Hugging Face's logo

Spaces:
Echo-AI-official
/
Fire-crawl
Paused

App Files Community
Fire-crawl
File size: 4,870 Bytes
0e759d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
import { Logger } from "winston";
import * as Sentry from "@sentry/node";
import { z } from "zod";

import { robustFetch } from "../../lib/fetch";
import {
  ActionError,
  EngineError,
  SiteError,
  UnsupportedFileError,
} from "../../error";
import { MockState } from "../../lib/mock";
import { fireEngineURL } from "./scrape";

const successSchema = z.object({
  jobId: z.string(),
  state: z.literal("completed"),
  processing: z.literal(false),

  // timeTaken: z.number(),
  content: z.string(),
  url: z.string().optional(),

  pageStatusCode: z.number(),
  pageError: z.string().optional(),

  // TODO: this needs to be non-optional, might need fixes on f-e side to ensure reliability
  responseHeaders: z.record(z.string(), z.string()).optional(),

  // timeTakenCookie: z.number().optional(),
  // timeTakenRequest: z.number().optional(),

  // legacy: playwright only
  screenshot: z.string().optional(),

  // new: actions
  screenshots: z.string().array().optional(),
  actionContent: z
    .object({
      url: z.string(),
      html: z.string(),
    })
    .array()
    .optional(),
  actionResults: z.union([
    z.object({
      idx: z.number(),
      type: z.literal("screenshot"),
      result: z.object({
        path: z.string(),
      }),
    }),
    z.object({
      idx: z.number(),
      type: z.literal("scrape"),
      result: z.union([
        z.object({
          url: z.string(),
          html: z.string(),
        }),
        z.object({
          url: z.string(),
          accessibility: z.string(),
        }),
      ]),
    }),
    z.object({
      idx: z.number(),
      type: z.literal("executeJavascript"),
      result: z.object({
        return: z.string(),
      }),
    }),
  ]).array().optional(),

  // chrome-cdp only -- file download handler
  file: z
    .object({
      name: z.string(),
      content: z.string(),
    })
    .optional()
    .or(z.null()),
});

export type FireEngineCheckStatusSuccess = z.infer<typeof successSchema>;

const processingSchema = z.object({
  jobId: z.string(),
  state: z.enum([
    "delayed",
    "active",
    "waiting",
    "waiting-children",
    "unknown",
    "prioritized",
  ]),
  processing: z.boolean(),
});

const failedSchema = z.object({
  jobId: z.string(),
  state: z.literal("failed"),
  processing: z.literal(false),
  error: z.string(),
});

export class StillProcessingError extends Error {
  constructor(jobId: string) {
    super("Job is still under processing", { cause: { jobId } });
  }
}

export async function fireEngineCheckStatus(
  logger: Logger,
  jobId: string,
  mock: MockState | null,
  abort?: AbortSignal,
): Promise<FireEngineCheckStatusSuccess> {
  const status = await Sentry.startSpan(
    {
      name: "fire-engine: Check status",
      attributes: {
        jobId,
      },
    },
    async (span) => {
      return await robustFetch({
        url: `${fireEngineURL}/scrape/${jobId}`,
        method: "GET",
        logger: logger.child({ method: "fireEngineCheckStatus/robustFetch" }),
        headers: {
          ...(Sentry.isInitialized()
            ? {
                "sentry-trace": Sentry.spanToTraceHeader(span),
                baggage: Sentry.spanToBaggageHeader(span),
              }
            : {}),
        },
        mock,
      });
    },
  );

  const successParse = successSchema.safeParse(status);
  const processingParse = processingSchema.safeParse(status);
  const failedParse = failedSchema.safeParse(status);

  if (successParse.success) {
    logger.debug("Scrape succeeded!", { jobId });
    return successParse.data;
  } else if (processingParse.success) {
    throw new StillProcessingError(jobId);
  } else if (failedParse.success) {
    logger.debug("Scrape job failed", { status, jobId });
    if (
      typeof status.error === "string" &&
      status.error.includes("Chrome error: ")
    ) {
      throw new SiteError(status.error.split("Chrome error: ")[1]);
    } else if (
      typeof status.error === "string" &&
      status.error.includes("File size exceeds")
    ) {
      throw new UnsupportedFileError(
        "File size exceeds " + status.error.split("File size exceeds ")[1],
      );
    } else if (
      typeof status.error === "string" &&
      // TODO: improve this later
      (status.error.includes("Element") || status.error.includes("Javascript execution failed"))
    ) {
      throw new ActionError(status.error.split("Error: ")[1]);
    } else {
      throw new EngineError("Scrape job failed", {
        cause: {
          status,
          jobId,
        },
      });
    }
  } else {
    logger.debug("Check status returned response not matched by any schema", {
      status,
      jobId,
    });
    throw new Error(
      "Check status returned response not matched by any schema",
      {
        cause: {
          status,
          jobId,
        },
      },
    );
  }
}