mirror of
https://github.com/mendableai/firecrawl.git
synced 2024-11-16 11:42:24 +08:00
Nick: fixed credits issue
Some checks are pending
Fly Deploy / Pre-deploy checks (push) Waiting to run
Fly Deploy / Test Suite (push) Blocked by required conditions
Fly Deploy / Python SDK Tests (push) Blocked by required conditions
Fly Deploy / JavaScript SDK Tests (push) Blocked by required conditions
Fly Deploy / Go SDK Tests (push) Blocked by required conditions
Fly Deploy / Deploy app (push) Blocked by required conditions
Fly Deploy / Build and publish Python SDK (push) Blocked by required conditions
Fly Deploy / Build and publish JavaScript SDK (push) Blocked by required conditions
Some checks are pending
Fly Deploy / Pre-deploy checks (push) Waiting to run
Fly Deploy / Test Suite (push) Blocked by required conditions
Fly Deploy / Python SDK Tests (push) Blocked by required conditions
Fly Deploy / JavaScript SDK Tests (push) Blocked by required conditions
Fly Deploy / Go SDK Tests (push) Blocked by required conditions
Fly Deploy / Deploy app (push) Blocked by required conditions
Fly Deploy / Build and publish Python SDK (push) Blocked by required conditions
Fly Deploy / Build and publish JavaScript SDK (push) Blocked by required conditions
This commit is contained in:
parent
c3158b0f98
commit
67229c6b3a
|
@ -63,6 +63,7 @@ export async function scrapeHelper(
|
|||
pageOptions,
|
||||
extractorOptions,
|
||||
origin: req.body.origin ?? defaultOrigin,
|
||||
is_scrape: true,
|
||||
},
|
||||
{},
|
||||
jobId,
|
||||
|
@ -179,12 +180,10 @@ export async function scrapeController(req: Request, res: Response) {
|
|||
typeof extractorOptions.extractionSchema !== "object" ||
|
||||
extractorOptions.extractionSchema === null
|
||||
) {
|
||||
return res
|
||||
.status(400)
|
||||
.json({
|
||||
error:
|
||||
"extractorOptions.extractionSchema must be an object if llm-extraction mode is specified",
|
||||
});
|
||||
return res.status(400).json({
|
||||
error:
|
||||
"extractorOptions.extractionSchema must be an object if llm-extraction mode is specified",
|
||||
});
|
||||
}
|
||||
|
||||
pageOptions.onlyMainContent = true;
|
||||
|
@ -202,12 +201,10 @@ export async function scrapeController(req: Request, res: Response) {
|
|||
} catch (error) {
|
||||
Logger.error(error);
|
||||
earlyReturn = true;
|
||||
return res
|
||||
.status(500)
|
||||
.json({
|
||||
error:
|
||||
"Error checking team credits. Please contact hello@firecrawl.com for help.",
|
||||
});
|
||||
return res.status(500).json({
|
||||
error:
|
||||
"Error checking team credits. Please contact hello@firecrawl.com for help.",
|
||||
});
|
||||
}
|
||||
|
||||
const jobId = uuidv4();
|
||||
|
@ -231,8 +228,8 @@ export async function scrapeController(req: Request, res: Response) {
|
|||
: 0;
|
||||
|
||||
if (result.success) {
|
||||
let creditsToBeBilled = 0; // billing for doc done on queue end
|
||||
const creditsPerLLMExtract = 50;
|
||||
let creditsToBeBilled = 1;
|
||||
const creditsPerLLMExtract = 49;
|
||||
|
||||
if (extractorOptions.mode.includes("llm-extraction")) {
|
||||
// creditsToBeBilled = creditsToBeBilled + (creditsPerLLMExtract * filteredDocs.length);
|
||||
|
@ -245,13 +242,16 @@ export async function scrapeController(req: Request, res: Response) {
|
|||
// Don't bill if we're early returning
|
||||
return;
|
||||
}
|
||||
const billingResult = await billTeam(team_id, creditsToBeBilled);
|
||||
if (!billingResult.success) {
|
||||
return res.status(402).json({
|
||||
success: false,
|
||||
error:
|
||||
"Failed to bill team. Insufficient credits or subscription not found.",
|
||||
});
|
||||
if (creditsToBeBilled > 0) {
|
||||
// billing for doc done on queue end, bill only for llm extraction
|
||||
const billingResult = await billTeam(team_id, creditsToBeBilled);
|
||||
if (!billingResult.success) {
|
||||
return res.status(402).json({
|
||||
success: false,
|
||||
error:
