{ "name": "The Register", "description": "A catalogue of production web-data extractors running on Apify. Every output field is documented with a type, a written description and an example value.", "source": "https://alaudinburki-scrapers.pages.dev/", "apifyProfile": "https://apify.com/alaudinburki", "generatedAt": "2026-10-18T17:53:53.089Z", "totals": { "actors": 113, "fields": 1383, "documented": 113, "runs": 3818, "users": 203, "categories": 12 }, "categories": [ { "id": "DEVELOPER_TOOLS", "slug": "developer-tools", "label": "Developer tools", "count": 75 }, { "id": "BUSINESS", "slug": "business", "label": "Business", "count": 57 }, { "id": "AUTOMATION", "slug": "automation", "label": "Automation", "count": 26 }, { "id": "AI", "slug": "ai", "label": "AI", "count": 17 }, { "id": "SEO_TOOLS", "slug": "seo-tools", "label": "SEO tools", "count": 14 }, { "id": "LEAD_GENERATION", "slug": "lead-generation", "label": "Lead generation", "count": 8 }, { "id": "ECOMMERCE", "slug": "ecommerce", "label": "E-commerce", "count": 8 }, { "id": "INTEGRATIONS", "slug": "integrations", "label": "Integrations", "count": 8 }, { "id": "MARKETING", "slug": "marketing", "label": "Marketing", "count": 6 }, { "id": "NEWS", "slug": "news", "label": "News", "count": 6 }, { "id": "JOBS", "slug": "jobs", "label": "Jobs", "count": 4 }, { "id": "MCP_SERVERS", "slug": "mcp-servers", "label": "MCP servers", "count": 2 } ], "extractors": [ { "slug": "rest-api-paginator", "entry": "001", "title": "REST API Fetcher & Paginator — Any JSON API to Dataset", "description": "Fetch any JSON REST API into an Apify dataset — extract the items array by dot-path and auto-follow pagination (page, offset, cursor, or next-link). Custom headers for auth. Turns any API into a dataset.", "categories": [ "DEVELOPER_TOOLS", "AUTOMATION" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/rest-api-paginator/", "apifyUrl": "https://apify.com/alaudinburki/rest-api-paginator", "usage": { "runs": 843, "users": 4, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "value", "type": "number", "nullable": false, "description": "The measured value for this row. Units are in the README and sometimes in a sibling field.", "example": "42.5" }, { "key": "status", "type": "string", "nullable": false, "description": "Outcome recorded for this row.", "example": "active" }, { "key": "message", "type": "string", "nullable": false, "description": "Human-readable note about this row or the run.", "example": "Add your API key to classify answers. No text was sent anywhere." }, { "key": "rowsReturned", "type": "number", "nullable": false, "description": "How many rows the run returned. Zero on a blocked run, which is a real value and the entire point of such a record.", "example": "0" } ], "inputs": [ { "key": "url", "type": "string", "required": true, "secret": false, "description": "The JSON API endpoint (include query params)." }, { "key": "itemsPath", "type": "string", "required": false, "secret": false, "description": "Dot-path to the array in the response, e.g. data.results or hits. Empty = response is the array." }, { "key": "paginationStrategy", "type": "string", "required": false, "secret": false, "description": "none, page, offset, cursor, or link." }, { "key": "paginationParam", "type": "string", "required": false, "secret": false, "description": "Query param for page/offset/cursor (e.g. page, offset, cursor)." }, { "key": "cursorPath", "type": "string", "required": false, "secret": false, "description": "For cursor/link: dot-path to the cursor value or next URL in the response (e.g. meta.next)." }, { "key": "pageSize", "type": "integer", "required": false, "secret": false, "description": "For offset strategy: how much to advance each page." }, { "key": "headers", "type": "object", "required": false, "secret": false, "description": "Extra request headers, e.g. {\"Authorization\":\"Bearer ...\"}." }, { "key": "maxPages", "type": "integer", "required": false, "secret": false, "description": "Stop after N pages." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard cap." } ] }, { "slug": "job-change-monitor", "entry": "002", "title": "Job Monitor — Only What's New Since Last Run", "description": "Watch job pages and get only the NEW and CHANGED postings since your last run. Reads schema.org JobPosting data, so no per-site setup - see the README for which pages work.", "categories": [ "JOBS", "AUTOMATION" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/job-change-monitor/", "apifyUrl": "https://apify.com/alaudinburki/job-change-monitor", "usage": { "runs": 60, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "changeType", "type": "string", "nullable": true, "description": "What changed: initial, content, status, or a combination.", "example": "content" }, { "key": "title", "type": "string", "nullable": true, "description": "Title as the source writes it.", "example": "Wireless Bluetooth Headphones" }, { "key": "company", "type": "string", "nullable": true, "description": "Company name as the source writes it.", "example": "Northwind Traders" }, { "key": "location", "type": "string", "nullable": true, "description": "Location as the source writes it.", "example": "Austin, TX" }, { "key": "salaryMin", "type": "number", "nullable": true, "description": "Lower bound of the advertised salary.", "example": "95000" }, { "key": "salaryMax", "type": "number", "nullable": true, "description": "Upper bound of the advertised salary.", "example": "130000" }, { "key": "remote", "type": "boolean", "nullable": true, "description": "Whether the posting is remote.", "example": "true" }, { "key": "url", "type": "string", "nullable": true, "description": "The URL this row describes.", "example": "https://example.com/pricing" } ], "inputs": [ { "key": "boardUrls", "type": "array", "required": true, "secret": false, "description": "Pages whose HTML contains schema.org JobPosting data - individual job pages, and server-rendered boards. Board index and search pages usually do NOT work: they build their list in the browser, so the HTML has no jobs in it. To check a page, View Source and search for 'JobPosting'. The defaults below are real pages you can run as-is." }, { "key": "returnMode", "type": "string", "required": false, "secret": false, "description": "'New and changed only' is the point of a monitor. Use 'all' for a one-off full scrape." }, { "key": "titleIncludes", "type": "array", "required": false, "secret": false, "description": "Case-insensitive. Leave empty for all titles." }, { "key": "titleExcludes", "type": "array", "required": false, "secret": false, "description": "Filter out seniority levels or roles you don't want." }, { "key": "remoteOnly", "type": "boolean", "required": false, "secret": false, "description": "Keep only postings whose location or job type says remote. Off by default." }, { "key": "minSalary", "type": "integer", "required": false, "secret": false, "description": "Jobs with no published salary are always kept - most listings omit it." }, { "key": "postedWithinDays", "type": "integer", "required": false, "secret": false, "description": "Ignore postings older than this many days. Leave empty for no age limit." }, { "key": "includeRemoved", "type": "boolean", "required": false, "secret": false, "description": "Report postings that disappeared since the last run." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit, strictly enforced." }, { "key": "maxConcurrency", "type": "integer", "required": false, "secret": false, "description": "How many board pages to fetch at once. Lower it if a site rate-limits you." } ] }, { "slug": "sitemap-url-extractor", "entry": "003", "title": "Sitemap URL Extractor — Every URL From Any Sitemap", "description": "Extract every URL from a site's sitemaps — follows sitemap-index files, reads robots.txt to discover them, decompresses .gz sitemaps, and returns lastmod/changefreq/priority. Feeds any other scraper. Pure logic.", "categories": [ "SEO_TOOLS", "DEVELOPER_TOOLS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/sitemap-url-extractor/", "apifyUrl": "https://apify.com/alaudinburki/sitemap-url-extractor", "usage": { "runs": 60, "users": 2, "lastRun": "2026-10-15" }, "outputSchema": [ { "key": "url", "type": "string", "nullable": true, "description": "The URL this row describes.", "example": "https://example.com/pricing" }, { "key": "lastmod", "type": "string", "nullable": true, "description": "Last-modified date the sitemap declares.", "example": "" }, { "key": "changefreq", "type": "string", "nullable": true, "description": "Change frequency the sitemap declares.", "example": "" }, { "key": "priority", "type": "string", "nullable": true, "description": "Priority the sitemap declares, between 0.0 and 1.0. Higher means the page is considered more important relative to others on the site.", "example": "high" }, { "key": "sitemap", "type": "string", "nullable": true, "description": "Sitemap URL this row came from.", "example": "" } ], "inputs": [ { "key": "siteUrl", "type": "string", "required": false, "secret": false, "description": "A site to extract sitemaps from — standard locations (sitemap.xml, sitemap_index.xml) and robots.txt are tried automatically." }, { "key": "sitemapUrls", "type": "array", "required": false, "secret": false, "description": "Exact sitemap URLs to parse, if you already know them (index or urlset, .xml or .xml.gz)." }, { "key": "urlIncludes", "type": "array", "required": false, "secret": false, "description": "Keep only URLs containing one of these substrings (e.g. /blog/)." }, { "key": "urlExcludes", "type": "array", "required": false, "secret": false, "description": "Drop URLs containing any of these substrings." }, { "key": "maxUrls", "type": "integer", "required": false, "secret": false, "description": "Hard cap on URLs returned. Strictly enforced." }, { "key": "maxSitemaps", "type": "integer", "required": false, "secret": false, "description": "Cap on how many sitemap files to fetch (for huge sitemap-index sites)." }, { "key": "useProxy", "type": "boolean", "required": false, "secret": false, "description": "Route through a proxy for sites that block datacenter IPs." } ] }, { "slug": "email-verifier-honest", "entry": "004", "title": "Email Verifier — Honest Grades, No False Certainty", "description": "Verify email lists without sending mail. Returns a 0-100 deliverability score, syntax, MX records, mail provider, catch-all detection, disposable and role-account flags, and typo correction. Every result explains its verdict, and says plainly when a check could not be performed rather than guessing.", "categories": [ "LEAD_GENERATION", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/email-verifier-honest/", "apifyUrl": "https://apify.com/alaudinburki/email-verifier-honest", "usage": { "runs": 57, "users": 1, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "email", "type": "string", "nullable": true, "description": "Email address, as published by the source.", "example": "hello@example.com" }, { "key": "status", "type": "string", "nullable": true, "description": "Outcome recorded for this row.", "example": "ok" }, { "key": "confidence", "type": "string", "nullable": true, "description": "How confident the Actor is in this result, from 0 to 1. Not a probability of correctness.", "example": "" }, { "key": "reason", "type": "string", "nullable": true, "description": "Why this row carries its status.", "example": "row retrieved successfully" }, { "key": "domain", "type": "string", "nullable": true, "description": "Domain name, without the scheme.", "example": "example.com" }, { "key": "isDisposable", "type": "boolean", "nullable": true, "description": "Whether the domain is a known disposable-address provider.", "example": "true" }, { "key": "isRoleAccount", "type": "boolean", "nullable": true, "description": "Whether the address is a shared role mailbox such as info@ or sales@.", "example": "true" }, { "key": "mailServer", "type": "string", "nullable": true, "description": "Mail server the domain uses.", "example": "" }, { "key": "suggestedCorrection", "type": "string", "nullable": true, "description": "Likely intended address, when the one given looks mistyped.", "example": "" }, { "key": "score", "type": "integer", "nullable": true, "description": "Score on the Actor's own scale. The scale is stated in the field's own band.", "example": "82" }, { "key": "scoreBand", "type": "string", "nullable": true, "description": "Band the score falls into, in words.", "example": "" }, { "key": "mailProvider", "type": "string", "nullable": true, "description": "Mail provider hosting the domain.", "example": "" }, { "key": "isCatchAll", "type": "boolean", "nullable": true, "description": "Whether the domain accepts mail for any address, which makes single-address verification unreliable.", "example": "true" }, { "key": "catchAllStatus", "type": "string", "nullable": true, "description": "Whether the domain accepts mail for any address.", "example": "" }, { "key": "smtpStatus", "type": "string", "nullable": true, "description": "Outcome of the SMTP conversation.", "example": "" }, { "key": "smtpCode", "type": "integer", "nullable": true, "description": "SMTP response code returned by the server.", "example": "0" } ], "inputs": [ { "key": "emails", "type": "array", "required": true, "secret": false, "description": "One address per line, or paste a comma-separated list." }, { "key": "onlyStatus", "type": "string", "required": false, "secret": false, "description": "Filter the output. Choose 'valid' to get a clean sending list." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit, strictly enforced. You will never be charged for more." }, { "key": "concurrency", "type": "integer", "required": false, "secret": false, "description": "Higher is faster. Lower if your DNS resolver rate-limits." }, { "key": "catchAllCheck", "type": "boolean", "required": false, "secret": false, "description": "Probe each domain once to see whether it accepts mail for ANY address. On a catch-all domain a 'valid' verdict proves nothing — this is the single biggest cause of bounced 'verified' lists. Needs outbound port 25, which most cloud hosts block; the result says so plainly when blocked." }, { "key": "smtpCheck", "type": "boolean", "required": false, "secret": false, "description": "Ask the mail server directly whether the recipient exists (RCPT TO, no mail sent). The only direct evidence available — but port 25 is blocked on most cloud hosts, and some providers answer misleadingly. Off by default." } ] }, { "slug": "google-trends-full-scraper", "entry": "005", "title": "Google Trends Full Scraper — Interest & Related", "description": "Interest over time, related queries and topics, and interest by region for up to 5 compared keywords. Handles rate limits with backoff + proxy, and flags every incomplete-period data point instead of returning it silently.", "categories": [ "SEO_TOOLS", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/google-trends-full-scraper/", "apifyUrl": "https://apify.com/alaudinburki/google-trends-full-scraper", "usage": { "runs": 56, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "type", "type": "string", "nullable": true, "description": "Type of this record, as classified by the Actor.", "example": "article" }, { "key": "keyword", "type": "string", "nullable": true, "description": "The keyword this record relates to.", "example": "" }, { "key": "date", "type": "string", "nullable": true, "description": "ISO 8601 date associated with this record.", "example": "2026-10-15" }, { "key": "value", "type": "number", "nullable": true, "description": "Value as recorded for this row.", "example": "42.5" }, { "key": "isPartial", "type": "boolean", "nullable": true, "description": "Whether the source marks this record as incomplete.", "example": "true" }, { "key": "query", "type": "string", "nullable": true, "description": "The query that produced this row.", "example": "shopify scraper" }, { "key": "rank", "type": "integer", "nullable": true, "description": "Position in the source's own ordering. 1 is highest.", "example": "1" }, { "key": "geoName", "type": "string", "nullable": true, "description": "Geo Name as recorded for this row.", "example": "" } ], "inputs": [ { "key": "keywords", "type": "array", "required": true, "secret": false, "description": "Search terms to analyze, up to 5 — they are compared on the same scale, exactly like the Google Trends website. For more, run separate jobs." }, { "key": "geo", "type": "string", "required": false, "secret": false, "description": "Two-letter country code (US, GB, DE...) or a sub-region (US-CA). Leave empty for worldwide." }, { "key": "timeRange", "type": "string", "required": false, "secret": false, "description": "One of: now 1-H, now 4-H, now 1-d, now 7-d, today 1-m, today 3-m, today 12-m, today 5-y, all." }, { "key": "datasets", "type": "array", "required": false, "secret": false, "description": "Which data to return: interestOverTime, relatedQueries, relatedTopics, interestByRegion." }, { "key": "category", "type": "integer", "required": false, "secret": false, "description": "Google Trends category number to narrow results (0 = all categories). See Google Trends for category IDs." }, { "key": "property", "type": "string", "required": false, "secret": false, "description": "Search surface: web (empty), news, images, youtube, or froogle (shopping)." }, { "key": "language", "type": "string", "required": false, "secret": false, "description": "Result language, e.g. en-US, de-DE." }, { "key": "proxyConfiguration", "type": "object", "required": true, "secret": false, "description": "A proxy is required because Google rate-limits by IP. The example uses Apify Proxy; select residential access or provide an external proxy if the shared proxy is blocked for your run." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit on output rows. Strictly enforced — you will never be charged for more than this." } ] }, { "slug": "amazon-product-scraper-reliable", "entry": "006", "title": "Amazon Product Scraper — Reliable, No Silent Blanks", "description": "Scrape Amazon products with per-field reporting. Every row tells you exactly what was found and what was missing - no silent blanks, no surprise failures.", "categories": [ "ECOMMERCE", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/amazon-product-scraper-reliable/", "apifyUrl": "https://apify.com/alaudinburki/amazon-product-scraper-reliable", "usage": { "runs": 55, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "asin", "type": "string", "nullable": false, "description": "Amazon Standard Identification Number.", "example": "B09XS7JWHH" }, { "key": "title", "type": "string", "nullable": false, "description": "Title as the source writes it.", "example": "Wireless Bluetooth Headphones" }, { "key": "brand", "type": "string", "nullable": false, "description": "Brand the item is sold under.", "example": "" }, { "key": "price", "type": "number", "nullable": true, "description": "Price as reported by the source. Currency is given by the currency field.", "example": "9.99" }, { "key": "currency", "type": "string", "nullable": true, "description": "Three-letter ISO 4217 currency code.", "example": "USD" }, { "key": "priceStatus", "type": "string", "nullable": false, "description": "Whether a price was found and parsed.", "example": "" }, { "key": "rating", "type": "number", "nullable": true, "description": "Average rating as reported by the source.", "example": "4.6" }, { "key": "reviewCount", "type": "integer", "nullable": true, "description": "Number of reviews the source counts.", "example": "1284" }, { "key": "completeness", "type": "integer", "nullable": true, "description": "Share of expected values actually present, between 0 and 1.", "example": "0" }, { "key": "url", "type": "string", "nullable": false, "description": "The URL this row describes.", "example": "https://example.com/pricing" }, { "key": "dealScore", "type": "integer", "nullable": true, "description": "Deal Score as recorded for this row.", "example": "0" }, { "key": "isPriceAnomaly", "type": "boolean", "nullable": true, "description": "Whether this price deviates enough from the norm to be flagged.", "example": "true" }, { "key": "priceVsAvgPercent", "type": "number", "nullable": true, "description": "This price against the average, as a percentage.", "example": "0" }, { "key": "bestSellersRank", "type": "integer", "nullable": true, "description": "Sales rank as the marketplace publishes it. Lower is better.", "example": "0" }, { "key": "amazonsChoice", "type": "boolean", "nullable": true, "description": "Whether the item carries the marketplace's choice badge.", "example": "true" }, { "key": "bestSeller", "type": "boolean", "nullable": true, "description": "Whether the item carries a best-seller badge.", "example": "true" }, { "key": "variantCount", "type": "integer", "nullable": true, "description": "How many variants the product has.", "example": "6" }, { "key": "fulfillment", "type": "string", "nullable": true, "description": "How the item is fulfilled.", "example": "" }, { "key": "soldBy", "type": "string", "nullable": true, "description": "Seller the item is sold by.", "example": "" }, { "key": "imageCount", "type": "integer", "nullable": true, "description": "Number of images found.", "example": "7" }, { "key": "discountPercent", "type": "number", "nullable": true, "description": "Discount off the comparison price, as a percentage.", "example": "15" } ], "inputs": [ { "key": "productUrls", "type": "array", "required": true, "secret": false, "description": "Product page URLs from any Amazon marketplace (.com, .co.uk, .de, .in, .ae and 14 more)." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit, strictly enforced. You will never be charged for more than this." }, { "key": "minCompleteness", "type": "integer", "required": false, "secret": false, "description": "Skip products where fewer than this percentage of fields were found. Leave at 0 to return everything with its completeness score." }, { "key": "proxyCountry", "type": "string", "required": false, "secret": false, "description": "Two-letter country code. Prices and availability differ by delivery location — set this to match the marketplace you're scraping." }, { "key": "useResidentialProxy", "type": "boolean", "required": false, "secret": false, "description": "Slower and more expensive, but far less likely to be blocked. Turn on if you see captcha blocks in the log." }, { "key": "maxConcurrency", "type": "integer", "required": false, "secret": false, "description": "Lower this if you hit blocks. 5 is a safe default." }, { "key": "trackPriceHistory", "type": "boolean", "required": false, "secret": false, "description": "Remembers each product's price across runs. Adds priceVsAvgPercent, priceLow/High and isPriceAnomaly (flags a price >2σ from its own history). Schedule this actor daily to build the history." }, { "key": "detectChanges", "type": "boolean", "required": false, "secret": false, "description": "Compares each product to the previous run and adds a whatChanged list (price, stock, rating, review count, BSR) plus isNew. Turns this into a price/stock monitor you can schedule." } ] }, { "slug": "ebay-sold-listings", "entry": "007", "title": "eBay Sold Listings — Real Comps & Price Stats", "description": "Get eBay SOLD/completed listings (what items actually sold for) with per-query price stats — min, max, average, median. eBay's official API hides sold data; this reports it, paginated, with honest block handling.", "categories": [ "ECOMMERCE", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/ebay-sold-listings/", "apifyUrl": "https://apify.com/alaudinburki/ebay-sold-listings", "usage": { "runs": 54, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "query", "type": "string", "nullable": true, "description": "The query that produced this row.", "example": "shopify scraper" }, { "key": "title", "type": "string", "nullable": true, "description": "Title as the source writes it.", "example": "Wireless Bluetooth Headphones" }, { "key": "soldPrice", "type": "number", "nullable": true, "description": "Price the item actually sold for.", "example": "0" }, { "key": "currency", "type": "string", "nullable": true, "description": "Three-letter ISO 4217 currency code.", "example": "USD" }, { "key": "soldDate", "type": "string", "nullable": true, "description": "Date the sale completed.", "example": "" }, { "key": "condition", "type": "string", "nullable": true, "description": "Condition of the item.", "example": "" }, { "key": "shipping", "type": "string", "nullable": true, "description": "Shipping cost or terms as published.", "example": "" }, { "key": "soldPriceRaw", "type": "string", "nullable": true, "description": "Sale price exactly as the source renders it, before parsing.", "example": "" }, { "key": "bids", "type": "integer", "nullable": true, "description": "Bids as recorded for this row.", "example": "0" }, { "key": "bestOfferAccepted", "type": "boolean", "nullable": true, "description": "Best Offer Accepted as recorded for this row.", "example": "true" }, { "key": "itemUrl", "type": "string", "nullable": true, "description": "Direct link to this item at the source.", "example": "" }, { "key": "imageUrl", "type": "string", "nullable": true, "description": "Direct URL of this image.", "example": "https://cdn.example.com/products/1.jpg" }, { "key": "itemId", "type": "string", "nullable": true, "description": "Identifier of this item at the source.", "example": "" }, { "key": "sponsored", "type": "boolean", "nullable": true, "description": "Whether the listing is a sponsored placement.", "example": "true" }, { "key": "country", "type": "string", "nullable": true, "description": "Country code associated with this record.", "example": "US" }, { "key": "status", "type": "string", "nullable": true, "description": "Outcome recorded for this row.", "example": "ok" }, { "key": "page", "type": "integer", "nullable": true, "description": "Page number this record came from. 1-based.", "example": "1" }, { "key": "note", "type": "boolean", "nullable": false, "description": "Short free-text note recorded with this row.", "example": "true" } ], "inputs": [ { "key": "queries", "type": "array", "required": true, "secret": false, "description": "What to look up sold comps for, one per line, e.g. 