": "github",
"url": "https://github.com/sponsors/fb55"
}
]
],
"license": "BSD-2-Clause"
},
"node_modules/domexception": {
"version": "4.0.0",
@ -4966,6 +4988,7 @@
"version": "5.0.3",
"resolved": "https://registry.npmjs.org/domhandler/-/domhandler-5.0.3.tgz",
"integrity": "sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w==",
"license": "BSD-2-Clause",
"dependencies": {
"domelementtype": "^2.3.0"
},
@ -4980,6 +5003,7 @@
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/domutils/-/domutils-3.1.0.tgz",
"integrity": "sha512-H78uMmQtI2AhgDJjWeQmHwJJ2bLPD3GMmO7Zja/ZZh84wkm+4ut+IUnUdRa8uCGX88DiVx1j6FRe1XfxEgjEZA==",
"license": "BSD-2-Clause",
"dependencies": {
"dom-serializer": "^2.0.0",
"domelementtype": "^2.3.0",
@ -5221,6 +5245,43 @@
"iconv-lite": "^0.6.2"
}
},
"node_modules/encoding-sniffer": {
"version": "0.2.0",
"resolved": "https://registry.npmjs.org/encoding-sniffer/-/encoding-sniffer-0.2.0.tgz",
"integrity": "sha512-ju7Wq1kg04I3HtiYIOrUrdfdDvkyO9s5XM8QAj/bN61Yo/Vb4vgJxy5vi4Yxk01gWHbrofpPtpxM8bKger9jhg==",
"license": "MIT",
"dependencies": {
"iconv-lite": "^0.6.3",
"whatwg-encoding": "^3.1.1"
},
"funding": {
"url": "https://github.com/fb55/encoding-sniffer?sponsor=1"
}
},
"node_modules/encoding-sniffer/node_modules/iconv-lite": {
"version": "0.6.3",
"resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz",
"integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==",
"license": "MIT",
"dependencies": {
"safer-buffer": ">= 2.1.2 < 3.0.0"
},
"engines": {
"node": ">=0.10.0"
}
},
"node_modules/encoding-sniffer/node_modules/whatwg-encoding": {
"version": "3.1.1",
"resolved": "https://registry.npmjs.org/whatwg-encoding/-/whatwg-encoding-3.1.1.tgz",
"integrity": "sha512-6qN4hJdMwfYBtE3YBTTHhoeuUrDBPZmbQaxWAqSALV/MeEnR5z1xd8UKud2RAkFoPkmB+hli1TZSnyi84xz1vQ==",
"license": "MIT",
"dependencies": {
"iconv-lite": "0.6.3"
},
"engines": {
"node": ">=18"
}
},
"node_modules/encoding/node_modules/iconv-lite": {
"version": "0.6.3",
"resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz",
@ -7145,9 +7206,9 @@
}
},
"node_modules/htmlparser2": {
"version": "8.0.2",
"resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-8.0.2.tgz",
"integrity": "sha512-GYdjWKDkbRLkZ5geuHs5NY1puJ+PXwP7+fHPRz06Eirsb9ugf6d8kkXav6ADhcODhFFPMIXyxkxSuMf3D6NCFA==",
"version": "9.1.0",
"resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-9.1.0.tgz",
"integrity": "sha512-5zfg6mHUoaer/97TxnGpxmbR7zJtPwIYFMZ/H5ucTlPZhKvtum05yiPK3Mgai3a0DyVxv7qYqoweaEd2nrYQzQ==",
"funding": [
"https://github.com/fb55/htmlparser2?sponsor=1",
{
@ -7155,11 +7216,12 @@
"url": "https://github.com/sponsors/fb55"
}
],
"license": "MIT",
"dependencies": {
"domelementtype": "^2.3.0",
"domhandler": "^5.0.3",
"domutils": "^3.0.1",
"entities": "^4.4.0"
"domutils": "^3.1.0",
"entities": "^4.5.0"
}
},
"node_modules/http-cache-semantics": {
@ -11559,6 +11621,7 @@
"version": "2.1.1",
"resolved": "https://registry.npmjs.org/nth-check/-/nth-check-2.1.1.tgz",
"integrity": "sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w==",
"license": "BSD-2-Clause",
"dependencies": {
"boolbase": "^1.0.0"
},
@ -11927,11 +11990,24 @@
}
},
"node_modules/parse5-htmlparser2-tree-adapter": {
"version": "7.0.0",
"resolved": "https://registry.npmjs.org/parse5-htmlparser2-tree-adapter/-/parse5-htmlparser2-tree-adapter-7.0.0.tgz",
"integrity": "sha512-B77tOZrqqfUfnVcOrUvfdLbz4pu4RopLD/4vmu3HUPswwTA8OH0EMW9BlWR2B0RCoiZRAHEUu7IxeP1Pd1UU+g==",
"version": "7.1.0",
"resolved": "https://registry.npmjs.org/parse5-htmlparser2-tree-adapter/-/parse5-htmlparser2-tree-adapter-7.1.0.tgz",
"integrity": "sha512-ruw5xyKs6lrpo9x9rCZqZZnIUntICjQAd0Wsmp396Ul9lN/h+ifgVV1x1gZHi8euej6wTfpqX8j+BFQxF0NS/g==",
"license": "MIT",
"dependencies": {
"domhandler": "^5.0.3",
"parse5": "^7.0.0"
},
"funding": {
"url": "https://github.com/inikulin/parse5?sponsor=1"
}
},
"node_modules/parse5-parser-stream": {
"version": "7.1.2",
"resolved": "https://registry.npmjs.org/parse5-parser-stream/-/parse5-parser-stream-7.1.2.tgz",
"integrity": "sha512-JyeQc9iwFLn5TbvvqACIF/VXG6abODeB3Fwmv/TGdLk2LfbWkaySGY72at4+Ty7EkPZj854u4CrICqNk2qIbow==",
"license": "MIT",
"dependencies": {
"domhandler": "^5.0.2",
"parse5": "^7.0.0"
},
"funding": {
@ -15174,6 +15250,15 @@
"url": "https://github.com/sponsors/ljharb"
}
},
"node_modules/undici": {
"version": "6.20.1",
"resolved": "https://registry.npmjs.org/undici/-/undici-6.20.1.tgz",
"integrity": "sha512-AjQF1QsmqfJys+LXfGTNum+qw4S88CojRInG/6t31W/1fk6G59s92bnAvGz5Cmur+kQv2SURXEvvudLmbrE8QA==",
"license": "MIT",
"engines": {
"node": ">=18.17"
}
},
"node_modules/unified": {
"version": "11.0.4",
"resolved": "https://registry.npmjs.org/unified/-/unified-11.0.4.tgz",

View File

@ -24,7 +24,7 @@
"axios": "^1.1.3",
"axios-retry": "^3.3.1",
"chart.js": "^3.9.1",
"cheerio": "^1.0.0-rc.12",
"cheerio": "^1.0.0",
"concurrently": "^7.6.0",
"cookies": "^0.8.0",
"croner": "^5.3.5",

View File

@ -1,5 +1,5 @@
import axios, { AxiosResponse, CreateAxiosDefaults } from 'axios';
import cheerio from 'cheerio';
import * as cheerio from 'cheerio';
import { readFile, writeFile } from 'fs/promises';
import HttpsProxyAgent from 'https-proxy-agent';
import countries from './countries';
@ -124,7 +124,7 @@ export const scrapeKeywordFromGoogle = async (keyword:KeywordType, settings:Sett
throw new Error(res);
}
} catch (error:any) {
refreshedResults.error = scraperError;
refreshedResults.error = scraperError || 'Unknown Error';
if (settings.scraper_type === 'proxy' && error && error.response && error.response.statusText) {
refreshedResults.error = `[${error.response.status}] ${error.response.statusText}`;
}