salesprompter-cli 0.1.42 → 0.1.43

package/dist/cli.js

@@ -407,6 +407,8 @@ const helpAliasByCommandName = new Map([
     ["companies:find-linkedin-urls", "companies:resolve-linkedin-urls"],
     ["contacts:process-emails", "contacts:resolve-emails"],
     ["linkedin-companies:backfill", "companies:enrich"],
+    ["linkedin-companies:scrape-local", "companies:scrape-linkedin"],
+    ["dealroom-companies:scrape-local", "companies:scrape-dealroom"],
     ["linkedin-products:scrape", "market:scrape"],
     ["salesnav:from-product-category", "leads:discover"],
     ["salesnav:crawl", "search:run"],
@@ -444,6 +446,8 @@ const helpVisibleCommandNames = new Set([
     "sync:crm",
     "sync:outreach",
     "linkedin-companies:backfill",
+    "linkedin-companies:scrape-local",
+    "dealroom-companies:scrape-local",
     "linkedin-products:scrape",
     "salesnav:from-product-category",
     "salesnav:crawl",
@@ -7365,6 +7369,632 @@ function sanitizeForPostgresJson(value) {
 function sanitizeOptionalPostgresText(value) {
     return typeof value === "string" ? stripPostgresUnsafeStringBytes(value) : null;
 }
+function normalizeLinkedInCompanyScrapeUrl(rawUrl) {
+    let parsed;
+    try {
+        parsed = new URL(rawUrl.startsWith("http") ? rawUrl : `https://${rawUrl}`);
+    }
+    catch {
+        throw new Error(`Invalid LinkedIn company URL: ${rawUrl}`);
+    }
+    const idMatch = parsed.pathname.match(/\/(?:sales\/)?company\/([0-9]+)/i);
+    if (!idMatch) {
+        throw new Error(`LinkedIn company URL must include a numeric company id: ${rawUrl}`);
+    }
+    const id = Number(idMatch[1]);
+    if (!Number.isFinite(id)) {
+        throw new Error(`LinkedIn company URL has an invalid company id: ${rawUrl}`);
+    }
+    return {
+        id,
+        sourceUrl: parsed.toString(),
+        companyUrl: `https://www.linkedin.com/company/${id}`,
+        salesNavigatorLink: `https://www.linkedin.com/sales/company/${id}/`,
+    };
+}
+function normalizeDealroomCompanyScrapeUrl(rawUrl) {
+    let parsed;
+    try {
+        parsed = new URL(rawUrl.startsWith("http") ? rawUrl : `https://${rawUrl}`);
+    }
+    catch {
+        throw new Error(`Invalid Dealroom company URL: ${rawUrl}`);
+    }
+    const slugMatch = parsed.pathname.match(/\/companies\/([^/?#]+)/i);
+    if (!slugMatch) {
+        throw new Error(`Dealroom company URL must include /companies/<slug>: ${rawUrl}`);
+    }
+    const slug = decodeURIComponent(slugMatch[1] || "").trim();
+    if (!slug) {
+        throw new Error(`Dealroom company URL has an invalid company slug: ${rawUrl}`);
+    }
+    return {
+        slug,
+        sourceUrl: parsed.toString(),
+        companyUrl: `https://app.dealroom.co/companies/${encodeURIComponent(slug)}`,
+    };
+}
+function normalizeLocalCompanyDomain(website) {
+    if (!website) {
+        return null;
+    }
+    try {
+        const url = new URL(website.startsWith("http") ? website : `https://${website}`);
+        return url.hostname.replace(/^www\./i, "").toLowerCase();
+    }
+    catch {
+        return null;
+    }
+}
+function normalizeDealroomWebsite(value) {
+    if (!value) {
+        return null;
+    }
+    const trimmed = value.trim();
+    if (!trimmed || /^view job openings$/i.test(trimmed)) {
+        return null;
+    }
+    try {
+        return new URL(trimmed.startsWith("http") ? trimmed : `https://${trimmed}`).toString();
+    }
+    catch {
+        return trimmed;
+    }
+}
+function parseLinkedInAboutTextValue(lines, label) {
+    const labelIndex = lines.findIndex((line) => line.toLowerCase() === label.toLowerCase());
+    if (labelIndex === -1) {
+        return null;
+    }
+    return lines[labelIndex + 1]?.trim() || null;
+}
+function parseLabeledTextValue(lines, label) {
+    const expected = label.toLowerCase();
+    const labelIndex = lines.findIndex((line) => line.toLowerCase() === expected);
+    if (labelIndex !== -1) {
+        return lines[labelIndex + 1]?.trim() || null;
+    }
+    const inline = lines.find((line) => line.toLowerCase().startsWith(`${expected} `));
+    if (!inline) {
+        return null;
+    }
+    return inline.slice(label.length).trim() || null;
+}
+function parseLinkedInCompactInteger(value) {
+    if (!value) {
+        return null;
+    }
+    const match = value.replace(/,/g, "").match(/([0-9]+(?:\.[0-9]+)?)\s*([kmb])?/i);
+    if (!match) {
+        return null;
+    }
+    const base = Number(match[1]);
+    if (!Number.isFinite(base)) {
+        return null;
+    }
+    const suffix = match[2]?.toLowerCase();
+    const multiplier = suffix === "b" ? 1_000_000_000 : suffix === "m" ? 1_000_000 : suffix === "k" ? 1_000 : 1;
+    return Math.round(base * multiplier);
+}
+function parseDealroomEnterpriseValueUsd(value) {
+    if (!value) {
+        return null;
+    }
+    const match = value.replace(/,/g, "").match(/([$€£])?\s*([0-9]+(?:\.[0-9]+)?)\s*([kmb])?/i);
+    if (!match) {
+        return null;
+    }
+    const base = Number(match[2]);
+    if (!Number.isFinite(base)) {
+        return null;
+    }
+    const suffix = match[3]?.toLowerCase();
+    const multiplier = suffix === "b" ? 1_000_000_000 : suffix === "m" ? 1_000_000 : suffix === "k" ? 1_000 : 1;
+    return Math.round(base * multiplier);
+}
+function parseLinkedInNumber(value) {
+    if (!value) {
+        return null;
+    }
+    const normalized = value.replace(/,/g, "").match(/[0-9]+(?:\.[0-9]+)?/);
+    if (!normalized) {
+        return null;
+    }
+    const parsed = Number(normalized[0]);
+    return Number.isFinite(parsed) ? parsed : null;
+}
+function parseLinkedInGrowth(value) {
+    if (!value) {
+        return { value: null, label: null };
+    }
+    const label = value.replace(/^▲\s*/i, "").trim();
+    if (!label || /^n\/a$/i.test(label)) {
+        return { value: null, label: label || null };
+    }
+    const parsed = parseLinkedInNumber(label);
+    return { value: parsed, label };
+}
+function parseLinkedInTenureYears(lines) {
+    const tenureLine = lines.find((line) => /median employee tenure/i.test(line));
+    return parseLinkedInNumber(tenureLine);
+}
+function isLikelyLinkedInGrowthToken(value) {
+    if (!value) {
+        return false;
+    }
+    return /^(?:▲\s*)?(?:[0-9][0-9,]*(?:\.[0-9]+)?%?\+?|N\/A)$/i.test(value.trim());
+}
+function parseLinkedInInsightRows(lines) {
+    const insights = [];
+    const jobOpeningsIndex = lines.findIndex((line) => /^Total job openings$/i.test(line));
+    if (jobOpeningsIndex >= 0) {
+        const totalValue = parseLinkedInNumber(lines[jobOpeningsIndex + 1]);
+        const period = lines[jobOpeningsIndex + 2] || null;
+        insights.push({
+            insightType: "job_openings_total",
+            label: "Total",
+            period,
+            metricValue: totalValue,
+            metricUnit: "jobs",
+            growth3mPercent: null,
+            growth6mPercent: null,
+            growth1yPercent: null,
+            growth2yPercent: null,
+            growth3mLabel: null,
+            growth6mLabel: null,
+            growth1yLabel: null,
+            growth2yLabel: null,
+            rawPayload: { source: "total_job_openings", lines: lines.slice(jobOpeningsIndex, jobOpeningsIndex + 12) },
+        });
+        const jobEndIndex = lines.findIndex((line, index) => index > jobOpeningsIndex && /^Total employee count$/i.test(line));
+        const jobRows = lines.slice(jobOpeningsIndex + 3, jobEndIndex === -1 ? lines.length : jobEndIndex);
+        for (let index = 0; index < jobRows.length - 2; index += 1) {
+            const label = jobRows[index];
+            const growth3m = jobRows[index + 1];
+            const growth6m = jobRows[index + 2];
+            if (!label || !isLikelyLinkedInGrowthToken(growth3m) || !isLikelyLinkedInGrowthToken(growth6m)) {
+                continue;
+            }
+            const parsed3m = parseLinkedInGrowth(growth3m);
+            const parsed6m = parseLinkedInGrowth(growth6m);
+            insights.push({
+                insightType: "job_openings_function",
+                label,
+                period,
+                metricValue: null,
+                metricUnit: "jobs",
+                growth3mPercent: parsed3m.value,
+                growth6mPercent: parsed6m.value,
+                growth1yPercent: null,
+                growth2yPercent: null,
+                growth3mLabel: parsed3m.label,
+                growth6mLabel: parsed6m.label,
+                growth1yLabel: null,
+                growth2yLabel: null,
+                rawPayload: { source: "job_openings_function", label, growth3m, growth6m },
+            });
+            index += 2;
+        }
+    }
+    const employeeCountIndex = lines.findIndex((line) => /^Total employee count$/i.test(line));
+    if (employeeCountIndex >= 0) {
+        const growth6m = parseLinkedInGrowth(lines[employeeCountIndex + 3]);
+        const growth1y = parseLinkedInGrowth(lines[employeeCountIndex + 4]);
+        const growth2y = parseLinkedInGrowth(lines[employeeCountIndex + 5]);
+        insights.push({
+            insightType: "employee_count_total",
+            label: "Total",
+            period: "current",
+            metricValue: parseLinkedInNumber(lines[employeeCountIndex + 1]),
+            metricUnit: "employees",
+            growth3mPercent: null,
+            growth6mPercent: growth6m.value,
+            growth1yPercent: growth1y.value,
+            growth2yPercent: growth2y.value,
+            growth3mLabel: null,
+            growth6mLabel: growth6m.label,
+            growth1yLabel: growth1y.label,
+            growth2yLabel: growth2y.label,
+            rawPayload: { source: "total_employee_count", lines: lines.slice(employeeCountIndex, employeeCountIndex + 8) },
+        });
+    }
+    const functionIndex = lines.findIndex((line) => /^Employee distribution and headcount growth by function$/i.test(line));
+    if (functionIndex >= 0) {
+        const period = lines[functionIndex + 2] || null;
+        const functionEndIndex = lines.findIndex((line, index) => index > functionIndex && /^Select insights not available$/i.test(line));
+        const functionRows = lines.slice(functionIndex + 3, functionEndIndex === -1 ? lines.length : functionEndIndex);
+        for (let index = 0; index < functionRows.length - 2; index += 1) {
+            const label = functionRows[index];
+            const growth6m = functionRows[index + 1];
+            const growth1y = functionRows[index + 2];
+            if (!label || !isLikelyLinkedInGrowthToken(growth6m) || !isLikelyLinkedInGrowthToken(growth1y)) {
+                continue;
+            }
+            const parsed6m = parseLinkedInGrowth(growth6m);
+            const parsed1y = parseLinkedInGrowth(growth1y);
+            insights.push({
+                insightType: "employee_function_distribution",
+                label,
+                period,
+                metricValue: null,
+                metricUnit: "employees",
+                growth3mPercent: null,
+                growth6mPercent: parsed6m.value,
+                growth1yPercent: parsed1y.value,
+                growth2yPercent: null,
+                growth3mLabel: null,
+                growth6mLabel: parsed6m.label,
+                growth1yLabel: parsed1y.label,
+                growth2yLabel: null,
+                rawPayload: { source: "employee_function_distribution", label, growth6m, growth1y },
+            });
+            index += 2;
+        }
+    }
+    const unavailableIndex = lines.findIndex((line) => /^Select insights not available$/i.test(line));
+    if (unavailableIndex >= 0) {
+        const detail = lines[unavailableIndex + 1] || null;
+        insights.push({
+            insightType: "unavailable_insight",
+            label: detail,
+            period: null,
+            metricValue: null,
+            metricUnit: null,
+            growth3mPercent: null,
+            growth6mPercent: null,
+            growth1yPercent: null,
+            growth2yPercent: null,
+            growth3mLabel: null,
+            growth6mLabel: null,
+            growth1yLabel: null,
+            growth2yLabel: null,
+            rawPayload: { source: "select_insights_not_available", detail },
+        });
+    }
+    return insights;
+}
+function parseLocalLinkedInCompanyText(text, rawUrl, insightsText = "") {
+    const urls = normalizeLinkedInCompanyScrapeUrl(rawUrl);
+    const lines = text
+        .split(/\r?\n/)
+        .map((line) => line.replace(/\s+/g, " ").trim())
+        .filter(Boolean);
+    const insightLines = insightsText
+        .split(/\r?\n/)
+        .map((line) => line.replace(/\s+/g, " ").trim())
+        .filter(Boolean);
+    const website = parseLinkedInAboutTextValue(lines, "Website");
+    const industry = parseLinkedInAboutTextValue(lines, "Industry");
+    const companySize = parseLinkedInAboutTextValue(lines, "Company size");
+    const associatedMembersText = lines.find((line) => /associated members\b/i.test(line)) ?? null;
+    const founded = parseLinkedInCompactInteger(parseLinkedInAboutTextValue(lines, "Founded"));
+    const headquarters = parseLinkedInAboutTextValue(lines, "Headquarters");
+    const overviewIndex = lines.findIndex((line) => line.toLowerCase() === "overview");
+    const description = overviewIndex >= 0
+        ? lines
+            .slice(overviewIndex + 1)
+            .find((line) => !["Website", "Industry", "Company size", "Founded", "Locations (1)", "Headquarters"].includes(line)) ?? null
+        : null;
+    const name = lines.find((line, index) => {
+        if (index > 12) {
+            return false;
+        }
+        return (!["Home", "About", "Posts", "Jobs", "People", "Insights", "Message", "Following", "Follow"].includes(line) &&
+            !line.includes("followers") &&
+            !line.includes("employees") &&
+            !line.includes("connections"));
+    }) ?? null;
+    const insights = parseLinkedInInsightRows(insightLines);
+    return {
+        ...urls,
+        name,
+        website,
+        domain: normalizeLocalCompanyDomain(website),
+        industry,
+        companySize,
+        employeesOnLinkedIn: parseLinkedInCompactInteger(associatedMembersText),
+        totalEmployeeCount: parseLinkedInCompactInteger(associatedMembersText),
+        followerCount: parseLinkedInCompactInteger(lines.find((line) => /followers\b/i.test(line))),
+        headquarters,
+        founded,
+        description,
+        medianEmployeeTenureYears: parseLinkedInTenureYears(insightLines),
+        insights,
+        rawPayload: {
+            sourceTextLines: lines,
+            insightsTextLines: insightLines,
+        },
+        timestamp: new Date().toISOString(),
+    };
+}
+function parseLocalDealroomCompanyText(text, rawUrl) {
+    const urls = normalizeDealroomCompanyScrapeUrl(rawUrl);
+    const lines = text
+        .split(/\r?\n/)
+        .map((line) => line.replace(/\s+/g, " ").trim())
+        .filter(Boolean);
+    const reservedTopLines = new Set([
+        "dealroom.co",
+        "Dashboard",
+        "News",
+        "Companies",
+        "Stats & Insights",
+        "Sectors",
+        "Locations",
+        "Investors",
+        "Transactions",
+        "Public Multiples",
+        "People",
+        "More organizations",
+        "Deep Dives",
+        "Knowledge base",
+        "Login",
+        "Book a Demo",
+        "Save",
+        "Overview",
+        "Similar companies",
+        "Investments (1)",
+        "Job openings",
+    ]);
+    const name = lines.find((line) => {
+        if (reservedTopLines.has(line)) {
+            return false;
+        }
+        if (/search for companies/i.test(line)) {
+            return false;
+        }
+        return true;
+    }) ?? null;
+    const tagline = name ? lines[lines.indexOf(name) + 1] ?? null : null;
+    const website = normalizeDealroomWebsite(parseLabeledTextValue(lines, "Website"));
+    const recentDealText = parseLabeledTextValue(lines, "Recent deals");
+    const signalLine = lines.find((line) => /^\d{1,3}$/.test(line) && Number(line) <= 100 && lines[lines.indexOf(line) + 1] === "Dealroom.co signal");
+    const sector = lines.find((line) => /#\d+\)?$/i.test(line) && !/^\d+$/.test(line)) ?? null;
+    const knownLabels = new Set([
+        "HQ location",
+        "Website",
+        "Launch date",
+        "Employees",
+        "Enterprise value",
+        "Company register number",
+        "Jobs",
+        "Recent deals",
+    ]);
+    const nonTagValues = new Set();
+    for (const label of knownLabels) {
+        const value = parseLabeledTextValue(lines, label);
+        if (value) {
+            nonTagValues.add(value);
+        }
+    }
+    const tagStartIndex = lines.findIndex((line) => /^B2B$/i.test(line) || /^\$?\s*saas$/i.test(line));
+    const tagEndIndex = sector ? lines.indexOf(sector) : -1;
+    const tags = tagStartIndex >= 0
+        ? lines
+            .slice(tagStartIndex, tagEndIndex > tagStartIndex ? tagEndIndex : undefined)
+            .filter((line) => !knownLabels.has(line) && !nonTagValues.has(line))
+        : [];
+    const socialLinks = {};
+    for (const line of lines) {
+        if (/^https?:\/\/(www\.)?linkedin\.com\//i.test(line)) {
+            socialLinks.linkedin = line;
+        }
+        else if (/^https?:\/\/(www\.)?(x|twitter)\.com\//i.test(line)) {
+            socialLinks.x = line;
+        }
+    }
+    const enterpriseValueText = parseLabeledTextValue(lines, "Enterprise value");
+    return {
+        ...urls,
+        name,
+        tagline,
+        hqLocation: parseLabeledTextValue(lines, "HQ location"),
+        website,
+        domain: normalizeLocalCompanyDomain(website),
+        launchDateText: parseLabeledTextValue(lines, "Launch date"),
+        employeeRange: parseLabeledTextValue(lines, "Employees"),
+        enterpriseValueText,
+        enterpriseValueUsd: parseDealroomEnterpriseValueUsd(enterpriseValueText),
+        companyRegisterNumber: parseLabeledTextValue(lines, "Company register number"),
+        jobsText: parseLabeledTextValue(lines, "Jobs"),
+        recentDeals: recentDealText ? [recentDealText] : [],
+        tags,
+        sector,
+        signalScore: signalLine ? Number(signalLine) : null,
+        socialLinks,
+        rawPayload: { sourceTextLines: lines },
+        timestamp: new Date().toISOString(),
+    };
+}
+async function upsertLocalLinkedInCompanyScrape(row) {
+    const databaseUrl = process.env.SALESPROMPTER_DATABASE_URL?.trim() ||
+        process.env.DATABASE_URL?.trim() ||
+        "";
+    if (!databaseUrl) {
+        throw new Error("Missing DATABASE_URL or SALESPROMPTER_DATABASE_URL for LinkedIn company scraper storage.");
+    }
+    const client = new pg.Client({
+        connectionString: databaseUrl,
+        ssl: { rejectUnauthorized: false },
+    });
+    await client.connect();
+    let committed = false;
+    try {
+        await client.query("BEGIN");
+        await client.query(`INSERT INTO public.linkedin_companies_processed (
+        error, query, timestamp, name, description, follower_count, website, domain, industry,
+        company_size, founded, company_address, main_company_id, linkedin_id, sales_navigator_link,
+        employees_on_linked_in, company_name, total_employee_count, company_url, headquarters
+      ) VALUES (
+        NULL, $1, $2, $3, $4, $5, $6, $7, $8,
+        $9, $10, $11, $12, $13, $14,
+        $15, $16, $17, $18, $19
+      )`, [
+            `linkedin.com/company/${row.id}`,
+            row.timestamp,
+            row.name,
+            row.description,
+            row.followerCount,
+            row.website,
+            row.domain,
+            row.industry,
+            row.companySize,
+            row.founded,
+            row.headquarters,
+            row.id,
+            String(row.id),
+            row.salesNavigatorLink,
+            row.employeesOnLinkedIn,
+            row.name,
+            row.totalEmployeeCount,
+            row.companyUrl,
+            row.headquarters,
+        ]);
+        const snapshotResult = await client.query(`INSERT INTO public.linkedin_company_local_scrape_snapshots (
+        linkedin_company_id, linkedin_company_url, sales_navigator_link, company_name,
+        scrape_source, scraped_at, observed_at, overview_text, website, domain, industry,
+        company_size, employees_on_linkedin, total_employee_count, follower_count,
+        headquarters, founded, median_employee_tenure_years, raw_payload
+      ) VALUES (
+        $1, $2, $3, $4,
+        'linkedin_company_scraper_local', $5, $5, $6, $7, $8, $9,
+        $10, $11, $12, $13,
+        $14, $15, $16, $17::jsonb
+      )
+      RETURNING id`, [
+            row.id,
+            row.companyUrl,
+            row.salesNavigatorLink,
+            row.name,
+            row.timestamp,
+            row.description,
+            row.website,
+            row.domain,
+            row.industry,
+            row.companySize,
+            row.employeesOnLinkedIn,
+            row.totalEmployeeCount,
+            row.followerCount,
+            row.headquarters,
+            row.founded,
+            row.medianEmployeeTenureYears,
+            JSON.stringify(sanitizeForPostgresJson(row.rawPayload)),
+        ]);
+        const snapshotId = snapshotResult.rows[0]?.id;
+        if (!snapshotId) {
+            throw new Error("Failed to create LinkedIn company local scrape snapshot.");
+        }
+        for (const insight of row.insights) {
+            await client.query(`INSERT INTO public.linkedin_company_local_scrape_insights (
+          snapshot_id, linkedin_company_id, insight_type, label, period, metric_value,
+          metric_unit, growth_3m_percent, growth_6m_percent, growth_1y_percent,
+          growth_2y_percent, growth_3m_label, growth_6m_label, growth_1y_label,
+          growth_2y_label, raw_payload, scraped_at
+        ) VALUES (
+          $1, $2, $3, $4, $5, $6,
+          $7, $8, $9, $10,
+          $11, $12, $13, $14,
+          $15, $16::jsonb, $17
+        )`, [
+                snapshotId,
+                row.id,
+                insight.insightType,
+                insight.label,
+                insight.period,
+                insight.metricValue,
+                insight.metricUnit,
+                insight.growth3mPercent,
+                insight.growth6mPercent,
+                insight.growth1yPercent,
+                insight.growth2yPercent,
+                insight.growth3mLabel,
+                insight.growth6mLabel,
+                insight.growth1yLabel,
+                insight.growth2yLabel,
+                JSON.stringify(sanitizeForPostgresJson(insight.rawPayload)),
+                row.timestamp,
+            ]);
+        }
+        await client.query("COMMIT");
+        committed = true;
+    }
+    finally {
+        if (!committed) {
+            try {
+                await client.query("ROLLBACK");
+            }
+            catch {
+                // The transaction may already be closed by the database.
+            }
+        }
+        await client.end();
+    }
+}
+async function insertLocalDealroomCompanyScrape(row) {
+    const databaseUrl = process.env.SALESPROMPTER_DATABASE_URL?.trim() ||
+        process.env.DATABASE_URL?.trim() ||
+        "";
+    if (!databaseUrl) {
+        throw new Error("Missing DATABASE_URL or SALESPROMPTER_DATABASE_URL for Dealroom company scraper storage.");
+    }
+    const client = new pg.Client({
+        connectionString: databaseUrl,
+        ssl: { rejectUnauthorized: false },
+    });
+    await client.connect();
+    let committed = false;
+    try {
+        await client.query("BEGIN");
+        await client.query(`INSERT INTO public.dealroom_company_local_scrape_snapshots (
+        dealroom_company_slug, dealroom_company_url, source_url, scrape_source,
+        scraped_at, observed_at, company_name, tagline, hq_location, website,
+        domain, launch_date_text, employee_range, enterprise_value_text,
+        enterprise_value_usd, company_register_number, jobs_text, recent_deals,
+        tags, sector, signal_score, social_links, raw_payload
+      ) VALUES (
+        $1, $2, $3, 'dealroom_company_scraper_local',
+        $4, $4, $5, $6, $7, $8,
+        $9, $10, $11, $12,
+        $13, $14, $15, $16,
+        $17, $18, $19, $20::jsonb, $21::jsonb
+      )`, [
+            row.slug,
+            row.companyUrl,
+            row.sourceUrl,
+            row.timestamp,
+            row.name,
+            row.tagline,
+            row.hqLocation,
+            row.website,
+            row.domain,
+            row.launchDateText,
+            row.employeeRange,
+            row.enterpriseValueText,
+            row.enterpriseValueUsd,
+            row.companyRegisterNumber,
+            row.jobsText,
+            row.recentDeals,
+            row.tags,
+            row.sector,
+            row.signalScore,
+            JSON.stringify(sanitizeForPostgresJson(row.socialLinks)),
+            JSON.stringify(sanitizeForPostgresJson(row.rawPayload)),
+        ]);
+        await client.query("COMMIT");
+        committed = true;
+    }
+    finally {
+        if (!committed) {
+            try {
+                await client.query("ROLLBACK");
+            }
+            catch {
+                // The transaction may already be closed by the database.
+            }
+        }
+        await client.end();
+    }
+}
 async function upsertSalesNavigatorAccounts(params) {
     if (params.accounts.length === 0) {
         return 0;
@@ -10599,6 +11229,10 @@ program.hook("preAction", async (_thisCommand, actionCommand) => {
         commandName === "accounts:local-import" ||
         commandName === "salesnav:accounts:repair" ||
         commandName === "accounts:repair" ||
+        commandName === "linkedin-companies:scrape-local" ||
+        commandName === "companies:scrape-linkedin" ||
+        commandName === "dealroom-companies:scrape-local" ||
+        commandName === "companies:scrape-dealroom" ||
         commandName.startsWith("packs:") ||
         ((commandName === "list" || commandName === "add") && parentCommandName === "packs")) {
         return;
@@ -10945,6 +11579,76 @@ program
         mergeSql: result.mergeSql
     });
 });
+program
+    .command("linkedin-companies:scrape-local")
+    .alias("companies:scrape-linkedin")
+    .description("LinkedIn Company Scraper: parse a locally opened LinkedIn company page and store it in Salesprompter.")
