@crawlee/templates 3.0.2-beta.5 → 3.0.2-beta.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/package.json +1 -1
- package/templates/cheerio-js/src/main.js +2 -6
- package/templates/cheerio-js/src/routes.js +1 -1
- package/templates/cheerio-ts/src/main.ts +2 -6
- package/templates/cheerio-ts/src/routes.ts +1 -1
- package/templates/playwright-js/src/main.js +2 -6
- package/templates/playwright-js/src/routes.js +1 -1
- package/templates/playwright-ts/src/main.ts +2 -6
- package/templates/playwright-ts/src/routes.ts +1 -1
- package/templates/puppeteer-js/src/main.js +2 -6
- package/templates/puppeteer-js/src/routes.js +1 -1
- package/templates/puppeteer-ts/src/main.ts +2 -6
- package/templates/puppeteer-ts/src/routes.ts +1 -1
package/package.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
import { CheerioCrawler, KeyValueStore, log, ProxyConfiguration } from 'crawlee';
|
|
3
3
|
import { router } from './routes.js';
|
|
4
4
|
|
|
5
|
-
const { startUrls = ['https://
|
|
5
|
+
const { startUrls = ['https://crawlee.dev'], debug } = await KeyValueStore.getInput() ?? {};
|
|
6
6
|
|
|
7
7
|
if (debug) {
|
|
8
8
|
log.setLevel(log.LEVELS.DEBUG);
|
|
@@ -15,8 +15,4 @@ const crawler = new CheerioCrawler({
|
|
|
15
15
|
requestHandler: router,
|
|
16
16
|
});
|
|
17
17
|
|
|
18
|
-
await crawler.
|
|
19
|
-
|
|
20
|
-
log.info('Starting the crawl.');
|
|
21
|
-
await crawler.run();
|
|
22
|
-
log.info('Crawl finished.');
|
|
18
|
+
await crawler.run(startUrls);
|
|
@@ -7,7 +7,7 @@ interface InputSchema {
|
|
|
7
7
|
debug?: boolean;
|
|
8
8
|
}
|
|
9
9
|
|
|
10
|
-
const { startUrls = ['https://
|
|
10
|
+
const { startUrls = ['https://crawlee.dev'], debug } = await KeyValueStore.getInput<InputSchema>() ?? {};
|
|
11
11
|
|
|
12
12
|
if (debug) {
|
|
13
13
|
log.setLevel(log.LEVELS.DEBUG);
|
|
@@ -20,8 +20,4 @@ const crawler = new CheerioCrawler({
|
|
|
20
20
|
requestHandler: router,
|
|
21
21
|
});
|
|
22
22
|
|
|
23
|
-
await crawler.
|
|
24
|
-
|
|
25
|
-
log.info('Starting the crawl.');
|
|
26
|
-
await crawler.run();
|
|
27
|
-
log.info('Crawl finished.');
|
|
23
|
+
await crawler.run(startUrls);
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
import { KeyValueStore, PlaywrightCrawler, ProxyConfiguration, log } from 'crawlee';
|
|
3
3
|
import { router } from './routes.js';
|
|
4
4
|
|
|
5
|
-
const { startUrls = ['https://
|
|
5
|
+
const { startUrls = ['https://crawlee.dev'], debug } = await KeyValueStore.getInput() ?? {};
|
|
6
6
|
|
|
7
7
|
if (debug) {
|
|
8
8
|
log.setLevel(log.LEVELS.DEBUG);
|
|
@@ -15,8 +15,4 @@ const crawler = new PlaywrightCrawler({
|
|
|
15
15
|
requestHandler: router,
|
|
16
16
|
});
|
|
17
17
|
|
|
18
|
-
await crawler.
|
|
19
|
-
|
|
20
|
-
log.info('Starting the crawl.');
|
|
21
|
-
await crawler.run();
|
|
22
|
-
log.info('Crawl finished.');
|
|
18
|
+
await crawler.run(startUrls);
|
|
@@ -5,7 +5,7 @@ export const router = createPlaywrightRouter();
|
|
|
5
5
|
router.addDefaultHandler(async ({ enqueueLinks, log }) => {
|
|
6
6
|
log.info(`Handle Start URLs`);
|
|
7
7
|
await enqueueLinks({
|
|
8
|
-
globs: ['https://
|
|
8
|
+
globs: ['https://crawlee.dev/*'],
|
|
9
9
|
label: 'DETAIL',
|
|
10
10
|
});
|
|
11
11
|
});
|
|
@@ -7,7 +7,7 @@ interface InputSchema {
|
|
|
7
7
|
debug?: boolean;
|
|
8
8
|
}
|
|
9
9
|
|
|
10
|
-
const { startUrls = ['https://
|
|
10
|
+
const { startUrls = ['https://crawlee.dev'], debug } = await KeyValueStore.getInput<InputSchema>() ?? {};
|
|
11
11
|
|
|
12
12
|
if (debug) {
|
|
13
13
|
log.setLevel(log.LEVELS.DEBUG);
|
|
@@ -20,8 +20,4 @@ const crawler = new PlaywrightCrawler({
|
|
|
20
20
|
requestHandler: router,
|
|
21
21
|
});
|
|
22
22
|
|
|
23
|
-
await crawler.
