def parse(self, response): results = response.xpath('//table[@class="table2"]/tr[@bgcolor]') for result in results: item = MybtItem() item['name'] = result.xpath('.//div[@class="tt-name"]/a[2]/text()').extract()[0] item['source'] = result.xpath('.//div[@class="tt-name"]/a[2]/@href').extract() item['source'] = 'https://www.limetorrents.info' + item['source'][0] yield Request(url = item['source'], meta = {'item': item}, callback = self.secondParse)
def parse(self, response): results = response.xpath('//table/tbody/tr') for result in results: item = MybtItem() item['name'] = result.xpath('./td[@class="coll-1 name"]/a[2]/text()').extract()[0] item['source'] = result.xpath('./td[@class="coll-1 name"]/a[2]/@href').extract() item['source'] = 'https://1337x.to' + item['source'][0] yield Request(url = item['source'], meta = {'item': item}, callback = self.secondParse)
def parse(self, response): results = response.xpath( '//div[@class="panel panel-default"]/table/tr') for result in results: item = MybtItem() item['name'] = result.xpath('string(./td[1]//b)').extract()[0] item['source'] = result.xpath('./td[1]//a/@href').extract() item['source'] = 'https://www.torlock.com' + item['source'][0] item['size'] = result.xpath('./td[3]/text()').extract()[0] item['seeder'] = result.xpath('./td[4]/text()').extract()[0] item['leecher'] = result.xpath('./td[5]/text()').extract()[0] if int(item['seeder']): yield Request(url=item['source'], meta={'item': item}, callback=self.secondParse)
def parse(self, response): results = response.xpath( '//table[@class="forum_header_border"]/tr[@class="forum_header_border"]' ) for result in results: item = MybtItem() item['name'] = result.xpath( './td[2]/a/text()').extract()[0].rstrip(' [eztv]') item['source'] = result.xpath('./td[2]/a/@href').extract() item['source'] = 'https://eztv.io' + item['source'][0] item['link'] = result.xpath( './td[3]/a[@class="magnet"]/@href').extract()[0] item['size'] = result.xpath('./td[4]/text()').extract()[0] yield Request(url=item['source'], meta={'item': item}, callback=self.secondParse)
def parse(self, response): item = MybtItem() results = response.xpath('//div[@id="index"]/table/tr')[1:] for result in results: item['name'] = result.xpath('./td[2]/a[3]/text()').extract()[0][:-1] item['source'] = result.xpath('./td[2]/a[3]/@href').extract() item['source'] = 'http://rutor.info' + item['source'][0] item['link'] = result.xpath('./td[2]/a[2]/@href').extract()[0] item['size'] = result.xpath('./td[last()-1]/text()').extract()[0].replace('\xa0', ' ') item['seeder'] = result.xpath('./td[last()]/span[1]/text()').extract()[0][1:] item['leecher'] = result.xpath('./td[last()]/span[2]/text()').extract()[0][1:] item['site'] = 'RUTOR' item['search'] = self.search item['cat'] = self.cat if int(item['seeder']): yield item
def parse(self, response): item = MybtItem() results = response.xpath('//table/tr')[:-1] for result in results: item['name'] = result.xpath('./td[2]/div/a/text()').extract()[0] item['source'] = result.xpath('./td[2]/div/a/@href').extract()[0] item['link'] = result.xpath('./td[2]/a/@href').extract()[0] item['size'] = result.xpath('./td[2]/font/text()').extract()[0] item['size'] = item['size'].split(', ')[1].lstrip('Size ').replace( 'i', '').replace('\xa0', ' ') item['seeder'] = result.xpath('./td[3]/text()').extract()[0] item['leecher'] = result.xpath('./td[4]/text()').extract()[0] item['site'] = 'ThePirateBay' item['search'] = self.search item['cat'] = self.cat if int(item['seeder']): yield item
def secondParse(self, response): try: item = MybtItem() results = loads(response.text)['torrent_results'] for result in results: item['name'] = result['title'] item['source'] = result['info_page'] item['link'] = result['download'] item['size'] = sizeConvert(result['size']) item['seeder'] = result['seeders'] item['leecher'] = result['leechers'] item['site'] = 'RARBG' item['search'] = self.search item['cat'] = self.cat if item['seeder']: yield item except KeyError: pass
def parse(self, response): item = MybtItem() results = response.xpath('//table/tr') for result in results: item['name'] = result.xpath( 'string(./td[2]/a[@class=" small"])').extract()[0] if not item['name']: continue item['source'] = result.xpath('./td[2]/a/@href').extract() item['source'] = 'https://zooqle.com' + item['source'][0] item['link'] = result.xpath( './td[3]/ul/li[2]/a/@href').extract()[0] item['size'] = result.xpath('./td[4]//text()').extract()[0] seeder_leecher = result.xpath( './/td[6]/div/@title').extract()[0].split(' | ') item['seeder'] = seeder_leecher[0].lstrip('Seeders: ') item['leecher'] = seeder_leecher[1].lstrip('Leechers: ') item['site'] = 'Zooqle' item['search'] = self.search item['cat'] = self.cat yield item