|
||||
"Failed to bill team. Insufficient credits or subscription not found.",
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -276,13 +276,11 @@ export async function scrapeController(req: Request, res: Response) {
|
|||
} catch (error) {
|
||||
Sentry.captureException(error);
|
||||
Logger.error(error);
|
||||
return res
|
||||
.status(500)
|
||||
.json({
|
||||
error:
|
||||
typeof error === "string"
|
||||
? error
|
||||
: error?.message ?? "Internal Server Error",
|
||||
});
|
||||
return res.status(500).json({
|
||||
error:
|
||||
typeof error === "string"
|
||||
? error
|
||||
: error?.message ?? "Internal Server Error",
|
||||
});
|
||||
}
|
||||
}
|
||||
|
|
|
@ -29,6 +29,7 @@ export async function scrapeController(req: RequestWithAuth<{}, ScrapeResponse,
|
|||
pageOptions,
|
||||
extractorOptions: {},
|
||||
origin: req.body.origin,
|
||||
is_scrape: true,
|
||||
}, {}, jobId, jobPriority);
|
||||
|
||||
let doc: any | undefined;
|
||||
|
|
|
@ -57,6 +57,7 @@ export async function startWebScraperPipeline({
|
|||
team_id: job.data.team_id,
|
||||
bull_job_id: job.id.toString(),
|
||||
priority: job.opts.priority,
|
||||
is_scrape: job.data.is_scrape ?? false,
|
||||
})) as { success: boolean; message: string; docs: Document[] };
|
||||
}
|
||||
export async function runWebScraper({
|
||||
|
@ -71,6 +72,7 @@ export async function runWebScraper({
|
|||
team_id,
|
||||
bull_job_id,
|
||||
priority,
|
||||
is_scrape=false,
|
||||
}: RunWebScraperParams): Promise<RunWebScraperResult> {
|
||||
try {
|
||||
const provider = new WebScraperDataProvider();
|
||||
|
@ -117,18 +119,21 @@ export async function runWebScraper({
|
|||
}
|
||||
})
|
||||
: docs;
|
||||
|
||||
const billingResult = await billTeam(team_id, filteredDocs.length);
|
||||
|
||||
if (!billingResult.success) {
|
||||
// throw new Error("Failed to bill team, no subscription was found");
|
||||
return {
|
||||
success: false,
|
||||
message: "Failed to bill team, no subscription was found",
|
||||
docs: [],
|
||||
};
|
||||
if(is_scrape === false) {
|
||||
const billingResult = await billTeam(team_id, filteredDocs.length);
|
||||
if (!billingResult.success) {
|
||||
// throw new Error("Failed to bill team, no subscription was found");
|
||||
return {
|
||||
success: false,
|
||||
message: "Failed to bill team, no subscription was found",
|
||||
docs: [],
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
// This is where the returnvalue from the job is set
|
||||
onSuccess(filteredDocs, mode);
|
||||
|
||||
|
|
|
@ -32,6 +32,7 @@ export interface WebScraperOptions {
|
|||
sitemapped?: boolean;
|
||||
webhook?: string;
|
||||
v1?: boolean;
|
||||
is_scrape?: boolean;
|
||||
}
|
||||
|
||||
export interface RunWebScraperParams {
|
||||
|
@ -46,6 +47,7 @@ export interface RunWebScraperParams {
|
|||
team_id: string;
|
||||
bull_job_id: string;
|
||||
priority?: number;
|
||||
is_scrape?: boolean;
|
||||
}
|
||||
|
||||
export interface RunWebScraperResult {
|
||||
|
|
16
apps/js-sdk/firecrawl/types/index.d.ts
vendored
16
apps/js-sdk/firecrawl/types/index.d.ts
vendored
|
@ -153,16 +153,14 @@ export interface ScrapeResponseV0 {
|
|||
* Includes options for both scraping and mapping during a crawl.
|
||||
*/
|
||||
export interface CrawlParams {
|
||||
includePaths?: string[];
|
||||
excludePaths?: string[];
|
||||
maxDepth?: number;
|
||||
limit?: number;
|
||||
allowBackwardLinks?: boolean;
|
||||
allowExternalLinks?: boolean;
|
||||
ignoreSitemap?: boolean;
|
||||
scrapeOptions?: ScrapeParams;
|
||||
crawlerOptions?: {
|
||||
includePaths?: string[];
|
||||
excludePaths?: string[];
|
||||
maxDepth?: number;
|
||||
limit?: number;
|
||||
allowBackwardLinks?: boolean;
|
||||
allowExternalLinks?: boolean;
|
||||
ignoreSitemap?: boolean;
|
||||
};
|
||||
}
|
||||
/**
|
||||
* Parameters for crawling operations on v0.
|
||||
|
|
Loading…
Reference in New Issue
Block a user