File size: 11,055 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
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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
import { v7 as uuidv7 } from "uuid";
import {
  TeamFlags,
  MapDocument,
  scrapeOptions,
  ScrapeOptions,
  MAX_MAP_LIMIT,
} from "../controllers/v2/types";
import { crawlToCrawler, StoredCrawl } from "./crawl-redis";
import { getScrapeZDR } from "./zdr-helpers";
import {
  checkAndUpdateURLForMap,
  isSameDomain,
  isSameSubdomain,
  resolveRedirects,
} from "./validateUrl";
import { fireEngineMap } from "../search/fireEngine";
import { redisEvictConnection } from "../services/redis";
import {
  generateURLSplits,
  queryIndexAtDomainSplitLevelWithMeta,
  queryIndexAtSplitLevelWithMeta,
} from "../services/index";
import { performCosineSimilarityV2 } from "./map-cosine";
import { Logger } from "winston";

// Max Links that "Smart /map" can return
const MAX_FIRE_ENGINE_RESULTS = 100;

export interface MapResult {
  success: boolean;
  job_id: string;
  time_taken: number;
  mapResults: MapDocument[];
}

function dedupeMapDocumentArray(documents: MapDocument[]): MapDocument[] {
  const urlMap = new Map<string, MapDocument>();

  for (const doc of documents) {
    const existing = urlMap.get(doc.url);

    if (!existing) {
      urlMap.set(doc.url, doc);
    } else if (doc.title !== undefined && existing.title === undefined) {
      urlMap.set(doc.url, doc);
    }
  }

  return Array.from(urlMap.values());
}

async function queryIndex(
  url: string,
  limit: number,
  useIndex: boolean,
  includeSubdomains: boolean,
): Promise<MapDocument[]> {
  if (!useIndex) {
    return [];
  }

  const urlSplits = generateURLSplits(url);
  if (urlSplits.length === 1) {
    const urlObj = new URL(url);
    const hostname = urlObj.hostname;

    // TEMP: this should be altered on June 15th 2025 7AM PT - mogery
    const [domainLinks, splitLinks] = await Promise.all([
      includeSubdomains
        ? queryIndexAtDomainSplitLevelWithMeta(hostname, limit)
        : [],
      queryIndexAtSplitLevelWithMeta(url, limit),
    ]);

    return dedupeMapDocumentArray([...domainLinks, ...splitLinks]);
  } else {
    return await queryIndexAtSplitLevelWithMeta(url, limit);
  }
}

export async function getMapResults({
  url,
  search,
  limit = MAX_MAP_LIMIT,
  includeSubdomains = true,
  crawlerOptions = {},
  teamId,
  allowExternalLinks,
  abort = new AbortController().signal,
  filterByPath = true,
  flags,
  useIndex = true,
  ignoreCache = false,
  location,
  headers,
  maxFireEngineResults = MAX_FIRE_ENGINE_RESULTS,
  id: providedId,
}: {
  url: string;
  search?: string;
  limit?: number;
  includeSubdomains?: boolean;
  crawlerOptions?: any;
  teamId: string;
  origin?: string;
  includeMetadata?: boolean;
  allowExternalLinks?: boolean;
  abort?: AbortSignal;
  mock?: string;
  filterByPath?: boolean;
  flags: TeamFlags | null;
  useIndex?: boolean;
  ignoreCache?: boolean;
  location?: ScrapeOptions["location"];
  headers?: Record<string, string>;
  maxFireEngineResults?: number;
  id?: string;
}): Promise<MapResult> {
  const functionStartTime = Date.now();

  const resolvedUrl = await resolveRedirects(url, abort);

  // If the resolved URL is on a different domain, replace the hostname
  if (!isSameDomain(url, resolvedUrl)) {
    const urlObj = new URL(url);
    urlObj.hostname = new URL(resolvedUrl).hostname;

    url = urlObj.toString();
  }

  const id = providedId ?? uuidv7();
  let mapResults: MapDocument[] = [];
  const zeroDataRetention = getScrapeZDR(flags) === "forced" || false;

  const sc: StoredCrawl = {
    originUrl: url,
    crawlerOptions: {
      ...crawlerOptions,
      limit: crawlerOptions.sitemapOnly ? 10000000 : limit,
      scrapeOptions: undefined,
    },
    scrapeOptions: scrapeOptions.parse({
      ...(location ? { location } : {}),
      ...(headers ? { headers } : {}),
    }),
    internalOptions: { teamId },
    team_id: teamId,
    createdAt: Date.now(),
    zeroDataRetention,
  };

  const crawler = crawlToCrawler(id, sc, flags);

  try {
    sc.robots = await crawler.getRobotsTxt(false, abort);
    crawler.importRobotsTxt(sc.robots);
  } catch (_) {
    // Robots.txt fetch failed, continue without it
  }

  // If sitemapOnly is true, only get links from sitemap
  if (crawlerOptions.sitemap === "only") {
    const sitemap = await crawler.tryGetSitemap(
      urls => {
        urls.forEach(x => {
          mapResults.push({
            url: x,
          });
        });
      },
      true,
      true,
      crawlerOptions.timeout ?? 30000,
      abort,
      crawlerOptions.useMock,
      ignoreCache ? 0 : undefined,
    );

    if (sitemap > 0) {
      mapResults = mapResults
        .slice(1)
        .map(x => {
          try {
            return {
              ...x,
              url: checkAndUpdateURLForMap(x.url).url.trim(),
            };
          } catch (_) {
            return null;
          }
        })
        .filter(x => x !== null) as MapDocument[];
    }
  } else {
    let urlWithoutWww = url.replace("www.", "");
    let mapUrl =
      search && allowExternalLinks
        ? `${search} ${urlWithoutWww}`
        : search
          ? `${search} site:${urlWithoutWww}`
          : `site:${url}`;

    const resultsPerPage = 100;
    const maxPages = Math.ceil(
      Math.min(maxFireEngineResults, limit) / resultsPerPage,
    );

    const cacheKey = `fireEngineMap:${mapUrl}`;
    const cachedResult = ignoreCache
      ? null
      : await redisEvictConnection.get(cacheKey);

    const fetchPage = async (page: number) => {
      return await fireEngineMap(
        mapUrl,
        {
          numResults: resultsPerPage,
          page,
        },
        abort,
      );
    };

    const fetchAllPages = async (): Promise<any[]> => {
      if (cachedResult) {
        return JSON.parse(cachedResult);
      }
      // if page 1 has no results, don't fetch remaining pages
      const page1Result = await fetchPage(1);
      if (!page1Result || page1Result.length === 0 || maxPages === 1) {
        return [page1Result];
      }
      const remainingPages = await Promise.all(
        Array.from({ length: maxPages - 1 }, (_, i) => fetchPage(i + 2)),
      );
      return [page1Result, ...remainingPages];
    };

    const [indexResults, searchResults] = await Promise.all([
      queryIndex(url, limit, useIndex, includeSubdomains),
      fetchAllPages(),
    ]);

    if (!zeroDataRetention) {
      await redisEvictConnection.set(
        cacheKey,
        JSON.stringify(searchResults),
        "EX",
        48 * 60 * 60,
      ); // Cache for 48 hours
    }

    if (indexResults.length > 0) {
      mapResults.push(...indexResults);
    }

    if (crawlerOptions.sitemap === "include") {
      try {
        await crawler.tryGetSitemap(
          urls => {
            mapResults.push(
              ...urls.map(x => ({
                url: x,
              })),
            );
          },
          true,
          false,
          crawlerOptions.timeout ?? 30000,
          abort,
          undefined,
          ignoreCache ? 0 : undefined,
        );
      } catch (e) {
        // Silently handle sitemap errors
      }
    }

    if (search) {
      mapResults = searchResults
        .flat()
        .map<MapDocument>(
          x =>
            ({
              url: x.url,
              title: x.title,
              description: x.description,
            }) satisfies MapDocument,
        )
        .concat(mapResults);
    } else {
      mapResults = mapResults.concat(
        searchResults.flat().map(x => ({
          url: x.url,
          title: x.title,
          description: x.description,
        })),
      );
    }

    const minimumCutoff = Math.min(MAX_MAP_LIMIT, limit);
    if (mapResults.length > minimumCutoff) {
      mapResults = mapResults.slice(0, minimumCutoff);
    }

    if (search) {
      const searchQuery = search.toLowerCase();
      mapResults = performCosineSimilarityV2(mapResults, searchQuery);
    }
  }

  mapResults = mapResults
    .map(x => {
      try {
        return {
          ...x,
          url: checkAndUpdateURLForMap(
            x.url,
            crawlerOptions.ignoreQueryParameters ?? true,
          ).url.trim(),
        };
      } catch (_) {
        return null;
      }
    })
    .filter(x => x !== null) as MapDocument[];

  mapResults = mapResults.filter(x => isSameDomain(x.url, url));

  if (!includeSubdomains) {
    mapResults = mapResults.filter(x => isSameSubdomain(x.url, url));
  }

  if (filterByPath && !allowExternalLinks) {
    try {
      const urlObj = new URL(url);
      const urlPath = urlObj.pathname;
      // Only apply path filtering if the URL has a significant path (not just '/' or empty)
      // This means we only filter by path if the user has not selected a root domain
      if (urlPath && urlPath !== "/" && urlPath.length > 1) {
        mapResults = mapResults.filter(x => {
          try {
            const linkObj = new URL(x.url);
            return linkObj.pathname.startsWith(urlPath);
          } catch (e) {
            return false;
          }
        });
      }
    } catch (e) {
      // If URL parsing fails, continue without path filtering
    }
  }

  mapResults = dedupeMapDocumentArray(mapResults);
  mapResults = mapResults.slice(0, limit);

  const totalTimeMs = Date.now() - functionStartTime;

  return {
    success: true,
    mapResults,
    job_id: id,
    time_taken: totalTimeMs,
  };
}

export async function buildPromptWithWebsiteStructure({
  basePrompt,
  url,
  teamId,
  flags,
  logger,
  limit = 50,
  includeSubdomains = true,
  allowExternalLinks = false,
  useIndex = true,
  maxFireEngineResults = 500,
}: {
  basePrompt: string;
  url: string;
  teamId: string;
  flags: TeamFlags | null;
  logger: Logger;
  limit?: number;
  includeSubdomains?: boolean;
  allowExternalLinks?: boolean;
  useIndex?: boolean;
  maxFireEngineResults?: number;
}): Promise<{ prompt: string; websiteUrls: string[] }> {
  try {
    logger.debug("Getting website structure for prompt enhancement");
    const mapResult = await getMapResults({
      url,
      limit,
      includeSubdomains,
      crawlerOptions: { sitemap: "include" },
      teamId,
      flags,
      allowExternalLinks,
      filterByPath: false,
      useIndex,
      maxFireEngineResults,
    });

    const websiteUrls = mapResult.mapResults.map(doc => doc.url);
    logger.debug("Found website URLs for prompt enhancement", {
      urlCount: websiteUrls.length,
      sampleUrls: websiteUrls.slice(0, 5),
    });

    const prompt = `${basePrompt}\n\n--- WEBSITE STRUCTURE ---\nThe website has the following URL structure (${websiteUrls.length} URLs found, here is a sample of the first ${Math.min(
      120,
      websiteUrls.length,
    )} URLs):\n${websiteUrls.slice(0, 120).join("\n")}\n\nBased on this structure and the user's request, generate appropriate crawler options.`;

    return { prompt, websiteUrls };
  } catch (e) {
    logger.warn("Failed to get website structure for prompt enhancement", {
      error: (e as any)?.message ?? e,
    });
    return { prompt: basePrompt, websiteUrls: [] };
  }
}