Get web data delivered in 10 days

1{
2  "name": "StoneShoesbasket",
3  "productName": "Stoneshoes",
4  "price": 149,
5  "currency": "USD",
6  "currencyRaw": "$",
7  "regularPrice": 199.00,
8  "availability": "InStock",
9  "sku": "A123DK9823",
10  "mpn": "code-123",
11  "gtin": [],
12  "brand": {},
13  "breadcrumbs": [],
14  "mainImage": {},
15  "images": [],
16  "description": "product description",
17  "descriptionHtml": "<article>HTML description for Product ...</article>",
18  "color": "Red",
19  "size": "XL",
20  "weight": {},
21  "material": ["Metal", "Plastic"]
22}

1{
2  "realEstateListing": {
3    "id": "hl-ATX-1427-woodland",
4    "url": "https://hearthlane.example/listings/woodland-ave-1427",
5    "status": "ForSale",
6    "price": {
7      "amount": 849000,
8      "currency": "USD",
9      "display": "$849,000"
10    },
11    "address": {
12      "street": "1427 Woodtree Ave",
13      "city": "Austin",
14      "region": "TX",
15      "postalCode": "78704",
16      "country": "US"
17    },
18    "property": {
19      "type": "SingleFamily",
20      "bedrooms": 4,
21      "bathrooms": 3,
22      "livingAreaSqft": 2418,
23      "lotSizeAcres": 0.19,
24      "yearBuilt": 1998,
25      "parking": {
26        "type": "Garage",
27        "spaces": 2
28      }
29    },
30    "location": {
31      "neighborhood": "Bouldin Creek",
32      "coordinates": {
33        "lat": 30.2492,
34        "lng": -97.7546
35      }
36    },
37    "media": {
38      "mainImage": {
39        "url": "https://hearthlane.example/media/hl-1427/main.jpg",
40        "alt": "Front exterior of 1427 Woodland Ave"
41      },
42      "images": [
43        "https://hearthlane.example/media/hl-1427/01.jpg",
44        "https://hearthlane.example/media/hl-1427/02.jpg",
45        "https://hearthlane.example/media/hl-1427/03.jpg"
46      ],
47      "floorplan": {
48        "url": "https://hearthlane.example/media/hl-1427/floorplan.png"
49      }
50    },
51    "highlights": [
52      "Renovated kitchen (2022)",
53      "10-panel solar system",
54      "EV charger in garage",
55      "Walkable to South Congress"
56    ],
57    "amenities": [
58      "Central air",
59      "Hardwood floors",
60      "Fenced yard",
61      "Gas range",
62      "Smart thermostat"
63    ],
64    "openHouses": [
65      {
66        "start": "2026-02-01T13:00:00-06:00",
67        "end": "2026-02-01T15:00:00-06:00",
68        "note": "Hosted by listing agent"
69      }
70    ],
71    "description": "Bright, updated home in Bouldin Creek with an open layout, chef-friendly kitchen, and a private backyard. Solar panels keep energy costs low, and the EV charger makes commuting easy. Minutes to local shops and dining.",
72    "agent": {
73      "brokerage": "Hearthlane Realty",
74      "phone": "+1-512-555-0188",
75    },
76    "disclaimer": "All information deemed reliable but not guaranteed. Buyer to verify."
77  }
78}

1{
2  "name": "dREAMjOBSTODAY",
3  "jobTitle": "Crew Member - Thamesmead 939",
4  "employmentType": "Full Time",
5  "salary": "£9.52 - £12.26",
6  "salaryMax": 12.26,
7  "currency": "GBP",
8  "currencyRaw": "£",
9  "availability": "Open",
10  "jobLocation": "SE28 8RD UK",
11  "hiringOrganization": "dREAMjOBSTODAY Careers UK",
12  "datePublished": "2025-10-08T00:00:00",
13  "datePublishedRaw": "2025-10-08",
14  "probability": 0.6755940318107605,
15  "url": "https://careers.dreamjobstoday.example/job-search/location-london/crew-member-thamesmead-939/pdx-djt-3ef1bf0e-0015-4d0f-8201-000246a1a831-77342",
16  "description": "dREAMjOBSTODAY is a fictional global hiring platform focused on connecting people with entry-level and customer-facing roles across the UK.",
17  "descriptionHtml": "<article><p>dREAMjOBSTODAY is a fictional global hiring platform.</p><p>Join our team and become part of a friendly, fast-paced environment where collaboration and great customer experiences come first.</p></article>",
18  "metadata": {
19    "dateDownloaded": "2025-10-09T09:39:58Z"
20  }
21}

1{
2  "title": "20 Years Ago, Daniel D. Cave Built the 'Best cave yacht app of all time'. It sank like a stone.",
3  "category": "Tech",
4  "description": "This month marks the 20th anniversary of Yacht Cave, which debuted July 19, 2005, and didn't get far at all.",
5  "image": {
6    "url": "https://helloworldnews.example/images/articles/yacht-cave.jpg"
7  },
8  "url": "https://www.helloworldnews.example/tech/apple/yacht-cave",
9  "publisher": {
10    "name": "HelloWorldNews"
11  },
12  "author": {
13    "name": "Martin J. Sally",
14    "profileImage": "https://helloworldnews.example/images/authors/Jordana-j-sally-ptolemy.jpg"
15  },
16  "publishedTime": "12 hours ago",
17  "lastModified": "12 hours ago",
18  "engagement": {
19    "likes": 28
20  },
21  "disclaimer": "Article metadata is fictional and provided solely for demonstration, testing, and schema validation purposes."
22}

1{
2  "_comment": "JSON example for indicative processes only.",
3
4  "dataset": {
5    "id": "td-webarticles-corpus-1042",
6    "url": "https://trainingdataipsum.example/datasets/web-articles-corpus",
7    "name": "Global Web Articles Corpus (Multilingual)",
8    "category": [
9      "LLM Training",
10      "Text Corpus",
11      "Web Data"
12    ],
13    "summary": "A large-scale corpus of publicly available web articles collected from approximately 10,100,000 websites across multiple domains, curated for AI",
14
15    "version": "1.0.0",
16    "releaseDate": "2026-01-15",
17    "lastUpdated": "2026-02-10",
18
19    "format": [
20      "JSONL",
21      "Parquet"
22    ],
23
24    "language": [
25      "en",
26      "es",
27      "fr",
28      "de",
29      "pt",
30      "it",
31      "nl"
32    ],
33
34    "size": {
35      "documents": 10321323,
36      "tokensApprox": 3100000000,
37      "compressedBytes": 12400000000
38    },
39
40    "schema": {
41      "recordType": "web_document",
42      "fields": [
43        { "name": "document_id", "type": "string" },
44        { "name": "source_url", "type": "string" },
45        { "name": "domain", "type": "string" },
46        { "name": "title", "type": "string" },
47        { "name": "content", "type": "string" },
48        { "name": "language", "type": "string" },
49        { "name": "publication_date", "type": "date" },
50        { "name": "topics", "type": "array" },
51        { "name": "content_length", "type": "integer" },
52        { "name": "quality_score", "type": "number" }
53      ]
54    },
55
56    "labels": {
57      "topics": [
58        "technology",
59        "business",
60        "finance",
61        "health",
62        "science",
63        "education",
64        "entertainment",
65        "lifestyle",
66        "travel",
67        "environment"
68      ]
69    },
70
71    "quality": {
72      "deduplication": "MinHash + URL canonicalization + content similarity filtering",
73      "contentFiltering": "Removal of boilerplate, navigation text, and low-content pages",
74      "languageId": "fastText-based language identification",
75      "qualityScoring": "Custom",
76      "safetyFiltering": "Custom"
77    },
78
79    "compliance": {
80      "pii": "No intentional collection of personal data. Automated filtering applied to exclude personal identifiers where detected.",
81      "sourceType": "Publicly accessible web content",
82      "jurisdictions": [
83        "EU",
84        "US",
85        "UK"
86      ]
87    },
88
89    "coverage": {
90      "numberOfDomains": 10321323,
91      "domainTypes": [
92        "news",
93        "blogs",
94        "documentation sites",
95        "magazines",
96        "public reports"
97      ],
98      "collectionWindow": {
99        "start": "2023-06-01",
100        "end": "2026-01-01"
101      }
102    },
103
104    "disclaimer": "This dataset is a synthetic representation of a web-scale corpus for demonstration and testing purposes. It does not contain proprietary or restricted data and is intended solely for evaluation, benchmarking, and schema validation."
105  }
106}

