File size: 3,536 Bytes
097eaf0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import { v7 as uuidv7 } from "uuid";
import { config } from "../../config";
import {
  Document,
  ScrapeOptions,
  TeamFlags,
  URLTrace,
  scrapeOptions as scrapeOptionsSchema,
} from "../../controllers/v2/types";
import { waitForJob } from "../../services/queue-jobs";
import { addScrapeJob } from "../../services/queue-jobs";
import { getJobPriority } from "../job-priority";
import type { Logger } from "winston";
import { isUrlBlocked } from "../../scraper/WebScraper/utils/blocklist";
import { scrapeQueue } from "../../services/worker/nuq";

interface ScrapeDocumentOptions {
  url: string;
  teamId: string;
  origin: string;
  timeout: number;
  isSingleUrl?: boolean;
  flags: TeamFlags | null;
  apiKeyId: number | null;
  requestId?: string;
}

export async function scrapeDocument(
  options: ScrapeDocumentOptions,
  urlTraces: URLTrace[],
  logger: Logger,
  internalScrapeOptions: Partial<ScrapeOptions> = { onlyMainContent: false },
): Promise<Document | null> {
  const trace = urlTraces.find(t => t.url === options.url);
  if (trace) {
    trace.status = "scraped";
    trace.timing.scrapedAt = new Date().toISOString();
  }

  if (
    isUrlBlocked(options.url, options.flags ?? null, {
      team_id: options.teamId,
      origin: options.origin,
    })
  ) {
    return null;
  }

  async function attemptScrape(timeout: number) {
    const jobId = uuidv7();
    const jobPriority = await getJobPriority({
      team_id: options.teamId,
      basePriority: 10,
    });

    await addScrapeJob(
      {
        url: options.url,
        mode: "single_urls",
        team_id: options.teamId,
        scrapeOptions: scrapeOptionsSchema.parse({
          ...internalScrapeOptions,
          maxAge: 4 * 60 * 60 * 1000,
        }),
        internalOptions: {
          teamId: options.teamId,
          saveScrapeResultToGCS: config.GCS_FIRE_ENGINE_BUCKET_NAME
            ? true
            : false,
          bypassBilling: true,
        },
        origin: options.origin,
        is_scrape: true,
        from_extract: true,
        startTime: Date.now(),
        zeroDataRetention: false, // not supported
        apiKeyId: options.apiKeyId,
        requestId: options.requestId,
      },
      jobId,
      jobPriority,
      false,
      true,
    );

    const doc = await waitForJob(jobId, timeout, false, logger);
    try {
      await scrapeQueue.removeJob(jobId, logger);
    } catch (error) {
      logger.warn("Error removing job from queue", { error, scrapeId: jobId });
    }

    if (trace) {
      trace.timing.completedAt = new Date().toISOString();
      trace.contentStats = {
        rawContentLength: doc.markdown?.length || 0,
        processedContentLength: doc.markdown?.length || 0,
        tokensUsed: 0,
      };
    }

    return doc;
  }

  try {
    try {
      logger.debug("Attempting scrape...");
      const x = await attemptScrape(options.timeout);
      logger.debug("Scrape finished!");
      return x;
    } catch (timeoutError) {
      logger.warn("Scrape failed.", { error: timeoutError });

      if (options.isSingleUrl) {
        // For single URLs, try again with double timeout
        logger.debug("Attempting scrape...");
        const x = await attemptScrape(options.timeout * 2);
        logger.debug("Scrape finished!");
        return x;
      }

      throw timeoutError;
    }
  } catch (error) {
    logger.error(`error in scrapeDocument`, { error });
    if (trace) {
      trace.status = "error";
      trace.error = error.message;
    }
    return null;
  }
}