|
|
24
|
-
|
|
25
|
-
log.info('Starting the crawl.');
|
|
26
|
-
await crawler.run();
|
|
27
|
-
log.info('Crawl finished.');
|
|
23
|
+
await crawler.run(startUrls);
|
|
@@ -5,7 +5,7 @@ export const router = createPlaywrightRouter();
|
|
|
5
5
|
router.addDefaultHandler(async ({ enqueueLinks, log }) => {
|
|
6
6
|
log.info(`Handle Start URLs`);
|
|
7
7
|
await enqueueLinks({
|
|
8
|
-
globs: ['https://
|
|
8
|
+
globs: ['https://crawlee.dev/*'],
|
|
9
9
|
label: 'DETAIL',
|
|
10
10
|
});
|
|
11
11
|
});
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
import { KeyValueStore, PuppeteerCrawler, ProxyConfiguration, log } from 'crawlee';
|
|
3
3
|
import { router } from './routes.js';
|
|
4
4
|
|
|
5
|
-
const { startUrls = ['https://
|
|
5
|
+
const { startUrls = ['https://crawlee.dev'], debug } = await KeyValueStore.getInput() ?? {};
|
|
6
6
|
|
|
7
7
|
if (debug) {
|
|
8
8
|
log.setLevel(log.LEVELS.DEBUG);
|
|
@@ -15,8 +15,4 @@ const crawler = new PuppeteerCrawler({
|
|
|
15
15
|
requestHandler: router,
|
|
16
16
|
});
|
|
17
17
|
|
|
18
|
-
await crawler.
|
|
19
|
-
|
|
20
|
-
log.info('Starting the crawl.');
|
|
21
|
-
await crawler.run();
|
|
22
|
-
log.info('Crawl finished.');
|
|
18
|
+
await crawler.run(startUrls);
|
|
@@ -5,7 +5,7 @@ export const router = createPuppeteerRouter();
|
|
|
5
5
|
router.addDefaultHandler(async ({ enqueueLinks, log }) => {
|
|
6
6
|
log.info(`Handle Start URLs`);
|
|
7
7
|
await enqueueLinks({
|
|
8
|
-
globs: ['https://
|
|
8
|
+
globs: ['https://crawlee.dev/*'],
|
|
9
9
|
label: 'DETAIL',
|
|
10
10
|
});
|
|
11
11
|
});
|
|
@@ -7,7 +7,7 @@ interface InputSchema {
|
|
|
7
7
|
debug?: boolean;
|
|
8
8
|
}
|
|
9
9
|
|
|
10
|
-
const { startUrls = ['https://
|
|
10
|
+
const { startUrls = ['https://crawlee.dev'], debug } = await KeyValueStore.getInput<InputSchema>() ?? {};
|
|
11
11
|
|
|
12
12
|
if (debug) {
|
|
13
13
|
log.setLevel(log.LEVELS.DEBUG);
|
|
@@ -20,8 +20,4 @@ const crawler = new PuppeteerCrawler({
|
|
|
20
20
|
requestHandler: router,
|
|
21
21
|
});
|
|
22
22
|
|
|
23
|
-
await crawler.
|
|
24
|
-
|
|
25
|
-
log.info('Starting the crawl.');
|
|
26
|
-
await crawler.run();
|
|
27
|
-
log.info('Crawl finished.');
|
|
23
|
+
await crawler.run(startUrls);
|
|
@@ -5,7 +5,7 @@ export const router = createPuppeteerRouter();
|
|
|
5
5
|
router.addDefaultHandler(async ({ enqueueLinks, log }) => {
|
|
6
6
|
log.info(`Handle Start URLs`);
|
|
7
7
|
await enqueueLinks({
|
|
8
|
-
globs: ['https://
|
|
8
|
+
globs: ['https://crawlee.dev/*'],
|
|
9
9
|
label: 'DETAIL',
|
|
10
10
|
});
|
|
11
11
|
});
|