mirror of
https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl
synced 2025-08-06 08:26:05 +08:00
Nick:
This commit is contained in:
parent
522d256b11
commit
d347160ff9
@ -254,13 +254,26 @@ export async function scrapeController(req: Request, res: Response) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let doc = result.data;
|
||||
if (!pageOptions || !pageOptions.includeRawHtml) {
|
||||
if (doc && doc.rawHtml) {
|
||||
delete doc.rawHtml;
|
||||
}
|
||||
}
|
||||
|
||||
if(pageOptions && pageOptions.includeExtract) {
|
||||
if(!pageOptions.includeMarkdown && doc && doc.markdown) {
|
||||
delete doc.markdown;
|
||||
}
|
||||
}
|
||||
|
||||
logJob({
|
||||
job_id: jobId,
|
||||
success: result.success,
|
||||
message: result.error,
|
||||
num_docs: 1,
|
||||
docs: [result.data],
|
||||
docs: [doc],
|
||||
time_taken: timeTakenInSeconds,
|
||||
team_id: team_id,
|
||||
mode: "scrape",
|
||||
|
@ -115,6 +115,18 @@ export async function scrapeController(
|
||||
});
|
||||
}
|
||||
|
||||
if (!pageOptions || !pageOptions.includeRawHtml) {
|
||||
if (doc && doc.rawHtml) {
|
||||
delete doc.rawHtml;
|
||||
}
|
||||
}
|
||||
|
||||
if(pageOptions && pageOptions.includeExtract) {
|
||||
if(!pageOptions.includeMarkdown && doc && doc.markdown) {
|
||||
delete doc.markdown;
|
||||
}
|
||||
}
|
||||
|
||||
logJob({
|
||||
job_id: jobId,
|
||||
success: true,
|
||||
|
@ -202,24 +202,6 @@ async function processJob(job: Job, token: string) {
|
||||
|
||||
const rawHtml = docs[0] ? docs[0].rawHtml : "";
|
||||
|
||||
if (job.data.crawl_id && (!job.data.pageOptions || !job.data.pageOptions.includeRawHtml)) {
|
||||
if (docs[0] && docs[0].rawHtml) {
|
||||
delete docs[0].rawHtml;
|
||||
}
|
||||
}
|
||||
|
||||
if(job.data.pageOptions && job.data.pageOptions.includeExtract ) {
|
||||
if(!job.data.pageOptions.includeMarkdown) {
|
||||
delete docs[0].markdown;
|
||||
}
|
||||
// if(!job.data.pageOptions.includeRawHtml) {
|
||||
// delete docs[0].rawHtml;
|
||||
// }
|
||||
// if(!job.data.pageOptions.includeHtml) {
|
||||
// delete docs[0].html;
|
||||
// }
|
||||
}
|
||||
|
||||
const data = {
|
||||
success,
|
||||
result: {
|
||||
|
Loading…
x
Reference in New Issue
Block a user