Skip to content

Instantly share code, notes, and snippets.

@lucafluri
Last active July 10, 2020 18:37
Show Gist options
  • Select an option

  • Save lucafluri/528d5c168da2c87a97d44fc93a082bd6 to your computer and use it in GitHub Desktop.

Select an option

Save lucafluri/528d5c168da2c87a97d44fc93a082bd6 to your computer and use it in GitHub Desktop.
test json for price tracker
{
"domains": {
"amazon.de": {
"xpath": "false",
"name": [{
"path": "#productTitle",
"regex": {
"pattern": "",
"remove": "",
"group": 1
}
}],
"price": [{
"path": "#priceblock_ourprice",
"regex": {
"pattern": "(\\d+[,.]?[\\d]*)",
"remove": "",
"group": 1
}
},
{
"path": "#priceblock_dealprice",
"regex": {
"pattern": "(\\d+[,.]?[\\d]*)",
"remove": "",
"group": 1
}
},
{
"path": "#priceblock_saleprice",
"regex": {
"pattern": "(\\d+[,.]?[\\d]*)",
"remove": "",
"group": 1
}
}
],
"image": [{
"path": "#landingImage",
"regex": {
"attribute": "data-old-hires",
"pattern": "",
"remove": "",
"group": 1
}
},
{
"path": "#landingImage",
"regex": {
"attribute": "src",
"pattern": "",
"remove": "",
"group": 1
}
}
]
},
"amazon.com": {
"xpath": "false",
"name": [{
"path": "#productTitle",
"regex": {
"pattern": "",
"remove": "",
"group": 1
}
}],
"price": [{
"path": "#priceblock_ourprice",
"regex": {
"pattern": "(\\d+[,.]?[\\d]*)",
"remove": "",
"group": 1
}
},
{
"path": "#priceblock_dealprice",
"regex": {
"pattern": "(\\d+[,.]?[\\d]*)",
"remove": "",
"group": 1
}
},
{
"path": "#priceblock_saleprice",
"regex": {
"pattern": "(\\d+[,.]?[\\d]*)",
"remove": "",
"group": 1
}
}
],
"image": [{
"path": "#landingImage",
"regex": {
"attribute": "data-old-hires",
"pattern": "",
"remove": "",
"group": 1
}
},
{
"path": "#landingImage",
"regex": {
"attribute": "src",
"pattern": "",
"remove": "",
"group": 1
}
}
]
},
"officeworld.ch": {
"xpath": "true",
"name": [{
"path": "//*[@id='pageHeader']/div[1]/div/div[2]/div[1]/h1",
"regex": {
"pattern": ">(.*)<",
"remove": "",
"group": 1
}
}],
"price": [{
"path": "//*[@id='pageHeader']/div[1]/div/div[2]/div[2]/div[1]/div[1]/div/div/div[1]/div[2]",
"regex": {
"pattern": "(\\d+[,.]?[\\d]*)",
"remove": "",
"group": 1
}
}
],
"image": [{
"path": "//*[@id='currentPicture']",
"regex": {
"attribute": "src",
"pattern": "src=\"(\\S*)\"",
"remove": "",
"group": 1
}
}
]
}
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment