{ "openapi": "3.0.1", "info": { "title": "Google News Scraper - Real URL & Source Metadata", "description": "Automate Google News scraping for large topics or keyword lists. Retrieve headlines, summaries, sources, and publication timestamps in structured form. Useful for tracking industry updates, global events, or competitive news trends.", "version": "0.1", "x-build-id": "HIcEc9qNpa4uDIwTL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/api-empire~google-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-api-empire-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/api-empire~google-news-scraper/runs": { "post": { "operationId": "runs-sync-api-empire-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/api-empire~google-news-scraper/run-sync": { "post": { "operationId": "run-sync-api-empire-google-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "maxItems", "query" ], "properties": { "maxItems": { "title": "Number Of Articles", "minimum": 1, "maximum": 50000, "type": "integer", "description": "How many article rows to save. Google News RSS has no pagination and returns roughly 100-110 items per query, so higher values are capped by the feed itself. Each saved row is one charged result.", "default": 10 }, "query": { "title": "Search Query", "type": "string", "description": "Search term. Google News query operators work here too: \"exact phrase\", intitle:tesla, site:reuters.com, -excludedword, when:1d, after:2026-01-01 before:2026-01-31.", "default": "Elon Musk" }, "gl": { "title": "Country Edition", "enum": [ "Ascension Island", "Andorra", "United Arab Emirates", "Antigua & Barbuda", "Anguilla", "Albania", "Armenia", "Angola", "Antarctica", "Argentina", "American Samoa", "Austria", "Australia", "Aruba", "Åland Islands", "Azerbaijan", "Bosnia & Herzegovina", "Barbados", "Bangladesh", "Belgium", "Burkina Faso", "Bulgaria", "Bahrain", "Burundi", "Benin", "St. Barthélemy", "Bermuda", "Brunei", "Bolivia", "Caribbean Netherlands", "Brazil", "Bahamas", "Bhutan", "Bouvet Island", "Botswana", "Belarus", "Belize", "Canada", "Cocos (Keeling) Islands", "Congo (DRC)", "Central African Republic", "Congo (Republic)", "Switzerland", "Côte d'Ivoire", "Cook Islands", "Chile", "Cameroon", "Colombia", "Costa Rica", "Cape Verde", "Curaçao", "Christmas Island", "Cyprus", "Czech Republic", "Germany", "Djibouti", "Denmark", "Dominica", "Dominican Republic", "Algeria", "Ecuador", "Estonia", "Egypt", "Western Sahara", "Eritrea", "Spain", "Ethiopia", "Finland", "Fiji", "Falkland Islands (Islas Malvinas)", "Micronesia", "Faroe Islands", "France", "Gabon", "United Kingdom", "Grenada", "Georgia", "French Guiana", "Guernsey", "Ghana", "Gibraltar", "Greenland", "Gambia", "Guinea", "Guadeloupe", "Equatorial Guinea", "Greece", "South Georgia & South Sandwich Islands", "Guatemala", "Guam", "Guinea-Bissau", "Guyana", "Hong Kong", "Heard & McDonald Islands", "Honduras", "Croatia", "Haiti", "Hungary", "Indonesia", "Ireland", "Israel", "Isle of Man", "India", "British Indian Ocean Territory", "Iraq", "Iceland", "Italy", "Jersey", "Jamaica", "Jordan", "Japan", "Kenya", "Kyrgyzstan", "Cambodia", "Kiribati", "Comoros", "St. Kitts & Nevis", "South Korea", "Kuwait", "Cayman Islands", "Kazakhstan", "Laos", "Lebanon", "St. Lucia", "Liechtenstein", "Sri Lanka", "Liberia", "Lesotho", "Lithuania", "Luxembourg", "Latvia", "Libya", "Morocco", "Monaco", "Moldova", "Montenegro", "St. Martin", "Madagascar", "Marshall Islands", "Macedonia (FYROM)", "Mali", "Myanmar (Burma)", "Mongolia", "Macau", "Northern Mariana