+    .requiredOption("--url <url>", "LinkedIn company URL with a numeric company id")
+    .option("--text-file <path>", "Path to text copied from the LinkedIn company About page")
+    .option("--insights-text-file <path>", "Path to text copied from the LinkedIn company Insights page")
+    .option("--apply", "Store the scraped company profile in the Salesprompter database", false)
+    .option("--no-open", "Do not open the LinkedIn company URL in the local browser")
+    .action(async (options) => {
+    const target = normalizeLinkedInCompanyScrapeUrl(options.url);
+    if (options.open !== false) {
+        await new Promise((resolve) => {
+            const child = spawn("open", [target.companyUrl], { stdio: "ignore" });
+            child.on("close", () => resolve());
+            child.on("error", () => resolve());
+        });
+    }
+    const inputText = options.textFile
+        ? await readFile(path.resolve(String(options.textFile)), "utf8")
+        : await readAllStdin();
+    if (!inputText.trim()) {
+        throw new Error("No LinkedIn company page text provided. Open the company page, copy the About page text, then pass --text-file or pipe it on stdin.");
+    }
+    const insightsText = options.insightsTextFile
+        ? await readFile(path.resolve(String(options.insightsTextFile)), "utf8")
+        : "";
+    const profile = parseLocalLinkedInCompanyText(inputText, target.sourceUrl, insightsText);
+    if (options.apply) {
+        await upsertLocalLinkedInCompanyScrape(profile);
+    }
+    printOutput({
+        status: "ok",
+        stored: Boolean(options.apply),
+        profile,
+    });
+});
+program
+    .command("dealroom-companies:scrape-local")
+    .alias("companies:scrape-dealroom")
+    .description("Dealroom Company Scraper: parse a locally opened Dealroom company page and store it in Salesprompter.")
+    .requiredOption("--url <url>", "Dealroom company URL with /companies/<slug>")
+    .option("--text-file <path>", "Path to text copied from the Dealroom company page")
+    .option("--apply", "Store the scraped Dealroom company profile in the Salesprompter database", false)
+    .option("--no-open", "Do not open the Dealroom company URL in the local browser")
+    .action(async (options) => {
+    const target = normalizeDealroomCompanyScrapeUrl(options.url);
+    if (options.open !== false) {
+        await new Promise((resolve) => {
+            const child = spawn("open", [target.companyUrl], { stdio: "ignore" });
+            child.on("close", () => resolve());
+            child.on("error", () => resolve());
+        });
+    }
+    const inputText = options.textFile
+        ? await readFile(path.resolve(String(options.textFile)), "utf8")
+        : await readAllStdin();
+    if (!inputText.trim()) {
+        throw new Error("No Dealroom company page text provided. Open the company page, copy the visible profile text, then pass --text-file or pipe it on stdin.");
+    }
+    const profile = parseLocalDealroomCompanyText(inputText, target.sourceUrl);
+    if (options.apply) {
+        await insertLocalDealroomCompanyScrape(profile);
+    }
+    printOutput({
+        status: "ok",
+        stored: Boolean(options.apply),
+        profile,
+    });
+});
 program
     .command("linkedin-products:scrape")
     .alias("market:scrape")

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "salesprompter-cli",
-  "version": "0.1.42",
+  "version": "0.1.43",
   "description": "Sales workflow CLI for guided lead generation, enrichment, scoring, and sync.",
   "author": "Daniel Sinewe <hello@danielsinewe.com>",
   "type": "module",