name: girls of pb performerByName: action: scrapeXPath queryURL: http://www.girlsofpb.com/search/?do=1&q={} scraper: performerSearch performerByURL: - action: scrapeXPath url: - http://www.girlsofpb.com/ scraper: performerScraper xPathScrapers: performerSearch: common: $perfLIs: '//ul/li' performer: Name: $perfLIs/h3/a/text() Image: selector: $perfLIs/a/img/@src postProcess: - replace: - regex: ^ with: http://www.girlsofpb.com URL: selector: $perfLIs/h3/a/@href postProcess: - replace: - regex: ^ with: http://www.girlsofpb.com performerScraper: common: $topcard: /html/body/div[1]/div[3]/div performer: Name: selector: $topcard/div/div[1]/h1/text postProcess: - replace: - regex: 'Nude - .*' with: '' Details: $topcard/p[2]/text() Image: selector: /html/body/div[1]/div[5]/div/div[1]/div/a/img/@src postProcess: - replace: - regex: ^ with: http://www.girlsofpb.com URL: selector: //a[@id='goright']/@href postProcess: - replace: - regex: ^ with: http://www.girlsofpb.com - subScraper: selector: //a[@id='goleft']/@href postProcess: - replace: - regex: ^ with: http://www.girlsofpb.com Measurements: selector: $topcard/text() concat: " " postProcess: - replace: - regex: ".*Bust: (.+), Waist: (.+), Hips: (.+?), .*$" with: "$1-$2-$3" Height: selector: $topcard/text() concat: " " postProcess: - replace: - regex: ".*Height: (.+?), .*$" with: "$1" - javascript: | return parseInt(value) * 2.54 Weight: selector: $topcard/text() concat: " " postProcess: - replace: - regex: ".*Weight: (.+?), .*$" with: "$1" - lbToKg: true Birthdate: selector: $topcard/text() concat: " " postProcess: - replace: - regex: '.*Birth Date: (.+ \d+, \d{4}), .*$' with: "$1" - parseDate: January 2, 2006 # Last Updated April 3, 2024