Islands", "Martinique", "Mauritania", "Montserrat", "Malta", "Mauritius", "Maldives", "Malawi", "Mexico", "Malaysia", "Mozambique", "Namibia", "New Caledonia", "Niger", "Norfolk Island", "Nigeria", "Nicaragua", "Netherlands", "Norway", "Nepal", "Nauru", "Niue", "New Zealand", "Oman", "Panama", "Peru", "French Polynesia", "Papua New Guinea", "Philippines", "Pakistan", "Poland", "St. Pierre & Miquelon", "Pitcairn Islands", "Puerto Rico", "Palestine", "Portugal", "Palau", "Paraguay", "Qatar", "Réunion", "Romania", "Serbia", "Russia", "Rwanda", "Saudi Arabia", "Solomon Islands", "Seychelles", "Sweden", "Singapore", "St. Helena", "Slovenia", "Svalbard & Jan Mayen", "Slovakia", "Sierra Leone", "San Marino", "Senegal", "Somalia", "Suriname", "South Sudan", "São Tomé & Príncipe", "El Salvador", "Sint Maarten", "Swaziland", "Tristan da Cunha", "Turks & Caicos Islands", "Chad", "French Southern Territories", "Togo", "Thailand", "Tajikistan", "Tokelau", "Timor-Leste", "Turkmenistan", "Tunisia", "Tonga", "Turkey", "Trinidad & Tobago", "Tuvalu", "Taiwan", "Tanzania", "Ukraine", "Uganda", "U.S. Outlying Islands", "United States", "Uruguay", "Uzbekistan", "Vatican City", "St. Vincent & Grenadines", "Venezuela", "British Virgin Islands", "U.S. Virgin Islands", "Vietnam", "Vanuatu", "Wallis & Futuna", "Samoa", "Kosovo", "Yemen", "Mayotte", "South Africa", "Zambia", "Zimbabwe" ], "type": "string", "description": "Google News country edition. Honored by the feed." }, "hl": { "title": "Interface Language", "enum": [ "Afrikaans", "Akan", "Albanian", "Amharic", "Arabic", "Armenian", "Azerbaijani", "Basque", "Belarusian", "Bemba", "Bengali", "Bihari", "Bosnian", "Breton", "Bulgarian", "Catalan", "Cherokee", "Chichewa", "Chinese (Simplified)", "Chinese (Traditional)", "Corsican", "Croatian", "Czech", "Danish", "Dutch", "English", "Esperanto", "Estonian", "Ewe", "Filipino", "Finnish", "French", "Frisian", "Ga", "Galician", "Georgian", "German", "Greek", "Guarani", "Gujarati", "Haitian Creole", "Hausa", "Hawaiian", "Hebrew", "Hindi", "Hungarian", "Icelandic", "Igbo", "Indonesian", "Interlingua", "Irish", "Italian", "Japanese", "Javanese", "Kannada", "Kazakh", "Khmer", "Korean", "Krio", "Kurdish", "Kurdish (Sorani)", "Kyrgyz", "Lao", "Latin", "Latvian", "Lingala", "Lithuanian", "Lozi", "Luganda", "Acholi", "Macedonian", "Malagasy", "Malay", "Malayalam", "Maltese", "Maori", "Marathi", "Mauritian Creole", "Moldovan", "Mongolian", "Montenegrin", "Nepali", "Nigerian Pidgin", "Northern Sotho", "Norwegian", "Norwegian (Nynorsk)", "Occitan", "Oromo", "Pashto", "Persian", "Polish", "Portuguese", "Portuguese (Brazil)", "Portuguese (Portugal)", "Punjabi", "Quechua", "Romanian", "Romansh", "Runyankole", "Russian", "Scots Gaelic", "Serbian", "Serbo-Croatian", "Sesotho", "Shona", "Sindhi", "Sinhala", "Slovak", "Slovenian", "Somali", "Spanish", "Spanish (Latin America)", "Sundanese", "Swahili", "Swedish", "Tajik", "Tamil", "Telugu", "Thai", "Tigrinya", "Tonga", "Tumbuka", "Turkish", "Turkmen", "Twi", "Ukrainian", "Urdu", "Uzbek", "Vietnamese", "Welsh", "Wolof", "Xhosa", "Yiddish", "Yoruba", "Zulu" ], "type": "string", "description": "Google News language edition. Honored by the feed." }, "lr": { "title": "Result Language (no-op)", "enum": [ "Arabic", "Armenian", "Belarusian", "Bulgarian", "Catalan", "Chinese (Simplified)", "Chinese (Traditional)", "Croatian", "Czech", "Danish", "Dutch", "English", "Esperanto", "Estonian", "Filipino", "Finnish", "French", "German", "Greek", "Hebrew", "Hungarian", "Icelandic", "Indonesian", "Italian", "Japanese", "Korean", "Latvian", "Lithuanian", "Norwegian", "Persian", "Polish", "Portuguese", "Romanian", "Russian", "Serbian", "Slovak", "Slovenian", "Spanish", "Swedish", "Thai", "Turkish", "Ukrainian", "Vietnamese" ], "type": "string", "description": "Kept for input compatibility. Measured live: the Google News RSS surface ignores lr and returns a byte-identical feed. Use the Country Edition and Interface Language fields instead." }, "cr": { "title": "Result Country (no-op)", "enum": [ "Ascension Island", "Andorra", "United Arab Emirates", "Antigua & Barbuda", "Anguilla", "Albania", "Armenia", "Angola", "Antarctica", "Argentina", "American Samoa", "Austria", "Australia", "Aruba", "Åland Islands", "Azerbaijan", "Bosnia & Herzegovina", "Barbados", "Bangladesh", "Belgium", "Burkina Faso", "Bulgaria", "Bahrain", "Burundi", "Benin", "St. Barthélemy", "Bermuda", "Brunei", "Bolivia", "Caribbean Netherlands", "Brazil", "Bahamas", "Bhutan", "Bouvet Island", "Botswana", "Belarus", "Belize", "Canada", "Cocos (Keeling) Islands", "Congo (DRC)", "Central African Republic", "Congo (Republic)", "Switzerland", "Côte d'Ivoire", "Cook Islands", "Chile", "Cameroon", "Colombia", "Costa Rica", "Cape Verde", "Curaçao", "Christmas Island", "Cyprus", "Czech Republic", "Germany", "Djibouti", "Denmark", "Dominica", "Dominican Republic", "Algeria", "Ecuador", "Estonia", "Egypt", "Western Sahara", "Eritrea", "Spain", "Ethiopia", "Finland", "Fiji", "Falkland Islands (Islas Malvinas)", "Micronesia", "Faroe Islands", "France", "Gabon", "United Kingdom", "Grenada", "Georgia", "French Guiana", "Guernsey", "Ghana", "Gibraltar", "Greenland", "Gambia", "Guinea", "Guadeloupe", "Equatorial Guinea", "Greece", "South Georgia & South Sandwich Islands", "Guatemala", "Guam", "Guinea-Bissau", "Guyana", "Hong Kong", "Heard & McDonald Islands", "Honduras", "Croatia", "Haiti", "Hungary", "Indonesia", "Ireland", "Israel", "Isle of Man", "India", "British Indian Ocean Territory", "Iraq", "Iceland", "Italy", "Jersey", "Jamaica", "Jordan", "Japan", "Kenya", "Kyrgyzstan", "Cambodia", "Kiribati", "Comoros", "St. Kitts & Nevis", "South Korea", "Kuwait", "Cayman Islands", "Kazakhstan", "Laos", "Lebanon", "St. Lucia", "Liechtenstein", "Sri Lanka", "Liberia", "Lesotho", "Lithuania", "Luxembourg", "Latvia", "Libya", "Morocco", "Monaco", "Moldova", "Montenegro", "St. Martin", "Madagascar", "Marshall Islands", "Macedonia (FYROM)", "Mali", "Myanmar (Burma)", "Mongolia", "Macau", "Northern Mariana Islands", "Martinique", "Mauritania", "Montserrat", "Malta", "Mauritius", "Maldives", "Malawi", "Mexico", "Malaysia", "Mozambique", "Namibia", "New Caledonia", "Niger", "Norfolk Island", "Nigeria", "Nicaragua", "Netherlands", "Norway", "Nepal", "Nauru", "Niue", "New Zealand", "Oman", "Panama", "Peru", "French Polynesia", "Papua New Guinea", "Philippines", "Pakistan", "Poland", "St. Pierre & Miquelon", "Pitcairn Islands", "Puerto Rico", "Palestine", "Portugal", "Palau", "Paraguay", "Qatar", "Réunion", "Romania", "Serbia", "Russia", "Rwanda", "Saudi Arabia", "Solomon Islands", "Seychelles", "Sweden", "Singapore", "St. Helena", "Slovenia", "Svalbard & Jan Mayen", "Slovakia", "Sierra Leone", "San Marino", "Senegal", "Somalia", "Suriname", "South Sudan", "São Tomé & Príncipe", "El Salvador", "Sint Maarten", "Swaziland", "Tristan da Cunha", "Turks & Caicos Islands", "Chad", "French Southern Territories", "Togo", "Thailand", "Tajikistan", "Tokelau", "Timor-Leste", "Turkmenistan", "Tunisia", "Tonga", "Turkey", "Trinidad & Tobago", "Tuvalu", "Taiwan", "Tanzania", "Ukraine", "Uganda", "U.S. Outlying Islands", "United States", "Uruguay", "Uzbekistan", "Vatican City", "St. Vincent & Grenadines", "Venezuela", "British Virgin Islands", "U.S. Virgin