|
1 | 1 | { |
2 | 2 | "title": "Cheerio Scraper Input", |
3 | 3 | "type": "object", |
4 | | - "description": "Cheerio Scraper loads <b>Start URLs</b> using raw HTTP requests, parses the HTML using the <a href='https://cheerio.js.org' target='_blank' rel='noopener noreferrer'>Cheerio</a> library and then executes <b>Page function</b> for each page to extract data from it. To follow links and scrape additional pages, set <b>Link selector</b> with <b>Pseudo-URLs</b> and/or <b>Glob patterns</b> to specify which links to follow. Alternatively, you can manually enqueue new links in the <b>Page function</b>. For details, see the actor's <a href='https://apify.com/apify/cheerio-scraper' target='_blank' rel='noopener'>README</a> or the <a href='https://docs.apify.com/academy/apify-scrapers/cheerio-scraper' target='_blank' rel='noopener'>Web scraping tutorial</a> in the Apify documentation.", |
| 4 | + "description": "Cheerio Scraper loads <b>Start URLs</b> using raw HTTP requests, parses the HTML using the <a href='https://cheerio.js.org' target='_blank' rel='noopener noreferrer'>Cheerio</a> library and then executes <b>Page function</b> for each page to extract data from it. To follow links and scrape additional pages, set <b>Link selector</b> with <b>Pseudo-URLs</b> and/or <b>Glob patterns</b> to specify which links to follow. Alternatively, you can manually enqueue new links in the <b>Page function</b>. For details, see the Actor's <a href='https://apify.com/apify/cheerio-scraper' target='_blank' rel='noopener'>README</a> or the <a href='https://docs.apify.com/academy/apify-scrapers/cheerio-scraper' target='_blank' rel='noopener'>Web scraping tutorial</a> in the Apify documentation.", |
5 | 5 | "schemaVersion": 1, |
6 | 6 | "properties": { |
7 | 7 | "startUrls": { |
|
32 | 32 | "pseudoUrls": { |
33 | 33 | "title": "Pseudo-URLs", |
34 | 34 | "type": "array", |
35 | | - "description": "Specifies what kind of URLs found by the <b>Link selector</b> should be added to the request queue. A pseudo-URL is a URL with <b>regular expressions</b> enclosed in <code>[]</code> brackets, e.g. <code>http://www.example.com/[.*]</code>. <br><br>If <b>Pseudo-URLs</b> are omitted, the actor enqueues all links matched by the <b>Link selector</b>.<br><br>For details, see <a href='https://apify.com/apify/cheerio-scraper#pseudo-urls' target='_blank' rel='noopener'>Pseudo-URLs</a> in README.", |
| 35 | + "description": "Specifies what kind of URLs found by the <b>Link selector</b> should be added to the request queue. A pseudo-URL is a URL with <b>regular expressions</b> enclosed in <code>[]</code> brackets, e.g. <code>http://www.example.com/[.*]</code>. <br><br>If <b>Pseudo-URLs</b> are omitted, the Actor enqueues all links matched by the <b>Link selector</b>.<br><br>For details, see <a href='https://apify.com/apify/cheerio-scraper#pseudo-urls' target='_blank' rel='noopener'>Pseudo-URLs</a> in README.", |
36 | 36 | "editor": "pseudoUrls", |
37 | 37 | "default": [], |
38 | 38 | "prefill": [] |
|
58 | 58 | "title": "Page function", |
59 | 59 | "type": "string", |
60 | 60 | "description": "A JavaScript function that is executed for every page loaded server-side in Node.js 12. Use it to scrape data from the page, perform actions or add new URLs to the request queue.<br><br>For details, see <a href='https://apify.com/apify/cheerio-scraper#page-function' target='_blank' rel='noopener'>Page function</a> in README.", |
61 | | - "prefill": "async function pageFunction(context) {\n const { $, request, log } = context;\n\n // The \"$\" property contains the Cheerio object which is useful\n // for querying DOM elements and extracting data from them.\n const pageTitle = $('title').first().text();\n\n // The \"request\" property contains various information about the web page loaded. \n const url = request.url;\n \n // Use \"log\" object to print information to actor log.\n log.info('Page scraped', { url, pageTitle });\n\n // Return an object with the data extracted from the page.\n // It will be stored to the resulting dataset.\n return {\n url,\n pageTitle\n };\n}", |
| 61 | + "prefill": "async function pageFunction(context) {\n const { $, request, log } = context;\n\n // The \"$\" property contains the Cheerio object which is useful\n // for querying DOM elements and extracting data from them.\n const pageTitle = $('title').first().text();\n\n // The \"request\" property contains various information about the web page loaded. \n const url = request.url;\n \n // Use \"log\" object to print information to Actor log.\n log.info('Page scraped', { url, pageTitle });\n\n // Return an object with the data extracted from the page.\n // It will be stored to the resulting dataset.\n return {\n url,\n pageTitle\n };\n}", |
62 | 62 | "editor": "javascript" |
63 | 63 | }, |
64 | 64 | "proxyConfiguration": { |
|
90 | 90 | "sessionPoolName": { |
91 | 91 | "title": "Session pool name", |
92 | 92 | "type": "string", |
93 | | - "description": "<b>Use only english alphanumeric characters dashes and underscores.</b> A session is a representation of a user. It has it's own IP and cookies which are then used together to emulate a real user. Usage of the sessions is controlled by the Proxy rotation option. By providing a session pool name, you enable sharing of those sessions across multiple actor runs. This is very useful when you need specific cookies for accessing the websites or when a lot of your proxies are already blocked. Instead of trying randomly, a list of working sessions will be saved and a new actor run can reuse those sessions. Note that the IP lock on sessions expires after 24 hours, unless the session is used again in that window.", |
| 93 | + "description": "<b>Use only english alphanumeric characters dashes and underscores.</b> A session is a representation of a user. It has it's own IP and cookies which are then used together to emulate a real user. Usage of the sessions is controlled by the Proxy rotation option. By providing a session pool name, you enable sharing of those sessions across multiple Actor runs. This is very useful when you need specific cookies for accessing the websites or when a lot of your proxies are already blocked. Instead of trying randomly, a list of working sessions will be saved and a new Actor run can reuse those sessions. Note that the IP lock on sessions expires after 24 hours, unless the session is used again in that window.", |
94 | 94 | "editor": "textfield", |
95 | 95 | "minLength": 3, |
96 | 96 | "maxLength": 200, |
|
203 | 203 | "debugLog": { |
204 | 204 | "title": "Enable debug log", |
205 | 205 | "type": "boolean", |
206 | | - "description": "If enabled, the actor log will include debug messages. Beware that this can be quite verbose. Use <code>context.log.debug('message')</code> to log your own debug messages from the <b>Page function</b>.", |
| 206 | + "description": "If enabled, the Actor log will include debug messages. Beware that this can be quite verbose. Use <code>context.log.debug('message')</code> to log your own debug messages from the <b>Page function</b>.", |
207 | 207 | "default": false, |
208 | 208 | "groupCaption": "Logging" |
209 | 209 | }, |
|
0 commit comments