1{
2  "marketFinancialData": {
3    "id": "mk-financialipsum-fip",
4    "url": "https://marketdeck.io/quote/FIP",
5    "asOf": "2026-01-19T14:32:10Z",
6    "instrument": {
7      "symbol": "FIP",
8      "name": "FinancialIpsum Corp",
9      "type": "Equity",
10      "exchange": "NASDAQ",
11      "currency": "USD",
12      "isin": "US0FIP000001",
13      "cusip": "0FIP00000",
14      "sector": "Technology",
15      "industry": "Financial Data & Analytics Software"
16    },
17    "price": {
18      "last": 74.36,
19      "change": 1.28,
20      "changePercent": 1.75,
21      "open": 72.95,
22      "high": 75.1,
23      "low": 72.4,
24      "previousClose": 73.08
25    },
26    "volume": {
27      "current": 3894521,
28      "avg30d": 4621180
29    },
30    "marketCap": 24380000000,
31    "valuation": {
32      "peTTM": 31.6,
33      "epsTTM": 2.35,
34      "forwardPE": 27.2,
35      "peg": 1.8,
36      "priceToSalesTTM": 7.1
37    },
38    "dividend": {
39      "yieldPercent": 0.6,
40      "annual": 0.44,
41      "exDate": "2026-02-03",
42      "payDate": "2026-02-21"
43    },
44    "range": {
45      "day": {
46        "low": 72.4,
47        "high": 75.1
48      },
49      "week52": {
50        "low": 52.18,
51        "high": 81.42
52      }
53    },
54    "technical": {
55      "movingAvg50d": 71.92,
56      "movingAvg200d": 64.38,
57      "rsi14d": 54.1,
58      "beta": 1.18
59    },
60    "financials": {
61      "revenueTTM": 3840000000,
62      "grossMarginPercent": 69.8,
63      "operatingMarginPercent": 21.4,
64      "netIncomeTTM": 624000000,
65      "freeCashFlowTTM": 581000000
66    },
67    "events": {
68      "earnings": {
69        "nextDate": "2026-02-12",
70        "time": "AfterMarketClose"
71      }
72    },
73    "news": [
74      {
75        "headline": "FinancialIpsum reports strong demand for synthetic market data platforms",
76        "url": "https://marketdeck.io/news/financialipsum-synthetic-data-growth",
77        "publishedAt": "2026-01-18T10:05:00Z",
78        "source": "MarketDeck Wire"
79      },
80      {
81        "headline": "Analytics software stocks rally as fintech infrastructure spending rises",
82        "url": "https://marketdeck.io/news/fintech-infrastructure-rally",
83        "publishedAt": "2026-01-17T16:42:00Z",
84        "source": "MarketDeck Insights"
85      }
86    ],
87    "disclaimer": "Market data shown is fictional and provided solely for demonstration, testing, and schema validation purposes. It does not represent any real company or security."
88  }
89}

1{
2  "travelHospitality": {
3    "id": "sp-lisbon-neverendingsummer-001",
4    "url": "https://staypilot.example/hotels/lisbon/neverending-summer-resort",
5    "type": "Hotel",
6    "name": "NeverendingSummer Resort",
7    "brand": "StayPilot",
8    "status": "Available",
9    "rating": {
10      "value": 4.6,
11      "count": 1287
12    },
13    "address": {
14      "street": "Rua do Sol Eterno 18",
15      "city": "Lisbon",
16      "region": "Lisboa",
17      "postalCode": "1100-312",
18      "country": "PT"
19    },
20    "location": {
21      "neighborhood": "Alfama",
22      "coordinates": {
23        "lat": 38.7112,
24        "lng": -9.1291
25      }
26    },
27    "stay": {
28      "checkIn": "2026-04-18",
29      "checkOut": "2026-04-21",
30      "nights": 3,
31      "guests": 2,
32      "rooms": 1
33    },
34    "pricing": {
35      "currency": "EUR",
36      "total": 612.0,
37      "nightly": 204.0,
38      "taxesAndFees": 48.0,
39      "freeCancellationUntil": "2026-04-16",
40      "payAtProperty": false
41    },
42    "rooms": [
43      {
44        "name": "Standard Double",
45        "bed": "1 Queen",
46        "maxGuests": 2,
47        "refundable": true,
48        "breakfastIncluded": false,
49        "pricePerNight": 189.0,
50        "currency": "EUR"
51      },
52      {
53        "name": "River View Suite",
54        "bed": "1 King",
55        "maxGuests": 3,
56        "refundable": true,
57        "breakfastIncluded": true,
58        "pricePerNight": 246.0,
59        "currency": "EUR"
60      }
61    ],
62    "amenities": [
63      "Free Wi-Fi",
64      "Breakfast available",
65      "Airport shuttle",
66      "Air conditioning",
67      "24-hour front desk",
68      "Rooftop terrace"
69    ],
70    "policies": {
71      "checkInFrom": "15:00",
72      "checkOutUntil": "11:00",
73      "petsAllowed": false,
74      "smokingAllowed": false
75    },
76    "highlights": [
77      "5-minute walk to São Jorge Castle",
78      "Rooftop terrace with river views",
79      "Recently renovated rooms"
80    ],
81    "media": {
82      "mainImage": {
83        "url": "https://staypilot.example/media/neverending-summer/main.jpg",
84        "alt": "Rooftop terrace overlooking the Tagus River at NeverendingSummer Resort"
85      },
86      "images": [
87        "https://staypilot.example/media/neverending-summer/01.jpg",
88        "https://staypilot.example/media/neverending-summer/02.jpg",
89        "https://staypilot.example/media/neverending-summer/03.jpg"
90      ]
91    },
92    "hostOrOperator": {
93      "name": "NeverendingSummer Resort",
94      "phone": "+351-21-555-0123",
95      "email": "hello@neverendingsummer.staypilot.example"
96    },
97    "booking": {
98      "provider": "StayPilot",
99      "bookingUrl": "https://staypilot.example/booking?hotel=neverending-summer-resort&checkin=2026-04-18&checkout=2026-04-21&guests=2",
100      "confirmationInstant": true
101    },
102    "disclaimer": "All property information is fictional and provided for demonstration, testing, and schema validation purposes only."
103  }
104}

