Austin/firecrawl
1
0
Fork 0
mirror of https://github.com/mendableai/firecrawl.git synced 2024-11-16 11:42:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Update removeUnwantedElements.ts

Browse Source
This commit is contained in:
rafaelsideguide 2024-07-16 18:22:56 -03:00
parent db0545014f
commit dba1fb2dc8
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
apps/api/src/scraper/WebScraper/utils/removeUnwantedElements.ts
View File

@ -8,7 +8,11 @@ export const removeUnwantedElements = (
) => { ) => {
const soup = cheerio.load(html); const soup = cheerio.load(html);
if (pageOptions.onlyIncludeTags) { if (
pageOptions.onlyIncludeTags &&
pageOptions.onlyIncludeTags.length > 0 &&
pageOptions.onlyIncludeTags[0] !== ''
) {
if (typeof pageOptions.onlyIncludeTags === "string") { if (typeof pageOptions.onlyIncludeTags === "string") {
pageOptions.onlyIncludeTags = [pageOptions.onlyIncludeTags]; pageOptions.onlyIncludeTags = [pageOptions.onlyIncludeTags];
} }
@ -26,7 +30,11 @@ export const removeUnwantedElements = (
soup("script, style, iframe, noscript, meta, head").remove(); soup("script, style, iframe, noscript, meta, head").remove();
if (pageOptions.removeTags) { if (
pageOptions.removeTags &&
pageOptions.removeTags.length > 0 &&
pageOptions.removeTags[0] !== ''
) {
if (typeof pageOptions.removeTags === "string") { if (typeof pageOptions.removeTags === "string") {
pageOptions.removeTags = [pageOptions.removeTags]; pageOptions.removeTags = [pageOptions.removeTags];
} }