kfir/Web_Crawler_API
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

improved - nameing convention and spaces

Browse source
This commit is contained in:
Kfir Dayan 2023-06-01 08:50:34 +03:00
parent 231cd17902
commit a9e810b8fb
3 changed files with 33 additions and 34 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
README.md
View file

@ -52,8 +52,8 @@ # GET /api/crawl:
Crawls a website and stores the crawled data in the database. Required query parameter: url. Optional query parameter: depth (default: 1). Crawls a website and stores the crawled data in the database. Required query parameter: url. Optional query parameter: depth (default: 1).
Parameters: Parameters:
- `url` (required): The URL of the website to crawl. - `url` (required): The URL of the website to crawl.
- `depth` (optional): The depth of the crawling process (default: 1). - `depth` (optional): The depth of the crawling process (default: 0).
- `refresh` (optional): If set to true, the crawler will refresh the results for an existing URL (default: false). - `refresh` (optional): If set to 1, the crawler will refresh the results for an existing URL (default: false).
# GET /api: # GET /api:
Retrieves all crawled data from the database. Retrieves all crawled data from the database.
# DELETE /api/crawl/{id}: # DELETE /api/crawl/{id}:

48
app/Http/Controllers/WebCrawlController.php
View file

@ -7,34 +7,34 @@
class WebCrawlController extends Controller class WebCrawlController extends Controller
{ {
protected $webCrawlerService; protected $webCrawlerService;
public function __construct(WebCrawlerService $webCrawlerService) public function __construct(WebCrawlerService $webCrawlerService)
{ {
$this->webCrawlerService = $webCrawlerService; $this->webCrawlerService = $webCrawlerService;
} }
public function index() public function index()
{ {
return $this->webCrawlerService->getAllCrawls(); return $this->webCrawlerService->getAllCrawls();
} }
public function crawlWebsite(WebCrawlRequest $request) public function crawlWebsite(WebCrawlRequest $request)
{ {
$url = $request->query('url'); $url = $request->query('url');
$depth = $request->query('depth', 0); $depth = $request->query('depth', 0);
$refresh = $request->query('refresh', false); $refresh = $request->query('refresh', 0);
return $this->webCrawlerService->crawlWebsite($url, $depth, $refresh); return $this->webCrawlerService->crawlWebsite($url, $depth, $refresh);
} }
public function destroy($id) public function destroy($id)
{ {
return $this->webCrawlerService->deleteCrawl($id); return $this->webCrawlerService->deleteCrawl($id);
} }
public function destroyAll() public function destroyAll()
{ {
return $this->webCrawlerService->deleteAllCrawls(); return $this->webCrawlerService->deleteAllCrawls();
} }
} }

15
app/Services/WebCrawlerService.php
View file

@ -23,10 +23,9 @@ public function getAllCrawls()
public function crawlWebsite($url, $depth, $refresh) public function crawlWebsite($url, $depth, $refresh)
{ {
// Check if the URL is already in the database
$webCrawl = WebCrawl::where('url', $url)->first(); $webCrawl = WebCrawl::where('url', $url)->first();
if ($webCrawl && !$refresh) { if ($webCrawl && !$refresh) {
Log::error("This URL already exists in the database $url"); Log::error("This URL already exists in the database: $url");
return response()->json([ return response()->json([
'error' => 'This URL already exists in the database', 'error' => 'This URL already exists in the database',
], 400); ], 400);
@ -57,13 +56,13 @@ public function crawlWebsite($url, $depth, $refresh)
]); ]);
} }
} else { } else {
Log::error("Failed to retrieve the URL $url"); Log::error("Failed to retrieve the URL: $url");
return response()->json([ return response()->json([
'error' => 'Failed to retrieve the URL', 'error' => 'Failed to retrieve the URL',
], 500); ], 500);
} }
Log::info("Crawling completed successfully For URL $url"); Log::info("Crawling completed successfully for URL: $url");
return response()->json([ return response()->json([
'message' => 'Crawling completed successfully', 'message' => 'Crawling completed successfully',
]); ]);
@ -74,12 +73,12 @@ public function deleteCrawl($id)
$webCrawl = WebCrawl::find($id); $webCrawl = WebCrawl::find($id);
if ($webCrawl) { if ($webCrawl) {
$webCrawl->delete(); $webCrawl->delete();
Log::info("Web crawl deleted successfully For ID $id"); Log::info("Web crawl deleted successfully for ID: $id");
return response()->json([ return response()->json([
'message' => 'Web crawl deleted successfully', 'message' => 'Web crawl deleted successfully',
]); ]);
} }
Log::error("Web crawl not found For ID $id"); Log::error("Web crawl not found for ID: $id");
return response()->json([ return response()->json([
'error' => 'Web crawl not found', 'error' => 'Web crawl not found',
], 404); ], 404);
@ -109,9 +108,9 @@ protected function crawlWebsiteRecursive($url, $depth)
$linksFromPage = $this->getLinksFromPage($crawler->content); $linksFromPage = $this->getLinksFromPage($crawler->content);
try { try {
$crawler->save(); $crawler->save();
Log::info("URL saved to the database $url"); Log::info("URL saved to the database: $url");
} catch (\Exception $e) { } catch (\Exception $e) {
Log::error("Can't save the URL to the database $url"); Log::error("Can't save the URL to the database: $url");
return []; return [];
} }
if ($depth > 0 && count($linksFromPage) > 0) { if ($depth > 0 && count($linksFromPage) > 0) {