1{
2  "businessListing": {
3    "id": "np-ldn-theloremfactory-7421",
4    "url": "https://nimbuspages.example/companies/the-lorem-factory-ltd",
5    "name": "TheLoremFactory Ltd",
6    "legalName": "The Lorem Factory Limited",
7    "type": "PrivateCompany",
8    "industry": [
9      "Content Generation",
10      "Digital Tooling",
11      "SaaS"
12    ],
13    "description": "TheLoremFactory builds placeholder content and mock data tools for designers, developers, and product teams, helping them prototype faster with realistic lorem-style assets.",
14    "foundedYear": 2019,
15    "employeeCount": {
16      "value": 42,
17      "range": "11-50"
18    },
19    "headquarters": {
20      "street": "14 Placeholder Street",
21      "city": "London",
22      "region": "England",
23      "postalCode": "EC1A 4JL",
24      "country": "GB"
25    },
26    "locations": [
27      {
28        "city": "London",
29        "country": "GB",
30        "type": "Headquarters"
31      }
32    ],
33    "contact": {
34      "phone": "+44 20 7000 1234",
35      "email": "hello@theloremfactory.nimbuspages.example",
36      "website": "https://theloremfactory.nimbuspages.example"
37    },
38    "identifiers": {
39      "companyNumber": "11840291",
40      "vatNumber": "GB 312 4456 78",
41      "lei": "5493009LOREMFACTORY1"
42    },
43    "social": {
44      "x": "https://x.com/theloremfactory"
45    },
46    "categories": [
47      "Software Company",
48      "Developer Tools",
49      "B2B SaaS"
50    ],
51    "businessHours": [
52      {
53        "day": "Mon",
54        "opens": "09:00",
55        "closes": "18:00"
56      },
57      {
58        "day": "Tue",
59        "opens": "09:00",
60        "closes": "18:00"
61      },
62      {
63        "day": "Wed",
64        "opens": "09:00",
65        "closes": "18:00"
66      },
67      {
68        "day": "Thu",
69        "opens": "09:00",
70        "closes": "18:00"
71      },
72      {
73        "day": "Fri",
74        "opens": "09:00",
75        "closes": "17:00"
76      }
77    ],
78    "rating": {
79      "value": 4.7,
80      "count": 96,
81      "source": "NimbusPages"
82    },
83    "tags": [
84      "Lorem ipsum",
85      "Mock data",
86      "Prototyping",
87      "Developer tools"
88    ],
89    "media": {
90      "logo": {
91        "url": "https://nimbuspages.example/media/logos/the-lorem-factory.png",
92        "alt": "TheLoremFactory logo"
93      }
94    },
95    "lastUpdated": "2026-01-05T11:22:40Z",
96    "disclaimer": "Company information is fictional and provided for demonstration and testing purposes only."
97  }
98}