Islands", "Vietnam", "Vanuatu", "Wallis & Futuna", "Samoa", "Kosovo", "Yemen", "Mayotte", "South Africa", "Zambia", "Zimbabwe" ], "type": "string", "description": "Kept for input compatibility. Measured live: the Google News RSS surface ignores cr and returns a byte-identical feed. Use the Country Edition field instead." }, "time_period": { "title": "Time Period", "enum": [ "last_hour", "last_day", "last_week", "last_month", "last_year", "custom" ], "type": "string", "description": "Restrict results by age. The base actor sent this as tbs=qdr:* which Google News RSS ignores; this actor translates it into the query operators that do work (last_hour to when:1h, last_day to when:1d, last_week to when:7d, last_month to when:30d, last_year to when:365d, custom to after:/before:). The applied query is echoed in every row." }, "time_period_min": { "title": "Custom Range Start (MM/DD/YYYY)", "pattern": "^\\d{2}/\\d{2}/\\d{4}$", "type": "string", "description": "Used when Time Period = custom. Becomes after:YYYY-MM-DD." }, "time_period_max": { "title": "Custom Range End (MM/DD/YYYY)", "pattern": "^\\d{2}/\\d{2}/\\d{4}$", "type": "string", "description": "Used when Time Period = custom. Becomes before:YYYY-MM-DD." }, "nfpr": { "title": "No Autocorrect (no-op)", "minimum": 0, "maximum": 1, "type": "integer", "description": "Kept for input compatibility. Measured live: the Google News RSS surface ignores nfpr.", "default": 0 }, "filter": { "title": "Similar/Omitted Filter (no-op)", "minimum": 0, "maximum": 1, "type": "integer", "description": "Kept for input compatibility. Measured live: the Google News RSS surface ignores filter.", "default": 1 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional. Google News and the URL resolver normally work with no proxy at all. If Google throttles the run (HTTP 429), the actor escalates by itself to an Apify datacenter proxy and then to residential - both rungs were verified live." }, "resolveRealUrl": { "title": "Resolve Real Publisher URL", "type": "boolean", "description": "Decode every news.google.com/rss/articles redirect into the publisher's own article URL (realUrl). Measured 100/100 on a live 100-article run at about 0.1 s per article. Costs 2 lightweight requests per article.", "default": true }, "fetchSourceMeta": { "title": "Fetch Destination Page Metadata", "type": "boolean", "description": "Read the publisher page head only: canonical URL, og:title, og:description, og:image, article published/modified time, section, keywords, site name, page language and schema.org publisher name. The article body is never downloaded. Needs the real URL, so it switches URL resolving on.", "default": true }, "skipUnresolved": { "title": "Skip Articles Without A Real URL", "type": "boolean", "description": "Drop rows whose Google News redirect could not be decoded, so every saved row carries a publisher URL. Skipped rows are not saved and not charged.", "default": false }, "concurrency": { "title": "Parallel Requests", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many articles to resolve and enrich at the same time. 8 measured about 0.06 s per article with zero throttling on a single IP.", "default": 8 }, "includeThumbnailBase64": { "title": "Embed Base64 Thumbnail (slow)", "type": "boolean", "description": "Off by default. The base actor downloaded an image and inlined it as a base64 data URL in every row, which costs an extra page fetch plus an image download per article. The ogImage and image columns already give you the image URL for free.", "default": false } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }