From 8b48ec8d300ba8a7c4747f919b17d22a77b710bf Mon Sep 17 00:00:00 2001 From: Nicolas Date: Wed, 24 Jul 2024 11:02:20 -0400 Subject: [PATCH 1/2] Update website_params.ts --- .../WebScraper/utils/custom/website_params.ts | 32 ++++++++++++++++--- 1 file changed, 27 insertions(+), 5 deletions(-) diff --git a/apps/api/src/scraper/WebScraper/utils/custom/website_params.ts b/apps/api/src/scraper/WebScraper/utils/custom/website_params.ts index 4da56619..322053d7 100644 --- a/apps/api/src/scraper/WebScraper/utils/custom/website_params.ts +++ b/apps/api/src/scraper/WebScraper/utils/custom/website_params.ts @@ -22,7 +22,7 @@ export const urlSpecificParams = { }, }, "support.greenpay.me":{ - defaultScraper: "playwright", + defaultScraper: "fire-engine", params: { wait_browser: "networkidle2", block_resources: false, @@ -43,7 +43,7 @@ export const urlSpecificParams = { }, }, "docs.pdw.co":{ - defaultScraper: "playwright", + defaultScraper: "fire-engine", params: { wait_browser: "networkidle2", block_resources: false, @@ -83,7 +83,7 @@ export const urlSpecificParams = { }, }, "developers.notion.com":{ - defaultScraper: "playwright", + defaultScraper: "fire-engine", params: { wait_browser: "networkidle2", block_resources: false, @@ -103,7 +103,7 @@ export const urlSpecificParams = { }, }, "docs2.hubitat.com":{ - defaultScraper: "playwright", + defaultScraper: "fire-engine", params: { wait_browser: "networkidle2", block_resources: false, @@ -153,7 +153,7 @@ export const urlSpecificParams = { }, }, "help.salesforce.com":{ - defaultScraper: "playwright", + defaultScraper: "fire-engine", params: { wait_browser: "networkidle2", block_resources: false, @@ -203,4 +203,26 @@ export const urlSpecificParams = { }, }, }, + "notion.com":{ + defaultScraper: "fire-engine", + params: { + wait_browser: "networkidle2", + block_resources: false, + wait: 2000, + engine: "playwright", + }, + headers: { + "User-Agent": + "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36", + "sec-fetch-site": "same-origin", + "sec-fetch-mode": "cors", + "sec-fetch-dest": "empty", + referer: "https://www.google.com/", + "accept-language": "en-US,en;q=0.9", + "accept-encoding": "gzip, deflate, br", + accept: + "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9", + }, + }, + }; From 3a1b8a9797279f74f212d797c6ffe06cb4ec72c9 Mon Sep 17 00:00:00 2001 From: Nicolas Date: Wed, 24 Jul 2024 11:04:47 -0400 Subject: [PATCH 2/2] Update website_params.ts --- .../WebScraper/utils/custom/website_params.ts | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) diff --git a/apps/api/src/scraper/WebScraper/utils/custom/website_params.ts b/apps/api/src/scraper/WebScraper/utils/custom/website_params.ts index 322053d7..89836b4a 100644 --- a/apps/api/src/scraper/WebScraper/utils/custom/website_params.ts +++ b/apps/api/src/scraper/WebScraper/utils/custom/website_params.ts @@ -210,19 +210,6 @@ export const urlSpecificParams = { block_resources: false, wait: 2000, engine: "playwright", - }, - headers: { - "User-Agent": - "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36", - "sec-fetch-site": "same-origin", - "sec-fetch-mode": "cors", - "sec-fetch-dest": "empty", - referer: "https://www.google.com/", - "accept-language": "en-US,en;q=0.9", - "accept-encoding": "gzip, deflate, br", - accept: - "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9", - }, + } }, - };