2016-08-13 14:55:47 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								"""
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 DigBT (Videos, Music, Files)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 @website     https://digbt.org
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 @provide-api no
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 @using-api   no
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 @results     HTML (using search portal)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 @stable      no (HTML can change)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 @parse       url, title, content, magnetlink
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								"""
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2020-08-06 17:42:46 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								from urllib.parse import urljoin
							 | 
						
					
						
							
								
									
										
										
										
											2016-08-13 14:55:47 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								from lxml import html
							 | 
						
					
						
							
								
									
										
										
										
											2020-10-02 18:13:56 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								from searx.utils import extract_text, get_torrent_size
							 | 
						
					
						
							
								
									
										
										
										
											2016-11-30 18:43:03 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2016-08-13 14:55:47 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								categories = ['videos', 'music', 'files']
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								paging = True
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								URL = 'https://digbt.org'
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								SEARCH_URL = URL + '/search/{query}-time-{pageno}'
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								FILESIZE = 3
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								FILESIZE_MULTIPLIER = 4
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								def request(query, params):
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    params['url'] = SEARCH_URL.format(query=query, pageno=params['pageno'])
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    return params
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								def response(resp):
							 | 
						
					
						
							
								
									
										
										
										
											2016-11-30 18:43:03 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								    dom = html.fromstring(resp.text)
							 | 
						
					
						
							
								
									
										
										
										
											2016-08-13 14:55:47 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    search_res = dom.xpath('.//td[@class="x-item"]')
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    if not search_res:
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        return list()
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    results = list()
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    for result in search_res:
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        url = urljoin(URL, result.xpath('.//a[@title]/@href')[0])
							 | 
						
					
						
							
								
									
										
										
										
											2016-09-20 22:35:54 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								        title = extract_text(result.xpath('.//a[@title]'))
							 | 
						
					
						
							
								
									
										
										
										
											2016-08-13 14:55:47 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        content = extract_text(result.xpath('.//div[@class="files"]'))
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        files_data = extract_text(result.xpath('.//div[@class="tail"]')).split()
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        filesize = get_torrent_size(files_data[FILESIZE], files_data[FILESIZE_MULTIPLIER])
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        magnetlink = result.xpath('.//div[@class="tail"]//a[@class="title"]/@href')[0]
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        results.append({'url': url,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                        'title': title,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                        'content': content,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                        'filesize': filesize,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                        'magnetlink': magnetlink,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                        'seed': 'N/A',
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                        'leech': 'N/A',
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                        'template': 'torrent.html'})
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    return results
							 |