charlestehio/crawlshot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update

Browse Source
This commit is contained in:
ct
2025-08-11 02:56:17 +08:00
parent 9469d97ddc
commit a2d2ed0117
3 changed files with 8 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
CLAUDE.md
View File

@@ -50,7 +50,7 @@ ### Supported Parameters (mapped to Browsershot capabilities)
- `block_cookie_banners`: true/false - Uses cookie banner blocking patterns - `block_cookie_banners`: true/false - Uses cookie banner blocking patterns
- `block_trackers`: true/false - Uses tracker blocking patterns - `block_trackers`: true/false - Uses tracker blocking patterns
- `delay`: Wait time before capture in milliseconds (via `setDelay()`) - `delay`: Wait time before capture in milliseconds (via `setDelay()`)
- `wait_until_network_idle`: Wait for network activity to cease (via `waitUntilNetworkIdle()`) - Network idle waiting is always enabled for optimal rendering (no parameter needed)
**Screenshot Capture**: **Screenshot Capture**:
@@ -177,7 +177,7 @@ ### Browsershot Configuration
->windowSize($width, $height) ->windowSize($width, $height)
->setScreenshotType('webp', $quality) // Always WebP format ->setScreenshotType('webp', $quality) // Always WebP format
->setDelay($delayInMs) ->setDelay($delayInMs)
->waitUntilNetworkIdle() // Network idle waiting is always enabled
->timeout($timeoutInSeconds); ->timeout($timeoutInSeconds);
// Apply EasyList filters if block_ads is true // Apply EasyList filters if block_ads is true
@@ -193,7 +193,7 @@ ### Browsershot Configuration
// HTML crawling configuration with EasyList filtering // HTML crawling configuration with EasyList filtering
$browsershot = Browsershot::url($url) $browsershot = Browsershot::url($url)
->setDelay($delayInMs) ->setDelay($delayInMs)
->waitUntilNetworkIdle() // Network idle waiting is always enabled
->timeout($timeoutInSeconds); ->timeout($timeoutInSeconds);
// Apply EasyList filters if block_ads is true // Apply EasyList filters if block_ads is true

6
CLIENT_DOCUMENTATION.md
View File

@@ -117,7 +117,7 @@ ### Fluent HTML Crawling
->blockAds(true) ->blockAds(true)
->blockCookieBanners(true) ->blockCookieBanners(true)
->blockTrackers(true) ->blockTrackers(true)
->waitUntilNetworkIdle(true) // Network idle waiting is always enabled for optimal rendering
->webhookUrl('https://myapp.com/webhooks/crawlshot') ->webhookUrl('https://myapp.com/webhooks/crawlshot')
->webhookEventsFilter(['completed', 'failed']) ->webhookEventsFilter(['completed', 'failed'])
->create(); // Returns CrawlResponse ->create(); // Returns CrawlResponse
@@ -179,7 +179,7 @@ #### CrawlJobBuilder Methods
->blockAds(bool $block = true) // Block ads via EasyList ->blockAds(bool $block = true) // Block ads via EasyList
->blockCookieBanners(bool $block = true) // Block cookie banners ->blockCookieBanners(bool $block = true) // Block cookie banners
->blockTrackers(bool $block = true) // Block tracking scripts ->blockTrackers(bool $block = true) // Block tracking scripts
->waitUntilNetworkIdle(bool $wait = true) // Wait for network idle // waitUntilNetworkIdle is always enabled server-side for optimal rendering
->create(); // Execute and return CrawlResponse ->create(); // Execute and return CrawlResponse
``` ```
@@ -382,7 +382,7 @@ ### Custom Options
$crawl = $client->crawl('https://spa-website.com') $crawl = $client->crawl('https://spa-website.com')
->timeout(120) // Long timeout for slow sites ->timeout(120) // Long timeout for slow sites
->delay(3000) // Wait 3 seconds for JS ->delay(3000) // Wait 3 seconds for JS
->waitUntilNetworkIdle(true) // Wait for AJAX requests // Network idle waiting is always enabled for AJAX/dynamic content
->blockAds(false) // Allow ads for testing ->blockAds(false) // Allow ads for testing
->blockCookieBanners(true) // But block cookie banners ->blockCookieBanners(true) // But block cookie banners
->webhookUrl('https://myapp.com/webhook') ->webhookUrl('https://myapp.com/webhook')

7
src/CrawlJobBuilder.php
View File

@@ -56,11 +56,8 @@ public function blockTrackers(bool $block = true): self
return $this; return $this;
} }
public function waitUntilNetworkIdle(bool $wait = true): self // waitUntilNetworkIdle is always enabled server-side for optimal rendering
{ // This method has been removed as the parameter is no longer supported
$this->options['wait_until_network_idle'] = $wait;
return $this;
}
public function create(): CrawlResponse public function create(): CrawlResponse
{ {