'nintendo switch oled', 'airpods pro 2'." }, { "key": "sessionCookie", "type": "string", "required": false, "secret": true, "description": "Secret — supply your own value." }, { "key": "country", "type": "string", "required": false, "secret": false, "description": "Two-letter country for the eBay site: US, GB, DE, FR, IT, ES, CA, AU." }, { "key": "maxPagesPerQuery", "type": "integer", "required": false, "secret": false, "description": "How many result pages to fetch per search term (240 listings per page)." }, { "key": "excludeSponsored", "type": "boolean", "required": false, "secret": false, "description": "Drop sponsored/ad items, which distort 'what it actually sold for' statistics." }, { "key": "useResidentialProxy", "type": "boolean", "required": false, "secret": false, "description": "On by default: eBay login-gates datacenter IPs almost immediately. Turn off only to cut proxy cost if you're fine with more blocked pages." }, { "key": "maxConcurrency", "type": "integer", "required": false, "secret": false, "description": "Higher is faster but more likely to be throttled." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit on rows. Strictly enforced — never charged beyond it." } ] }, { "slug": "lead-finder-verified-emails", "entry": "008", "title": "Lead Finder — Named Contacts & Verified Emails", "description": "Crawl company websites for leads: named people with job titles, verified emails, phones and socials. Works out each company's email convention and labels every address by how it was obtained - found on the site, inferred, or constructed. Guesses are never presented as findings.", "categories": [ "LEAD_GENERATION", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/lead-finder-verified-emails/", "apifyUrl": "https://apify.com/alaudinburki/lead-finder-verified-emails", "usage": { "runs": 54, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "site", "type": "string", "nullable": true, "description": "Site as recorded for this row.", "example": "example.com" }, { "key": "companyName", "type": "string", "nullable": true, "description": "Registered company name.", "example": "" }, { "key": "email", "type": "string", "nullable": true, "description": "Email address, as published by the source.", "example": "hello@example.com" }, { "key": "emailStatus", "type": "string", "nullable": true, "description": "Verification verdict for this address.", "example": "" }, { "key": "emailReason", "type": "string", "nullable": true, "description": "Why the address carries its verdict.", "example": "" }, { "key": "isRoleAccount", "type": "boolean", "nullable": true, "description": "Whether the address is a shared role mailbox such as info@ or sales@.", "example": "true" }, { "key": "phones", "type": "string", "nullable": true, "description": "Phone numbers found for this record.", "example": "" }, { "key": "linkedin", "type": "string", "nullable": true, "description": "LinkedIn profile or company URL.", "example": "" }, { "key": "foundOnPage", "type": "string", "nullable": true, "description": "Page number where this record was found.", "example": "" }, { "key": "personName", "type": "string", "nullable": true, "description": "Person Name as recorded for this row.", "example": "" }, { "key": "jobTitle", "type": "string", "nullable": true, "description": "Job title as posted.", "example": "" }, { "key": "personProfileUrl", "type": "string", "nullable": true, "description": "Person Profile Url as recorded for this row.", "example": "" }, { "key": "emailSource", "type": "string", "nullable": true, "description": "Where the address was found.", "example": "" }, { "key": "emailPattern", "type": "string", "nullable": true, "description": "The address pattern the company appears to use.", "example": "" } ], "inputs": [ { "key": "domains", "type": "array", "required": false, "secret": false, "description": "Company domains to scan, one per line (with or without https://). Invalid entries are reported and skipped, never silently dropped." }, { "key": "startUrls", "type": "array", "required": false, "secret": false, "description": "Full page URLs to start from instead of (or in addition to) the domains list." }, { "key": "maxPagesPerSite", "type": "integer", "required": false, "secret": false, "description": "Homepage plus up to this many contact-like pages (contact, about, team, impressum...). 5 finds nearly everything; raise it for very large sites." }, { "key": "maxLeads", "type": "integer", "required": false, "secret": false, "description": "Hard limit on output rows. Strictly enforced — you will never be charged for more than this." }, { "key": "includeSitesWithoutEmails", "type": "boolean", "required": false, "secret": false, "description": "On: sites with no published email still get one row saying so (with phones/socials if found) — you always know every site was actually scanned. Off: only rows with an email." }, { "key": "findPeople", "type": "boolean", "required": false, "secret": false, "description": "Extract people (name + role) from team/about pages, and work out the company's email convention from any address that belongs to one of them. A named contact with a title is worth far more than a generic info@ address." }, { "key": "guessMissingEmails", "type": "boolean", "required": false, "secret": false, "description": "For a person found without a published address, build one from the company's convention. These are clearly labelled (emailSource: pattern_inferred / guessed) and are NEVER presented as found. Off by default — a constructed address is a hypothesis, not a lead." } ] }, { "slug": "amazon-reviews-honest", "entry": "009", "title": "Amazon Reviews Scraper — Honest Scope, No Fake Blanks", "description": "Scrape the reviews Amazon serves on the product page (top reviews, rating and star histogram) with per-page accounting. Blocked pages are reported as blocked, never returned as zero reviews.", "categories": [ "ECOMMERCE", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/amazon-reviews-honest/", "apifyUrl": "https://apify.com/alaudinburki/amazon-reviews-honest", "usage": { "runs": 52, "users": 2, "lastRun": "2026-10-15" }, "outputSchema": [ { "key": "rowType", "type": "string", "nullable": true, "description": "What kind of row this is, when one dataset mixes several shapes.", "example": "" }, { "key": "reviewId", "type": "string", "nullable": true, "description": "Identifier of this review at the source.", "example": "" }, { "key": "title", "type": "string", "nullable": true, "description": "Title as the source writes it.", "example": "Wireless Bluetooth Headphones" }, { "key": "body", "type": "string", "nullable": true, "description": "Body text of this record.", "example": "" }, { "key": "stars", "type": "number", "nullable": true, "description": "Number of stars recorded upstream.", "example": "131" }, { "key": "author", "type": "string", "nullable": true, "description": "Author of this record, as the source publishes it.", "example": "jane.cooper" }, { "key": "date", "type": "string", "nullable": true, "description": "ISO 8601 date associated with this record.", "example": "2026-10-15" }, { "key": "country", "type": "string", "nullable": true, "description": "Country code associated with this record.", "example": "US" }, { "key": "verifiedPurchase", "type": "boolean", "nullable": true, "description": "Whether the source marks this review as a verified purchase.", "example": "true" }, { "key": "helpfulVotes", "type": "integer", "nullable": true, "description": "How many users marked this review helpful.", "example": "0" }, { "key": "variant", "type": "string", "nullable": true, "description": "Variant identifier.", "example": "" }, { "key": "images", "type": "string", "nullable": true, "description": "Image URLs found in this record.", "example": "" }, { "key": "imageCount", "type": "integer", "nullable": true, "description": "Number of images found.", "example": "7" }, { "key": "asin", "type": "string", "nullable": true, "description": "Amazon Standard Identification Number.", "example": "B09XS7JWHH" }, { "key": "marketplace", "type": "string", "nullable": true, "description": "Marketplace this record came from.", "example": "" }, { "key": "countryCode", "type": "string", "nullable": true, "description": "Two-letter ISO 3166-1 country code.", "example": "US" }, { "key": "page", "type": "integer", "nullable": true, "description": "Page number this record came from. 1-based.", "example": "1" }, { "key": "overallRating", "type": "number", "nullable": true, "description": "Overall rating the source publishes.", "example": "0" }, { "key": "totalRatingsOnPage", "type": "integer", "nullable": true, "description": "Total ratings shown on the fetched page.", "example": "0" }, { "key": "url", "type": "string", "nullable": true, "description": "The URL this row describes.", "example": "https://example.com/pricing" }, { "key": "reviewsOnPage", "type": "integer", "nullable": true, "description": "Number of reviews present on the fetched page.", "example": "0" }, { "key": "stars5Percent", "type": "integer", "nullable": true, "description": "Stars5 Percent as recorded for this row.", "example": "0" }, { "key": "stars4Percent", "type": "integer", "nullable": true, "description": "Stars4 Percent as recorded for this row.", "example": "0" }, { "key": "stars3Percent", "type": "integer", "nullable": true, "description": "Stars3 Percent as recorded for this row.", "example": "0" }, { "key": "stars2Percent", "type": "integer", "nullable": true, "description": "Stars2 Percent as recorded for this row.", "example": "0" }, { "key": "stars1Percent", "type": "integer", "nullable": true, "description": "Stars1 Percent as recorded for this row.", "example": "0" }, { "key": "status", "type": "string", "nullable": true, "description": "Outcome recorded for this row.", "example": "ok" }, { "key": "note", "type": "boolean", "nullable": false, "description": "Short free-text note recorded with this row.", "example": "true" } ], "inputs": [ { "key": "productUrls", "type": "array", "required": true, "secret": false, "description": "Product pages to read reviews from (with /dp/ASIN). One per line." }, { "key": "minStars", "type": "integer", "required": false, "secret": false, "description": "Keep only reviews at or above this rating (1-5). Leave empty for all." }, { "key": "maxStars", "type": "integer", "required": false, "secret": false, "description": "Keep only reviews at or below this rating (1-5). Set both min and max to 1 to get only 1-star reviews." }, { "key": "sessionCookie", "type": "string", "required": false, "secret": true, "description": "Secret — supply your own value." }, { "key": "sortBy", "type": "string", "required": false, "secret": false, "description": "recent (newest first) or helpful (most helpful first)." }, { "key": "maxReviewPages", "type": "integer", "required": false, "secret": false, "description": "How many review pages to fetch per product. Page 1 is served without login (~10 reviews); pages 2+ usually hit Amazon's login wall (reported as login_required, not faked). Default 1." }, { "key": "verifiedOnly", "type": "boolean", "required": false, "secret": false, "description": "Keep only reviews marked Verified Purchase." }, { "key": "includeSummary", "type": "boolean", "required": false, "secret": false, "description": "Add one row per product with the overall rating, total ratings, and star histogram — so a product is never a silent blank even if reviews are login-gated." }, { "key": "useResidentialProxy", "type": "boolean", "required": false, "secret": false, "description": "Turn on if pages get blocked. Costs more but gets through Amazon's throttling." }, { "key": "maxConcurrency", "type": "integer", "required": false, "secret": false, "description": "Higher is faster but more likely to be throttled." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit on rows (reviews + summaries). Strictly enforced — never charged beyond it." } ] }, { "slug": "screenshot-reliable", "entry": "010", "title": "Screenshot & PDF — Reliable Full-Page Capture", "description": "Capture full-page or viewport screenshots (PNG/JPEG) and PDFs of any URL — retina, wait-for-selector, cookie-banner hiding, and a per-URL success/failure report. No silent broken images.", "categories": [ "DEVELOPER_TOOLS", "AUTOMATION" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/screenshot-reliable/", "apifyUrl": "https://apify.com/alaudinburki/screenshot-reliable", "usage": { "runs": 50, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "url", "type": "string", "nullable": true, "description": "The URL this row describes.", "example": "https://example.com/pricing" }, { "key": "status", "type": "string", "nullable": true, "description": "Outcome recorded for this row.", "example": "ok" }, { "key": "httpStatus", "type": "integer", "nullable": true, "description": "HTTP status code returned by the request.", "example": "200" }, { "key": "key", "type": "string", "nullable": true, "description": "Key this record is stored or deduplicated under.", "example": "" }, { "key": "screenshotUrl", "type": "string", "nullable": true, "description": "Link to a screenshot captured for this record.", "example": "" }, { "key": "format", "type": "string", "nullable": true, "description": "Format of this record.", "example": "" }, { "key": "fullPage", "type": "boolean", "nullable": true, "description": "Full Page as recorded for this row.", "example": "true" }, { "key": "width", "type": "number", "nullable": true, "description": "Width in pixels.", "example": "0" }, { "key": "height", "type": "number", "nullable": true, "description": "Height in pixels.", "example": "0" }, { "key": "deviceScaleFactor", "type": "number", "nullable": true, "description": "Device Scale Factor as recorded for this row.", "example": "0" }, { "key": "bytes", "type": "integer", "nullable": true, "description": "Size in bytes.", "example": "0" }, { "key": "tookMs", "type": "integer", "nullable": true, "description": "Time the operation took, in milliseconds.", "example": "0" }, { "key": "error", "type": "string", "nullable": true, "description": "Why this row failed, when it did. Null on success.", "example": "" } ], "inputs": [ { "key": "urls", "type": "array", "required": true, "secret": false, "description": "Pages to capture, one per line (with or without https://)." }, { "key": "format", "type": "string", "required": false, "secret": false, "description": "png (lossless), jpeg (smaller), or pdf (whole page)." }, { "key": "fullPage", "type": "boolean", "required": false, "secret": false, "description": "Capture the entire scrollable page (on) or just the viewport (off). PDF is always full page." }, { "key": "device", "type": "string", "required": false, "secret": false, "description": "Preset viewport: desktop, laptop, tablet, mobile. Overridden by explicit width/height." }, { "key": "width", "type": "integer", "required": false, "secret": false, "description": "Custom viewport width in px (1–5000). Overrides the device preset." }, { "key": "height", "type": "integer", "required": false, "secret": false, "description": "Custom viewport height in px (1–5000)." }, { "key": "deviceScaleFactor", "type": "integer", "required": false, "secret": false, "description": "2 or 3 gives crisp HiDPI/retina images at the cost of larger files." }, { "key": "quality", "type": "integer", "required": false, "secret": false, "description": "1–100, only for jpeg." }, { "key": "waitForSelector", "type": "string", "required": false, "secret": false, "description": "Wait until this CSS selector appears before capturing (e.g. '#main'). Failing to find it is reported as a failed capture, not a blank image." }, { "key": "waitMs", "type": "integer", "required": false, "secret": false, "description": "Additional wait before capture, for animations or late content (max 30000)." }, { "key": "hideCookieBanners", "type": "boolean", "required": false, "secret": false, "description": "Hide common cookie/consent overlays before capturing." }, { "key": "useProxy", "type": "boolean", "required": false, "secret": false, "description": "Route through a proxy for sites that block datacenter IPs." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit on captures. Strictly enforced — never charged beyond it." } ] }, { "slug": "broken-link-checker", "entry": "011", "title": "Broken Link Checker — Honest Link Health", "description": "Crawl your pages and check every link's HTTP status. Reports broken links (404/410/5xx/DNS) separately from blocked (403/429) and redirects, with the source page — so a login-walled link is never falsely flagged as broken.", "categories": [ "SEO_TOOLS", "DEVELOPER_TOOLS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/broken-link-checker/", "apifyUrl": "https://apify.com/alaudinburki/broken-link-checker", "usage": { "runs": 49, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "sourcePage", "type": "string", "nullable": true, "description": "Page this row's link was found on.", "example": "" }, { "key": "url", "type": "string", "nullable": true, "description": "The URL this row describes.", "example": "https://example.com/pricing" }, { "key": "anchorText", "type": "string", "nullable": true, "description": "Anchor Text as recorded for this row.", "example": "View the full comparison" }, { "key": "internal", "type": "boolean", "nullable": true, "description": "Internal identifier, not for display.", "example": "true" }, { "key": "state", "type": "string", "nullable": true, "description": "State, province or region name.", "example": "active" }, { "key": "httpStatus", "type": "integer", "nullable": true, "description": "HTTP status code returned by the request.", "example": "200" }, { "key": "reason", "type": "string", "nullable": true, "description": "Why this row carries its status.", "example": "row retrieved successfully" }, { "key": "finalUrl", "type": "string", "nullable": true, "description": "URL of the final response after any redirects.", "example": "https://example.com/products/widget" } ], "inputs": [ { "key": "startUrls", "type": "array", "required": true, "secret": false, "description": "Pages to check (with or without https://)." }, { "key": "maxPages", "type": "integer", "required": false, "secret": false, "description": "1 = check only the start pages. Higher follows internal links (same host) up to this many pages." }, { "key": "checkExternal", "type": "boolean", "required": false, "secret": false, "description": "Also check links pointing to other domains (on) or only internal links (off)." }, { "key": "onlyBroken", "type": "boolean", "required": false, "secret": false, "description": "Return only broken/error/blocked/redirect links, not healthy ones." }, { "key": "useProxy", "type": "boolean", "required": false, "secret": false, "description": "Route page crawling through a proxy for sites that block datacenter IPs." }, { "key": "maxConcurrency", "type": "integer", "required": false, "secret": false, "description": "Crawl/check speed." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard cap on rows. Strictly enforced." } ] }, { "slug": "ai-brand-visibility-tracker", "entry": "012", "title": "AI Brand Visibility Tracker — ChatGPT, Perplexity, Gemini", "description": "Ask AI assistants the questions your customers ask. Track brand mentions and competitor rank per answer; Perplexity runs include provider citations, while other modes label URLs found in the answer. Bring your own API keys.", "categories": [ "MARKETING", "AI" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/ai-brand-visibility-tracker/", "apifyUrl": "https://apify.com/alaudinburki/ai-brand-visibility-tracker", "usage": { "runs": 48, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "provider", "type": "string", "nullable": true, "description": "The AI provider this row measured.", "example": "openai" }, { "key": "model", "type": "string", "nullable": true, "description": "The model that produced this answer.", "example": "gpt-4.1" }, { "key": "sampleIndex", "type": "integer", "nullable": true, "description": "Which sample run this row came from, when the same prompt is asked more than once.", "example": "0" }, { "key": "answerMode", "type": "string", "nullable": true, "description": "Whether the answer came from the model's own knowledge or from live search.", "example": "" }, { "key": "citationMode", "type": "string", "nullable": true, "description": "How citations were presented in the answer.", "example": "" }, { "key": "brandCited", "type": "boolean", "nullable": true, "description": "Whether the brand was cited in the answer.", "example": "true" }, { "key": "competitorsCited", "type": "string", "nullable": true, "description": "Competitor domains the answer cited.", "example": "" }, { "key": "prompt", "type": "string", "nullable": true, "description": "The prompt this record resulted from.", "example": "" }, { "key": "mentioned", "type": "boolean", "nullable": true, "description": "Whether the brand was mentioned at all.", "example": "true" }, { "key": "rankAmongTracked", "type": "integer", "nullable": true, "description": "Rank within the set this run tracked.", "example": "0" }, { "key": "competitorsMentioned", "type": "string", "nullable": true, "description": "Competitors mentioned in the answer.", "example": "" }, { "key": "citedDomains", "type": "string", "nullable": true, "description": "Domains the answer cited.", "example": "" } ], "inputs": [ { "key": "brandName", "type": "string", "required": true, "secret": false, "description": "The brand or product name to look for in AI answers, e.g. Notion." }, { "key": "brandAliases", "type": "array", "required": false, "secret": false, "description": "Other names the AI might use for the same brand (old names, abbreviations, product lines). Counted as brand mentions." }, { "key": "brandDomain", "type": "string", "required": false, "secret": false, "description": "For citation analysis only, e.g. notion.so. Perplexity rows can then show whether an official brand domain was cited. Leave blank if you only want name mentions." }, { "key": "competitors", "type": "array", "required": false, "secret": false, "description": "Competitor names to track in the same answers. Rank is the order of first mention among your brand and these names." }, { "key": "competitorDomains", "type": "object", "required": false, "secret": false, "description": "Map each tracked competitor name to its official domain, e.g. {\"Evernote\": \"evernote.com\"}. Used only for provider-citation analysis." }, { "key": "topic", "type": "string", "required": false, "secret": false, "description": "What your customers would ask about, e.g. 'note-taking apps'. Generates a 5-question panel (best/recommend/compare/choose/list). Ignored if you supply custom prompts below." }, { "key": "prompts", "type": "array", "required": false, "secret": false, "description": "Your own questions, one per line. If set, these replace the auto-generated panel." }, { "key": "openaiApiKey", "type": "string", "required": false, "secret": true, "description": "Secret — supply your own value." }, { "key": "openaiWebSearch", "type": "boolean", "required": false, "secret": false, "description": "Optional and off by default. Uses OpenAI's Responses API web_search tool, forces a live search for each question, and records provider-returned sources. This can cost more than a normal model answer." }, { "key": "anthropicApiKey", "type": "string", "required": false, "secret": true, "description": "Secret — supply your own value." }, { "key": "perplexityApiKey", "type": "string", "required": false, "secret": true, "description": "Secret — supply your own value." }, { "key": "geminiApiKey", "type": "string", "required": false, "secret": true, "description": "Secret — supply your own value." }, { "key": "models", "type": "object", "required": false, "secret": false, "description": "Optional model per provider, e.g. {\"openai\": \"gpt-4o\", \"anthropic\": \"claude-opus-5\"}. Leave empty for the cost-efficient defaults." }, { "key": "runsPerPrompt", "type": "integer", "required": false, "secret": false, "description": "Repeat each provider-question pair to measure answer variation. Start with 1; use 5 or more before treating the displayed confidence range as a useful directional signal. Each sample uses your provider API and counts toward max answers." }, { "key": "promptSetVersion", "type": "string", "required": false, "secret": false, "description": "Label this exact question panel, for example 2026-Q3. Change it when you intentionally change prompts, competitors, or measurement design; history comparisons will then safely start a new baseline." }, { "key": "historyStoreId", "type": "string", "required": false, "secret": false, "description": "For recurring measurement, enter a reusable named Apify key-value store. The next compatible run then reports visibility and rank deltas. Leave blank for a one-off scan." }, { "key": "historyKey", "type": "string", "required": false, "secret": false, "description": "Use a different key for each brand or market panel that shares the same history store." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit on analyzed answers (providers × questions). Strictly enforced — you will never be charged for more than this." } ] }, { "slug": "prediction-markets-unified", "entry": "013", "title": "Prediction Markets — Polymarket & Kalshi, One Schema", "description": "Live prices, volume and liquidity from Polymarket and Kalshi in one unified, CSV-ready dataset — so you can compare or arbitrage across both venues without writing two parsers. Free public APIs, no keys.", "categories": [ "BUSINESS", "NEWS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/prediction-markets-unified/", "apifyUrl": "https://apify.com/alaudinburki/prediction-markets-unified", "usage": { "runs": 48, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "source", "type": "string", "nullable": true, "description": "Which upstream source produced this row.", "example": "official public API" }, { "key": "question", "type": "string", "nullable": true, "description": "The question this record answers.", "example": "" }, { "key": "category", "type": "string", "nullable": true, "description": "Category this record belongs to, as classified upstream.", "example": "electronics" }, { "key": "yesPrice", "type": "number", "nullable": true, "description": "Implied probability of the outcome, between 0 and 1.", "example": "0" }, { "key": "noPrice", "type": "number", "nullable": true, "description": "Whether the listing has no published price.", "example": "0" }, { "key": "volume", "type": "number", "nullable": true, "description": "Trading volume over the measured period.", "example": "31157278261" }, { "key": "liquidity", "type": "number", "nullable": true, "description": "Liquidity measure as the source defines it.", "example": "0" }, { "key": "status", "type": "string", "nullable": true, "description": "Outcome recorded for this row.", "example": "ok" }, { "key": "url", "type": "string", "nullable": true, "description": "The URL this row describes.", "example": "https://example.com/pricing" } ], "inputs": [ { "key": "sources", "type": "array", "required": false, "secret": false, "description": "Which venues to include: polymarket, kalshi, or both." }, { "key": "query", "type": "string", "required": false, "secret": false, "description": "Keep only markets whose question, category or ticker contains this text (case-insensitive). Leave empty for all." }, { "key": "onlyOpen", "type": "boolean", "required": false, "secret": false, "description": "On: only markets currently trading. Off: also include closed/resolved markets." }, { "key": "minVolume", "type": "integer", "required": false, "secret": false, "description": "Drop markets with total volume below this. Leave empty to keep all." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit on returned markets. Strictly enforced — you will never be charged for more than this." } ] }, { "slug": "docs-to-answers", "entry": "014", "title": "Docs to Answers Pack — Citable AI-Ready Chunks", "description": "Turn a documentation site into a corpus an AI can answer FROM and CITE. Splits on headings rather than character counts, attaches a heading path and deep link to every chunk, drops boilerplate that repeats across pages, and hashes each chunk so you re-embed only what changed.", "categories": [ "AI", "DEVELOPER_TOOLS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/docs-to-answers/", "apifyUrl": "https://apify.com/alaudinburki/docs-to-answers", "usage": { "runs": 47, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "chunkId", "type": "string", "nullable": true, "description": "Stable identifier for this chunk, derived from its content so it survives re-runs.", "example": "" }, { "key": "text", "type": "string", "nullable": true, "description": "Plain text content of this record.", "example": "" }, { "key": "headingPath", "type": "string", "nullable": true, "description": "Full heading path from the page root, joined with ' > '.", "example": "" }, { "key": "heading", "type": "string", "nullable": true, "description": "Heading this record sits under.", "example": "" }, { "key": "sourceUrl", "type": "string", "nullable": true, "description": "The page or endpoint this row was read from.", "example": "https://api.example.com/v1/items" }, { "key": "citationUrl", "type": "string", "nullable": true, "description": "URL the answer cited.", "example": "" }, { "key": "pageTitle", "type": "string", "nullable": true, "description": "Title of the page this record was read from.", "example": "" }, { "key": "position", "type": "integer", "nullable": true, "description": "Position in the source's ordering.", "example": "3" }, { "key": "tokensEstimate", "type": "integer", "nullable": true, "description": "Estimated token count of the text, for sizing against a model context window.", "example": "1180" }, { "key": "charCount", "type": "integer", "nullable": true, "description": "Number of characters in this record's text.", "example": "4821" }, { "key": "contentHash", "type": "string", "nullable": true, "description": "Hash of this record's content.", "example": "a8f3c9e1b2d40456" }, { "key": "duplicateCount", "type": "integer", "nullable": true, "description": "Rows that repeat a value already seen in this run.", "example": "0" }, { "key": "changeType", "type": "string", "nullable": true, "description": "What changed: initial, content, status, or a combination.", "example": "content" }, { "key": "mergedHeadings", "type": "string", "nullable": true, "description": "Headings merged into one line, for compact display.", "example": "" } ], "inputs": [ { "key": "startUrls", "type": "array", "required": false, "secret": false, "description": "Where to start crawling. Point it at a docs homepage or section index." }, { "key": "pathPrefix", "type": "string", "required": false, "secret": false, "description": "Only crawl URLs whose path starts with this, e.g. /docs. The single most effective way to keep a blog or marketing site out of your corpus." }, { "key": "maxPages", "type": "integer", "required": false, "secret": false, "description": "Upper bound on pages fetched." }, { "key": "followLinks", "type": "boolean", "required": false, "secret": false, "description": "Crawl onward from the pages given. Turn off to process only the exact URLs supplied." }, { "key": "sameOriginOnly", "type": "boolean", "required": false, "secret": false, "description": "Only follow links on the same domain as the start URL. Turn off only if your docs span subdomains." }, { "key": "maxChunkChars", "type": "integer", "required": false, "secret": false, "description": "Chunks split on headings first and size second, so this is a ceiling rather than a target. ~1500 chars suits most embedding models." }, { "key": "minChunkChars", "type": "integer", "required": false, "secret": false, "description": "Anything smaller is folded into the previous chunk instead of being emitted as an unanswerable fragment." }, { "key": "overlapChars", "type": "integer", "required": false, "secret": false, "description": "Repeat this many characters from the previous chunk so a sentence spanning a boundary stays retrievable from both sides." }, { "key": "dropRepeatedBoilerplate", "type": "boolean", "required": false, "secret": false, "description": "Remove chunks that repeat across pages — \"Was this page helpful?\", licence footers, the same admonition on 90 pages. These match every query and answer none." }, { "key": "nearDuplicateDetection", "type": "boolean", "required": false, "secret": false, "description": "Catch boilerplate that differs by a word or two, not just exact repeats." }, { "key": "incrementalMode", "type": "boolean", "required": false, "secret": false, "description": "Store a hash per chunk and label each one added / changed / unchanged / removed on the next run. For scheduled refreshes, also provide a Snapshot store ID or name so the baseline survives separate runs." }, { "key": "changedOnly", "type": "boolean", "required": false, "secret": false, "description": "With incremental mode on, return just the added and changed chunks. Turns this into a scheduled corpus-refresh job." }, { "key": "snapshotKey", "type": "string", "required": false, "secret": false, "description": "Key-value store key holding the previous run's hashes. Use different keys to track several corpora independently." }, { "key": "snapshotStoreId", "type": "string", "required": false, "secret": false, "description": "Which named key-value store holds the previous run's hashes. Leave blank to use the shared default store \"docs-to-answers-state\", which is what makes change tracking work between scheduled runs. Set it explicitly to track several corpora independently." }, { "key": "concurrency", "type": "integer", "required": false, "secret": false, "description": "How many pages to fetch at once. Lower it if the docs site is rate-limiting you." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard cap on results. You are never charged beyond this." }, { "key": "proxyConfiguration", "type": "object", "required": false, "secret": false, "description": "Optional. Most documentation sites need no proxy." }, { "key": "targetChunkChars", "type": "integer", "required": false, "secret": false, "description": "Consecutive short sections on the same page are merged until they reach roughly this size. A 30-token chunk cannot answer a question — it only adds noise to retrieval. Set to 0 to keep every heading as its own chunk." } ] }, { "slug": "pdf-text-extractor", "entry": "015", "title": "PDF Text Extractor — Text & Metadata from URLs", "description": "Download PDF files by URL and extract their text and metadata (page count, title, author) — whole-document or per-page. Honest per-URL status. No auth.", "categories": [ "DEVELOPER_TOOLS", "AUTOMATION" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/pdf-text-extractor/", "apifyUrl": "https://apify.com/alaudinburki/pdf-text-extractor", "usage": { "runs": 47, "users": 1, "lastRun": "2026-10-15" }, "outputSchema": [ { "key": "url", "type": "string", "nullable": true, "description": "The URL this row describes.", "example": "https://example.com/pricing" }, { "key": "status", "type": "string", "nullable": true, "description": "Outcome recorded for this row.", "example": "ok" }, { "key": "pages", "type": "integer", "nullable": true, "description": "Total pages seen or fetched.", "example": "0" }, { "key": "totalPages", "type": "integer", "nullable": true, "description": "Total pages available or fetched.", "example": "0" }, { "key": "page", "type": "integer", "nullable": true, "description": "Page number this record came from. 1-based.", "example": "1" }, { "key": "title", "type": "string", "nullable": true, "description": "Title as the source writes it.", "example": "Wireless Bluetooth Headphones" }, { "key": "author", "type": "string", "nullable": true, "description": "Author of this record, as the source publishes it.", "example": "jane.cooper" }, { "key": "charCount", "type": "integer", "nullable": true, "description": "Number of characters in this record's text.", "example": "4821" }, { "key": "text", "type": "string", "nullable": true, "description": "Plain text content of this record.", "example": "" }, { "key": "error", "type": "string", "nullable": true, "description": "Why this row failed, when it did. Null on success.", "example": "" } ], "inputs": [ { "key": "pdfUrls", "type": "array", "required": true, "secret": false, "description": "Direct links to PDF files." }, { "key": "perPage", "type": "boolean", "required": false, "secret": false, "description": "Off: one row per PDF (full text). On: one row per page." }, { "key": "useProxy", "type": "boolean", "required": false, "secret": false, "description": "For hosts that block datacenter IPs." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard cap." } ] }, { "slug": "sec-edgar-filings", "entry": "016", "title": "SEC EDGAR Filings — 8-K, 10-K & Insider Forms", "description": "Pull SEC filings for any US-listed company and get the meaning, not just the form code: 8-K items decoded into plain language, material events flagged (bankruptcy, exec change, acquisition, restatement), newest first. Free official SEC data, no key.", "categories": [ "BUSINESS", "DEVELOPER_TOOLS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/sec-edgar-filings/", "apifyUrl": "https://apify.com/alaudinburki/sec-edgar-filings", "usage": { "runs": 46, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "company", "type": "string", "nullable": true, "description": "Company name as the source writes it.", "example": "Northwind Traders" }, { "key": "ticker", "type": "string", "nullable": true, "description": "Stock ticker symbol as the source writes it.", "example": "" }, { "key": "cik", "type": "string", "nullable": true, "description": "Central Index Key, the SEC's identifier for a filer.", "example": "" }, { "key": "formType", "type": "string", "nullable": true, "description": "Form type as the source labels it.", "example": "" }, { "key": "signal", "type": "string", "nullable": true, "description": "The signal this row represents.", "example": "new posting" }, { "key": "materialEvent", "type": "boolean", "nullable": true, "description": "Whether the change is material to the entity.", "example": "true" }, { "key": "filingDate", "type": "string", "nullable": true, "description": "Date the filing was received or processed, when published.", "example": "2026-09-03T00:00:00" }, { "key": "reportDate", "type": "string", "nullable": true, "description": "Date the report was issued.", "example": "2026-10-15" }, { "key": "items", "type": "string", "nullable": true, "description": "The items this record carries.", "example": "[{\"id\":\"1\",\"name\":\"Widget\"}]" }, { "key": "ageDays", "type": "integer", "nullable": true, "description": "Age of this item in days.", "example": "0" }, { "key": "accessionNumber", "type": "string", "nullable": true, "description": "SEC accession number identifying one filing.", "example": "" }, { "key": "filingUrl", "type": "string", "nullable": true, "description": "Link to the filing at its source.", "example": "" }, { "key": "documentDescription", "type": "string", "nullable": true, "description": "Description of the document, as published by the source.", "example": "" }, { "key": "isXBRL", "type": "boolean", "nullable": true, "description": "Whether the filing carries machine-readable XBRL data.", "example": "true" } ], "inputs": [ { "key": "tickers", "type": "array", "required": false, "secret": false, "description": "Stock tickers, e.g. AAPL, TSLA. Resolved to SEC CIKs automatically." }, { "key": "ciks", "type": "array", "required": false, "secret": false, "description": "SEC CIK numbers, if you already have them. Zero-padding is handled for you." }, { "key": "contactEmail", "type": "string", "required": true, "secret": false, "description": "The SEC's fair-access policy requires a contact address in the request header. It is sent only to the SEC, never stored or shared." }, { "key": "formTypes", "type": "array", "required": false, "secret": false, "description": "Filter by form, e.g. 8-K, 10-K, 10-Q, 4, S-1, SC 13D. Leave empty for all forms. Prefix match, so \"10-\" catches 10-K and 10-Q." }, { "key": "sinceDate", "type": "string", "required": false, "secret": false, "description": "YYYY-MM-DD. Leave empty for the company's full recent history." }, { "key": "materialEventsOnly", "type": "boolean", "required": false, "secret": false, "description": "Return only filings flagged as material — bankruptcy, restatement, executive change, acquisition, earnings, activist stake, delisting risk and similar." }, { "key": "maxPerCompany", "type": "integer", "required": false, "secret": false, "description": "Caps how far back to read per company." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit, strictly enforced. You are never charged beyond this." } ] }, { "slug": "wayback-machine-snapshots", "entry": "017", "title": "Wayback Machine Scraper — Website History & Snapshots", "description": "Extract every Wayback Machine (archive.org) snapshot of any URL, domain or subdomain — capture date, HTTP status, MIME type, content digest, byte size and direct snapshot links. Up to 50,000 rows, many URLs per run, $0.50 per 1,000 rows. No API key.", "categories": [ "DEVELOPER_TOOLS", "SEO_TOOLS", "AI" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/wayback-machine-snapshots/", "apifyUrl": "https://apify.com/alaudinburki/wayback-machine-snapshots", "usage": { "runs": 46, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "inputUrl", "type": "string", "nullable": true, "description": "The input URL this row was produced for. Present on multi-URL runs so rows stay attributable.", "example": "example.com/pricing" }, { "key": "timestamp", "type": "string", "nullable": true, "description": "The source's own timestamp for this record, unmodified.", "example": "20231015143022" }, { "key": "capturedAt", "type": "string", "nullable": true, "description": "ISO 8601 timestamp of when this record was captured or archived.", "example": "2026-10-16T08:17:07.000Z" }, { "key": "original", "type": "string", "nullable": true, "description": "The URL exactly as it was captured or found.", "example": "https://example.com/pricing" }, { "key": "snapshotUrl", "type": "string", "nullable": true, "description": "Direct link to view this record at its source.", "example": "https://web.archive.org/web/20231015143022/https://apify.com/" }, { "key": "mimeType", "type": "string", "nullable": true, "description": "MIME type of the content.", "example": "text/html" }, { "key": "statusCode", "type": "integer", "nullable": true, "description": "HTTP status code recorded for this record.", "example": "200" }, { "key": "digest", "type": "string", "nullable": true, "description": "Content hash. Two rows with the same digest hold identical content.", "example": "UXM5L6MWWKE4YESNBTX2OENTT62FEW4Y" }, { "key": "length", "type": "integer", "nullable": true, "description": "Size of the content in bytes.", "example": "48523" } ], "inputs": [ { "key": "urls", "type": "array", "required": true, "secret": false, "description": "URLs (or domains) to list snapshots for." }, { "key": "matchType", "type": "string", "required": false, "secret": false, "description": "exact, prefix, host, or domain (domain = all subpages/subdomains)." }, { "key": "from", "type": "string", "required": false, "secret": false, "description": "YYYY-MM-DD (optional)." }, { "key": "to", "type": "string", "required": false, "secret": false, "description": "YYYY-MM-DD (optional)." }, { "key": "collapseDuplicates", "type": "boolean", "required": false, "secret": false, "description": "Skip snapshots identical to the previous (by content digest)." }, { "key": "maxSnapshotsPerUrl", "type": "integer", "required": false, "secret": false, "description": "Cap per URL." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard cap overall." } ] }, { "slug": "ai-crawler-audit", "entry": "018", "title": "AI Crawler Audit — Are You Blocking ChatGPT?", "description": "Check whether your site is visible to AI search or accidentally blocking it. Audits robots.txt for GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot, Google-Extended and 7 more, detects llms.txt, and returns an AI-readiness score with the exact fixes. No key, no login.", "categories": [ "SEO_TOOLS", "DEVELOPER_TOOLS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/ai-crawler-audit/", "apifyUrl": "https://apify.com/alaudinburki/ai-crawler-audit", "usage": { "runs": 45, "users": 2, "lastRun": "2026-10-15" }, "outputSchema": [ { "key": "domain", "type": "string", "nullable": true, "description": "Domain name, without the scheme.", "example": "example.com" }, { "key": "aiReadinessScore", "type": "integer", "nullable": true, "description": "How ready this site is for AI crawlers, from 0 to 100.", "example": "0" }, { "key": "aiSearchReadiness", "type": "string", "nullable": true, "description": "Readiness for AI search in words.", "example": "" }, { "key": "blocksAiSearch", "type": "boolean", "nullable": true, "description": "Whether the site blocks AI search crawlers.", "example": "true" }, { "key": "blockedSearchBots", "type": "string", "nullable": true, "description": "Search crawlers the site blocks.", "example": "" }, { "key": "blockedBots", "type": "string", "nullable": true, "description": "User agents the site blocks.", "example": "" }, { "key": "hasLlmsTxt", "type": "boolean", "nullable": true, "description": "Whether the site publishes an llms.txt file.", "example": "true" }, { "key": "llmsTitle", "type": "string", "nullable": true, "description": "Title the site publishes in its llms.txt.", "example": "" }, { "key": "allowedBotCount", "type": "integer", "nullable": true, "description": "How many of the checked bots are allowed.", "example": "0" }, { "key": "totalBotsChecked", "type": "integer", "nullable": true, "description": "How many bots were checked.", "example": "0" }, { "key": "sitemapCount", "type": "integer", "nullable": true, "description": "How many sitemaps were found.", "example": "0" }, { "key": "robotsStatus", "type": "integer", "nullable": true, "description": "Outcome of reading robots.txt.", "example": "0" }, { "key": "recommendations", "type": "string", "nullable": true, "description": "The recommended actions for this row.", "example": "[\"Declare a canonical URL\",\"Publish a sitemap\"]" }, { "key": "status", "type": "string", "nullable": true, "description": "Outcome recorded for this row.", "example": "ok" } ], "inputs": [ { "key": "domains", "type": "array", "required": true, "secret": false, "description": "Domains or URLs to audit. Scheme, www and path are stripped automatically." }, { "key": "onlyBlockedSites", "type": "boolean", "required": false, "secret": false, "description": "Filter the output down to the sites with a real problem — useful when auditing a long client list." }, { "key": "includeBotDetail", "type": "boolean", "required": false, "secret": false, "description": "Adds a botDetail array with the verdict and matched robots.txt rule for every AI crawler checked." }, { "key": "useProxy", "type": "boolean", "required": false, "secret": false, "description": "Route requests through Apify Proxy. Rarely needed — robots.txt is public." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit, strictly enforced. You are never charged beyond this." } ] }, { "slug": "google-news-scraper", "entry": "019", "title": "Google News Scraper — Search, Topics & RSS Feeds", "description": "Fetch Google News articles by keyword search or topic (title, source, link, date, snippet) via the public RSS feed — deduplicated, newest-first, with keyword and age filters. No API key.", "categories": [ "NEWS", "SEO_TOOLS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/google-news-scraper/", "apifyUrl": "https://apify.com/alaudinburki/google-news-scraper", "usage": { "runs": 45, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "query", "type": "string", "nullable": true, "description": "The query that produced this row.", "example": "shopify scraper" }, { "key": "title", "type": "string", "nullable": true, "description": "Title as the source writes it.", "example": "Wireless Bluetooth Headphones" }, { "key": "source", "type": "string", "nullable": true, "description": "Which upstream source produced this row.", "example": "official public API" }, { "key": "link", "type": "string", "nullable": true, "description": "Direct link to this record at its source.", "example": "https://example.com/listing/1" }, { "key": "publishedAt", "type": "string", "nullable": true, "description": "ISO 8601 timestamp of publication.", "example": "2026-10-15T09:00:00.000Z" }, { "key": "snippet", "type": "string", "nullable": true, "description": "Text excerpt around the match. Whitespace is collapsed.", "example": "" }, { "key": "rank", "type": "integer", "nullable": true, "description": "Position in the source's own ordering. 1 is highest.", "example": "1" }, { "key": "guid", "type": "string", "nullable": true, "description": "Guid as recorded for this row.", "example": "" } ], "inputs": [ { "key": "queries", "type": "array", "required": false, "secret": false, "description": "Keywords to search Google News for." }, { "key": "topics", "type": "array", "required": false, "secret": false, "description": "Google News topics: WORLD, NATION, BUSINESS, TECHNOLOGY, ENTERTAINMENT, SPORTS, SCIENCE, HEALTH." }, { "key": "language", "type": "string", "required": false, "secret": false, "description": "Two-letter language code (en, es, de...)." }, { "key": "country", "type": "string", "required": false, "secret": false, "description": "Two-letter country code (US, GB, IN...)." }, { "key": "mustInclude", "type": "array", "required": false, "secret": false, "description": "Keep only articles whose title/snippet contains one of these." }, { "key": "maxAgeHours", "type": "integer", "required": false, "secret": false, "description": "e.g. 24 for the last day." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard cap. Strictly enforced." } ] }, { "slug": "ats-jobs-scraper", "entry": "020", "title": "ATS Jobs Scraper — Greenhouse, Lever, Ashby", "description": "Get open jobs from any company on Greenhouse, Lever, or Ashby in one unified schema — title, location, department, type, url, posted date. Public JSON APIs, no auth. Pairs with the job-change monitor.", "categories": [ "JOBS", "LEAD_GENERATION" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/ats-jobs-scraper/", "apifyUrl": "https://apify.com/alaudinburki/ats-jobs-scraper", "usage": { "runs": 43, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "provider", "type": "string", "nullable": true, "description": "The AI provider this row measured.", "example": "openai" }, { "key": "company", "type": "string", "nullable": true, "description": "Company name as the source writes it.", "example": "Northwind Traders" }, { "key": "title", "type": "string", "nullable": true, "description": "Title as the source writes it.", "example": "Wireless Bluetooth Headphones" }, { "key": "location", "type": "string", "nullable": true, "description": "Location as the source writes it.", "example": "Austin, TX" }, { "key": "department", "type": "string", "nullable": true, "description": "Government department the contract or grant belongs to.", "example": "Transportation" }, { "key": "employmentType", "type": "string", "nullable": true, "description": "Employment type as posted.", "example": "" }, { "key": "url", "type": "string", "nullable": true, "description": "The URL this row describes.", "example": "https://example.com/pricing" }, { "key": "postedAt", "type": "string", "nullable": true, "description": "ISO 8601 timestamp of when this was posted.", "example": "2026-10-14T00:00:00.000Z" } ], "inputs": [ { "key": "boards", "type": "array", "required": false, "secret": false, "description": "provider:company entries, e.g. greenhouse:stripe, lever:netflix, ashby:ramp." }, { "key": "companies", "type": "array", "required": false, "secret": false, "description": "Company slugs to try across all three providers." }, { "key": "titleIncludes", "type": "array", "required": false, "secret": false, "description": "Keep only roles whose title contains one of these." }, { "key": "titleExcludes", "type": "array", "required": false, "secret": false, "description": "Drop roles whose title contains any of these." }, { "key": "locationIncludes", "type": "array", "required": false, "secret": false, "description": "Keep only roles whose location contains one of these (e.g. remote)." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard cap. Strictly enforced." } ] }, { "slug": "itunes-app-store-search", "entry": "021", "title": "iTunes & App Store Search — Apps, Podcasts, Media", "description": "Search Apple's App Store and iTunes for apps, podcasts, music, books, and movies, or look items up by ID — normalized into one schema with ratings, price, genre, artwork and URLs. Public API, no auth.", "categories": [ "ECOMMERCE", "DEVELOPER_TOOLS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/itunes-app-store-search/", "apifyUrl": "https://apify.com/alaudinburki/itunes-app-store-search", "usage": { "runs": 43, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "query", "type": "string", "nullable": true, "description": "The query that produced this row.", "example": "shopify scraper" }, { "key": "name", "type": "string", "nullable": true, "description": "Display name as the source writes it.", "example": "Bitcoin" }, { "key": "artist", "type": "string", "nullable": true, "description": "Artist the track or release is credited to.", "example": "" }, { "key": "type", "type": "string", "nullable": true, "description": "Type of this record, as classified by the Actor.", "example": "article" }, { "key": "genre", "type": "string", "nullable": true, "description": "Genre classification.", "example": "Documentary" }, { "key": "price", "type": "string", "nullable": true, "description": "Price as reported by the source. Currency is given by the currency field.", "example": "9.99" }, { "key": "averageRating", "type": "number", "nullable": true, "description": "Mean rating across the reviews counted.", "example": "0" }, { "key": "ratingCount", "type": "integer", "nullable": true, "description": "How many ratings the source counts.", "example": "0" }, { "key": "url", "type": "string", "nullable": true, "description": "The URL this row describes.", "example": "https://example.com/pricing" }, { "key": "ratingTier", "type": "string", "nullable": true, "description": "Band the rating falls into.", "example": "" }, { "key": "popularity", "type": "string", "nullable": true, "description": "Popularity measure as the source publishes it.", "example": "74" } ], "inputs": [ { "key": "terms", "type": "array", "required": false, "secret": false, "description": "Keywords to search for." }, { "key": "entity", "type": "string", "required": false, "secret": false, "description": "What to search for." }, { "key": "lookupIds", "type": "array", "required": false, "secret": false, "description": "Specific iTunes/App IDs to fetch metadata for." }, { "key": "country", "type": "string", "required": false, "secret": false, "description": "Two-letter code (us, gb, de...)." }, { "key": "limitPerTerm", "type": "integer", "required": false, "secret": false, "description": "Up to 200 per search term." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard cap. Strictly enforced." } ] }, { "slug": "small-business-website-audit", "entry": "022", "title": "Website Audit — In Plain English, Not Scores", "description": "Audit any list of websites and get findings a business owner actually understands: what is wrong, what it costs them, and the exact fix. Every row ships a paste-ready summary for a client email. No browser, no API key, no anti-bot.", "categories": [ "SEO_TOOLS", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/small-business-website-audit/", "apifyUrl": "https://apify.com/alaudinburki/small-business-website-audit", "usage": { "runs": 43, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "domain", "type": "string", "nullable": true, "description": "Domain name, without the scheme.", "example": "example.com" }, { "key": "url", "type": "string", "nullable": true, "description": "The URL this row describes.", "example": "https://example.com/pricing" }, { "key": "auditStatus", "type": "string", "nullable": true, "description": "Outcome of the dependency audit.", "example": "" }, { "key": "auditNote", "type": "string", "nullable": true, "description": "Note recorded during the audit.", "example": "" }, { "key": "score", "type": "integer", "nullable": true, "description": "Score on the Actor's own scale. The scale is stated in the field's own band.", "example": "82" }, { "key": "grade", "type": "object", "nullable": false, "description": "Letter or numeric grade awarded.", "example": "{\"letter\":\"B\",\"score\":78}" }, { "key": "verdict", "type": "string", "nullable": true, "description": "The Actor's conclusion for this row, stated in words.", "example": "pass" }, { "key": "reachable", "type": "boolean", "nullable": true, "description": "Whether the host responded at all.", "example": "true" }, { "key": "criticalCount", "type": "integer", "nullable": true, "description": "How many critical findings were recorded.", "example": "0" }, { "key": "importantCount", "type": "integer", "nullable": true, "description": "How many important findings were recorded.", "example": "0" }, { "key": "minorCount", "type": "integer", "nullable": true, "description": "How many minor findings were recorded.", "example": "0" }, { "key": "topIssue", "type": "string", "nullable": true, "description": "The highest-priority issue found.", "example": "" }, { "key": "topIssueFound", "type": "string", "nullable": true, "description": "The highest-priority issue found.", "example": "" }, { "key": "emailSummary", "type": "string", "nullable": true, "description": "One-line summary of the verification result.", "example": "" }, { "key": "findings", "type": "array", "nullable": true, "description": "The findings recorded for this row.", "example": "[{\"check\":\"title-length\",\"level\":\"warning\",\"detail\":\"Title is 71 characters; 60 or fewer reads better in results.\"}]" }, { "key": "passed", "type": "array", "nullable": true, "description": "The checks that passed.", "example": "[\"https\",\"robots-txt\",\"canonical\"]" }, { "key": "platform", "type": "string", "nullable": true, "description": "Platform this record came from.", "example": "" }, { "key": "responseMs", "type": "integer", "nullable": true, "description": "Response time in milliseconds.", "example": "412" }, { "key": "pageBytes", "type": "integer", "nullable": true, "description": "Size of the fetched page in bytes.", "example": "0" }, { "key": "auditedAt", "type": "string", "nullable": true, "description": "ISO 8601 timestamp of the most recent audit.", "example": "" } ], "inputs": [ { "key": "domains", "type": "array", "required": true, "secret": false, "description": "Domains or full URLs to audit. Paste a client list, or the website column from a Google Maps export." }, { "key": "startUrls", "type": "array", "required": false, "secret": false, "description": "Same thing in Apify's URL-list format, so this actor chains directly onto another actor's output." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit, strictly enforced — you will never be charged for more than this." }, { "key": "minSeverity", "type": "string", "required": false, "secret": false, "description": "Trim the findings list. The score and counts always reflect every check." }, { "key": "concurrency", "type": "integer", "required": false, "secret": false, "description": "Kept low on purpose. Hitting sites hard makes bot protection return 403, which looks like a broken website but is not one." } ] }, { "slug": "bank-health-lookup", "entry": "023", "title": "Bank Financial Health Lookup — FDIC BankFind", "description": "Bank financial snapshot per charter — total assets, domestic deposits, active status, charter class — from FDIC's free official BankFind data. Asset/deposit figures converted from FDIC's thousands-of-dollars convention to real dollar amounts.", "categories": [ "DEVELOPER_TOOLS", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/bank-health-lookup/", "apifyUrl": "https://apify.com/alaudinburki/bank-health-lookup", "usage": { "runs": 42, "users": 1, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "matchedQuery", "type": "string", "nullable": true, "description": "The query this row matched.", "example": "amazon product scraper" }, { "key": "name", "type": "string", "nullable": true, "description": "Display name as the source writes it.", "example": "Bitcoin" }, { "key": "cert", "type": "integer", "nullable": true, "description": "Certificate details for this host.", "example": "0" }, { "key": "isActive", "type": "boolean", "nullable": true, "description": "Whether the record is still active at the source.", "example": "true" }, { "key": "totalAssets", "type": "number", "nullable": true, "description": "Total assets in the stated currency.", "example": "0" }, { "key": "totalDomesticDeposits", "type": "number", "nullable": true, "description": "Total Domestic Deposits as recorded for this row.", "example": "0" }, { "key": "city", "type": "string", "nullable": true, "description": "City name.", "example": "Austin" }, { "key": "state", "type": "string", "nullable": true, "description": "State, province or region name.", "example": "active" }, { "key": "established", "type": "string", "nullable": true, "description": "Date the entity was established.", "example": "" }, { "key": "charterClass", "type": "string", "nullable": true, "description": "Charter class, for a financial institution.", "example": "" }, { "key": "charterClassLabel", "type": "string", "nullable": true, "description": "Human-readable label for the charter class.", "example": "" }, { "key": "status", "type": "string", "nullable": true, "description": "Outcome recorded for this row.", "example": "ok" }, { "key": "verdict", "type": "string", "nullable": true, "description": "The Actor's conclusion for this row, stated in words.", "example": "pass" } ], "inputs": [ { "key": "banks", "type": "array", "required": true, "secret": false, "description": "Bank names to look up, e.g. Wells Fargo, JPMorgan Chase. One bank per line." }, { "key": "maxResultsPerBank", "type": "integer", "required": false, "secret": false, "description": "How many matching charters to return per bank name." } ] }, { "slug": "google-trends-rss-reliable", "entry": "024", "title": "Google Trends Daily Searches — The Endpoint That Doesn't 429", "description": "Today's trending searches for 60+ countries, with the news stories driving each one. Uses Google's RSS feed, which does not rate-limit — so runs don't fail the way explore-API scrapers do.", "categories": [ "SEO_TOOLS", "NEWS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/google-trends-rss-reliable/", "apifyUrl": "https://apify.com/alaudinburki/google-trends-rss-reliable", "usage": { "runs": 42, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "geo", "type": "string", "nullable": true, "description": "Geographic coordinates in 'lat,lon' form.", "example": "" }, { "key": "term", "type": "string", "nullable": true, "description": "Term this row relates to.", "example": "" }, { "key": "approxTraffic", "type": "integer", "nullable": true, "description": "Approx Traffic as recorded for this row.", "example": "0" }, { "key": "pubDate", "type": "string", "nullable": true, "description": "Pub Date as recorded for this row.", "example": "" }, { "key": "newsTitle", "type": "string", "nullable": true, "description": "News Title as recorded for this row.", "example": "" }, { "key": "newsSource", "type": "string", "nullable": true, "description": "News Source as recorded for this row.", "example": "" }, { "key": "trendUrl", "type": "string", "nullable": true, "description": "Trend Url as recorded for this row.", "example": "" } ], "inputs": [ { "key": "geos", "type": "array", "required": false, "secret": false, "description": "Two-letter country codes to fetch trending searches for (e.g. US, GB, IN, DE, BR, JP). Google publishes feeds for 50+ countries; an unknown code fails immediately with the full supported list." }, { "key": "expandNews", "type": "boolean", "required": false, "secret": false, "description": "Off: one row per trend, with the top news story attached and a newsCount. On: one row per news story, trend fields repeated — better for CSV pivoting on articles." }, { "key": "termIncludes", "type": "array", "required": false, "secret": false, "description": "Keep only trends whose search term contains at least one of these words (case-insensitive). Leave empty for all trends." }, { "key": "termExcludes", "type": "array", "required": false, "secret": false, "description": "Drop trends whose search term contains any of these words (case-insensitive). Leave empty to drop nothing." }, { "key": "minTraffic", "type": "integer", "required": false, "secret": false, "description": "Drop trends with published traffic below this number (e.g. 50000 keeps only 50K+ trends). Trends where Google publishes no figure are always kept, so real trends are never silently hidden." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard limit on results returned. This is strictly enforced — you will never be charged for more than this." }, { "key": "maxAgeHours", "type": "integer", "required": false, "secret": false, "description": "Leave empty for the full feed. Set to 24 to keep only trends that surfaced in the last day. Trends without a published date are kept." } ] }, { "slug": "site-health-suite", "entry": "025", "title": "Site Health Suite — One Graded Audit, Six Checks", "description": "One letter-graded audit combining SSL, security headers, uptime, broken links, structured data and subdomain takeover risk — with a prioritized, plain-English fix list instead of six separate scanner reports. Built for agencies who need a deliverable, not a data dump.", "categories": [ "DEVELOPER_TOOLS", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/site-health-suite/", "apifyUrl": "https://apify.com/alaudinburki/site-health-suite", "usage": { "runs": 42, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "site", "type": "string", "nullable": true, "description": "Site as recorded for this row.", "example": "example.com" }, { "key": "grade", "type": "string", "nullable": true, "description": "Letter or numeric grade awarded.", "example": "B" }, { "key": "score", "type": "integer", "nullable": true, "description": "Score on the Actor's own scale. The scale is stated in the field's own band.", "example": "82" }, { "key": "sslScore", "type": "integer", "nullable": true, "description": "TLS configuration score, from 0 to 100.", "example": "0" }, { "key": "headersScore", "type": "integer", "nullable": true, "description": "Security headers score, from 0 to 100.", "example": "0" }, { "key": "uptimeScore", "type": "integer", "nullable": true, "description": "Uptime on a 0-100 scale. Higher is more available.", "example": "0" }, { "key": "brokenLinksScore", "type": "integer", "nullable": true, "description": "Link health score, from 0 to 100. Higher is healthier.", "example": "0" }, { "key": "structuredDataScore", "type": "integer", "nullable": true, "description": "Structured-data quality score, from 0 to 100.", "example": "0" }, { "key": "subdomainScore", "type": "integer", "nullable": true, "description": "Subdomain hygiene score, from 0 to 100.", "example": "0" }, { "key": "sslDaysToExpiry", "type": "integer", "nullable": true, "description": "Days until the TLS certificate expires.", "example": "0" }, { "key": "sslIssuer", "type": "string", "nullable": true, "description": "Issuer of the TLS certificate.", "example": "" }, { "key": "hasHsts", "type": "boolean", "nullable": true, "description": "Whether the response sets a Strict-Transport-Security header.", "example": "true" }, { "key": "hasCsp", "type": "boolean", "nullable": true, "description": "Whether the response sets a Content-Security-Policy header.", "example": "true" }, { "key": "up", "type": "boolean", "nullable": true, "description": "Whether the service responded successfully.", "example": "true" }, { "key": "statusCode", "type": "integer", "nullable": true, "description": "HTTP status code recorded for this record.", "example": "200" }, { "key": "responseMs", "type": "integer", "nullable": true, "description": "Response time in milliseconds.", "example": "412" }, { "key": "linksChecked", "type": "integer", "nullable": true, "description": "How many links were checked.", "example": "214" }, { "key": "brokenLinksCount", "type": "integer", "nullable": true, "description": "How many links failed.", "example": "0" }, { "key": "structuredDataTypes", "type": "string", "nullable": true, "description": "Schema.org types the page declares.", "example": "" }, { "key": "subdomainsChecked", "type": "integer", "nullable": true, "description": "How many subdomains were checked.", "example": "18" }, { "key": "subdomainsSuspicious", "type": "integer", "nullable": true, "description": "Subdomains that look takeover-prone.", "example": "0" }, { "key": "topFixes", "type": "string", "nullable": true, "description": "The highest-priority fixes to apply.", "example": "" }, { "key": "fixCount", "type": "integer", "nullable": true, "description": "How many fixes were applied or are available.", "example": "0" }, { "key": "checkedAt", "type": "string", "nullable": true, "description": "ISO 8601 timestamp of the most recent check.", "example": "2026-10-16T09:12:44.000Z" }, { "key": "status", "type": "string", "nullable": true, "description": "Outcome recorded for this row.", "example": "ok" } ], "inputs": [ { "key": "sites", "type": "array", "required": false, "secret": false, "description": "Domains or URLs to audit. Each gets all six checks: SSL, security headers, uptime, broken links, structured data, and subdomain takeover risk." }, { "key": "maxLinksToCheck", "type": "integer", "required": false, "secret": false, "description": "How many links from the homepage to check for broken-link scoring." }, { "key": "checkSubdomains", "type": "boolean", "required": false, "secret": false, "description": "Enumerate subdomains from certificate transparency and check for dangling DNS. Adds time but is weighted heaviest in the grade — it is the one active exploitable risk on this list." }, { "key": "maxSubdomainsToCheck", "type": "integer", "required": false, "secret": false, "description": "Cap on subdomains checked for takeover risk per site." }, { "key": "maxItems", "type": "integer", "required": false, "secret": false, "description": "Hard cap on sites returned. You are never charged beyond this." } ] }, { "slug": "country-economic-snapshot", "entry": "026", "title": "Country Economic Snapshot — World Bank, One Flat Row", "description": "GDP, population, inflation, unemployment and more for any country as one flat row — the latest available observation per indicator, each with its own year. Free, keyless World Bank data. Any World Bank indicator code also works.", "categories": [ "DEVELOPER_TOOLS", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/country-economic-snapshot/", "apifyUrl": "https://apify.com/alaudinburki/country-economic-snapshot", "usage": { "runs": 41, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "countryCode", "type": "string", "nullable": true, "description": "Two-letter ISO 3166-1 country code.", "example": "US" }, { "key": "countryName", "type": "string", "nullable": true, "description": "Country name in English.", "example": "" }, { "key": "gdpUsdValue", "type": "number", "nullable": true, "description": "Gross domestic product in current US dollars.", "example": "0" }, { "key": "gdpUsdYear", "type": "string", "nullable": true, "description": "Year the GDP figure refers to.", "example": "" }, { "key": "gdpPerCapitaUsdValue", "type": "number", "nullable": true, "description": "Gross domestic product per person in current US dollars.", "example": "0" }, { "key": "gdpPerCapitaUsdYear", "type": "string", "nullable": true, "description": "Year the GDP per capita figure refers to.", "example": "" }, { "key": "populationValue", "type": "number", "nullable": true, "description": "Population of this area.", "example": "0" }, { "key": "populationYear", "type": "string", "nullable": true, "description": "Year the population figure refers to.", "example": "" }, { "key": "inflationPercentValue", "type": "number", "nullable": true, "description": "Annual inflation rate as a percentage.", "example": "0" }, { "key": "inflationPercentYear", "type": "string", "nullable": true, "description": "Year the inflation figure refers to.", "example": "" }, { "key": "unemploymentPercentValue", "type": "number", "nullable": true, "description": "Unemployment rate as a percentage.", "example": "0" }, { "key": "unemploymentPercentYear", "type": "string", "nullable": true, "description": "Year the unemployment figure refers to.", "example": "" }, { "key": "internetUsersPercentValue", "type": "number", "nullable": true, "description": "Share of the population with internet access, as a percentage.", "example": "0" }, { "key": "internetUsersPercentYear", "type": "string", "nullable": true, "description": "Year the internet users figure refers to.", "example": "" }, { "key": "indicatorsRequested", "type": "integer", "nullable": true, "description": "Indicators Requested as recorded for this row.", "example": "0" }, { "key": "indicatorsWithData", "type": "integer", "nullable": true, "description": "Indicators With Data as recorded for this row.", "example": "0" } ], "inputs": [ { "key": "countries", "type": "array", "required": true, "secret": false, "description": "ISO country codes, e.g. US, PK, DE. Two-letter or three-letter codes both work." }, { "key": "indicators", "type": "array", "required": false, "secret": false, "description": "Which indicators to fetch. Use the built-in keys (gdpUsd, gdpPerCapitaUsd, population, inflationPercent, unemploymentPercent, internetUsersPercent) or any raw World Bank indicator code (e.g. EN.ATM.CO2E.PC). Leave empty for all built-ins." } ] }, { "slug": "earthquake-monitor", "entry": "027", "title": "Earthquake Business Impact Monitor — USGS, By Location", "description": "Recent earthquakes near your specific business locations (lat/lon), not a global feed. USGS's own magnitude, PAGER alert level, and tsunami flag passed through directly. Free, keyless, real-time.", "categories": [ "DEVELOPER_TOOLS", "BUSINESS" ], "url": "https://alaudinburki-scrapers.pages.dev/scrapers/earthquake-monitor/", "apifyUrl": "https://apify.com/alaudinburki/earthquake-monitor", "usage": { "runs": 41, "users": 2, "lastRun": "2026-10-16" }, "outputSchema": [ { "key": "locationLabel", "type": "string", "nullable": true, "description": "Short human-readable label for this location.", "example": "Austin, Texas" }, { "key": "lat", "type": "number", "nullable": true, "description": "Latitude in decimal degrees. Negative is south.", "example": "30.2672" }, { "key": "lon", "type": "number", "nullable": true, "description": "Longitude in decimal degrees. Negative is west.", "example": "-97.7431" }, { "key": "id", "type": "string", "nullable": true, "description": "Stable identifier from the source. Use it to link records across runs.", "example": "7524427347697896726" }, { "key": "magnitude", "type": "number", "nullable": true, "description": "How large the change is, classified as minor, moderate or major.", "example": "major" }, { "key": "place", "type": "string", "nullable": true, "description": "Place name as the source writes it.", "example": "" }, { "key": "time", "type": "string", "nullable": true, "description": "Time this row refers to.", "example": "