Created
July 2, 2012 20:30
-
-
Save emirkin/3035521 to your computer and use it in GitHub Desktop.
Scraping Online Drug Stores
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cvs" => { | |
"Image" => "//div[@class='productSection1']//img[1]/@src", | |
"Title" => "//h4[@class='productBrand']//span[1]", | |
"Size" => "//span[@class='prodWeight']/preceding-sibling::text()[1]", | |
"Price" => "//*[@class='productPrice']", | |
"Link" => "//div[@class='productSection1']//img[1]/ancestor::a/@href" | |
}, | |
"walgreens" => { | |
"Image" => "//div[@class='product-container']/div[contains(@class, 'image_container')]//img[1]/@src", | |
"Title" => "//div[@class='product-container']//div[contains(@class, 'product-name')]", | |
"Details" => "//div[@class='product-container']//div[@class='prod-info-box']", | |
"Price" => "//div[@class='product-container']//div[@class='pricing']/div[@class='prod-pricing']", | |
"Link" => "//div[@class='product-container']/div[contains(@class, 'image_container')]//img[1]/ancestor::a/@href" | |
}, | |
"drugstore.com" => { | |
"Image" => "//div[@class='prodImg']//img/@src", | |
"Title" => "//div[@class='info']/span[@class='description']//span[@class='name']", | |
"Details" => "//div[@class='info']/span[@class='description']", | |
"Price" => "//div[@class='pricing']", | |
"Link" => "//div[@class='prodImg']//img/ancestor::a/@href" | |
}, | |
"MyOTCStore" => { | |
"Title" => "//span[@class='CategoryProductNameLink']", | |
"Price" => "//span[@class='CategoryProductPrice']", | |
"Image" => "//div[@class='CategoryProductThumbnailArea']//img/@src", | |
"Link" => "//table[@id='dlProducts']//span[@class='CategoryProductNameLink']/a/@href" | |
}, | |
"FamilyMeds" => { | |
"Title" => "//table[@class='productSearchListing']//td[position()=2 and following-sibling::td]/a[1]", | |
"Price" => "//table[@class='productSearchListing']//td[3]//p", | |
"Image" => "//table[@class='productSearchListing']//td[1]/a/img/@src", | |
"Details" => "//table[@class='productSearchListing']//td[position()=2 and following-sibling::td]/a[1]/following-sibling::p[1]", | |
"Link" => "//table[@class='productSearchListing']//td[position()=2 and following-sibling::td]/a[1]/@href" | |
}, | |
"CanadaDrugs" => { | |
"Title" => "//div[@id='results']/div[contains(@class, 'row') and (.//@data-price)]//div[@class='link']/a", | |
"Price" => "//div[@id='results']/div[contains(@class, 'row') and (.//@data-price)]/div[@class='detailsLink']//select/option[1]/@data-price", | |
"Image" => "//div[@id='results']/div[contains(@class, 'row') and (.//@data-price)]//div[@class='imageGroup']//img/@src", | |
"Details" => "//div[@id='results']/div[contains(@class, 'row') and (.//@data-price)]//div[@class='iconGroup']/following-sibling::*[@name!='b' and position()=1]", | |
"Link" => "//div[@id='results']/div[contains(@class, 'row') and (.//@data-price)]//div[@class='link']/a/@href" | |
}, | |
"thebestonlinepharmacy" => { | |
"Title" => "//div[@class='product-group']//h2", | |
"Price" => "//tr[@class='productdetail']//td[2]", | |
"Image" => "//div[@class='product-group']//img/@src", | |
"Details" => "//table[@class='mpllc-body']//p", | |
"Link" => "//tr[@class='productdetail']//td[4]//a/@href" | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment